From af15c82bfe2c3f73142b8f310784a0e85841539d Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 10:49:03 -0700 Subject: [PATCH 01/99] Revert "SPARK-1786: Edge Partition Serialization" This reverts commit a6b02fb7486356493474c7f42bb714c9cce215ca. --- .../spark/graphx/GraphKryoRegistrator.scala | 9 +++------ .../spark/graphx/impl/EdgePartition.scala | 14 +++++++------- .../graphx/impl/EdgePartitionBuilder.scala | 4 ++-- .../graphx/impl/EdgeTripletIterator.scala | 2 +- .../graphx/impl/RoutingTablePartition.scala | 4 ++-- .../graphx/impl/ShippableVertexPartition.scala | 2 +- .../spark/graphx/impl/VertexPartition.scala | 2 +- .../graphx/impl/VertexPartitionBase.scala | 6 +++--- .../graphx/impl/VertexPartitionBaseOps.scala | 4 ++-- ...Map.scala => PrimitiveKeyOpenHashMap.scala} | 2 +- .../spark/graphx/impl/EdgePartitionSuite.scala | 18 ------------------ 11 files changed, 23 insertions(+), 44 deletions(-) rename graphx/src/main/scala/org/apache/spark/graphx/util/collection/{GraphXPrimitiveKeyOpenHashMap.scala => PrimitiveKeyOpenHashMap.scala} (98%) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala index f97f329c0e832..d295d0127ac72 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala @@ -24,9 +24,6 @@ import org.apache.spark.util.BoundedPriorityQueue import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx.impl._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap -import org.apache.spark.util.collection.OpenHashSet - /** * Registers GraphX classes with Kryo for improved performance. @@ -46,8 +43,8 @@ class GraphKryoRegistrator extends KryoRegistrator { kryo.register(classOf[PartitionStrategy]) kryo.register(classOf[BoundedPriorityQueue[Object]]) kryo.register(classOf[EdgeDirection]) - kryo.register(classOf[GraphXPrimitiveKeyOpenHashMap[VertexId, Int]]) - kryo.register(classOf[OpenHashSet[Int]]) - kryo.register(classOf[OpenHashSet[Long]]) + + // This avoids a large number of hash table lookups. + kryo.setReferences(false) } } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala index a5c9cd1f8b4e6..871e81f8d245c 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala @@ -20,7 +20,7 @@ package org.apache.spark.graphx.impl import scala.reflect.{classTag, ClassTag} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap /** * A collection of edges stored in columnar format, along with any vertex attributes referenced. The @@ -42,12 +42,12 @@ import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap private[graphx] class EdgePartition[ @specialized(Char, Int, Boolean, Byte, Long, Float, Double) ED: ClassTag, VD: ClassTag]( - val srcIds: Array[VertexId] = null, - val dstIds: Array[VertexId] = null, - val data: Array[ED] = null, - val index: GraphXPrimitiveKeyOpenHashMap[VertexId, Int] = null, - val vertices: VertexPartition[VD] = null, - val activeSet: Option[VertexSet] = None + @transient val srcIds: Array[VertexId], + @transient val dstIds: Array[VertexId], + @transient val data: Array[ED], + @transient val index: PrimitiveKeyOpenHashMap[VertexId, Int], + @transient val vertices: VertexPartition[VD], + @transient val activeSet: Option[VertexSet] = None ) extends Serializable { /** Return a new `EdgePartition` with the specified edge data. */ diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala index 4520beb991515..ecb49bef42e45 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala @@ -23,7 +23,7 @@ import scala.util.Sorting import org.apache.spark.util.collection.{BitSet, OpenHashSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap private[graphx] class EdgePartitionBuilder[@specialized(Long, Int, Double) ED: ClassTag, VD: ClassTag]( @@ -41,7 +41,7 @@ class EdgePartitionBuilder[@specialized(Long, Int, Double) ED: ClassTag, VD: Cla val srcIds = new Array[VertexId](edgeArray.size) val dstIds = new Array[VertexId](edgeArray.size) val data = new Array[ED](edgeArray.size) - val index = new GraphXPrimitiveKeyOpenHashMap[VertexId, Int] + val index = new PrimitiveKeyOpenHashMap[VertexId, Int] // Copy edges into columnar structures, tracking the beginnings of source vertex id clusters and // adding them to the index if (edgeArray.length > 0) { diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala index 56f79a7097fce..ebb0b9418d65d 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala @@ -20,7 +20,7 @@ package org.apache.spark.graphx.impl import scala.reflect.ClassTag import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap /** * The Iterator type returned when constructing edge triplets. This could be an anonymous class in diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala index d02e9238adba5..927e32ad0f448 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala @@ -25,7 +25,7 @@ import org.apache.spark.rdd.ShuffledRDD import org.apache.spark.util.collection.{BitSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap /** * A message from the edge partition `pid` to the vertex partition containing `vid` specifying that @@ -69,7 +69,7 @@ object RoutingTablePartition { : Iterator[RoutingTableMessage] = { // Determine which positions each vertex id appears in using a map where the low 2 bits // represent src and dst - val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, Byte] + val map = new PrimitiveKeyOpenHashMap[VertexId, Byte] edgePartition.srcIds.iterator.foreach { srcId => map.changeValue(srcId, 0x1, (b: Byte) => (b | 0x1).toByte) } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala index dca54b8a7da86..f4e221d4e05ae 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala @@ -22,7 +22,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.{BitSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap /** Stores vertex attributes to ship to an edge partition. */ private[graphx] diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala index 55c7a19d1bdab..f1d174720a1ba 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala @@ -22,7 +22,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap private[graphx] object VertexPartition { /** Construct a `VertexPartition` from the given vertices. */ diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala index 34939b24440aa..8d9e0204d27f2 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala @@ -23,7 +23,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap private[graphx] object VertexPartitionBase { /** @@ -32,7 +32,7 @@ private[graphx] object VertexPartitionBase { */ def initFrom[VD: ClassTag](iter: Iterator[(VertexId, VD)]) : (VertexIdToIndexMap, Array[VD], BitSet) = { - val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] + val map = new PrimitiveKeyOpenHashMap[VertexId, VD] iter.foreach { pair => map(pair._1) = pair._2 } @@ -45,7 +45,7 @@ private[graphx] object VertexPartitionBase { */ def initFrom[VD: ClassTag](iter: Iterator[(VertexId, VD)], mergeFunc: (VD, VD) => VD) : (VertexIdToIndexMap, Array[VD], BitSet) = { - val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] + val map = new PrimitiveKeyOpenHashMap[VertexId, VD] iter.foreach { pair => map.setMerge(pair._1, pair._2, mergeFunc) } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala index a4f769b294010..21ff615feca6c 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala @@ -25,7 +25,7 @@ import org.apache.spark.Logging import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap /** * An class containing additional operations for subclasses of VertexPartitionBase that provide @@ -224,7 +224,7 @@ private[graphx] abstract class VertexPartitionBaseOps * Construct a new VertexPartition whose index contains only the vertices in the mask. */ def reindex(): Self[VD] = { - val hashMap = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] + val hashMap = new PrimitiveKeyOpenHashMap[VertexId, VD] val arbitraryMerge = (a: VD, b: VD) => a for ((k, v) <- self.iterator) { hashMap.setMerge(k, v, arbitraryMerge) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala similarity index 98% rename from graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala rename to graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala index 57b01b6f2e1fb..7b02e2ed1a9cb 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala @@ -29,7 +29,7 @@ import scala.reflect._ * Under the hood, it uses our OpenHashSet implementation. */ private[graphx] -class GraphXPrimitiveKeyOpenHashMap[@specialized(Long, Int) K: ClassTag, +class PrimitiveKeyOpenHashMap[@specialized(Long, Int) K: ClassTag, @specialized(Long, Int, Double) V: ClassTag]( val keySet: OpenHashSet[K], var _values: Array[V]) extends Iterable[(K, V)] diff --git a/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala index 28fd112f2b124..d2e0c01bc35ef 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala @@ -22,9 +22,6 @@ import scala.util.Random import org.scalatest.FunSuite -import org.apache.spark.SparkConf -import org.apache.spark.serializer.KryoSerializer - import org.apache.spark.graphx._ class EdgePartitionSuite extends FunSuite { @@ -123,19 +120,4 @@ class EdgePartitionSuite extends FunSuite { assert(!ep.isActive(-1)) assert(ep.numActives == Some(2)) } - - test("Kryo serialization") { - val aList = List((0, 1, 0), (1, 0, 0), (1, 2, 0), (5, 4, 0), (5, 5, 0)) - val a: EdgePartition[Int, Int] = makeEdgePartition(aList) - val conf = new SparkConf() - .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer") - .set("spark.kryo.registrator", "org.apache.spark.graphx.GraphKryoRegistrator") - val s = new KryoSerializer(conf).newInstance() - val aSer: EdgePartition[Int, Int] = s.deserialize(s.serialize(a)) - assert(aSer.srcIds.toList === a.srcIds.toList) - assert(aSer.dstIds.toList === a.dstIds.toList) - assert(aSer.data.toList === a.data.toList) - assert(aSer.index != null) - assert(aSer.vertices.iterator.toSet === a.vertices.iterator.toSet) - } } From 3af1f386439cdddd42e545ad63d089f4dfdf9f8a Mon Sep 17 00:00:00 2001 From: Aaron Davidson Date: Mon, 12 May 2014 11:08:52 -0700 Subject: [PATCH 02/99] SPARK-1772 Stop catching Throwable, let Executors die The main issue this patch fixes is [SPARK-1772](https://issues.apache.org/jira/browse/SPARK-1772), in which Executors may not die when fatal exceptions (e.g., OOM) are thrown. This patch causes Executors to delegate to the ExecutorUncaughtExceptionHandler when a fatal exception is thrown. This patch also continues the fight in the neverending war against `case t: Throwable =>`, by only catching Exceptions in many places, and adding a wrapper for Threads and Runnables to make sure any uncaught exceptions are at least printed to the logs. It also turns out that it is unlikely that the IndestructibleActorSystem actually works, given testing ([here](https://gist.github.com/aarondav/ca1f0cdcd50727f89c0d)). The uncaughtExceptionHandler is not called from the places that we expected it would be. [SPARK-1620](https://issues.apache.org/jira/browse/SPARK-1620) deals with part of this issue, but refactoring our Actor Systems to ensure that exceptions are dealt with properly is a much bigger change, outside the scope of this PR. Author: Aaron Davidson Closes #715 from aarondav/throwable and squashes the following commits: f9b9bfe [Aaron Davidson] Remove other redundant 'throw e' e937a0a [Aaron Davidson] Address Prashant and Matei's comments 1867867 [Aaron Davidson] [RFC] SPARK-1772 Stop catching Throwable, let Executors die --- .../org/apache/spark/ContextCleaner.scala | 11 +-- .../scala/org/apache/spark/SparkContext.scala | 12 ++-- .../apache/spark/api/python/PythonRDD.scala | 3 +- .../api/python/PythonWorkerFactory.scala | 1 - .../org/apache/spark/deploy/Client.scala | 2 +- .../apache/spark/deploy/SparkHadoopUtil.scala | 2 +- .../spark/deploy/history/HistoryServer.scala | 8 +-- .../apache/spark/deploy/master/Master.scala | 4 +- .../spark/deploy/worker/DriverWrapper.scala | 2 +- .../CoarseGrainedExecutorBackend.scala | 2 +- .../org/apache/spark/executor/Executor.scala | 37 +++------- .../ExecutorUncaughtExceptionHandler.scala | 53 +++++++++++++++ .../scheduler/EventLoggingListener.scala | 4 +- .../spark/scheduler/TaskResultGetter.scala | 8 +-- .../spark/storage/DiskBlockManager.scala | 6 +- .../spark/storage/TachyonBlockManager.scala | 7 +- .../org/apache/spark/util/AkkaUtils.scala | 11 +-- .../util/IndestructibleActorSystem.scala | 68 ------------------- .../scala/org/apache/spark/util/Utils.scala | 26 ++++++- 19 files changed, 127 insertions(+), 140 deletions(-) create mode 100644 core/src/main/scala/org/apache/spark/executor/ExecutorUncaughtExceptionHandler.scala delete mode 100644 core/src/main/scala/org/apache/spark/util/IndestructibleActorSystem.scala diff --git a/core/src/main/scala/org/apache/spark/ContextCleaner.scala b/core/src/main/scala/org/apache/spark/ContextCleaner.scala index 54e08d7866f75..e2d2250982daa 100644 --- a/core/src/main/scala/org/apache/spark/ContextCleaner.scala +++ b/core/src/main/scala/org/apache/spark/ContextCleaner.scala @@ -23,6 +23,7 @@ import scala.collection.mutable.{ArrayBuffer, SynchronizedBuffer} import org.apache.spark.broadcast.Broadcast import org.apache.spark.rdd.RDD +import org.apache.spark.util.Utils /** * Classes that represent cleaning tasks. @@ -110,7 +111,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging { } /** Keep cleaning RDD, shuffle, and broadcast state. */ - private def keepCleaning() { + private def keepCleaning(): Unit = Utils.logUncaughtExceptions { while (!stopped) { try { val reference = Option(referenceQueue.remove(ContextCleaner.REF_QUEUE_POLL_TIMEOUT)) @@ -128,7 +129,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging { } } } catch { - case t: Throwable => logError("Error in cleaning thread", t) + case e: Exception => logError("Error in cleaning thread", e) } } } @@ -141,7 +142,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging { listeners.foreach(_.rddCleaned(rddId)) logInfo("Cleaned RDD " + rddId) } catch { - case t: Throwable => logError("Error cleaning RDD " + rddId, t) + case e: Exception => logError("Error cleaning RDD " + rddId, e) } } @@ -154,7 +155,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging { listeners.foreach(_.shuffleCleaned(shuffleId)) logInfo("Cleaned shuffle " + shuffleId) } catch { - case t: Throwable => logError("Error cleaning shuffle " + shuffleId, t) + case e: Exception => logError("Error cleaning shuffle " + shuffleId, e) } } @@ -166,7 +167,7 @@ private[spark] class ContextCleaner(sc: SparkContext) extends Logging { listeners.foreach(_.broadcastCleaned(broadcastId)) logInfo("Cleaned broadcast " + broadcastId) } catch { - case t: Throwable => logError("Error cleaning broadcast " + broadcastId, t) + case e: Exception => logError("Error cleaning broadcast " + broadcastId, e) } } diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 71bab295442fc..e6121a705497c 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -1494,8 +1494,8 @@ object SparkContext extends Logging { } catch { // TODO: Enumerate the exact reasons why it can fail // But irrespective of it, it means we cannot proceed ! - case th: Throwable => { - throw new SparkException("YARN mode not available ?", th) + case e: Exception => { + throw new SparkException("YARN mode not available ?", e) } } val backend = new CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem) @@ -1510,8 +1510,8 @@ object SparkContext extends Logging { cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl] } catch { - case th: Throwable => { - throw new SparkException("YARN mode not available ?", th) + case e: Exception => { + throw new SparkException("YARN mode not available ?", e) } } @@ -1521,8 +1521,8 @@ object SparkContext extends Logging { val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext]) cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend] } catch { - case th: Throwable => { - throw new SparkException("YARN mode not available ?", th) + case e: Exception => { + throw new SparkException("YARN mode not available ?", e) } } diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala index 2971c277aa863..57b28b9972366 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala @@ -171,7 +171,7 @@ private[spark] class PythonRDD[T: ClassTag]( this.interrupt() } - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { try { SparkEnv.set(env) val stream = new BufferedOutputStream(worker.getOutputStream, bufferSize) @@ -282,7 +282,6 @@ private[spark] object PythonRDD { } } catch { case eof: EOFException => {} - case e: Throwable => throw e } JavaRDD.fromRDD(sc.sc.parallelize(objs, parallelism)) } diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala b/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala index 002f2acd94dee..759cbe2c46c52 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala @@ -71,7 +71,6 @@ private[spark] class PythonWorkerFactory(pythonExec: String, envVars: Map[String stopDaemon() startDaemon() new Socket(daemonHost, daemonPort) - case e: Throwable => throw e } } } diff --git a/core/src/main/scala/org/apache/spark/deploy/Client.scala b/core/src/main/scala/org/apache/spark/deploy/Client.scala index 7ead1171525d2..aeb159adc31d9 100644 --- a/core/src/main/scala/org/apache/spark/deploy/Client.scala +++ b/core/src/main/scala/org/apache/spark/deploy/Client.scala @@ -157,7 +157,7 @@ object Client { // TODO: See if we can initialize akka so return messages are sent back using the same TCP // flow. Else, this (sadly) requires the DriverClient be routable from the Master. val (actorSystem, _) = AkkaUtils.createActorSystem( - "driverClient", Utils.localHostName(), 0, false, conf, new SecurityManager(conf)) + "driverClient", Utils.localHostName(), 0, conf, new SecurityManager(conf)) actorSystem.actorOf(Props(classOf[ClientActor], driverArgs, conf)) diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala b/core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala index e2df1b8954124..148115d3ed351 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala @@ -103,7 +103,7 @@ object SparkHadoopUtil { .newInstance() .asInstanceOf[SparkHadoopUtil] } catch { - case th: Throwable => throw new SparkException("Unable to load YARN support", th) + case e: Exception => throw new SparkException("Unable to load YARN support", e) } } else { new SparkHadoopUtil diff --git a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala index 1238bbf9da2fd..a9c11dca5678e 100644 --- a/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala +++ b/core/src/main/scala/org/apache/spark/deploy/history/HistoryServer.scala @@ -70,7 +70,7 @@ class HistoryServer( * TODO: Add a mechanism to update manually. */ private val logCheckingThread = new Thread { - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { while (!stopped) { val now = System.currentTimeMillis if (now - lastLogCheckTime > UPDATE_INTERVAL_MS) { @@ -154,7 +154,7 @@ class HistoryServer( numCompletedApplications = logInfos.size } catch { - case t: Throwable => logError("Exception in checking for event log updates", t) + case e: Exception => logError("Exception in checking for event log updates", e) } } else { logWarning("Attempted to check for event log updates before binding the server.") @@ -231,8 +231,8 @@ class HistoryServer( dir.getModificationTime } } catch { - case t: Throwable => - logError("Exception in accessing modification time of %s".format(dir.getPath), t) + case e: Exception => + logError("Exception in accessing modification time of %s".format(dir.getPath), e) -1L } } diff --git a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala index f254f5585ba25..c6dec305bffcb 100644 --- a/core/src/main/scala/org/apache/spark/deploy/master/Master.scala +++ b/core/src/main/scala/org/apache/spark/deploy/master/Master.scala @@ -684,8 +684,8 @@ private[spark] class Master( webUi.attachSparkUI(ui) return true } catch { - case t: Throwable => - logError("Exception in replaying log for application %s (%s)".format(appName, app.id), t) + case e: Exception => + logError("Exception in replaying log for application %s (%s)".format(appName, app.id), e) } } else { logWarning("Application %s (%s) has no valid logs: %s".format(appName, app.id, eventLogDir)) diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala b/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala index be15138f62406..05e242e6df702 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/DriverWrapper.scala @@ -31,7 +31,7 @@ object DriverWrapper { case workerUrl :: mainClass :: extraArgs => val conf = new SparkConf() val (actorSystem, _) = AkkaUtils.createActorSystem("Driver", - Utils.localHostName(), 0, false, conf, new SecurityManager(conf)) + Utils.localHostName(), 0, conf, new SecurityManager(conf)) actorSystem.actorOf(Props(classOf[WorkerWatcher], workerUrl), name = "workerWatcher") // Delegate to supplied main class diff --git a/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala b/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala index e912ae8a5d3c5..84aec65b7765d 100644 --- a/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala +++ b/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala @@ -105,7 +105,7 @@ private[spark] object CoarseGrainedExecutorBackend { // Create a new ActorSystem to run the backend, because we can't create a // SparkEnv / Executor before getting started with all our system properties, etc val (actorSystem, boundPort) = AkkaUtils.createActorSystem("sparkExecutor", hostname, 0, - indestructible = true, conf = conf, new SecurityManager(conf)) + conf, new SecurityManager(conf)) // set it val sparkHostPort = hostname + ":" + boundPort actorSystem.actorOf( diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala index 98e7e0be813be..baee7a216a7c3 100644 --- a/core/src/main/scala/org/apache/spark/executor/Executor.scala +++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala @@ -74,28 +74,7 @@ private[spark] class Executor( // Setup an uncaught exception handler for non-local mode. // Make any thread terminations due to uncaught exceptions kill the entire // executor process to avoid surprising stalls. - Thread.setDefaultUncaughtExceptionHandler( - new Thread.UncaughtExceptionHandler { - override def uncaughtException(thread: Thread, exception: Throwable) { - try { - logError("Uncaught exception in thread " + thread, exception) - - // We may have been called from a shutdown hook. If so, we must not call System.exit(). - // (If we do, we will deadlock.) - if (!Utils.inShutdown()) { - if (exception.isInstanceOf[OutOfMemoryError]) { - System.exit(ExecutorExitCode.OOM) - } else { - System.exit(ExecutorExitCode.UNCAUGHT_EXCEPTION) - } - } - } catch { - case oom: OutOfMemoryError => Runtime.getRuntime.halt(ExecutorExitCode.OOM) - case t: Throwable => Runtime.getRuntime.halt(ExecutorExitCode.UNCAUGHT_EXCEPTION_TWICE) - } - } - } - ) + Thread.setDefaultUncaughtExceptionHandler(ExecutorUncaughtExceptionHandler) } val executorSource = new ExecutorSource(this, executorId) @@ -259,6 +238,11 @@ private[spark] class Executor( } case t: Throwable => { + // Attempt to exit cleanly by informing the driver of our failure. + // If anything goes wrong (or this was a fatal exception), we will delegate to + // the default uncaught exception handler, which will terminate the Executor. + logError("Exception in task ID " + taskId, t) + val serviceTime = System.currentTimeMillis() - taskStart val metrics = attemptedTask.flatMap(t => t.metrics) for (m <- metrics) { @@ -268,10 +252,11 @@ private[spark] class Executor( val reason = ExceptionFailure(t.getClass.getName, t.toString, t.getStackTrace, metrics) execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason)) - // TODO: Should we exit the whole executor here? On the one hand, the failed task may - // have left some weird state around depending on when the exception was thrown, but on - // the other hand, maybe we could detect that when future tasks fail and exit then. - logError("Exception in task ID " + taskId, t) + // Don't forcibly exit unless the exception was inherently fatal, to avoid + // stopping other tasks unnecessarily. + if (Utils.isFatalError(t)) { + ExecutorUncaughtExceptionHandler.uncaughtException(t) + } } } finally { // TODO: Unregister shuffle memory only for ResultTask diff --git a/core/src/main/scala/org/apache/spark/executor/ExecutorUncaughtExceptionHandler.scala b/core/src/main/scala/org/apache/spark/executor/ExecutorUncaughtExceptionHandler.scala new file mode 100644 index 0000000000000..b0e984c03964c --- /dev/null +++ b/core/src/main/scala/org/apache/spark/executor/ExecutorUncaughtExceptionHandler.scala @@ -0,0 +1,53 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.executor + +import org.apache.spark.Logging +import org.apache.spark.util.Utils + +/** + * The default uncaught exception handler for Executors terminates the whole process, to avoid + * getting into a bad state indefinitely. Since Executors are relatively lightweight, it's better + * to fail fast when things go wrong. + */ +private[spark] object ExecutorUncaughtExceptionHandler + extends Thread.UncaughtExceptionHandler with Logging { + + override def uncaughtException(thread: Thread, exception: Throwable) { + try { + logError("Uncaught exception in thread " + thread, exception) + + // We may have been called from a shutdown hook. If so, we must not call System.exit(). + // (If we do, we will deadlock.) + if (!Utils.inShutdown()) { + if (exception.isInstanceOf[OutOfMemoryError]) { + System.exit(ExecutorExitCode.OOM) + } else { + System.exit(ExecutorExitCode.UNCAUGHT_EXCEPTION) + } + } + } catch { + case oom: OutOfMemoryError => Runtime.getRuntime.halt(ExecutorExitCode.OOM) + case t: Throwable => Runtime.getRuntime.halt(ExecutorExitCode.UNCAUGHT_EXCEPTION_TWICE) + } + } + + def uncaughtException(exception: Throwable) { + uncaughtException(Thread.currentThread(), exception) + } +} diff --git a/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala b/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala index 7968a0691db10..a90b0d475c04e 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala @@ -206,8 +206,8 @@ private[spark] object EventLoggingListener extends Logging { applicationComplete = filePaths.exists { path => isApplicationCompleteFile(path.getName) } ) } catch { - case t: Throwable => - logError("Exception in parsing logging info from directory %s".format(logDir), t) + case e: Exception => + logError("Exception in parsing logging info from directory %s".format(logDir), e) EventLoggingInfo.empty } } diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala index c9ad2b151daf0..99d305b36a959 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskResultGetter.scala @@ -43,7 +43,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul def enqueueSuccessfulTask( taskSetManager: TaskSetManager, tid: Long, serializedData: ByteBuffer) { getTaskResultExecutor.execute(new Runnable { - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { try { val result = serializer.get().deserialize[TaskResult[_]](serializedData) match { case directResult: DirectTaskResult[_] => directResult @@ -70,7 +70,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul case cnf: ClassNotFoundException => val loader = Thread.currentThread.getContextClassLoader taskSetManager.abort("ClassNotFound with classloader: " + loader) - case ex: Throwable => + case ex: Exception => taskSetManager.abort("Exception while deserializing and fetching task: %s".format(ex)) } } @@ -81,7 +81,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul serializedData: ByteBuffer) { var reason : TaskEndReason = UnknownReason getTaskResultExecutor.execute(new Runnable { - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { try { if (serializedData != null && serializedData.limit() > 0) { reason = serializer.get().deserialize[TaskEndReason]( @@ -94,7 +94,7 @@ private[spark] class TaskResultGetter(sparkEnv: SparkEnv, scheduler: TaskSchedul val loader = Utils.getContextOrSparkClassLoader logError( "Could not deserialize TaskEndReason: ClassNotFound with classloader " + loader) - case ex: Throwable => {} + case ex: Exception => {} } scheduler.handleFailedTask(taskSetManager, tid, taskState, reason) } diff --git a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala index cf6ef0029a861..3a7243a1ba19c 100644 --- a/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/DiskBlockManager.scala @@ -148,7 +148,7 @@ private[spark] class DiskBlockManager(shuffleManager: ShuffleBlockManager, rootD private def addShutdownHook() { localDirs.foreach(localDir => Utils.registerShutdownDeleteDir(localDir)) Runtime.getRuntime.addShutdownHook(new Thread("delete Spark local dirs") { - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { logDebug("Shutdown hook called") DiskBlockManager.this.stop() } @@ -162,8 +162,8 @@ private[spark] class DiskBlockManager(shuffleManager: ShuffleBlockManager, rootD try { if (!Utils.hasRootAsShutdownDeleteDir(localDir)) Utils.deleteRecursively(localDir) } catch { - case t: Throwable => - logError("Exception while deleting local spark dir: " + localDir, t) + case e: Exception => + logError("Exception while deleting local spark dir: " + localDir, e) } } } diff --git a/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala index b0b9674856568..a6cbe3aa440ff 100644 --- a/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/TachyonBlockManager.scala @@ -25,7 +25,6 @@ import tachyon.client.TachyonFile import org.apache.spark.Logging import org.apache.spark.executor.ExecutorExitCode -import org.apache.spark.network.netty.ShuffleSender import org.apache.spark.util.Utils @@ -137,7 +136,7 @@ private[spark] class TachyonBlockManager( private def addShutdownHook() { tachyonDirs.foreach(tachyonDir => Utils.registerShutdownDeleteDir(tachyonDir)) Runtime.getRuntime.addShutdownHook(new Thread("delete Spark tachyon dirs") { - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { logDebug("Shutdown hook called") tachyonDirs.foreach { tachyonDir => try { @@ -145,8 +144,8 @@ private[spark] class TachyonBlockManager( Utils.deleteRecursively(tachyonDir, client) } } catch { - case t: Throwable => - logError("Exception while deleting tachyon spark dir: " + tachyonDir, t) + case e: Exception => + logError("Exception while deleting tachyon spark dir: " + tachyonDir, e) } } } diff --git a/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala b/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala index 8afe09a117ebc..a8d12bb2a0165 100644 --- a/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala +++ b/core/src/main/scala/org/apache/spark/util/AkkaUtils.scala @@ -20,7 +20,7 @@ package org.apache.spark.util import scala.collection.JavaConversions.mapAsJavaMap import scala.concurrent.duration.{Duration, FiniteDuration} -import akka.actor.{ActorSystem, ExtendedActorSystem, IndestructibleActorSystem} +import akka.actor.{ActorSystem, ExtendedActorSystem} import com.typesafe.config.ConfigFactory import org.apache.log4j.{Level, Logger} @@ -41,7 +41,7 @@ private[spark] object AkkaUtils extends Logging { * If indestructible is set to true, the Actor System will continue running in the event * of a fatal exception. This is used by [[org.apache.spark.executor.Executor]]. */ - def createActorSystem(name: String, host: String, port: Int, indestructible: Boolean = false, + def createActorSystem(name: String, host: String, port: Int, conf: SparkConf, securityManager: SecurityManager): (ActorSystem, Int) = { val akkaThreads = conf.getInt("spark.akka.threads", 4) @@ -101,12 +101,7 @@ private[spark] object AkkaUtils extends Logging { |akka.log-dead-letters-during-shutdown = $lifecycleEvents """.stripMargin)) - val actorSystem = if (indestructible) { - IndestructibleActorSystem(name, akkaConf) - } else { - ActorSystem(name, akkaConf) - } - + val actorSystem = ActorSystem(name, akkaConf) val provider = actorSystem.asInstanceOf[ExtendedActorSystem].provider val boundPort = provider.getDefaultAddress.port.get (actorSystem, boundPort) diff --git a/core/src/main/scala/org/apache/spark/util/IndestructibleActorSystem.scala b/core/src/main/scala/org/apache/spark/util/IndestructibleActorSystem.scala deleted file mode 100644 index 4188a869c13da..0000000000000 --- a/core/src/main/scala/org/apache/spark/util/IndestructibleActorSystem.scala +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -// Must be in akka.actor package as ActorSystemImpl is protected[akka]. -package akka.actor - -import scala.util.control.{ControlThrowable, NonFatal} - -import com.typesafe.config.Config - -/** - * An akka.actor.ActorSystem which refuses to shut down in the event of a fatal exception - * This is necessary as Spark Executors are allowed to recover from fatal exceptions - * (see org.apache.spark.executor.Executor) - */ -object IndestructibleActorSystem { - def apply(name: String, config: Config): ActorSystem = - apply(name, config, ActorSystem.findClassLoader()) - - def apply(name: String, config: Config, classLoader: ClassLoader): ActorSystem = - new IndestructibleActorSystemImpl(name, config, classLoader).start() -} - -private[akka] class IndestructibleActorSystemImpl( - override val name: String, - applicationConfig: Config, - classLoader: ClassLoader) - extends ActorSystemImpl(name, applicationConfig, classLoader) { - - protected override def uncaughtExceptionHandler: Thread.UncaughtExceptionHandler = { - val fallbackHandler = super.uncaughtExceptionHandler - - new Thread.UncaughtExceptionHandler() { - def uncaughtException(thread: Thread, cause: Throwable): Unit = { - if (isFatalError(cause) && !settings.JvmExitOnFatalError) { - log.error(cause, "Uncaught fatal error from thread [{}] not shutting down " + - "ActorSystem [{}] tolerating and continuing.... ", thread.getName, name) - // shutdown() //TODO make it configurable - } else { - fallbackHandler.uncaughtException(thread, cause) - } - } - } - } - - def isFatalError(e: Throwable): Boolean = { - e match { - case NonFatal(_) | _: InterruptedException | _: NotImplementedError | _: ControlThrowable => - false - case _ => - true - } - } -} diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 95777fbf57d8b..8f7594ada2ba1 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -29,6 +29,7 @@ import scala.collection.mutable.ArrayBuffer import scala.io.Source import scala.reflect.ClassTag import scala.util.Try +import scala.util.control.{ControlThrowable, NonFatal} import com.google.common.io.Files import com.google.common.util.concurrent.ThreadFactoryBuilder @@ -41,7 +42,6 @@ import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkException} import org.apache.spark.deploy.SparkHadoopUtil import org.apache.spark.serializer.{DeserializationStream, SerializationStream, SerializerInstance} - /** * Various utility methods used by Spark. */ @@ -1125,4 +1125,28 @@ private[spark] object Utils extends Logging { } } + /** + * Executes the given block, printing and re-throwing any uncaught exceptions. + * This is particularly useful for wrapping code that runs in a thread, to ensure + * that exceptions are printed, and to avoid having to catch Throwable. + */ + def logUncaughtExceptions[T](f: => T): T = { + try { + f + } catch { + case t: Throwable => + logError(s"Uncaught exception in thread ${Thread.currentThread().getName}", t) + throw t + } + } + + /** Returns true if the given exception was fatal. See docs for scala.util.control.NonFatal. */ + def isFatalError(e: Throwable): Boolean = { + e match { + case NonFatal(_) | _: InterruptedException | _: NotImplementedError | _: ControlThrowable => + false + case _ => + true + } + } } From d9c97ba39723d36d3dcb53a75a3a2565357c0955 Mon Sep 17 00:00:00 2001 From: Bernardo Gomez Palacio Date: Mon, 12 May 2014 11:10:28 -0700 Subject: [PATCH 03/99] SPARK-1806: Upgrade Mesos dependency to 0.18.1 Enabled Mesos (0.18.1) dependency with shaded protobuf Why is this needed? Avoids any protobuf version collision between Mesos and any other dependency in Spark e.g. Hadoop HDFS 2.2+ or 1.0.4. Ticket: https://issues.apache.org/jira/browse/SPARK-1806 * Should close https://issues.apache.org/jira/browse/SPARK-1433 Author berngp Author: Bernardo Gomez Palacio Closes #741 from berngp/feature/SPARK-1806 and squashes the following commits: 5d70646 [Bernardo Gomez Palacio] SPARK-1806: Upgrade Mesos dependency to 0.18.1 --- core/pom.xml | 3 ++- .../apache/spark/executor/MesosExecutorBackend.scala | 2 +- .../cluster/mesos/MesosSchedulerBackend.scala | 2 +- pom.xml | 10 +++++++++- project/SparkBuild.scala | 2 +- 5 files changed, 14 insertions(+), 5 deletions(-) diff --git a/core/pom.xml b/core/pom.xml index 8fe215ab24289..bab50f5ce2888 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -140,6 +140,7 @@ org.apache.mesos mesos + ${mesos.classifier} io.netty @@ -322,7 +323,7 @@ - + src/main/resources diff --git a/core/src/main/scala/org/apache/spark/executor/MesosExecutorBackend.scala b/core/src/main/scala/org/apache/spark/executor/MesosExecutorBackend.scala index 9b56f711e0e0b..74100498bb2bd 100644 --- a/core/src/main/scala/org/apache/spark/executor/MesosExecutorBackend.scala +++ b/core/src/main/scala/org/apache/spark/executor/MesosExecutorBackend.scala @@ -19,7 +19,7 @@ package org.apache.spark.executor import java.nio.ByteBuffer -import com.google.protobuf.ByteString +import org.apache.mesos.protobuf.ByteString import org.apache.mesos.{Executor => MesosExecutor, ExecutorDriver, MesosExecutorDriver, MesosNativeLibrary} import org.apache.mesos.Protos.{TaskStatus => MesosTaskStatus, _} diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala index c975f312324ed..2cea1c8cf154a 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala @@ -24,7 +24,7 @@ import java.util.Collections import scala.collection.JavaConversions._ import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet} -import com.google.protobuf.ByteString +import org.apache.mesos.protobuf.ByteString import org.apache.mesos.{Scheduler => MScheduler} import org.apache.mesos._ import org.apache.mesos.Protos.{TaskInfo => MesosTaskInfo, TaskState => MesosTaskState, _} diff --git a/pom.xml b/pom.xml index c4e1c6be52a1b..dd1d262881b93 100644 --- a/pom.xml +++ b/pom.xml @@ -113,7 +113,8 @@ 2.10.4 2.10 - 0.13.0 + 0.18.1 + shaded-protobuf org.spark-project.akka 2.2.3-shaded-protobuf 1.7.5 @@ -349,6 +350,13 @@ org.apache.mesos mesos ${mesos.version} + ${mesos.classifier} + + + com.google.protobuf + protobuf-java + + commons-net diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 12791e490ae2b..57b3e22f81713 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -343,7 +343,7 @@ object SparkBuild extends Build { "org.spark-project.akka" %% "akka-testkit" % akkaVersion % "test", "org.json4s" %% "json4s-jackson" % "3.2.6" excludeAll(excludeScalap), "colt" % "colt" % "1.2.0", - "org.apache.mesos" % "mesos" % "0.13.0", + "org.apache.mesos" % "mesos" % "0.18.1" classifier("shaded-protobuf") exclude("com.google.protobuf", "protobuf-java"), "commons-net" % "commons-net" % "2.2", "net.java.dev.jets3t" % "jets3t" % jets3tVersion excludeAll(excludeCommonsLogging), "org.apache.derby" % "derby" % "10.4.2.0" % "test", From 0e2bde2030f8e455c5a269fc38d4ff05b395ca32 Mon Sep 17 00:00:00 2001 From: Ankur Dave Date: Mon, 12 May 2014 13:05:24 -0700 Subject: [PATCH 04/99] SPARK-1786: Reopening PR 724 Addressing issue in MimaBuild.scala. Author: Ankur Dave Author: Joseph E. Gonzalez Closes #742 from jegonzal/edge_partition_serialization and squashes the following commits: 8ba6e0d [Ankur Dave] Add concatenation operators to MimaBuild.scala cb2ed3a [Joseph E. Gonzalez] addressing missing exclusion in MimaBuild.scala 5d27824 [Ankur Dave] Disable reference tracking to fix serialization test c0a9ae5 [Ankur Dave] Add failing test for EdgePartition Kryo serialization a4a3faa [Joseph E. Gonzalez] Making EdgePartition serializable. --- .../spark/graphx/GraphKryoRegistrator.scala | 9 ++++++--- .../spark/graphx/impl/EdgePartition.scala | 14 +++++++------- .../graphx/impl/EdgePartitionBuilder.scala | 4 ++-- .../graphx/impl/EdgeTripletIterator.scala | 2 +- .../graphx/impl/RoutingTablePartition.scala | 4 ++-- .../graphx/impl/ShippableVertexPartition.scala | 2 +- .../spark/graphx/impl/VertexPartition.scala | 2 +- .../graphx/impl/VertexPartitionBase.scala | 6 +++--- .../graphx/impl/VertexPartitionBaseOps.scala | 4 ++-- ...ala => GraphXPrimitiveKeyOpenHashMap.scala} | 2 +- .../spark/graphx/impl/EdgePartitionSuite.scala | 18 ++++++++++++++++++ project/MimaBuild.scala | 8 +++++--- 12 files changed, 49 insertions(+), 26 deletions(-) rename graphx/src/main/scala/org/apache/spark/graphx/util/collection/{PrimitiveKeyOpenHashMap.scala => GraphXPrimitiveKeyOpenHashMap.scala} (98%) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala index d295d0127ac72..f97f329c0e832 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala @@ -24,6 +24,9 @@ import org.apache.spark.util.BoundedPriorityQueue import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx.impl._ +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap +import org.apache.spark.util.collection.OpenHashSet + /** * Registers GraphX classes with Kryo for improved performance. @@ -43,8 +46,8 @@ class GraphKryoRegistrator extends KryoRegistrator { kryo.register(classOf[PartitionStrategy]) kryo.register(classOf[BoundedPriorityQueue[Object]]) kryo.register(classOf[EdgeDirection]) - - // This avoids a large number of hash table lookups. - kryo.setReferences(false) + kryo.register(classOf[GraphXPrimitiveKeyOpenHashMap[VertexId, Int]]) + kryo.register(classOf[OpenHashSet[Int]]) + kryo.register(classOf[OpenHashSet[Long]]) } } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala index 871e81f8d245c..a5c9cd1f8b4e6 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala @@ -20,7 +20,7 @@ package org.apache.spark.graphx.impl import scala.reflect.{classTag, ClassTag} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap /** * A collection of edges stored in columnar format, along with any vertex attributes referenced. The @@ -42,12 +42,12 @@ import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap private[graphx] class EdgePartition[ @specialized(Char, Int, Boolean, Byte, Long, Float, Double) ED: ClassTag, VD: ClassTag]( - @transient val srcIds: Array[VertexId], - @transient val dstIds: Array[VertexId], - @transient val data: Array[ED], - @transient val index: PrimitiveKeyOpenHashMap[VertexId, Int], - @transient val vertices: VertexPartition[VD], - @transient val activeSet: Option[VertexSet] = None + val srcIds: Array[VertexId] = null, + val dstIds: Array[VertexId] = null, + val data: Array[ED] = null, + val index: GraphXPrimitiveKeyOpenHashMap[VertexId, Int] = null, + val vertices: VertexPartition[VD] = null, + val activeSet: Option[VertexSet] = None ) extends Serializable { /** Return a new `EdgePartition` with the specified edge data. */ diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala index ecb49bef42e45..4520beb991515 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartitionBuilder.scala @@ -23,7 +23,7 @@ import scala.util.Sorting import org.apache.spark.util.collection.{BitSet, OpenHashSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap private[graphx] class EdgePartitionBuilder[@specialized(Long, Int, Double) ED: ClassTag, VD: ClassTag]( @@ -41,7 +41,7 @@ class EdgePartitionBuilder[@specialized(Long, Int, Double) ED: ClassTag, VD: Cla val srcIds = new Array[VertexId](edgeArray.size) val dstIds = new Array[VertexId](edgeArray.size) val data = new Array[ED](edgeArray.size) - val index = new PrimitiveKeyOpenHashMap[VertexId, Int] + val index = new GraphXPrimitiveKeyOpenHashMap[VertexId, Int] // Copy edges into columnar structures, tracking the beginnings of source vertex id clusters and // adding them to the index if (edgeArray.length > 0) { diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala index ebb0b9418d65d..56f79a7097fce 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgeTripletIterator.scala @@ -20,7 +20,7 @@ package org.apache.spark.graphx.impl import scala.reflect.ClassTag import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap /** * The Iterator type returned when constructing edge triplets. This could be an anonymous class in diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala index 927e32ad0f448..d02e9238adba5 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/RoutingTablePartition.scala @@ -25,7 +25,7 @@ import org.apache.spark.rdd.ShuffledRDD import org.apache.spark.util.collection.{BitSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap /** * A message from the edge partition `pid` to the vertex partition containing `vid` specifying that @@ -69,7 +69,7 @@ object RoutingTablePartition { : Iterator[RoutingTableMessage] = { // Determine which positions each vertex id appears in using a map where the low 2 bits // represent src and dst - val map = new PrimitiveKeyOpenHashMap[VertexId, Byte] + val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, Byte] edgePartition.srcIds.iterator.foreach { srcId => map.changeValue(srcId, 0x1, (b: Byte) => (b | 0x1).toByte) } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala index f4e221d4e05ae..dca54b8a7da86 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/ShippableVertexPartition.scala @@ -22,7 +22,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.{BitSet, PrimitiveVector} import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap /** Stores vertex attributes to ship to an edge partition. */ private[graphx] diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala index f1d174720a1ba..55c7a19d1bdab 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartition.scala @@ -22,7 +22,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap private[graphx] object VertexPartition { /** Construct a `VertexPartition` from the given vertices. */ diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala index 8d9e0204d27f2..34939b24440aa 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBase.scala @@ -23,7 +23,7 @@ import scala.reflect.ClassTag import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap private[graphx] object VertexPartitionBase { /** @@ -32,7 +32,7 @@ private[graphx] object VertexPartitionBase { */ def initFrom[VD: ClassTag](iter: Iterator[(VertexId, VD)]) : (VertexIdToIndexMap, Array[VD], BitSet) = { - val map = new PrimitiveKeyOpenHashMap[VertexId, VD] + val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] iter.foreach { pair => map(pair._1) = pair._2 } @@ -45,7 +45,7 @@ private[graphx] object VertexPartitionBase { */ def initFrom[VD: ClassTag](iter: Iterator[(VertexId, VD)], mergeFunc: (VD, VD) => VD) : (VertexIdToIndexMap, Array[VD], BitSet) = { - val map = new PrimitiveKeyOpenHashMap[VertexId, VD] + val map = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] iter.foreach { pair => map.setMerge(pair._1, pair._2, mergeFunc) } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala index 21ff615feca6c..a4f769b294010 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/VertexPartitionBaseOps.scala @@ -25,7 +25,7 @@ import org.apache.spark.Logging import org.apache.spark.util.collection.BitSet import org.apache.spark.graphx._ -import org.apache.spark.graphx.util.collection.PrimitiveKeyOpenHashMap +import org.apache.spark.graphx.util.collection.GraphXPrimitiveKeyOpenHashMap /** * An class containing additional operations for subclasses of VertexPartitionBase that provide @@ -224,7 +224,7 @@ private[graphx] abstract class VertexPartitionBaseOps * Construct a new VertexPartition whose index contains only the vertices in the mask. */ def reindex(): Self[VD] = { - val hashMap = new PrimitiveKeyOpenHashMap[VertexId, VD] + val hashMap = new GraphXPrimitiveKeyOpenHashMap[VertexId, VD] val arbitraryMerge = (a: VD, b: VD) => a for ((k, v) <- self.iterator) { hashMap.setMerge(k, v, arbitraryMerge) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala similarity index 98% rename from graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala rename to graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala index 7b02e2ed1a9cb..57b01b6f2e1fb 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/util/collection/PrimitiveKeyOpenHashMap.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/collection/GraphXPrimitiveKeyOpenHashMap.scala @@ -29,7 +29,7 @@ import scala.reflect._ * Under the hood, it uses our OpenHashSet implementation. */ private[graphx] -class PrimitiveKeyOpenHashMap[@specialized(Long, Int) K: ClassTag, +class GraphXPrimitiveKeyOpenHashMap[@specialized(Long, Int) K: ClassTag, @specialized(Long, Int, Double) V: ClassTag]( val keySet: OpenHashSet[K], var _values: Array[V]) extends Iterable[(K, V)] diff --git a/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala index d2e0c01bc35ef..28fd112f2b124 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/impl/EdgePartitionSuite.scala @@ -22,6 +22,9 @@ import scala.util.Random import org.scalatest.FunSuite +import org.apache.spark.SparkConf +import org.apache.spark.serializer.KryoSerializer + import org.apache.spark.graphx._ class EdgePartitionSuite extends FunSuite { @@ -120,4 +123,19 @@ class EdgePartitionSuite extends FunSuite { assert(!ep.isActive(-1)) assert(ep.numActives == Some(2)) } + + test("Kryo serialization") { + val aList = List((0, 1, 0), (1, 0, 0), (1, 2, 0), (5, 4, 0), (5, 5, 0)) + val a: EdgePartition[Int, Int] = makeEdgePartition(aList) + val conf = new SparkConf() + .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer") + .set("spark.kryo.registrator", "org.apache.spark.graphx.GraphKryoRegistrator") + val s = new KryoSerializer(conf).newInstance() + val aSer: EdgePartition[Int, Int] = s.deserialize(s.serialize(a)) + assert(aSer.srcIds.toList === a.srcIds.toList) + assert(aSer.dstIds.toList === a.dstIds.toList) + assert(aSer.data.toList === a.data.toList) + assert(aSer.index != null) + assert(aSer.vertices.iterator.toSet === a.vertices.iterator.toSet) + } } diff --git a/project/MimaBuild.scala b/project/MimaBuild.scala index fafc9b36a77d3..e147be7ddaa61 100644 --- a/project/MimaBuild.scala +++ b/project/MimaBuild.scala @@ -30,7 +30,7 @@ object MimaBuild { // Read package-private excludes from file val excludeFilePath = (base.getAbsolutePath + "/.mima-excludes") - val excludeFile = file(excludeFilePath) + val excludeFile = file(excludeFilePath) val packagePrivateList: Seq[String] = if (!excludeFile.exists()) { Seq() @@ -41,10 +41,10 @@ object MimaBuild { // Exclude a single class and its corresponding object def excludeClass(className: String) = { Seq( - excludePackage(className), + excludePackage(className), ProblemFilters.exclude[MissingClassProblem](className), ProblemFilters.exclude[MissingTypesProblem](className), - excludePackage(className + "$"), + excludePackage(className + "$"), ProblemFilters.exclude[MissingClassProblem](className + "$"), ProblemFilters.exclude[MissingTypesProblem](className + "$") ) @@ -78,6 +78,8 @@ object MimaBuild { excludeSparkClass("graphx.VertexRDD") ++ excludeSparkClass("graphx.impl.GraphImpl") ++ excludeSparkClass("graphx.impl.RoutingTable") ++ + excludeSparkClass("graphx.util.collection.PrimitiveKeyOpenHashMap") ++ + excludeSparkClass("graphx.util.collection.GraphXPrimitiveKeyOpenHashMap") ++ excludeSparkClass("mllib.recommendation.MFDataGenerator") ++ excludeSparkClass("mllib.optimization.SquaredGradient") ++ excludeSparkClass("mllib.regression.RidgeRegressionWithSGD") ++ From 1e4a65e69489ff877e6da6f78b1c1306335e373c Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 13:20:23 -0700 Subject: [PATCH 05/99] BUILD: Include Hive with default packages when creating a release --- dev/create-release/create-release.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/dev/create-release/create-release.sh b/dev/create-release/create-release.sh index 33552a74920a7..b7a0a01c3bad2 100755 --- a/dev/create-release/create-release.sh +++ b/dev/create-release/create-release.sh @@ -109,9 +109,9 @@ make_binary_release() { spark-$RELEASE_VERSION-bin-$NAME.tgz.sha } -make_binary_release "hadoop1" "--hadoop 1.0.4" -make_binary_release "cdh4" "--hadoop 2.0.0-mr1-cdh4.2.0" -make_binary_release "hadoop2" "--with-yarn --hadoop 2.2.0" +make_binary_release "hadoop1" "--with-hive --hadoop 1.0.4" +make_binary_release "cdh4" "--with-hive --hadoop 2.0.0-mr1-cdh4.2.0" +make_binary_release "hadoop2" "--with-hive --with-yarn --hadoop 2.2.0" # Copy data echo "Copying release tarballs" From 7120a2979d0a9f0f54a88b2416be7ca10e74f409 Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Mon, 12 May 2014 14:16:19 -0700 Subject: [PATCH 06/99] SPARK-1798. Tests should clean up temp files MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Three issues related to temp files that tests generate – these should be touched up for hygiene but are not urgent. Modules have a log4j.properties which directs the unit-test.log output file to a directory like `[module]/target/unit-test.log`. But this ends up creating `[module]/[module]/target/unit-test.log` instead of former. The `work/` directory is not deleted by "mvn clean", in the parent and in modules. Neither is the `checkpoint/` directory created under the various external modules. Many tests create a temp directory, which is not usually deleted. This can be largely resolved by calling `deleteOnExit()` at creation and trying to call `Utils.deleteRecursively` consistently to clean up, sometimes in an `@After` method. _If anyone seconds the motion, I can create a more significant change that introduces a new test trait along the lines of `LocalSparkContext`, which provides management of temp directories for subclasses to take advantage of._ Author: Sean Owen Closes #732 from srowen/SPARK-1798 and squashes the following commits: 5af578e [Sean Owen] Try to consistently delete test temp dirs and files, and set deleteOnExit() for each b21b356 [Sean Owen] Remove work/ and checkpoint/ dirs with mvn clean bdd0f41 [Sean Owen] Remove duplicate module dir in log4j.properties output path for tests --- bagel/src/test/resources/log4j.properties | 2 +- .../scala/org/apache/spark/TestUtils.scala | 1 + .../scala/org/apache/spark/util/Utils.scala | 18 +++--- .../java/org/apache/spark/JavaAPISuite.java | 18 ++---- core/src/test/resources/log4j.properties | 2 +- .../org/apache/spark/CheckpointSuite.scala | 5 +- .../org/apache/spark/FileServerSuite.scala | 18 ++++-- .../scala/org/apache/spark/FileSuite.scala | 56 +++++++++---------- .../WholeTextFileRecordReaderSuite.scala | 4 +- .../spark/rdd/PairRDDFunctionsSuite.scala | 2 + .../scheduler/EventLoggingListenerSuite.scala | 15 +++-- .../spark/scheduler/ReplayListenerSuite.scala | 14 +++-- .../spark/storage/DiskBlockManagerSuite.scala | 30 +++++++--- .../apache/spark/util/FileLoggerSuite.scala | 17 ++++-- .../org/apache/spark/util/UtilsSuite.scala | 1 + .../flume/src/test/resources/log4j.properties | 2 +- .../kafka/src/test/resources/log4j.properties | 2 +- .../mqtt/src/test/resources/log4j.properties | 2 +- .../src/test/resources/log4j.properties | 2 +- .../src/test/resources/log4j.properties | 2 +- .../java/org/apache/spark/Java8APISuite.java | 3 + graphx/src/test/resources/log4j.properties | 2 +- mllib/src/test/resources/log4j.properties | 2 +- .../spark/mllib/util/MLUtilsSuite.scala | 17 ++---- pom.xml | 15 +++++ repl/src/test/resources/log4j.properties | 2 +- .../spark/repl/ExecutorClassLoaderSuite.scala | 24 ++++++-- .../org/apache/spark/repl/ReplSuite.scala | 3 + .../apache/spark/sql/InsertIntoSuite.scala | 12 ++++ .../org/apache/spark/sql/hive/TestHive.scala | 1 + .../streaming/util/MasterFailureTest.scala | 3 + .../apache/spark/streaming/JavaAPISuite.java | 5 +- streaming/src/test/resources/log4j.properties | 2 +- .../spark/streaming/CheckpointSuite.scala | 2 + .../spark/streaming/InputStreamsSuite.scala | 1 + 35 files changed, 193 insertions(+), 114 deletions(-) diff --git a/bagel/src/test/resources/log4j.properties b/bagel/src/test/resources/log4j.properties index 5cdcf35b23a6c..30b4baa4d714a 100644 --- a/bagel/src/test/resources/log4j.properties +++ b/bagel/src/test/resources/log4j.properties @@ -19,7 +19,7 @@ log4j.rootCategory=INFO, file log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=bagel/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/core/src/main/scala/org/apache/spark/TestUtils.scala b/core/src/main/scala/org/apache/spark/TestUtils.scala index 8ae02154823ee..885c6829a2d72 100644 --- a/core/src/main/scala/org/apache/spark/TestUtils.scala +++ b/core/src/main/scala/org/apache/spark/TestUtils.scala @@ -43,6 +43,7 @@ private[spark] object TestUtils { */ def createJarWithClasses(classNames: Seq[String], value: String = ""): URL = { val tempDir = Files.createTempDir() + tempDir.deleteOnExit() val files = for (name <- classNames) yield createCompiledClass(name, tempDir, value) val jarFile = new File(tempDir, "testJar-%s.jar".format(System.currentTimeMillis())) createJar(files, jarFile) diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 8f7594ada2ba1..0631e54237923 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -586,15 +586,17 @@ private[spark] object Utils extends Logging { * Don't follow directories if they are symlinks. */ def deleteRecursively(file: File) { - if ((file.isDirectory) && !isSymlink(file)) { - for (child <- listFilesSafely(file)) { - deleteRecursively(child) + if (file != null) { + if ((file.isDirectory) && !isSymlink(file)) { + for (child <- listFilesSafely(file)) { + deleteRecursively(child) + } } - } - if (!file.delete()) { - // Delete can also fail if the file simply did not exist - if (file.exists()) { - throw new IOException("Failed to delete: " + file.getAbsolutePath) + if (!file.delete()) { + // Delete can also fail if the file simply did not exist + if (file.exists()) { + throw new IOException("Failed to delete: " + file.getAbsolutePath) + } } } } diff --git a/core/src/test/java/org/apache/spark/JavaAPISuite.java b/core/src/test/java/org/apache/spark/JavaAPISuite.java index 1912015827927..3dd79243ab5bd 100644 --- a/core/src/test/java/org/apache/spark/JavaAPISuite.java +++ b/core/src/test/java/org/apache/spark/JavaAPISuite.java @@ -18,7 +18,6 @@ package org.apache.spark; import java.io.*; -import java.lang.StringBuilder; import java.util.*; import scala.Tuple2; @@ -49,16 +48,20 @@ import org.apache.spark.partial.PartialResult; import org.apache.spark.storage.StorageLevel; import org.apache.spark.util.StatCounter; +import org.apache.spark.util.Utils; // The test suite itself is Serializable so that anonymous Function implementations can be // serialized, as an alternative to converting these anonymous classes to static inner classes; // see http://stackoverflow.com/questions/758570/. public class JavaAPISuite implements Serializable { private transient JavaSparkContext sc; + private transient File tempDir; @Before public void setUp() { sc = new JavaSparkContext("local", "JavaAPISuite"); + tempDir = Files.createTempDir(); + tempDir.deleteOnExit(); } @After @@ -67,6 +70,7 @@ public void tearDown() { sc = null; // To avoid Akka rebinding to the same port, since it doesn't unbind immediately on shutdown System.clearProperty("spark.driver.port"); + Utils.deleteRecursively(tempDir); } static class ReverseIntComparator implements Comparator, Serializable { @@ -611,7 +615,6 @@ public void glom() { @Test public void textFiles() throws IOException { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); JavaRDD rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4)); rdd.saveAsTextFile(outputDir); @@ -630,7 +633,6 @@ public void wholeTextFiles() throws IOException { byte[] content1 = "spark is easy to use.\n".getBytes("utf-8"); byte[] content2 = "spark is also easy to use.\n".getBytes("utf-8"); - File tempDir = Files.createTempDir(); String tempDirName = tempDir.getAbsolutePath(); DataOutputStream ds = new DataOutputStream(new FileOutputStream(tempDirName + "/part-00000")); ds.write(content1); @@ -653,7 +655,6 @@ public void wholeTextFiles() throws IOException { @Test public void textFilesCompressed() throws IOException { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); JavaRDD rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4)); rdd.saveAsTextFile(outputDir, DefaultCodec.class); @@ -667,7 +668,6 @@ public void textFilesCompressed() throws IOException { @SuppressWarnings("unchecked") @Test public void sequenceFile() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -697,7 +697,6 @@ public Tuple2 call(Tuple2 pair) { @SuppressWarnings("unchecked") @Test public void writeWithNewAPIHadoopFile() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -728,7 +727,6 @@ public String call(Tuple2 x) { @SuppressWarnings("unchecked") @Test public void readWithNewAPIHadoopFile() throws IOException { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -758,7 +756,6 @@ public String call(Tuple2 x) { @Test public void objectFilesOfInts() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); JavaRDD rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4)); rdd.saveAsObjectFile(outputDir); @@ -771,7 +768,6 @@ public void objectFilesOfInts() { @SuppressWarnings("unchecked") @Test public void objectFilesOfComplexTypes() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -788,7 +784,6 @@ public void objectFilesOfComplexTypes() { @SuppressWarnings("unchecked") @Test public void hadoopFile() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -818,7 +813,6 @@ public String call(Tuple2 x) { @SuppressWarnings("unchecked") @Test public void hadoopFileCompressed() { - File tempDir = Files.createTempDir(); String outputDir = new File(tempDir, "output_compressed").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -948,7 +942,6 @@ public String call(Integer t) throws Exception { @Test public void checkpointAndComputation() { - File tempDir = Files.createTempDir(); JavaRDD rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); sc.setCheckpointDir(tempDir.getAbsolutePath()); Assert.assertEquals(false, rdd.isCheckpointed()); @@ -960,7 +953,6 @@ public void checkpointAndComputation() { @Test public void checkpointAndRestore() { - File tempDir = Files.createTempDir(); JavaRDD rdd = sc.parallelize(Arrays.asList(1, 2, 3, 4, 5)); sc.setCheckpointDir(tempDir.getAbsolutePath()); Assert.assertEquals(false, rdd.isCheckpointed()); diff --git a/core/src/test/resources/log4j.properties b/core/src/test/resources/log4j.properties index f6fef03689a7c..26b73a1b39744 100644 --- a/core/src/test/resources/log4j.properties +++ b/core/src/test/resources/log4j.properties @@ -19,7 +19,7 @@ log4j.rootCategory=INFO, file log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=core/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/core/src/test/scala/org/apache/spark/CheckpointSuite.scala b/core/src/test/scala/org/apache/spark/CheckpointSuite.scala index d2555b7c052c1..64933f4b1046d 100644 --- a/core/src/test/scala/org/apache/spark/CheckpointSuite.scala +++ b/core/src/test/scala/org/apache/spark/CheckpointSuite.scala @@ -35,6 +35,7 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { override def beforeEach() { super.beforeEach() checkpointDir = File.createTempFile("temp", "") + checkpointDir.deleteOnExit() checkpointDir.delete() sc = new SparkContext("local", "test") sc.setCheckpointDir(checkpointDir.toString) @@ -42,9 +43,7 @@ class CheckpointSuite extends FunSuite with LocalSparkContext with Logging { override def afterEach() { super.afterEach() - if (checkpointDir != null) { - checkpointDir.delete() - } + Utils.deleteRecursively(checkpointDir) } test("basic checkpointing") { diff --git a/core/src/test/scala/org/apache/spark/FileServerSuite.scala b/core/src/test/scala/org/apache/spark/FileServerSuite.scala index d651fbbac4e97..7e18f45de7b5b 100644 --- a/core/src/test/scala/org/apache/spark/FileServerSuite.scala +++ b/core/src/test/scala/org/apache/spark/FileServerSuite.scala @@ -24,9 +24,11 @@ import com.google.common.io.Files import org.scalatest.FunSuite import org.apache.spark.SparkContext._ +import org.apache.spark.util.Utils class FileServerSuite extends FunSuite with LocalSparkContext { + @transient var tmpDir: File = _ @transient var tmpFile: File = _ @transient var tmpJarUrl: String = _ @@ -38,15 +40,18 @@ class FileServerSuite extends FunSuite with LocalSparkContext { override def beforeAll() { super.beforeAll() - val tmpDir = new File(Files.createTempDir(), "test") - tmpDir.mkdir() - val textFile = new File(tmpDir, "FileServerSuite.txt") + tmpDir = Files.createTempDir() + tmpDir.deleteOnExit() + val testTempDir = new File(tmpDir, "test") + testTempDir.mkdir() + + val textFile = new File(testTempDir, "FileServerSuite.txt") val pw = new PrintWriter(textFile) pw.println("100") pw.close() - val jarFile = new File(tmpDir, "test.jar") + val jarFile = new File(testTempDir, "test.jar") val jarStream = new FileOutputStream(jarFile) val jar = new JarOutputStream(jarStream, new java.util.jar.Manifest()) System.setProperty("spark.authenticate", "false") @@ -70,6 +75,11 @@ class FileServerSuite extends FunSuite with LocalSparkContext { tmpJarUrl = jarFile.toURI.toURL.toString } + override def afterAll() { + super.afterAll() + Utils.deleteRecursively(tmpDir) + } + test("Distributing files locally") { sc = new SparkContext("local[4]", "test") sc.addFile(tmpFile.toString) diff --git a/core/src/test/scala/org/apache/spark/FileSuite.scala b/core/src/test/scala/org/apache/spark/FileSuite.scala index b9b668d3cc62a..1f2206b1f0379 100644 --- a/core/src/test/scala/org/apache/spark/FileSuite.scala +++ b/core/src/test/scala/org/apache/spark/FileSuite.scala @@ -30,12 +30,24 @@ import org.apache.hadoop.mapreduce.Job import org.scalatest.FunSuite import org.apache.spark.SparkContext._ +import org.apache.spark.util.Utils class FileSuite extends FunSuite with LocalSparkContext { + var tempDir: File = _ + + override def beforeEach() { + super.beforeEach() + tempDir = Files.createTempDir() + tempDir.deleteOnExit() + } + + override def afterEach() { + super.afterEach() + Utils.deleteRecursively(tempDir) + } test("text files") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 4) nums.saveAsTextFile(outputDir) @@ -49,7 +61,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("text files (compressed)") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val normalDir = new File(tempDir, "output_normal").getAbsolutePath val compressedOutputDir = new File(tempDir, "output_compressed").getAbsolutePath val codec = new DefaultCodec() @@ -71,7 +82,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("SequenceFiles") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (x, "a" * x)) // (1,a), (2,aa), (3,aaa) nums.saveAsSequenceFile(outputDir) @@ -82,7 +92,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("SequenceFile (compressed)") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val normalDir = new File(tempDir, "output_normal").getAbsolutePath val compressedOutputDir = new File(tempDir, "output_compressed").getAbsolutePath val codec = new DefaultCodec() @@ -104,7 +113,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("SequenceFile with writable key") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (new IntWritable(x), "a" * x)) nums.saveAsSequenceFile(outputDir) @@ -115,7 +123,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("SequenceFile with writable value") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (x, new Text("a" * x))) nums.saveAsSequenceFile(outputDir) @@ -126,7 +133,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("SequenceFile with writable key and value") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (new IntWritable(x), new Text("a" * x))) nums.saveAsSequenceFile(outputDir) @@ -137,7 +143,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("implicit conversions in reading SequenceFiles") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (x, "a" * x)) // (1,a), (2,aa), (3,aaa) nums.saveAsSequenceFile(outputDir) @@ -154,7 +159,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("object files of ints") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 4) nums.saveAsObjectFile(outputDir) @@ -165,7 +169,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("object files of complex types") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (x, "a" * x)) nums.saveAsObjectFile(outputDir) @@ -177,7 +180,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("write SequenceFile using new Hadoop API") { import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (new IntWritable(x), new Text("a" * x))) nums.saveAsNewAPIHadoopFile[SequenceFileOutputFormat[IntWritable, Text]]( @@ -189,7 +191,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("read SequenceFile using new Hadoop API") { import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val outputDir = new File(tempDir, "output").getAbsolutePath val nums = sc.makeRDD(1 to 3).map(x => (new IntWritable(x), new Text("a" * x))) nums.saveAsSequenceFile(outputDir) @@ -200,7 +201,6 @@ class FileSuite extends FunSuite with LocalSparkContext { test("file caching") { sc = new SparkContext("local", "test") - val tempDir = Files.createTempDir() val out = new FileWriter(tempDir + "/input") out.write("Hello world!\n") out.write("What's up?\n") @@ -214,67 +214,61 @@ class FileSuite extends FunSuite with LocalSparkContext { test ("prevent user from overwriting the empty directory (old Hadoop API)") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array((1, "a"), (1, "a"), (2, "b"), (3, "c")), 1) intercept[FileAlreadyExistsException] { - randomRDD.saveAsTextFile(tempdir.getPath) + randomRDD.saveAsTextFile(tempDir.getPath) } } test ("prevent user from overwriting the non-empty directory (old Hadoop API)") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array((1, "a"), (1, "a"), (2, "b"), (3, "c")), 1) - randomRDD.saveAsTextFile(tempdir.getPath + "/output") - assert(new File(tempdir.getPath + "/output/part-00000").exists() === true) + randomRDD.saveAsTextFile(tempDir.getPath + "/output") + assert(new File(tempDir.getPath + "/output/part-00000").exists() === true) intercept[FileAlreadyExistsException] { - randomRDD.saveAsTextFile(tempdir.getPath + "/output") + randomRDD.saveAsTextFile(tempDir.getPath + "/output") } } test ("prevent user from overwriting the empty directory (new Hadoop API)") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array(("key1", "a"), ("key2", "a"), ("key3", "b"), ("key4", "c")), 1) intercept[FileAlreadyExistsException] { - randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempdir.getPath) + randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempDir.getPath) } } test ("prevent user from overwriting the non-empty directory (new Hadoop API)") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array(("key1", "a"), ("key2", "a"), ("key3", "b"), ("key4", "c")), 1) - randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempdir.getPath + "/output") - assert(new File(tempdir.getPath + "/output/part-r-00000").exists() === true) + randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempDir.getPath + "/output") + assert(new File(tempDir.getPath + "/output/part-r-00000").exists() === true) intercept[FileAlreadyExistsException] { - randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempdir.getPath) + randomRDD.saveAsNewAPIHadoopFile[NewTextOutputFormat[String, String]](tempDir.getPath) } } test ("save Hadoop Dataset through old Hadoop API") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array(("key1", "a"), ("key2", "a"), ("key3", "b"), ("key4", "c")), 1) val job = new JobConf() job.setOutputKeyClass(classOf[String]) job.setOutputValueClass(classOf[String]) job.set("mapred.output.format.class", classOf[TextOutputFormat[String, String]].getName) - job.set("mapred.output.dir", tempdir.getPath + "/outputDataset_old") + job.set("mapred.output.dir", tempDir.getPath + "/outputDataset_old") randomRDD.saveAsHadoopDataset(job) - assert(new File(tempdir.getPath + "/outputDataset_old/part-00000").exists() === true) + assert(new File(tempDir.getPath + "/outputDataset_old/part-00000").exists() === true) } test ("save Hadoop Dataset through new Hadoop API") { sc = new SparkContext("local", "test") - val tempdir = Files.createTempDir() val randomRDD = sc.parallelize(Array(("key1", "a"), ("key2", "a"), ("key3", "b"), ("key4", "c")), 1) val job = new Job(sc.hadoopConfiguration) job.setOutputKeyClass(classOf[String]) job.setOutputValueClass(classOf[String]) job.setOutputFormatClass(classOf[NewTextOutputFormat[String, String]]) - job.getConfiguration.set("mapred.output.dir", tempdir.getPath + "/outputDataset_new") + job.getConfiguration.set("mapred.output.dir", tempDir.getPath + "/outputDataset_new") randomRDD.saveAsNewAPIHadoopDataset(job.getConfiguration) - assert(new File(tempdir.getPath + "/outputDataset_new/part-r-00000").exists() === true) + assert(new File(tempDir.getPath + "/outputDataset_new/part-r-00000").exists() === true) } } diff --git a/core/src/test/scala/org/apache/spark/input/WholeTextFileRecordReaderSuite.scala b/core/src/test/scala/org/apache/spark/input/WholeTextFileRecordReaderSuite.scala index 33d6de9a76405..d5ebfb3f3fae1 100644 --- a/core/src/test/scala/org/apache/spark/input/WholeTextFileRecordReaderSuite.scala +++ b/core/src/test/scala/org/apache/spark/input/WholeTextFileRecordReaderSuite.scala @@ -31,6 +31,7 @@ import org.scalatest.FunSuite import org.apache.hadoop.io.Text import org.apache.spark.SparkContext +import org.apache.spark.util.Utils /** * Tests the correctness of @@ -67,6 +68,7 @@ class WholeTextFileRecordReaderSuite extends FunSuite with BeforeAndAfterAll { test("Correctness of WholeTextFileRecordReader.") { val dir = Files.createTempDir() + dir.deleteOnExit() println(s"Local disk address is ${dir.toString}.") WholeTextFileRecordReaderSuite.files.foreach { case (filename, contents) => @@ -86,7 +88,7 @@ class WholeTextFileRecordReaderSuite extends FunSuite with BeforeAndAfterAll { s"file $filename contents can not match.") } - dir.delete() + Utils.deleteRecursively(dir) } } diff --git a/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala b/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala index 8f3e6bd21b752..1230565ea5b7e 100644 --- a/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala @@ -236,11 +236,13 @@ class PairRDDFunctionsSuite extends FunSuite with SharedSparkContext { test("zero-partition RDD") { val emptyDir = Files.createTempDir() + emptyDir.deleteOnExit() val file = sc.textFile(emptyDir.getAbsolutePath) assert(file.partitions.size == 0) assert(file.collect().toList === Nil) // Test that a shuffle on the file works, because this used to be a bug assert(file.map(line => (line, 1)).reduceByKey(_ + _).collect().toList === Nil) + emptyDir.delete() } test("keys and values") { diff --git a/core/src/test/scala/org/apache/spark/scheduler/EventLoggingListenerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/EventLoggingListenerSuite.scala index 95f5bcd855665..21e3db34b8b7a 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/EventLoggingListenerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/EventLoggingListenerSuite.scala @@ -19,7 +19,6 @@ package org.apache.spark.scheduler import scala.collection.mutable import scala.io.Source -import scala.util.Try import com.google.common.io.Files import org.apache.hadoop.fs.{FileStatus, Path} @@ -30,6 +29,8 @@ import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.io.CompressionCodec import org.apache.spark.util.{JsonProtocol, Utils} +import java.io.File + /** * Test whether EventLoggingListener logs events properly. * @@ -43,11 +44,17 @@ class EventLoggingListenerSuite extends FunSuite with BeforeAndAfter { "org.apache.spark.io.LZFCompressionCodec", "org.apache.spark.io.SnappyCompressionCodec" ) - private val testDir = Files.createTempDir() - private val logDirPath = Utils.getFilePath(testDir, "spark-events") + private var testDir: File = _ + private var logDirPath: Path = _ + + before { + testDir = Files.createTempDir() + testDir.deleteOnExit() + logDirPath = Utils.getFilePath(testDir, "spark-events") + } after { - Try { fileSystem.delete(logDirPath, true) } + Utils.deleteRecursively(testDir) } test("Parse names of special files") { diff --git a/core/src/test/scala/org/apache/spark/scheduler/ReplayListenerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/ReplayListenerSuite.scala index d1fe1fc348961..d81499ac6abef 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/ReplayListenerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/ReplayListenerSuite.scala @@ -17,9 +17,7 @@ package org.apache.spark.scheduler -import java.io.PrintWriter - -import scala.util.Try +import java.io.{File, PrintWriter} import com.google.common.io.Files import org.json4s.jackson.JsonMethods._ @@ -39,11 +37,15 @@ class ReplayListenerSuite extends FunSuite with BeforeAndAfter { "org.apache.spark.io.LZFCompressionCodec", "org.apache.spark.io.SnappyCompressionCodec" ) - private val testDir = Files.createTempDir() + private var testDir: File = _ + + before { + testDir = Files.createTempDir() + testDir.deleteOnExit() + } after { - Try { fileSystem.delete(Utils.getFilePath(testDir, "events.txt"), true) } - Try { fileSystem.delete(Utils.getFilePath(testDir, "test-replay"), true) } + Utils.deleteRecursively(testDir) } test("Simple replay") { diff --git a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala index 42bfbf1bdfc74..2167718fd2428 100644 --- a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala @@ -23,18 +23,16 @@ import scala.collection.mutable import scala.language.reflectiveCalls import com.google.common.io.Files -import org.scalatest.{BeforeAndAfterEach, FunSuite} +import org.scalatest.{BeforeAndAfterAll, BeforeAndAfterEach, FunSuite} import org.apache.spark.SparkConf +import org.apache.spark.util.Utils -class DiskBlockManagerSuite extends FunSuite with BeforeAndAfterEach { +class DiskBlockManagerSuite extends FunSuite with BeforeAndAfterEach with BeforeAndAfterAll { private val testConf = new SparkConf(false) - val rootDir0 = Files.createTempDir() - rootDir0.deleteOnExit() - val rootDir1 = Files.createTempDir() - rootDir1.deleteOnExit() - val rootDirs = rootDir0.getName + "," + rootDir1.getName - println("Created root dirs: " + rootDirs) + private var rootDir0: File = _ + private var rootDir1: File = _ + private var rootDirs: String = _ // This suite focuses primarily on consolidation features, // so we coerce consolidation if not already enabled. @@ -48,6 +46,22 @@ class DiskBlockManagerSuite extends FunSuite with BeforeAndAfterEach { var diskBlockManager: DiskBlockManager = _ + override def beforeAll() { + super.beforeAll() + rootDir0 = Files.createTempDir() + rootDir0.deleteOnExit() + rootDir1 = Files.createTempDir() + rootDir1.deleteOnExit() + rootDirs = rootDir0.getName + "," + rootDir1.getName + println("Created root dirs: " + rootDirs) + } + + override def afterAll() { + super.afterAll() + Utils.deleteRecursively(rootDir0) + Utils.deleteRecursively(rootDir1) + } + override def beforeEach() { diskBlockManager = new DiskBlockManager(shuffleBlockManager, rootDirs) shuffleBlockManager.idToSegmentMap.clear() diff --git a/core/src/test/scala/org/apache/spark/util/FileLoggerSuite.scala b/core/src/test/scala/org/apache/spark/util/FileLoggerSuite.scala index f675e1e5b4981..44332fc8dbc23 100644 --- a/core/src/test/scala/org/apache/spark/util/FileLoggerSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/FileLoggerSuite.scala @@ -17,10 +17,9 @@ package org.apache.spark.util -import java.io.IOException +import java.io.{File, IOException} import scala.io.Source -import scala.util.Try import com.google.common.io.Files import org.apache.hadoop.fs.Path @@ -38,12 +37,18 @@ class FileLoggerSuite extends FunSuite with BeforeAndAfter { "org.apache.spark.io.LZFCompressionCodec", "org.apache.spark.io.SnappyCompressionCodec" ) - private val testDir = Files.createTempDir() - private val logDirPath = Utils.getFilePath(testDir, "test-file-logger") - private val logDirPathString = logDirPath.toString + private var testDir: File = _ + private var logDirPath: Path = _ + private var logDirPathString: String = _ + + before { + testDir = Files.createTempDir() + logDirPath = Utils.getFilePath(testDir, "test-file-logger") + logDirPathString = logDirPath.toString + } after { - Try { fileSystem.delete(logDirPath, true) } + Utils.deleteRecursively(testDir) } test("Simple logging") { diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala index eb7fb6318262b..cf9e20d347ddd 100644 --- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala @@ -112,6 +112,7 @@ class UtilsSuite extends FunSuite { test("reading offset bytes of a file") { val tmpDir2 = Files.createTempDir() + tmpDir2.deleteOnExit() val f1Path = tmpDir2 + "/f1" val f1 = new FileOutputStream(f1Path) f1.write("1\n2\n3\n4\n5\n6\n7\n8\n9\n".getBytes(Charsets.UTF_8)) diff --git a/external/flume/src/test/resources/log4j.properties b/external/flume/src/test/resources/log4j.properties index d1bd73a8430e1..45d2ec676df66 100644 --- a/external/flume/src/test/resources/log4j.properties +++ b/external/flume/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=external/flume/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/external/kafka/src/test/resources/log4j.properties b/external/kafka/src/test/resources/log4j.properties index 38910d113050a..45d2ec676df66 100644 --- a/external/kafka/src/test/resources/log4j.properties +++ b/external/kafka/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=external/kafka/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/external/mqtt/src/test/resources/log4j.properties b/external/mqtt/src/test/resources/log4j.properties index d0462c7336df5..45d2ec676df66 100644 --- a/external/mqtt/src/test/resources/log4j.properties +++ b/external/mqtt/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=external/mqtt/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/external/twitter/src/test/resources/log4j.properties b/external/twitter/src/test/resources/log4j.properties index c918335fcdc70..45d2ec676df66 100644 --- a/external/twitter/src/test/resources/log4j.properties +++ b/external/twitter/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=external/twitter/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/external/zeromq/src/test/resources/log4j.properties b/external/zeromq/src/test/resources/log4j.properties index 304683dd0bac3..45d2ec676df66 100644 --- a/external/zeromq/src/test/resources/log4j.properties +++ b/external/zeromq/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=external/zeromq/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/extras/java8-tests/src/test/java/org/apache/spark/Java8APISuite.java b/extras/java8-tests/src/test/java/org/apache/spark/Java8APISuite.java index feabca6733484..84d3b6f243c72 100644 --- a/extras/java8-tests/src/test/java/org/apache/spark/Java8APISuite.java +++ b/extras/java8-tests/src/test/java/org/apache/spark/Java8APISuite.java @@ -39,6 +39,7 @@ import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.*; +import org.apache.spark.util.Utils; /** * Most of these tests replicate org.apache.spark.JavaAPISuite using java 8 @@ -249,6 +250,7 @@ public void mapPartitions() { @Test public void sequenceFile() { File tempDir = Files.createTempDir(); + tempDir.deleteOnExit(); String outputDir = new File(tempDir, "output").getAbsolutePath(); List> pairs = Arrays.asList( new Tuple2(1, "a"), @@ -265,6 +267,7 @@ public void sequenceFile() { JavaPairRDD readRDD = sc.sequenceFile(outputDir, IntWritable.class, Text.class) .mapToPair(pair -> new Tuple2(pair._1().get(), pair._2().toString())); Assert.assertEquals(pairs, readRDD.collect()); + Utils.deleteRecursively(tempDir); } @Test diff --git a/graphx/src/test/resources/log4j.properties b/graphx/src/test/resources/log4j.properties index 85e57f0c4b504..26b73a1b39744 100644 --- a/graphx/src/test/resources/log4j.properties +++ b/graphx/src/test/resources/log4j.properties @@ -19,7 +19,7 @@ log4j.rootCategory=INFO, file log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=graphx/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/mllib/src/test/resources/log4j.properties b/mllib/src/test/resources/log4j.properties index 4265ba6e5de33..ddfc4ac6b23ed 100644 --- a/mllib/src/test/resources/log4j.properties +++ b/mllib/src/test/resources/log4j.properties @@ -19,7 +19,7 @@ log4j.rootCategory=INFO, file log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=mllib/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala index 3f64baf6fe41f..3d05fb68988c8 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala @@ -32,6 +32,7 @@ import com.google.common.io.Files import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vectors} import org.apache.spark.mllib.regression.LabeledPoint import org.apache.spark.mllib.util.MLUtils._ +import org.apache.spark.util.Utils class MLUtilsSuite extends FunSuite with LocalSparkContext { @@ -67,6 +68,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext { |-1 2:4.0 4:5.0 6:6.0 """.stripMargin val tempDir = Files.createTempDir() + tempDir.deleteOnExit() val file = new File(tempDir.getPath, "part-00000") Files.write(lines, file, Charsets.US_ASCII) val path = tempDir.toURI.toString @@ -90,7 +92,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext { assert(multiclassPoints(1).label === -1.0) assert(multiclassPoints(2).label === -1.0) - deleteQuietly(tempDir) + Utils.deleteRecursively(tempDir) } test("saveAsLibSVMFile") { @@ -107,7 +109,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext { .toSet val expected = Set("1.1 1:1.23 3:4.56", "0.0 1:1.01 2:2.02 3:3.03") assert(lines === expected) - deleteQuietly(tempDir) + Utils.deleteRecursively(tempDir) } test("appendBias") { @@ -158,16 +160,5 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext { } } - /** Delete a file/directory quietly. */ - def deleteQuietly(f: File) { - if (f.isDirectory) { - f.listFiles().foreach(deleteQuietly) - } - try { - f.delete() - } catch { - case _: Throwable => - } - } } diff --git a/pom.xml b/pom.xml index dd1d262881b93..5542a32a91368 100644 --- a/pom.xml +++ b/pom.xml @@ -796,6 +796,21 @@ + + org.apache.maven.plugins + maven-clean-plugin + 2.5 + + + + work + + + checkpoint + + + + diff --git a/repl/src/test/resources/log4j.properties b/repl/src/test/resources/log4j.properties index a6d33e69d21f7..9c4896e49698c 100644 --- a/repl/src/test/resources/log4j.properties +++ b/repl/src/test/resources/log4j.properties @@ -19,7 +19,7 @@ log4j.rootCategory=INFO, file log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=repl/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/repl/src/test/scala/org/apache/spark/repl/ExecutorClassLoaderSuite.scala b/repl/src/test/scala/org/apache/spark/repl/ExecutorClassLoaderSuite.scala index 336df988a1b7f..c0af7ceb6d3ef 100644 --- a/repl/src/test/scala/org/apache/spark/repl/ExecutorClassLoaderSuite.scala +++ b/repl/src/test/scala/org/apache/spark/repl/ExecutorClassLoaderSuite.scala @@ -18,7 +18,7 @@ package org.apache.spark.repl import java.io.File -import java.net.URLClassLoader +import java.net.{URL, URLClassLoader} import org.scalatest.BeforeAndAfterAll import org.scalatest.FunSuite @@ -26,21 +26,35 @@ import org.scalatest.FunSuite import com.google.common.io.Files import org.apache.spark.TestUtils +import org.apache.spark.util.Utils class ExecutorClassLoaderSuite extends FunSuite with BeforeAndAfterAll { val childClassNames = List("ReplFakeClass1", "ReplFakeClass2") val parentClassNames = List("ReplFakeClass1", "ReplFakeClass2", "ReplFakeClass3") - val tempDir1 = Files.createTempDir() - val tempDir2 = Files.createTempDir() - val url1 = "file://" + tempDir1 - val urls2 = List(tempDir2.toURI.toURL).toArray + var tempDir1: File = _ + var tempDir2: File = _ + var url1: String = _ + var urls2: Array[URL] = _ override def beforeAll() { + super.beforeAll() + tempDir1 = Files.createTempDir() + tempDir1.deleteOnExit() + tempDir2 = Files.createTempDir() + tempDir2.deleteOnExit() + url1 = "file://" + tempDir1 + urls2 = List(tempDir2.toURI.toURL).toArray childClassNames.foreach(TestUtils.createCompiledClass(_, tempDir1, "1")) parentClassNames.foreach(TestUtils.createCompiledClass(_, tempDir2, "2")) } + override def afterAll() { + super.afterAll() + Utils.deleteRecursively(tempDir1) + Utils.deleteRecursively(tempDir2) + } + test("child first") { val parentLoader = new URLClassLoader(urls2, null) val classLoader = new ExecutorClassLoader(url1, parentLoader, true) diff --git a/repl/src/test/scala/org/apache/spark/repl/ReplSuite.scala b/repl/src/test/scala/org/apache/spark/repl/ReplSuite.scala index 566d96e16ed83..95460aa205331 100644 --- a/repl/src/test/scala/org/apache/spark/repl/ReplSuite.scala +++ b/repl/src/test/scala/org/apache/spark/repl/ReplSuite.scala @@ -26,6 +26,7 @@ import com.google.common.io.Files import org.scalatest.FunSuite import org.apache.spark.SparkContext import org.apache.commons.lang3.StringEscapeUtils +import org.apache.spark.util.Utils class ReplSuite extends FunSuite { @@ -178,6 +179,7 @@ class ReplSuite extends FunSuite { test("interacting with files") { val tempDir = Files.createTempDir() + tempDir.deleteOnExit() val out = new FileWriter(tempDir + "/input") out.write("Hello world!\n") out.write("What's up?\n") @@ -196,6 +198,7 @@ class ReplSuite extends FunSuite { assertContains("res0: Long = 3", output) assertContains("res1: Long = 3", output) assertContains("res2: Long = 3", output) + Utils.deleteRecursively(tempDir) } test("local-cluster mode") { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/InsertIntoSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/InsertIntoSuite.scala index 73d87963b3a0d..4f0b85f26254b 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/InsertIntoSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/InsertIntoSuite.scala @@ -29,6 +29,7 @@ class InsertIntoSuite extends QueryTest { test("insertInto() created parquet file") { val testFilePath = File.createTempFile("sparkSql", "pqt") testFilePath.delete() + testFilePath.deleteOnExit() val testFile = createParquetFile[TestData](testFilePath.getCanonicalPath) testFile.registerAsTable("createAndInsertTest") @@ -76,11 +77,14 @@ class InsertIntoSuite extends QueryTest { sql("SELECT * FROM createAndInsertTest"), testData.collect().toSeq ) + + testFilePath.delete() } test("INSERT INTO parquet table") { val testFilePath = File.createTempFile("sparkSql", "pqt") testFilePath.delete() + testFilePath.deleteOnExit() val testFile = createParquetFile[TestData](testFilePath.getCanonicalPath) testFile.registerAsTable("createAndInsertSQLTest") @@ -126,23 +130,31 @@ class InsertIntoSuite extends QueryTest { sql("SELECT * FROM createAndInsertSQLTest"), testData.collect().toSeq ) + + testFilePath.delete() } test("Double create fails when allowExisting = false") { val testFilePath = File.createTempFile("sparkSql", "pqt") testFilePath.delete() + testFilePath.deleteOnExit() val testFile = createParquetFile[TestData](testFilePath.getCanonicalPath) intercept[RuntimeException] { createParquetFile[TestData](testFilePath.getCanonicalPath, allowExisting = false) } + + testFilePath.delete() } test("Double create does not fail when allowExisting = true") { val testFilePath = File.createTempFile("sparkSql", "pqt") testFilePath.delete() + testFilePath.deleteOnExit() val testFile = createParquetFile[TestData](testFilePath.getCanonicalPath) createParquetFile[TestData](testFilePath.getCanonicalPath, allowExisting = true) + + testFilePath.delete() } } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala index 3ad66a3d7f45f..fa7d010459c63 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala @@ -99,6 +99,7 @@ class TestHiveContext(sc: SparkContext) extends LocalHiveContext(sc) { val hiveFilesTemp = File.createTempFile("catalystHiveFiles", "") hiveFilesTemp.delete() hiveFilesTemp.mkdir() + hiveFilesTemp.deleteOnExit() val inRepoTests = if (System.getProperty("user.dir").endsWith("sql" + File.separator + "hive")) { new File("src" + File.separator + "test" + File.separator + "resources" + File.separator) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/util/MasterFailureTest.scala b/streaming/src/main/scala/org/apache/spark/streaming/util/MasterFailureTest.scala index c48a38590e060..b3ed302db6a38 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/util/MasterFailureTest.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/util/MasterFailureTest.scala @@ -21,6 +21,7 @@ import org.apache.spark.Logging import org.apache.spark.rdd.RDD import org.apache.spark.streaming._ import org.apache.spark.streaming.dstream.{DStream, ForEachDStream} +import org.apache.spark.util.Utils import StreamingContext._ import scala.util.Random @@ -380,6 +381,7 @@ class FileGeneratingThread(input: Seq[String], testDir: Path, interval: Long) override def run() { val localTestDir = Files.createTempDir() + localTestDir.deleteOnExit() var fs = testDir.getFileSystem(new Configuration()) val maxTries = 3 try { @@ -421,6 +423,7 @@ class FileGeneratingThread(input: Seq[String], testDir: Path, interval: Long) case e: Exception => logWarning("File generating in killing thread", e) } finally { fs.close() + Utils.deleteRecursively(localTestDir) } } } diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java index f9bfb9b7444cc..ce58cb12a4564 100644 --- a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java +++ b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java @@ -17,7 +17,6 @@ package org.apache.spark.streaming; -import org.apache.spark.streaming.api.java.*; import scala.Tuple2; import org.junit.Assert; @@ -37,6 +36,8 @@ import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.*; import org.apache.spark.storage.StorageLevel; +import org.apache.spark.streaming.api.java.*; +import org.apache.spark.util.Utils; // The test suite itself is Serializable so that anonymous Function implementations can be // serialized, as an alternative to converting these anonymous classes to static inner classes; @@ -1606,6 +1607,7 @@ public void testCheckpointMasterRecovery() throws InterruptedException { Arrays.asList(8,7)); File tempDir = Files.createTempDir(); + tempDir.deleteOnExit(); ssc.checkpoint(tempDir.getAbsolutePath()); JavaDStream stream = JavaCheckpointTestUtils.attachTestInputStream(ssc, inputData, 1); @@ -1627,6 +1629,7 @@ public Integer call(String s) throws Exception { // will be re-processed after recovery List> finalResult = JavaCheckpointTestUtils.runStreams(ssc, 2, 3); assertOrderInvariantEquals(expectedFinal, finalResult.subList(1, 3)); + Utils.deleteRecursively(tempDir); } diff --git a/streaming/src/test/resources/log4j.properties b/streaming/src/test/resources/log4j.properties index 063529a9cbc67..45d2ec676df66 100644 --- a/streaming/src/test/resources/log4j.properties +++ b/streaming/src/test/resources/log4j.properties @@ -20,7 +20,7 @@ log4j.rootCategory=INFO, file # log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file=org.apache.log4j.FileAppender log4j.appender.file.append=false -log4j.appender.file.file=streaming/target/unit-tests.log +log4j.appender.file.file=target/unit-tests.log log4j.appender.file.layout=org.apache.log4j.PatternLayout log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n diff --git a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala index 25739956cb889..d20a7b728c741 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala @@ -232,6 +232,7 @@ class CheckpointSuite extends TestSuiteBase { test("recovery with file input stream") { // Set up the streaming context and input streams val testDir = Files.createTempDir() + testDir.deleteOnExit() var ssc = new StreamingContext(master, framework, Seconds(1)) ssc.checkpoint(checkpointDir) val fileStream = ssc.textFileStream(testDir.toString) @@ -326,6 +327,7 @@ class CheckpointSuite extends TestSuiteBase { ) // To ensure that all the inputs were received correctly assert(expectedOutput.last === output.last) + Utils.deleteRecursively(testDir) } diff --git a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala index 3fa254065cc44..cd0aa4d0dce70 100644 --- a/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala +++ b/streaming/src/test/scala/org/apache/spark/streaming/InputStreamsSuite.scala @@ -98,6 +98,7 @@ class InputStreamsSuite extends TestSuiteBase with BeforeAndAfter { // Set up the streaming context and input streams val testDir = Files.createTempDir() + testDir.deleteOnExit() val ssc = new StreamingContext(conf, batchDuration) val fileStream = ssc.textFileStream(testDir.toString) val outputBuffer = new ArrayBuffer[Seq[String]] with SynchronizedBuffer[Seq[String]] From 8586bf564fe010dfc19ef26874472a6f85e355fb Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Mon, 12 May 2014 14:17:25 -0700 Subject: [PATCH 07/99] SPARK-1802. Audit dependency graph when Spark is built with -Phive This initial commit resolves the conflicts in the Hive profiles as noted in https://issues.apache.org/jira/browse/SPARK-1802 . Most of the fix was to note that Hive drags in Avro, and so if the hive module depends on Spark's version of the `avro-*` dependencies, it will pull in our exclusions as needed too. But I found we need to copy some exclusions between the two Avro dependencies to get this right. And then had to squash some commons-logging intrusions. This turned up another annoying find, that `hive-exec` is basically an "assembly" artifact that _also_ packages all of its transitive dependencies. This means the final assembly shows lots of collisions between itself and its dependencies, and even other project dependencies. I have a TODO to examine whether that is going to be a deal-breaker or not. In the meantime I'm going to tack on a second commit to this PR that will also fix some similar, last collisions in the YARN profile. Author: Sean Owen Closes #744 from srowen/SPARK-1802 and squashes the following commits: a856604 [Sean Owen] Resolve JAR version conflicts specific to Hive profile --- pom.xml | 16 ++++++++++++++++ sql/hive/pom.xml | 21 +++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/pom.xml b/pom.xml index 5542a32a91368..3554efafb976a 100644 --- a/pom.xml +++ b/pom.xml @@ -535,6 +535,22 @@ io.netty netty + + org.mortbay.jetty + jetty + + + org.mortbay.jetty + jetty-util + + + org.mortbay.jetty + servlet-api + + + org.apache.velocity + velocity + diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml index 889d249146b8c..8b32451d76045 100644 --- a/sql/hive/pom.xml +++ b/sql/hive/pom.xml @@ -52,6 +52,12 @@ org.apache.hive hive-exec ${hive.version} + + + commons-logging + commons-logging + + org.codehaus.jackson @@ -61,6 +67,21 @@ org.apache.hive hive-serde ${hive.version} + + + commons-logging + commons-logging + + + commons-logging + commons-logging-api + + + + + + org.apache.avro + avro org.scalatest From 3ce526b168050c572a1feee8e0121e1426f7d9ee Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 17:09:13 -0700 Subject: [PATCH 08/99] Rename testExecutorEnvs --> executorEnvs. This was changed, but in fact, it's used for things other than tests. So I've changed it back. Author: Patrick Wendell Closes #747 from pwendell/executor-env and squashes the following commits: 36a60a5 [Patrick Wendell] Rename testExecutorEnvs --> executorEnvs. --- .../main/scala/org/apache/spark/SparkContext.scala | 11 +++++------ .../cluster/SparkDeploySchedulerBackend.scala | 2 +- .../cluster/mesos/CoarseMesosSchedulerBackend.scala | 2 +- .../cluster/mesos/MesosSchedulerBackend.scala | 2 +- 4 files changed, 8 insertions(+), 9 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index e6121a705497c..35beff0f8ef3d 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -276,19 +276,18 @@ class SparkContext(config: SparkConf) extends Logging { .getOrElse(512) // Environment variables to pass to our executors. - // NOTE: This should only be used for test related settings. - private[spark] val testExecutorEnvs = HashMap[String, String]() + private[spark] val executorEnvs = HashMap[String, String]() // Convert java options to env vars as a work around // since we can't set env vars directly in sbt. for { (envKey, propKey) <- Seq(("SPARK_TESTING", "spark.testing")) value <- Option(System.getenv(envKey)).orElse(Option(System.getProperty(propKey)))} { - testExecutorEnvs(envKey) = value + executorEnvs(envKey) = value } // The Mesos scheduler backend relies on this environment variable to set executor memory. // TODO: Set this only in the Mesos scheduler. - testExecutorEnvs("SPARK_EXECUTOR_MEMORY") = executorMemory + "m" - testExecutorEnvs ++= conf.getExecutorEnv + executorEnvs("SPARK_EXECUTOR_MEMORY") = executorMemory + "m" + executorEnvs ++= conf.getExecutorEnv // Set SPARK_USER for user who is running SparkContext. val sparkUser = Option { @@ -296,7 +295,7 @@ class SparkContext(config: SparkConf) extends Logging { }.getOrElse { SparkContext.SPARK_UNKNOWN_USER } - testExecutorEnvs("SPARK_USER") = sparkUser + executorEnvs("SPARK_USER") = sparkUser // Create and start the scheduler private[spark] var taskScheduler = SparkContext.createTaskScheduler(this, master) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala index cefa41729964a..933f6e0571518 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala @@ -54,7 +54,7 @@ private[spark] class SparkDeploySchedulerBackend( } val command = Command( - "org.apache.spark.executor.CoarseGrainedExecutorBackend", args, sc.testExecutorEnvs, + "org.apache.spark.executor.CoarseGrainedExecutorBackend", args, sc.executorEnvs, classPathEntries, libraryPathEntries, extraJavaOpts) val sparkHome = sc.getSparkHome() val appDesc = new ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command, diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala index 2cd9d6c12eaf7..cbe9bb093d1c9 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala @@ -122,7 +122,7 @@ private[spark] class CoarseMesosSchedulerBackend( val extraLibraryPath = conf.getOption(libraryPathOption).map(p => s"-Djava.library.path=$p") val extraOpts = Seq(extraJavaOpts, extraLibraryPath).flatten.mkString(" ") - sc.testExecutorEnvs.foreach { case (key, value) => + sc.executorEnvs.foreach { case (key, value) => environment.addVariables(Environment.Variable.newBuilder() .setName(key) .setValue(value) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala index 2cea1c8cf154a..ff8356f67681e 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala @@ -90,7 +90,7 @@ private[spark] class MesosSchedulerBackend( "Spark home is not set; set it through the spark.home system " + "property, the SPARK_HOME environment variable or the SparkContext constructor")) val environment = Environment.newBuilder() - sc.testExecutorEnvs.foreach { case (key, value) => + sc.executorEnvs.foreach { case (key, value) => environment.addVariables(Environment.Variable.newBuilder() .setName(key) .setValue(value) From 925d8b249b84d2706c52f0d1e29fb8dcd6de452e Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 17:27:28 -0700 Subject: [PATCH 09/99] SPARK-1623: Use File objects instead of String's in HTTPBroadcast This seems strictly better, and I think it's justified only the grounds of clean-up. It might also fix issues with path conversions, but I haven't yet isolated any instance of that happening. /cc @srowen @tdas Author: Patrick Wendell Closes #749 from pwendell/broadcast-cleanup and squashes the following commits: d6d54f2 [Patrick Wendell] SPARK-1623: Use File objects instead of string's in HTTPBroadcast --- .../scala/org/apache/spark/broadcast/HttpBroadcast.scala | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala b/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala index 78fc286e5192c..4f6cabaff2b99 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/HttpBroadcast.scala @@ -112,7 +112,7 @@ private[spark] object HttpBroadcast extends Logging { private var securityManager: SecurityManager = null // TODO: This shouldn't be a global variable so that multiple SparkContexts can coexist - private val files = new TimeStampedHashSet[String] + private val files = new TimeStampedHashSet[File] private val httpReadTimeout = TimeUnit.MILLISECONDS.convert(5, TimeUnit.MINUTES).toInt private var compressionCodec: CompressionCodec = null private var cleaner: MetadataCleaner = null @@ -173,7 +173,7 @@ private[spark] object HttpBroadcast extends Logging { val serOut = ser.serializeStream(out) serOut.writeObject(value) serOut.close() - files += file.getAbsolutePath + files += file } def read[T: ClassTag](id: Long): T = { @@ -216,7 +216,7 @@ private[spark] object HttpBroadcast extends Logging { SparkEnv.get.blockManager.master.removeBroadcast(id, removeFromDriver, blocking) if (removeFromDriver) { val file = getFile(id) - files.remove(file.toString) + files.remove(file) deleteBroadcastFile(file) } } @@ -232,7 +232,7 @@ private[spark] object HttpBroadcast extends Logging { val (file, time) = (entry.getKey, entry.getValue) if (time < cleanupTime) { iterator.remove() - deleteBroadcastFile(new File(file.toString)) + deleteBroadcastFile(file) } } } From 4b31f4ec7efab8eabf956284a99bfd96a58b79f7 Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Mon, 12 May 2014 17:35:29 -0700 Subject: [PATCH 10/99] SPARK-1802. (Addendium) Audit dependency graph when Spark is built with -Pyarn Following on a few more items from SPARK-1802 -- The first commit touches up a few similar problems remaining with the YARN profile. I think this is worth cherry-picking. The second commit is more of the same for hadoop-client, although the fix is a little more complex. It may or may not be worth bothering with. Author: Sean Owen Closes #746 from srowen/SPARK-1802.2 and squashes the following commits: 52aeb41 [Sean Owen] Add more commons-logging, servlet excludes to avoid conflicts in assembly when building for YARN --- pom.xml | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/pom.xml b/pom.xml index 3554efafb976a..4d4c5f63e44a3 100644 --- a/pom.xml +++ b/pom.xml @@ -583,6 +583,10 @@ org.jboss.netty netty + + commons-logging + commons-logging + @@ -606,6 +610,10 @@ javax.servlet servlet-api + + commons-logging + commons-logging + @@ -625,6 +633,14 @@ org.jboss.netty netty + + javax.servlet + servlet-api + + + commons-logging + commons-logging + @@ -648,6 +664,10 @@ javax.servlet servlet-api + + commons-logging + commons-logging + From beb9cbaca6dbbcaba77a34df692dc2e56b3e0638 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Mon, 12 May 2014 17:39:40 -0700 Subject: [PATCH 11/99] [SPARK-1736] Spark submit for Windows Tested on Windows 7. Author: Andrew Or Closes #745 from andrewor14/windows-submit and squashes the following commits: c0b58fb [Andrew Or] Allow spaces in parameters 162e54d [Andrew Or] Merge branch 'master' of github.com:apache/spark into windows-submit 91597ce [Andrew Or] Make spark-shell.cmd use spark-submit.cmd af6fd29 [Andrew Or] Add spark submit for Windows --- bin/spark-shell.cmd | 5 ++-- bin/spark-submit.cmd | 56 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+), 3 deletions(-) create mode 100644 bin/spark-submit.cmd diff --git a/bin/spark-shell.cmd b/bin/spark-shell.cmd index 99799128eb734..ca0c722c926f5 100755 --- a/bin/spark-shell.cmd +++ b/bin/spark-shell.cmd @@ -17,7 +17,6 @@ rem See the License for the specific language governing permissions and rem limitations under the License. rem -rem Find the path of sbin -set BIN=%~dp0..\bin\ +set SPARK_HOME=%~dp0.. -cmd /V /E /C %BIN%spark-class2.cmd org.apache.spark.repl.Main %* +cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-internal %* --class org.apache.spark.repl.Main diff --git a/bin/spark-submit.cmd b/bin/spark-submit.cmd new file mode 100644 index 0000000000000..6eb702ed8c561 --- /dev/null +++ b/bin/spark-submit.cmd @@ -0,0 +1,56 @@ +@echo off + +rem +rem Licensed to the Apache Software Foundation (ASF) under one or more +rem contributor license agreements. See the NOTICE file distributed with +rem this work for additional information regarding copyright ownership. +rem The ASF licenses this file to You under the Apache License, Version 2.0 +rem (the "License"); you may not use this file except in compliance with +rem the License. You may obtain a copy of the License at +rem +rem http://www.apache.org/licenses/LICENSE-2.0 +rem +rem Unless required by applicable law or agreed to in writing, software +rem distributed under the License is distributed on an "AS IS" BASIS, +rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +rem See the License for the specific language governing permissions and +rem limitations under the License. +rem + +set SPARK_HOME=%~dp0.. +set ORIG_ARGS=%* + +rem Clear the values of all variables used +set DEPLOY_MODE= +set DRIVER_MEMORY= +set SPARK_SUBMIT_LIBRARY_PATH= +set SPARK_SUBMIT_CLASSPATH= +set SPARK_SUBMIT_OPTS= +set SPARK_DRIVER_MEMORY= + +:loop +if [%1] == [] goto continue + if [%1] == [--deploy-mode] ( + set DEPLOY_MODE=%2 + ) else if [%1] == [--driver-memory] ( + set DRIVER_MEMORY=%2 + ) else if [%1] == [--driver-library-path] ( + set SPARK_SUBMIT_LIBRARY_PATH=%2 + ) else if [%1] == [--driver-class-path] ( + set SPARK_SUBMIT_CLASSPATH=%2 + ) else if [%1] == [--driver-java-options] ( + set SPARK_SUBMIT_OPTS=%2 + ) + shift +goto loop +:continue + +if [%DEPLOY_MODE%] == [] ( + set DEPLOY_MODE=client +) + +if not [%DRIVER_MEMORY%] == [] if [%DEPLOY_MODE%] == [client] ( + set SPARK_DRIVER_MEMORY=%DRIVER_MEMORY% +) + +cmd /V /E /C %SPARK_HOME%\bin\spark-class.cmd org.apache.spark.deploy.SparkSubmit %ORIG_ARGS% From 3e13b8c0bd46894392bd0fbd3e86dd55b8103858 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 15:40:48 -0700 Subject: [PATCH 12/99] Adding hadoop-2.2 profile to the build --- dev/create-release/create-release.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/dev/create-release/create-release.sh b/dev/create-release/create-release.sh index b7a0a01c3bad2..c4e74990860b6 100755 --- a/dev/create-release/create-release.sh +++ b/dev/create-release/create-release.sh @@ -52,14 +52,14 @@ if [[ ! "$@" =~ --package-only ]]; then -Darguments="-DskipTests=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ -Dusername=$GIT_USERNAME -Dpassword=$GIT_PASSWORD \ -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 \ - -Pyarn -Phive -Pspark-ganglia-lgpl\ + -Pyarn -Phive -Phadoop-2.2 -Pspark-ganglia-lgpl\ -Dtag=$GIT_TAG -DautoVersionSubmodules=true \ --batch-mode release:prepare mvn -DskipTests \ -Darguments="-DskipTests=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 \ - -Pyarn -Phive -Pspark-ganglia-lgpl\ + -Pyarn -Phive -Phadoop-2.2 -Pspark-ganglia-lgpl\ release:perform cd .. From 2f1a3373583f9b34a121236c25f5142ba8729546 Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Mon, 12 May 2014 18:40:30 -0700 Subject: [PATCH 13/99] [SQL] Make Hive Metastore conversion functions publicly visible. I need this to be public for the implementation of SharkServer2. However, I think this functionality is generally useful and should be pretty stable. Author: Michael Armbrust Closes #750 from marmbrus/metastoreTypes and squashes the following commits: f51b62e [Michael Armbrust] Make Hive Metastore conversion functions publicly visible. --- .../org/apache/spark/sql/hive/HiveMetastoreCatalog.scala | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala index ba837a274c51c..fa30f596f8c67 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala @@ -26,6 +26,7 @@ import org.apache.hadoop.hive.ql.plan.TableDesc import org.apache.hadoop.hive.ql.session.SessionState import org.apache.hadoop.hive.serde2.Deserializer +import org.apache.spark.annotation.DeveloperApi import org.apache.spark.sql.Logging import org.apache.spark.sql.catalyst.analysis.{EliminateAnalysisOperators, Catalog} import org.apache.spark.sql.catalyst.expressions._ @@ -172,7 +173,12 @@ private[hive] class HiveMetastoreCatalog(hive: HiveContext) extends Catalog with override def unregisterAllTables() = {} } -private[hive] object HiveMetastoreTypes extends RegexParsers { +/** + * :: DeveloperApi :: + * Provides conversions between Spark SQL data types and Hive Metastore types. + */ +@DeveloperApi +object HiveMetastoreTypes extends RegexParsers { protected lazy val primitiveType: Parser[DataType] = "string" ^^^ StringType | "float" ^^^ FloatType | From a5150d199ca97ab2992bc2bb221a3ebf3d3450ba Mon Sep 17 00:00:00 2001 From: Andrew Ash Date: Mon, 12 May 2014 18:46:28 -0700 Subject: [PATCH 14/99] Typo: resond -> respond Author: Andrew Ash Closes #743 from ash211/patch-4 and squashes the following commits: c959f3b [Andrew Ash] Typo: resond -> respond --- .../spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala index ff8356f67681e..f08b19e6782e3 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala @@ -175,7 +175,7 @@ private[spark] class MesosSchedulerBackend( override def reregistered(d: SchedulerDriver, masterInfo: MasterInfo) {} /** - * Method called by Mesos to offer resources on slaves. We resond by asking our active task sets + * Method called by Mesos to offer resources on slaves. We respond by asking our active task sets * for tasks in order of priority. We fill each node with tasks in a round-robin manner so that * tasks are balanced across the cluster. */ From 5c2275d6e4639946fd11ff6403338c8a9ade3d1e Mon Sep 17 00:00:00 2001 From: DB Tsai Date: Mon, 12 May 2014 19:20:24 -0700 Subject: [PATCH 15/99] L-BFGS Documentation Documentation for L-BFGS, and an example of training binary L2 logistic regression using L-BFGS. Author: DB Tsai Closes #702 from dbtsai/dbtsai-lbfgs-doc and squashes the following commits: 0712215 [DB Tsai] Update 38fdfa1 [DB Tsai] Removed extra empty line 5745b64 [DB Tsai] Update again e9e418e [DB Tsai] Update 7381521 [DB Tsai] L-BFGS Documentation --- docs/mllib-optimization.md | 120 +++++++++++++++++++++++++++++++++++-- 1 file changed, 116 insertions(+), 4 deletions(-) diff --git a/docs/mllib-optimization.md b/docs/mllib-optimization.md index bec3912b55dc7..aa0dec2130593 100644 --- a/docs/mllib-optimization.md +++ b/docs/mllib-optimization.md @@ -28,7 +28,6 @@ title: MLlib - Optimization ## Mathematical description ### Gradient descent - The simplest method to solve optimization problems of the form `$\min_{\wv \in\R^d} \; f(\wv)$` is [gradient descent](http://en.wikipedia.org/wiki/Gradient_descent). Such first-order optimization methods (including gradient descent and stochastic variants @@ -128,10 +127,19 @@ is sampled, i.e. `$|S|=$ miniBatchFraction $\cdot n = 1$`, then the algorithm is standard SGD. In that case, the step direction depends from the uniformly random sampling of the point. - +### Limited-memory BFGS (L-BFGS) +[L-BFGS](http://en.wikipedia.org/wiki/Limited-memory_BFGS) is an optimization +algorithm in the family of quasi-Newton methods to solve the optimization problems of the form +`$\min_{\wv \in\R^d} \; f(\wv)$`. The L-BFGS method approximates the objective function locally as a +quadratic without evaluating the second partial derivatives of the objective function to construct the +Hessian matrix. The Hessian matrix is approximated by previous gradient evaluations, so there is no +vertical scalability issue (the number of training features) when computing the Hessian matrix +explicitly in Newton's method. As a result, L-BFGS often achieves rapider convergence compared with +other first-order optimization. ## Implementation in MLlib +### Gradient descent and stochastic gradient descent Gradient descent methods including stochastic subgradient descent (SGD) as included as a low-level primitive in `MLlib`, upon which various ML algorithms are developed, see the @@ -142,12 +150,12 @@ The SGD method [GradientDescent.runMiniBatchSGD](api/scala/index.html#org.apache.spark.mllib.optimization.GradientDescent) has the following parameters: -* `gradient` is a class that computes the stochastic gradient of the function +* `Gradient` is a class that computes the stochastic gradient of the function being optimized, i.e., with respect to a single training example, at the current parameter value. MLlib includes gradient classes for common loss functions, e.g., hinge, logistic, least-squares. The gradient class takes as input a training example, its label, and the current parameter value. -* `updater` is a class that performs the actual gradient descent step, i.e. +* `Updater` is a class that performs the actual gradient descent step, i.e. updating the weights in each iteration, for a given gradient of the loss part. The updater is also responsible to perform the update from the regularization part. MLlib includes updaters for cases without regularization, as well as @@ -163,3 +171,107 @@ each iteration, to compute the gradient direction. Available algorithms for gradient descent: * [GradientDescent.runMiniBatchSGD](api/mllib/index.html#org.apache.spark.mllib.optimization.GradientDescent) + +### L-BFGS +L-BFGS is currently only a low-level optimization primitive in `MLlib`. If you want to use L-BFGS in various +ML algorithms such as Linear Regression, and Logistic Regression, you have to pass the gradient of objective +function, and updater into optimizer yourself instead of using the training APIs like +[LogisticRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD). +See the example below. It will be addressed in the next release. + +The L1 regularization by using +[L1Updater](api/mllib/index.html#org.apache.spark.mllib.optimization.L1Updater) will not work since the +soft-thresholding logic in L1Updater is designed for gradient descent. See the developer's note. + +The L-BFGS method +[LBFGS.runLBFGS](api/scala/index.html#org.apache.spark.mllib.optimization.LBFGS) +has the following parameters: + +* `Gradient` is a class that computes the gradient of the objective function +being optimized, i.e., with respect to a single training example, at the +current parameter value. MLlib includes gradient classes for common loss +functions, e.g., hinge, logistic, least-squares. The gradient class takes as +input a training example, its label, and the current parameter value. +* `Updater` is a class that computes the gradient and loss of objective function +of the regularization part for L-BFGS. MLlib includes updaters for cases without +regularization, as well as L2 regularizer. +* `numCorrections` is the number of corrections used in the L-BFGS update. 10 is +recommended. +* `maxNumIterations` is the maximal number of iterations that L-BFGS can be run. +* `regParam` is the regularization parameter when using regularization. + +The `return` is a tuple containing two elements. The first element is a column matrix +containing weights for every feature, and the second element is an array containing +the loss computed for every iteration. + +Here is an example to train binary logistic regression with L2 regularization using +L-BFGS optimizer. +{% highlight scala %} +import org.apache.spark.SparkContext +import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics +import org.apache.spark.mllib.linalg.Vectors +import org.apache.spark.mllib.util.MLUtils +import org.apache.spark.mllib.classification.LogisticRegressionModel + +val data = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt") +val numFeatures = data.take(1)(0).features.size + +// Split data into training (60%) and test (40%). +val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L) + +// Append 1 into the training data as intercept. +val training = splits(0).map(x => (x.label, MLUtils.appendBias(x.features))).cache() + +val test = splits(1) + +// Run training algorithm to build the model +val numCorrections = 10 +val convergenceTol = 1e-4 +val maxNumIterations = 20 +val regParam = 0.1 +val initialWeightsWithIntercept = Vectors.dense(new Array[Double](numFeatures + 1)) + +val (weightsWithIntercept, loss) = LBFGS.runLBFGS( + training, + new LogisticGradient(), + new SquaredL2Updater(), + numCorrections, + convergenceTol, + maxNumIterations, + regParam, + initialWeightsWithIntercept) + +val model = new LogisticRegressionModel( + Vectors.dense(weightsWithIntercept.toArray.slice(0, weightsWithIntercept.size - 1)), + weightsWithIntercept(weightsWithIntercept.size - 1)) + +// Clear the default threshold. +model.clearThreshold() + +// Compute raw scores on the test set. +val scoreAndLabels = test.map { point => + val score = model.predict(point.features) + (score, point.label) +} + +// Get evaluation metrics. +val metrics = new BinaryClassificationMetrics(scoreAndLabels) +val auROC = metrics.areaUnderROC() + +println("Loss of each step in training process") +loss.foreach(println) +println("Area under ROC = " + auROC) +{% endhighlight %} + +#### Developer's note +Since the Hessian is constructed approximately from previous gradient evaluations, +the objective function can not be changed during the optimization process. +As a result, Stochastic L-BFGS will not work naively by just using miniBatch; +therefore, we don't provide this until we have better understanding. + +* `Updater` is a class originally designed for gradient decent which computes +the actual gradient descent step. However, we're able to take the gradient and +loss of objective function of regularization for L-BFGS by ignoring the part of logic +only for gradient decent such as adaptive step size stuff. We will refactorize +this into regularizer to replace updater to separate the logic between +regularization and step update later. \ No newline at end of file From 9cf9f18973840f7287f7cfa5ce90efed3225bb30 Mon Sep 17 00:00:00 2001 From: Kousuke Saruta Date: Mon, 12 May 2014 19:21:06 -0700 Subject: [PATCH 16/99] Modify a typo in monitoring.md As I mentioned in SPARK-1765, there is a word 'JXM' in monitoring.md. I think it's typo for 'JMX'. Author: Kousuke Saruta Closes #698 from sarutak/SPARK-1765 and squashes the following commits: bae9843 [Kousuke Saruta] modified a typoe in monitoring.md --- docs/monitoring.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/monitoring.md b/docs/monitoring.md index 6f35fc37c4075..fffc58ac39230 100644 --- a/docs/monitoring.md +++ b/docs/monitoring.md @@ -156,7 +156,7 @@ Each instance can report to zero or more _sinks_. Sinks are contained in the * `ConsoleSink`: Logs metrics information to the console. * `CSVSink`: Exports metrics data to CSV files at regular intervals. -* `JmxSink`: Registers metrics for viewing in a JXM console. +* `JmxSink`: Registers metrics for viewing in a JMX console. * `MetricsServlet`: Adds a servlet within the existing Spark UI to serve metrics data as JSON data. * `GraphiteSink`: Sends metrics to a Graphite node. From 156df87e7ca0e6cda2cc970ecd1466ce06f7576f Mon Sep 17 00:00:00 2001 From: Andrew Ash Date: Mon, 12 May 2014 19:23:39 -0700 Subject: [PATCH 17/99] SPARK-1757 Failing test for saving null primitives with .saveAsParquetFile() https://issues.apache.org/jira/browse/SPARK-1757 The first test succeeds, but the second test fails with exception: ``` [info] - save and load case class RDD with Nones as parquet *** FAILED *** (14 milliseconds) [info] java.lang.RuntimeException: Unsupported datatype StructType(List()) [info] at scala.sys.package$.error(package.scala:27) [info] at org.apache.spark.sql.parquet.ParquetTypesConverter$.fromDataType(ParquetRelation.scala:201) [info] at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$1.apply(ParquetRelation.scala:235) [info] at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$1.apply(ParquetRelation.scala:235) [info] at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) [info] at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) [info] at scala.collection.immutable.List.foreach(List.scala:318) [info] at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) [info] at scala.collection.AbstractTraversable.map(Traversable.scala:105) [info] at org.apache.spark.sql.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetRelation.scala:234) [info] at org.apache.spark.sql.parquet.ParquetTypesConverter$.writeMetaData(ParquetRelation.scala:267) [info] at org.apache.spark.sql.parquet.ParquetRelation$.createEmpty(ParquetRelation.scala:143) [info] at org.apache.spark.sql.parquet.ParquetRelation$.create(ParquetRelation.scala:122) [info] at org.apache.spark.sql.execution.SparkStrategies$ParquetOperations$.apply(SparkStrategies.scala:139) [info] at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58) [info] at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58) [info] at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371) [info] at org.apache.spark.sql.catalyst.planning.QueryPlanner.apply(QueryPlanner.scala:59) [info] at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:264) [info] at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:264) [info] at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:265) [info] at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:265) [info] at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:268) [info] at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:268) [info] at org.apache.spark.sql.SchemaRDDLike$class.saveAsParquetFile(SchemaRDDLike.scala:66) [info] at org.apache.spark.sql.SchemaRDD.saveAsParquetFile(SchemaRDD.scala:98) ``` Author: Andrew Ash Author: Michael Armbrust Closes #690 from ash211/rdd-parquet-save and squashes the following commits: 747a0b9 [Andrew Ash] Merge pull request #1 from marmbrus/pr/690 54bd00e [Michael Armbrust] Need to put Option first since Option <: Seq. 8f3f281 [Andrew Ash] SPARK-1757 Add failing test for saving SparkSQL Schemas with Option[?] fields as parquet --- .../spark/sql/catalyst/ScalaReflection.scala | 6 +-- .../spark/sql/parquet/ParquetQuerySuite.scala | 44 +++++++++++++++++++ 2 files changed, 47 insertions(+), 3 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala index 792ef6cee6f5d..196695a0a188f 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/ScalaReflection.scala @@ -41,6 +41,9 @@ object ScalaReflection { /** Returns a catalyst DataType for the given Scala Type using reflection. */ def schemaFor(tpe: `Type`): DataType = tpe match { + case t if t <:< typeOf[Option[_]] => + val TypeRef(_, _, Seq(optType)) = t + schemaFor(optType) case t if t <:< typeOf[Product] => val params = t.member("": TermName).asMethod.paramss StructType( @@ -59,9 +62,6 @@ object ScalaReflection { case t if t <:< typeOf[String] => StringType case t if t <:< typeOf[Timestamp] => TimestampType case t if t <:< typeOf[BigDecimal] => DecimalType - case t if t <:< typeOf[Option[_]] => - val TypeRef(_, _, Seq(optType)) = t - schemaFor(optType) case t if t <:< typeOf[java.lang.Integer] => IntegerType case t if t <:< typeOf[java.lang.Long] => LongType case t if t <:< typeOf[java.lang.Double] => DoubleType diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala index d9c9b9a076ab9..ff1677eb8a480 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala @@ -42,6 +42,20 @@ import org.apache.spark.sql.test.TestSQLContext._ case class TestRDDEntry(key: Int, value: String) +case class NullReflectData( + intField: java.lang.Integer, + longField: java.lang.Long, + floatField: java.lang.Float, + doubleField: java.lang.Double, + booleanField: java.lang.Boolean) + +case class OptionalReflectData( + intField: Option[Int], + longField: Option[Long], + floatField: Option[Float], + doubleField: Option[Double], + booleanField: Option[Boolean]) + class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { import TestData._ TestData // Load test data tables. @@ -195,5 +209,35 @@ class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { Utils.deleteRecursively(ParquetTestData.testDir) ParquetTestData.writeFile() } + + test("save and load case class RDD with nulls as parquet") { + val data = NullReflectData(null, null, null, null, null) + val rdd = sparkContext.parallelize(data :: Nil) + + val file = getTempFilePath("parquet") + val path = file.toString + rdd.saveAsParquetFile(path) + val readFile = parquetFile(path) + + val rdd_saved = readFile.collect() + assert(rdd_saved(0) === Seq.fill(5)(null)) + Utils.deleteRecursively(file) + assert(true) + } + + test("save and load case class RDD with Nones as parquet") { + val data = OptionalReflectData(null, null, null, null, null) + val rdd = sparkContext.parallelize(data :: Nil) + + val file = getTempFilePath("parquet") + val path = file.toString + rdd.saveAsParquetFile(path) + val readFile = parquetFile(path) + + val rdd_saved = readFile.collect() + assert(rdd_saved(0) === Seq.fill(5)(null)) + Utils.deleteRecursively(file) + assert(true) + } } From ba96bb3d591130075763706526f86fb2aaffa3ae Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Mon, 12 May 2014 19:42:35 -0700 Subject: [PATCH 18/99] [SPARK-1780] Non-existent SPARK_DAEMON_OPTS is lurking around What they really mean is SPARK_DAEMON_***JAVA***_OPTS Author: Andrew Or Closes #751 from andrewor14/spark-daemon-opts and squashes the following commits: 70c41f9 [Andrew Or] SPARK_DAEMON_OPTS -> SPARK_DAEMON_JAVA_OPTS --- conf/spark-env.sh.template | 2 +- core/src/main/scala/org/apache/spark/SparkConf.scala | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/spark-env.sh.template b/conf/spark-env.sh.template index f906be611a931..4479e1e34cd4a 100755 --- a/conf/spark-env.sh.template +++ b/conf/spark-env.sh.template @@ -39,5 +39,5 @@ # - SPARK_WORKER_DIR, to set the working directory of worker processes # - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y") # - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y") -# - SPARK_DAEMON_OPTS, to set config properties for all daemons (e.g. "-Dx=y") +# - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y") # - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers diff --git a/core/src/main/scala/org/apache/spark/SparkConf.scala b/core/src/main/scala/org/apache/spark/SparkConf.scala index bd21fdc5a18e4..800616622d7bf 100644 --- a/core/src/main/scala/org/apache/spark/SparkConf.scala +++ b/core/src/main/scala/org/apache/spark/SparkConf.scala @@ -247,7 +247,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging { | - ./spark-submit with conf/spark-defaults.conf to set defaults for an application | - ./spark-submit with --driver-java-options to set -X options for a driver | - spark.executor.extraJavaOptions to set -X options for executors - | - SPARK_DAEMON_OPTS to set java options for standalone daemons (i.e. master, worker) + | - SPARK_DAEMON_JAVA_OPTS to set java options for standalone daemons (master or worker) """.stripMargin logError(error) From 2ffd1eafd28635dcecc0ac738d4a62c05d740925 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Mon, 12 May 2014 19:44:14 -0700 Subject: [PATCH 19/99] [SPARK-1753 / 1773 / 1814] Update outdated docs for spark-submit, YARN, standalone etc. YARN - SparkPi was updated to not take in master as an argument; we should update the docs to reflect that. - The default YARN build guide should be in maven, not sbt. - This PR also adds a paragraph on steps to debug a YARN application. Standalone - Emphasize spark-submit more. Right now it's one small paragraph preceding the legacy way of launching through `org.apache.spark.deploy.Client`. - The way we set configurations / environment variables according to the old docs is outdated. This needs to reflect changes introduced by the Spark configuration changes we made. In general, this PR also adds a little more documentation on the new spark-shell, spark-submit, spark-defaults.conf etc here and there. Author: Andrew Or Closes #701 from andrewor14/yarn-docs and squashes the following commits: e2c2312 [Andrew Or] Merge in changes in #752 (SPARK-1814) 25cfe7b [Andrew Or] Merge in the warning from SPARK-1753 a8c39c5 [Andrew Or] Minor changes 336bbd9 [Andrew Or] Tabs -> spaces 4d9d8f7 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-docs 041017a [Andrew Or] Abstract Spark submit documentation to cluster-overview.html 3cc0649 [Andrew Or] Detail how to set configurations + remove legacy instructions 5b7140a [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-docs 85a51fc [Andrew Or] Update run-example, spark-shell, configuration etc. c10e8c7 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-docs 381fe32 [Andrew Or] Update docs for standalone mode 757c184 [Andrew Or] Add a note about the requirements for the debugging trick f8ca990 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-docs 924f04c [Andrew Or] Revert addition of --deploy-mode d5fe17b [Andrew Or] Update the YARN docs --- conf/spark-defaults.conf.template | 3 +- conf/spark-env.sh.template | 4 +- docs/building-with-maven.md | 7 +++ docs/cluster-overview.md | 73 +++++++++++++++--------- docs/configuration.md | 64 +++++++++++++-------- docs/hadoop-third-party-distributions.md | 14 +++-- docs/index.md | 34 +++++++---- docs/java-programming-guide.md | 5 +- docs/python-programming-guide.md | 2 +- docs/quick-start.md | 4 +- docs/running-on-yarn.md | 15 +++-- docs/scala-programming-guide.md | 13 +++-- docs/spark-standalone.md | 71 ++++++++++------------- 13 files changed, 184 insertions(+), 125 deletions(-) diff --git a/conf/spark-defaults.conf.template b/conf/spark-defaults.conf.template index f840ff681d019..2779342769c14 100644 --- a/conf/spark-defaults.conf.template +++ b/conf/spark-defaults.conf.template @@ -2,6 +2,7 @@ # This is useful for setting default environmental settings. # Example: -# spark.master spark://master:7077 +# spark.master spark://master:7077 # spark.eventLog.enabled true # spark.eventLog.dir hdfs://namenode:8021/directory +# spark.serializer org.apache.spark.serializer.KryoSerializer diff --git a/conf/spark-env.sh.template b/conf/spark-env.sh.template index 4479e1e34cd4a..f8ffbf64278fb 100755 --- a/conf/spark-env.sh.template +++ b/conf/spark-env.sh.template @@ -30,11 +30,11 @@ # Options for the daemons used in the standalone deploy mode: # - SPARK_MASTER_IP, to bind the master to a different IP address or hostname -# - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports +# - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master # - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y") # - SPARK_WORKER_CORES, to set the number of cores to use on this machine # - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g) -# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT +# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker # - SPARK_WORKER_INSTANCES, to set the number of worker processes per node # - SPARK_WORKER_DIR, to set the working directory of worker processes # - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y") diff --git a/docs/building-with-maven.md b/docs/building-with-maven.md index b6dd553bbe06b..8b44535d82404 100644 --- a/docs/building-with-maven.md +++ b/docs/building-with-maven.md @@ -129,6 +129,13 @@ Java 8 tests are run when -Pjava8-tests profile is enabled, they will run in spi For these tests to run your system must have a JDK 8 installation. If you have JDK 8 installed but it is not the system default, you can set JAVA_HOME to point to JDK 8 before running the tests. +## Building for PySpark on YARN ## + +PySpark on YARN is only supported if the jar is built with maven. Further, there is a known problem +with building this assembly jar on Red Hat based operating systems (see SPARK-1753). If you wish to +run PySpark on a YARN cluster with Red Hat installed, we recommend that you build the jar elsewhere, +then ship it over to the cluster. We are investigating the exact cause for this. + ## Packaging without Hadoop dependencies for deployment on YARN ## The assembly jar produced by "mvn package" will, by default, include all of Spark's dependencies, including Hadoop and some of its ecosystem projects. On YARN deployments, this causes multiple versions of these to appear on executor classpaths: the version packaged in the Spark assembly and the version on each node, included with yarn.application.classpath. The "hadoop-provided" profile builds the assembly without including Hadoop-ecosystem projects, like ZooKeeper and Hadoop itself. diff --git a/docs/cluster-overview.md b/docs/cluster-overview.md index 162c415b5883e..f05a755de7fec 100644 --- a/docs/cluster-overview.md +++ b/docs/cluster-overview.md @@ -66,62 +66,76 @@ script as shown here while passing your jar. For Python, you can use the `pyFiles` argument of SparkContext or its `addPyFile` method to add `.py`, `.zip` or `.egg` files to be distributed. -### Launching Applications with ./bin/spark-submit +### Launching Applications with Spark submit Once a user application is bundled, it can be launched using the `spark-submit` script located in the bin directory. This script takes care of setting up the classpath with Spark and its -dependencies, and can support different cluster managers and deploy modes that Spark supports. -It's usage is +dependencies, and can support different cluster managers and deploy modes that Spark supports: - ./bin/spark-submit --class path.to.your.Class [options] [app options] + ./bin/spark-submit \ + --class + --master \ + --deploy-mode \ + ... // other options + + [application-arguments] -When calling `spark-submit`, `[app options]` will be passed along to your application's -main class. To enumerate all options available to `spark-submit` run it with -the `--help` flag. Here are a few examples of common options: + main-class: The entry point for your application (e.g. org.apache.spark.examples.SparkPi) + master-url: The URL of the master node (e.g. spark://23.195.26.187:7077) + deploy-mode: Whether to deploy this application within the cluster or from an external client (e.g. client) + application-jar: Path to a bundled jar including your application and all dependencies. The URL must be globally visible inside of your cluster, for instance, an `hdfs://` path or a `file://` path that is present on all nodes. + application-arguments: Space delimited arguments passed to the main method of , if any + +To enumerate all options available to `spark-submit` run it with the `--help` flag. Here are a few +examples of common options: {% highlight bash %} # Run application locally ./bin/spark-submit \ - --class my.main.ClassName + --class org.apache.spark.examples.SparkPi --master local[8] \ - my-app.jar + /path/to/examples.jar \ + 100 # Run on a Spark standalone cluster ./bin/spark-submit \ - --class my.main.ClassName - --master spark://mycluster:7077 \ + --class org.apache.spark.examples.SparkPi + --master spark://207.184.161.138:7077 \ --executor-memory 20G \ --total-executor-cores 100 \ - my-app.jar + /path/to/examples.jar \ + 1000 # Run on a YARN cluster -HADOOP_CONF_DIR=XX /bin/spark-submit \ - --class my.main.ClassName +HADOOP_CONF_DIR=XX ./bin/spark-submit \ + --class org.apache.spark.examples.SparkPi --master yarn-cluster \ # can also be `yarn-client` for client mode --executor-memory 20G \ --num-executors 50 \ - my-app.jar + /path/to/examples.jar \ + 1000 {% endhighlight %} ### Loading Configurations from a File -The `spark-submit` script can load default `SparkConf` values from a properties file and pass them -onto your application. By default it will read configuration options from -`conf/spark-defaults.conf`. Any values specified in the file will be passed on to the -application when run. They can obviate the need for certain flags to `spark-submit`: for -instance, if `spark.master` property is set, you can safely omit the +The `spark-submit` script can load default [Spark configuration values](configuration.html) from a +properties file and pass them on to your application. By default it will read configuration options +from `conf/spark-defaults.conf`. For more detail, see the section on +[loading default configurations](configuration.html#loading-default-configurations). + +Loading default Spark configurations this way can obviate the need for certain flags to +`spark-submit`. For instance, if the `spark.master` property is set, you can safely omit the `--master` flag from `spark-submit`. In general, configuration values explicitly set on a -`SparkConf` take the highest precedence, then flags passed to `spark-submit`, then values -in the defaults file. +`SparkConf` take the highest precedence, then flags passed to `spark-submit`, then values in the +defaults file. -If you are ever unclear where configuration options are coming from. fine-grained debugging -information can be printed by adding the `--verbose` option to `./spark-submit`. +If you are ever unclear where configuration options are coming from, you can print out fine-grained +debugging information by running `spark-submit` with the `--verbose` option. ### Advanced Dependency Management -When using `./bin/spark-submit` the app jar along with any jars included with the `--jars` option -will be automatically transferred to the cluster. `--jars` can also be used to distribute .egg and .zip -libraries for Python to executors. Spark uses the following URL scheme to allow different -strategies for disseminating jars: +When using `spark-submit`, the application jar along with any jars included with the `--jars` option +will be automatically transferred to the cluster. Spark uses the following URL scheme to allow +different strategies for disseminating jars: - **file:** - Absolute paths and `file:/` URIs are served by the driver's HTTP file server, and every executor pulls the file from the driver HTTP server. @@ -135,6 +149,9 @@ This can use up a significant amount of space over time and will need to be clea is handled automatically, and with Spark standalone, automatic cleanup can be configured with the `spark.worker.cleanup.appDataTtl` property. +For python, the equivalent `--py-files` option can be used to distribute .egg and .zip libraries +to executors. + # Monitoring Each driver program has a web UI, typically on port 4040, that displays information about running diff --git a/docs/configuration.md b/docs/configuration.md index 5b034e3cb3d47..2eed96f704a4f 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -5,9 +5,9 @@ title: Spark Configuration Spark provides three locations to configure the system: -* [Spark properties](#spark-properties) control most application parameters and can be set by passing - a [SparkConf](api/scala/index.html#org.apache.spark.SparkConf) object to SparkContext, or through Java - system properties. +* [Spark properties](#spark-properties) control most application parameters and can be set by + passing a [SparkConf](api/scala/index.html#org.apache.spark.SparkConf) object to SparkContext, + or through the `conf/spark-defaults.conf` properties file. * [Environment variables](#environment-variables) can be used to set per-machine settings, such as the IP address, through the `conf/spark-env.sh` script on each node. * [Logging](#configuring-logging) can be configured through `log4j.properties`. @@ -15,25 +15,41 @@ Spark provides three locations to configure the system: # Spark Properties -Spark properties control most application settings and are configured separately for each application. -The preferred way to set them is by passing a [SparkConf](api/scala/index.html#org.apache.spark.SparkConf) -class to your SparkContext constructor. -Alternatively, Spark will also load them from Java system properties, for compatibility with old versions -of Spark. - -SparkConf lets you configure most of the common properties to initialize a cluster (e.g., master URL and -application name), as well as arbitrary key-value pairs through the `set()` method. For example, we could -initialize an application as follows: +Spark properties control most application settings and are configured separately for each +application. The preferred way is to set them through +[SparkConf](api/scala/index.html#org.apache.spark.SparkConf) and passing it as an argument to your +SparkContext. SparkConf allows you to configure most of the common properties to initialize a +cluster (e.g. master URL and application name), as well as arbitrary key-value pairs through the +`set()` method. For example, we could initialize an application as follows: {% highlight scala %} -val conf = new SparkConf(). - setMaster("local"). - setAppName("My application"). - set("spark.executor.memory", "1g") +val conf = new SparkConf + .setMaster("local") + .setAppName("CountingSheep") + .set("spark.executor.memory", "1g") val sc = new SparkContext(conf) {% endhighlight %} -Most of the properties control internal settings that have reasonable default values. However, +## Loading Default Configurations + +In the case of `spark-shell`, a SparkContext has already been created for you, so you cannot control +the configuration properties through SparkConf. However, you can still set configuration properties +through a default configuration file. By default, `spark-shell` (and more generally `spark-submit`) +will read configuration options from `conf/spark-defaults.conf`, in which each line consists of a +key and a value separated by whitespace. For example, + + spark.master spark://5.6.7.8:7077 + spark.executor.memory 512m + spark.eventLog.enabled true + spark.serializer org.apache.spark.serializer.KryoSerializer + +Any values specified in the file will be passed on to the application, and merged with those +specified through SparkConf. If the same configuration property exists in both `spark-defaults.conf` +and SparkConf, then the latter will take precedence as it is the most application-specific. + +## All Configuration Properties + +Most of the properties that control internal settings have reasonable default values. However, there are at least five properties that you will commonly want to control: @@ -101,9 +117,9 @@ Apart from these, the following properties are also available, and may be useful @@ -696,7 +712,9 @@ Apart from these, the following properties are also available, and may be useful ## Viewing Spark Properties The application web UI at `http://:4040` lists Spark properties in the "Environment" tab. -This is a useful place to check to make sure that your properties have been set correctly. +This is a useful place to check to make sure that your properties have been set correctly. Note +that only values explicitly specified through either `spark-defaults.conf` or SparkConf will +appear. For all other configuration properties, you can assume the default value is used. # Environment Variables @@ -714,8 +732,8 @@ The following variables can be set in `spark-env.sh`: * `PYSPARK_PYTHON`, the Python binary to use for PySpark * `SPARK_LOCAL_IP`, to configure which IP address of the machine to bind to. * `SPARK_PUBLIC_DNS`, the hostname your Spark program will advertise to other machines. -* Options for the Spark [standalone cluster scripts](spark-standalone.html#cluster-launch-scripts), such as number of cores - to use on each machine and maximum memory. +* Options for the Spark [standalone cluster scripts](spark-standalone.html#cluster-launch-scripts), + such as number of cores to use on each machine and maximum memory. Since `spark-env.sh` is a shell script, some of these can be set programmatically -- for example, you might compute `SPARK_LOCAL_IP` by looking up the IP of a specific network interface. diff --git a/docs/hadoop-third-party-distributions.md b/docs/hadoop-third-party-distributions.md index 454877a7fa8a5..a0aeab5727bde 100644 --- a/docs/hadoop-third-party-distributions.md +++ b/docs/hadoop-third-party-distributions.md @@ -9,12 +9,14 @@ with these distributions: # Compile-time Hadoop Version -When compiling Spark, you'll need to -[set the SPARK_HADOOP_VERSION flag](index.html#a-note-about-hadoop-versions): +When compiling Spark, you'll need to specify the Hadoop version by defining the `hadoop.version` +property. For certain versions, you will need to specify additional profiles. For more detail, +see the guide on [building with maven](building-with-maven.html#specifying-the-hadoop-version): - SPARK_HADOOP_VERSION=1.0.4 sbt/sbt assembly + mvn -Dhadoop.version=1.0.4 -DskipTests clean package + mvn -Phadoop-2.2 -Dhadoop.version=2.2.0 -DskipTests clean package -The table below lists the corresponding `SPARK_HADOOP_VERSION` code for each CDH/HDP release. Note that +The table below lists the corresponding `hadoop.version` code for each CDH/HDP release. Note that some Hadoop releases are binary compatible across client versions. This means the pre-built Spark distribution may "just work" without you needing to compile. That said, we recommend compiling with the _exact_ Hadoop version you are running to avoid any compatibility errors. @@ -46,6 +48,10 @@ the _exact_ Hadoop version you are running to avoid any compatibility errors.
spark.default.parallelism
    +
  • Local mode: number of cores on the local machine
  • Mesos fine grained mode: 8
    • -
  • Local mode: core number of the local machine
    • -
  • Others: total core number of all executor nodes or 2, whichever is larger
    • +
  • Others: total number of cores on all executor nodes or 2, whichever is larger
 @@ -187,7 +203,7 @@ Apart from these, the following properties are also available, and may be useful Comma separated list of filter class names to apply to the Spark web ui. The filter should be a standard javax servlet Filter. Parameters to each filter can also be specified by setting a java system property of spark.<class name of filter>.params='param1=value1,param2=value2' - (e.g.-Dspark.ui.filters=com.test.filter1 -Dspark.com.test.filter1.params='param1=foo,param2=testing') + (e.g. -Dspark.ui.filters=com.test.filter1 -Dspark.com.test.filter1.params='param1=foo,param2=testing')
+In SBT, the equivalent can be achieved by setting the SPARK_HADOOP_VERSION flag: + + SPARK_HADOOP_VERSION=1.0.4 sbt/sbt assembly + # Linking Applications to the Hadoop Version In addition to compiling Spark itself against the right version, you need to add a Maven dependency on that diff --git a/docs/index.md b/docs/index.md index a2f1a84371ff4..48182a27d28ae 100644 --- a/docs/index.md +++ b/docs/index.md @@ -24,21 +24,31 @@ right version of Scala from [scala-lang.org](http://www.scala-lang.org/download/ # Running the Examples and Shell -Spark comes with several sample programs. Scala, Java and Python examples are in the `examples/src/main` directory. -To run one of the Java or Scala sample programs, use `./bin/run-example ` in the top-level Spark directory -(the `bin/run-example` script sets up the appropriate paths and launches that program). -For example, try `./bin/run-example org.apache.spark.examples.SparkPi local`. -To run a Python sample program, use `./bin/pyspark `. For example, try `./bin/pyspark ./examples/src/main/python/pi.py local`. +Spark comes with several sample programs. Scala, Java and Python examples are in the +`examples/src/main` directory. To run one of the Java or Scala sample programs, use +`bin/run-example [params]` in the top-level Spark directory. (Behind the scenes, this +invokes the more general +[Spark submit script](cluster-overview.html#launching-applications-with-spark-submit) for +launching applications). For example, -Each example prints usage help when run with no parameters. + ./bin/run-example SparkPi 10 -Note that all of the sample programs take a `` parameter specifying the cluster URL -to connect to. This can be a [URL for a distributed cluster](scala-programming-guide.html#master-urls), -or `local` to run locally with one thread, or `local[N]` to run locally with N threads. You should start by using -`local` for testing. +You can also run Spark interactively through modified versions of the Scala shell. This is a +great way to learn the framework. -Finally, you can run Spark interactively through modified versions of the Scala shell (`./bin/spark-shell`) or -Python interpreter (`./bin/pyspark`). These are a great way to learn the framework. + ./bin/spark-shell --master local[2] + +The `--master` option specifies the +[master URL for a distributed cluster](scala-programming-guide.html#master-urls), or `local` to run +locally with one thread, or `local[N]` to run locally with N threads. You should start by using +`local` for testing. For a full list of options, run Spark shell with the `--help` option. + +Spark also provides a Python interface. To run an example Spark application written in Python, use +`bin/pyspark [params]`. For example, + + ./bin/pyspark examples/src/main/python/pi.py local[2] 10 + +or simply `bin/pyspark` without any arguments to run Spark interactively in a python interpreter. # Launching on a Cluster diff --git a/docs/java-programming-guide.md b/docs/java-programming-guide.md index c34eb28fc06a2..943fdd9d019ff 100644 --- a/docs/java-programming-guide.md +++ b/docs/java-programming-guide.md @@ -215,7 +215,4 @@ Spark includes several sample programs using the Java API in [`examples/src/main/java`](https://github.com/apache/spark/tree/master/examples/src/main/java/org/apache/spark/examples). You can run them by passing the class name to the `bin/run-example` script included in Spark; for example: - ./bin/run-example org.apache.spark.examples.JavaWordCount - -Each example program prints usage help when run -without any arguments. + ./bin/run-example JavaWordCount README.md diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index 39fb5f0c99ca3..2ce2c346d7b04 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -164,6 +164,6 @@ some example applications. PySpark also includes several sample programs in the [`examples/src/main/python` folder](https://github.com/apache/spark/tree/master/examples/src/main/python). You can run them by passing the files to `pyspark`; e.g.: - ./bin/spark-submit examples/src/main/python/wordcount.py + ./bin/spark-submit examples/src/main/python/wordcount.py local[2] README.md Each program prints usage help when run without arguments. diff --git a/docs/quick-start.md b/docs/quick-start.md index 478b790f92e17..a4d01487bb494 100644 --- a/docs/quick-start.md +++ b/docs/quick-start.md @@ -18,7 +18,9 @@ you can download a package for any version of Hadoop. ## Basics Spark's interactive shell provides a simple way to learn the API, as well as a powerful tool to analyze datasets interactively. -Start the shell by running `./bin/spark-shell` in the Spark directory. +Start the shell by running the following in the Spark directory. + + ./bin/spark-shell Spark's primary abstraction is a distributed collection of items called a Resilient Distributed Dataset (RDD). RDDs can be created from Hadoop InputFormats (such as HDFS files) or by transforming other RDDs. Let's make a new RDD from the text of the README file in the Spark source directory: diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md index c563594296802..66c330fdee734 100644 --- a/docs/running-on-yarn.md +++ b/docs/running-on-yarn.md @@ -54,13 +54,13 @@ For example: --executor-memory 2g \ --executor-cores 1 lib/spark-examples*.jar \ - yarn-cluster 5 + 10 The above starts a YARN client program which starts the default Application Master. Then SparkPi will be run as a child thread of Application Master. The client will periodically poll the Application Master for status updates and display them in the console. The client will exit once your application has finished running. Refer to the "Viewing Logs" section below for how to see driver and executor logs. To launch a Spark application in yarn-client mode, do the same, but replace "yarn-cluster" with "yarn-client". To run spark-shell: - $ MASTER=yarn-client ./bin/spark-shell + $ ./bin/spark-shell --master yarn-client ## Adding additional jars @@ -70,9 +70,9 @@ In yarn-cluster mode, the driver runs on a different machine than the client, so --master yarn-cluster \ --jars my-other-jar.jar,my-other-other-jar.jar my-main-jar.jar - yarn-cluster 5 + app_arg1 app_arg2 -# Viewing logs +# Debugging your Application In YARN terminology, executors and application masters run inside "containers". YARN has two modes for handling container logs after an application has completed. If log aggregation is turned on (with the yarn.log-aggregation-enable config), container logs are copied to HDFS and deleted on the local machine. These logs can be viewed from anywhere on the cluster with the "yarn logs" command. @@ -82,6 +82,13 @@ will print out the contents of all log files from all containers from the given When log aggregation isn't turned on, logs are retained locally on each machine under YARN_APP_LOGS_DIR, which is usually configured to /tmp/logs or $HADOOP_HOME/logs/userlogs depending on the Hadoop version and installation. Viewing logs for a container requires going to the host that contains them and looking in this directory. Subdirectories organize log files by application ID and container ID. +To review per-container launch environment, increase yarn.nodemanager.delete.debug-delay-sec to a +large value (e.g. 36000), and then access the application cache through yarn.nodemanager.local-dirs +on the nodes on which containers are launched. This directory contains the launch script, jars, and +all environment variables used for launching each container. This process is useful for debugging +classpath problems in particular. (Note that enabling this requires admin privileges on cluster +settings and a restart of all node managers. Thus, this is not applicable to hosted clusters). + # Important notes - Before Hadoop 2.2, YARN does not support cores in container resource requests. Thus, when running against an earlier version, the numbers of cores given via command line arguments cannot be passed to YARN. Whether core requests are honored in scheduling decisions depends on which scheduler is in use and how it is configured. diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md index f25e9cca88524..3ed86e460c01c 100644 --- a/docs/scala-programming-guide.md +++ b/docs/scala-programming-guide.md @@ -56,7 +56,7 @@ The `master` parameter is a string specifying a [Spark, Mesos or YARN cluster UR to connect to, or a special "local" string to run in local mode, as described below. `appName` is a name for your application, which will be shown in the cluster web UI. It's also possible to set these variables [using a configuration file](cluster-overview.html#loading-configurations-from-a-file) -which avoids hard-coding the master name in your application. +which avoids hard-coding the master url in your application. In the Spark shell, a special interpreter-aware SparkContext is already created for you, in the variable called `sc`. Making your own SparkContext will not work. You can set which master the @@ -74,6 +74,11 @@ Or, to also add `code.jar` to its classpath, use: $ ./bin/spark-shell --master local[4] --jars code.jar {% endhighlight %} +For a complete list of options, run Spark shell with the `--help` option. Behind the scenes, +Spark shell invokes the more general [Spark submit script](cluster-overview.html#launching-applications-with-spark-submit) +used for launching applications, and passes on all of its parameters. As a result, these two scripts +share the same parameters. + ### Master URLs The master URL passed to Spark can be in one of the following formats: @@ -98,7 +103,7 @@ cluster mode. The cluster location will be inferred based on the local Hadoop co -If no master URL is specified, the spark shell defaults to "local[*]". +If no master URL is specified, the spark shell defaults to `local[*]`. # Resilient Distributed Datasets (RDDs) @@ -432,9 +437,7 @@ res2: Int = 10 You can see some [example Spark programs](http://spark.apache.org/examples.html) on the Spark website. In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `bin/run-example` script included in Spark; for example: - ./bin/run-example org.apache.spark.examples.SparkPi - -Each example program prints usage help when run without any arguments. + ./bin/run-example SparkPi For help on optimizing your program, the [configuration](configuration.html) and [tuning](tuning.html) guides provide information on best practices. They are especially important for diff --git a/docs/spark-standalone.md b/docs/spark-standalone.md index dc7f206e03996..eb3211b6b0e4e 100644 --- a/docs/spark-standalone.md +++ b/docs/spark-standalone.md @@ -70,7 +70,7 @@ Once you've set up this file, you can launch or stop your cluster with the follo - `sbin/start-slaves.sh` - Starts a slave instance on each machine specified in the `conf/slaves` file. - `sbin/start-all.sh` - Starts both a master and a number of slaves as described above. - `sbin/stop-master.sh` - Stops the master that was started via the `bin/start-master.sh` script. -- `sbin/stop-slaves.sh` - Stops the slave instances that were started via `bin/start-slaves.sh`. +- `sbin/stop-slaves.sh` - Stops all slave instances on the machines specified in the `conf/slaves` file. - `sbin/stop-all.sh` - Stops both the master and the slaves as described above. Note that these scripts must be executed on the machine you want to run the Spark master on, not your local machine. @@ -92,12 +92,8 @@ You can optionally configure the cluster further by setting environment variable Port for the master web UI (default: 8080). - SPARK_WORKER_PORT - Start the Spark worker on a specific port (default: random). - - - SPARK_WORKER_DIR - Directory to run applications in, which will include both logs and scratch space (default: SPARK_HOME/work). + SPARK_MASTER_OPTS + Configuration properties that apply only to the master in the form "-Dx=y" (default: none). SPARK_WORKER_CORES @@ -107,6 +103,10 @@ You can optionally configure the cluster further by setting environment variable SPARK_WORKER_MEMORY Total amount of memory to allow Spark applications to use on the machine, e.g. 1000m, 2g (default: total memory minus 1 GB); note that each application's individual memory is configured using its spark.executor.memory property. + + SPARK_WORKER_PORT + Start the Spark worker on a specific port (default: random). + SPARK_WORKER_WEBUI_PORT Port for the worker web UI (default: 8081). @@ -120,13 +120,25 @@ You can optionally configure the cluster further by setting environment variable or else each worker will try to use all the cores. + + SPARK_WORKER_DIR + Directory to run applications in, which will include both logs and scratch space (default: SPARK_HOME/work). + + + SPARK_WORKER_OPTS + Configuration properties that apply only to the worker in the form "-Dx=y" (default: none). + SPARK_DAEMON_MEMORY Memory to allocate to the Spark master and worker daemons themselves (default: 512m). SPARK_DAEMON_JAVA_OPTS - JVM options for the Spark master and worker daemons themselves (default: none). + JVM options for the Spark master and worker daemons themselves in the form "-Dx=y" (default: none). + + + SPARK_PUBLIC_DNS + The public DNS name of the Spark master and workers (default: none). @@ -148,38 +160,17 @@ You can also pass an option `--cores ` to control the number of cores # Launching Compiled Spark Applications -Spark supports two deploy modes. Spark applications may run with the driver inside the client process or entirely inside the cluster. - -The spark-submit script described in the [cluster mode overview](cluster-overview.html) provides the most straightforward way to submit a compiled Spark application to the cluster in either deploy mode. For info on the lower-level invocations used to launch an app inside the cluster, read ahead. - -## Launching Applications Inside the Cluster - - ./bin/spark-class org.apache.spark.deploy.Client launch - [client-options] \ - \ - [application-options] - - cluster-url: The URL of the master node. - application-jar-url: Path to a bundled jar including your application and all dependencies. Currently, the URL must be globally visible inside of your cluster, for instance, an `hdfs://` path or a `file://` path that is present on all nodes. - main-class: The entry point for your application. - - Client Options: - --memory (amount of memory, in MB, allocated for your driver program) - --cores (number of cores allocated for your driver program) - --supervise (whether to automatically restart your driver on application or node failure) - --verbose (prints increased logging output) - -Keep in mind that your driver program will be executed on a remote worker machine. You can control the execution environment in the following ways: - - * _Environment variables_: These will be captured from the environment in which you launch the client and applied when launching the driver program. - * _Java options_: You can add java options by setting `SPARK_JAVA_OPTS` in the environment in which you launch the submission client. - * _Dependencies_: You'll still need to call `sc.addJar` inside of your program to make your bundled application jar visible on all worker nodes. - -Once you submit a driver program, it will appear in the cluster management UI at port 8080 and -be assigned an identifier. If you'd like to prematurely terminate the program, you can do so using -the same client: +Spark supports two deploy modes: applications may run with the driver inside the client process or +entirely inside the cluster. The +[Spark submit script](cluster-overview.html#launching-applications-with-spark-submit) provides the +most straightforward way to submit a compiled Spark application to the cluster in either deploy +mode. - ./bin/spark-class org.apache.spark.deploy.Client kill +If your application is launched through Spark submit, then the application jar is automatically +distributed to all worker nodes. For any additional jars that your application depends on, you +should specify them through the `--jars` flag using comma as a delimiter (e.g. `--jars jar1,jar2`). +To control the application's configuration or execution environment, see +[Spark Configuration](configuration.html). # Resource Scheduling @@ -203,7 +194,7 @@ default for applications that don't set `spark.cores.max` to something less than Do this by adding the following to `conf/spark-env.sh`: {% highlight bash %} -export SPARK_JAVA_OPTS="-Dspark.deploy.defaultCores=" +export SPARK_MASTER_OPTS="-Dspark.deploy.defaultCores=" {% endhighlight %} This is useful on shared clusters where users might not have configured a maximum number of cores From 2792bd016af2a67848e6f403c4e1e05e9f3e3c2a Mon Sep 17 00:00:00 2001 From: Sandy Ryza Date: Mon, 12 May 2014 20:08:30 -0700 Subject: [PATCH 20/99] SPARK-1815. SparkContext should not be marked DeveloperApi Author: Sandy Ryza Closes #753 from sryza/sandy-spark-1815 and squashes the following commits: 957a8ac [Sandy Ryza] SPARK-1815. SparkContext should not be marked DeveloperApi --- core/src/main/scala/org/apache/spark/SparkContext.scala | 2 -- 1 file changed, 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 35beff0f8ef3d..c43b4fd6d926f 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -50,7 +50,6 @@ import org.apache.spark.ui.SparkUI import org.apache.spark.util.{ClosureCleaner, MetadataCleaner, MetadataCleanerType, TimeStampedWeakValueHashMap, Utils} /** - * :: DeveloperApi :: * Main entry point for Spark functionality. A SparkContext represents the connection to a Spark * cluster, and can be used to create RDDs, accumulators and broadcast variables on that cluster. * @@ -58,7 +57,6 @@ import org.apache.spark.util.{ClosureCleaner, MetadataCleaner, MetadataCleanerTy * this config overrides the default configs as well as system properties. */ -@DeveloperApi class SparkContext(config: SparkConf) extends Logging { // This is used only by YARN for now, but should be relevant to other cluster types (Mesos, From 52d905296fd75b3bff34a16cb69e604b68b3c246 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Mon, 12 May 2014 23:02:54 -0700 Subject: [PATCH 21/99] BUILD: Add more content to make-distribution.sh. --- make-distribution.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/make-distribution.sh b/make-distribution.sh index 1cc2844703fbb..7a08d6b9151c4 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -171,10 +171,22 @@ echo "Spark $VERSION built for Hadoop $SPARK_HADOOP_VERSION" > "$DISTDIR/RELEASE cp $FWDIR/assembly/target/scala*/*assembly*hadoop*.jar "$DISTDIR/lib/" cp $FWDIR/examples/target/scala*/spark-examples*.jar "$DISTDIR/lib/" +# Copy example sources (needed for python and SQL) +mkdir -p "$DISTDIR/examples/src/main" +cp -r $FWDIR/examples/src/main "$DISTDIR/examples/src/" + if [ "$SPARK_HIVE" == "true" ]; then cp $FWDIR/lib_managed/jars/datanucleus*.jar "$DISTDIR/lib/" fi +# Copy license and ASF files +cp "$FWDIR/LICENSE" "$DISTDIR" +cp "$FWDIR/NOTICE" "$DISTDIR" + +if [ -e $FWDIR/CHANGES.txt ]; then + cp "$FWDIR/CHANGES.txt" "$DISTDIR" +fi + # Copy other things mkdir "$DISTDIR"/conf cp "$FWDIR"/conf/*.template "$DISTDIR"/conf @@ -182,6 +194,7 @@ cp "$FWDIR"/conf/slaves "$DISTDIR"/conf cp -r "$FWDIR/bin" "$DISTDIR" cp -r "$FWDIR/python" "$DISTDIR" cp -r "$FWDIR/sbin" "$DISTDIR" +cp -r "$FWDIR/ec2" "$DISTDIR" # Download and copy in tachyon, if requested if [ "$SPARK_TACHYON" == "true" ]; then From 16ffadcc4af21430b5079dc555bcd9d8cf1fa1fa Mon Sep 17 00:00:00 2001 From: William Benton Date: Tue, 13 May 2014 13:45:23 -0700 Subject: [PATCH 22/99] SPARK-571: forbid return statements in cleaned closures This patch checks top-level closure arguments to `ClosureCleaner.clean` for `return` statements and raises an exception if it finds any. This is mainly a user-friendliness addition, since programs with return statements in closure arguments will currently fail upon RDD actions with a less-than-intuitive error message. Author: William Benton Closes #717 from willb/spark-571 and squashes the following commits: c41eb7d [William Benton] Another test case for SPARK-571 30c42f4 [William Benton] Stylistic cleanups 559b16b [William Benton] Stylistic cleanups from review de13b79 [William Benton] Style fixes 295b6a5 [William Benton] Forbid return statements in closure arguments. b017c47 [William Benton] Added a test for SPARK-571 --- .../apache/spark/util/ClosureCleaner.scala | 23 ++++++++++- .../spark/util/ClosureCleanerSuite.scala | 39 ++++++++++++++++++- 2 files changed, 60 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala b/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala index 2d05e09b10948..4916d9b86cca5 100644 --- a/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala +++ b/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala @@ -25,7 +25,7 @@ import scala.collection.mutable.Set import com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.{ClassReader, ClassVisitor, MethodVisitor, Type} import com.esotericsoftware.reflectasm.shaded.org.objectweb.asm.Opcodes._ -import org.apache.spark.Logging +import org.apache.spark.{Logging, SparkException} private[spark] object ClosureCleaner extends Logging { // Get an ASM class reader for a given class from the JAR that loaded it @@ -108,6 +108,9 @@ private[spark] object ClosureCleaner extends Logging { val outerObjects = getOuterObjects(func) val accessedFields = Map[Class[_], Set[String]]() + + getClassReader(func.getClass).accept(new ReturnStatementFinder(), 0) + for (cls <- outerClasses) accessedFields(cls) = Set[String]() for (cls <- func.getClass :: innerClasses) @@ -180,6 +183,24 @@ private[spark] object ClosureCleaner extends Logging { } } +private[spark] +class ReturnStatementFinder extends ClassVisitor(ASM4) { + override def visitMethod(access: Int, name: String, desc: String, + sig: String, exceptions: Array[String]): MethodVisitor = { + if (name.contains("apply")) { + new MethodVisitor(ASM4) { + override def visitTypeInsn(op: Int, tp: String) { + if (op == NEW && tp.contains("scala/runtime/NonLocalReturnControl")) { + throw new SparkException("Return statements aren't allowed in Spark closures") + } + } + } + } else { + new MethodVisitor(ASM4) {} + } + } +} + private[spark] class FieldAccessFinder(output: Map[Class[_], Set[String]]) extends ClassVisitor(ASM4) { override def visitMethod(access: Int, name: String, desc: String, diff --git a/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala b/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala index d7e48e633e0ee..054ef54e746a5 100644 --- a/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala +++ b/core/src/test/scala/org/apache/spark/util/ClosureCleanerSuite.scala @@ -20,7 +20,7 @@ package org.apache.spark.util import org.scalatest.FunSuite import org.apache.spark.LocalSparkContext._ -import org.apache.spark.SparkContext +import org.apache.spark.{SparkContext, SparkException} class ClosureCleanerSuite extends FunSuite { test("closures inside an object") { @@ -50,6 +50,19 @@ class ClosureCleanerSuite extends FunSuite { val obj = new TestClassWithNesting(1) assert(obj.run() === 96) // 4 * (1+2+3+4) + 4 * (1+2+3+4) + 16 * 1 } + + test("toplevel return statements in closures are identified at cleaning time") { + val ex = intercept[SparkException] { + TestObjectWithBogusReturns.run() + } + + assert(ex.getMessage.contains("Return statements aren't allowed in Spark closures")) + } + + test("return statements from named functions nested in closures don't raise exceptions") { + val result = TestObjectWithNestedReturns.run() + assert(result == 1) + } } // A non-serializable class we create in closures to make sure that we aren't @@ -108,6 +121,30 @@ class TestClassWithoutFieldAccess { } } +object TestObjectWithBogusReturns { + def run(): Int = { + withSpark(new SparkContext("local", "test")) { sc => + val nums = sc.parallelize(Array(1, 2, 3, 4)) + // this return is invalid since it will transfer control outside the closure + nums.map {x => return 1 ; x * 2} + 1 + } + } +} + +object TestObjectWithNestedReturns { + def run(): Int = { + withSpark(new SparkContext("local", "test")) { sc => + val nums = sc.parallelize(Array(1, 2, 3, 4)) + nums.map {x => + // this return is fine since it will not transfer control outside the closure + def foo(): Int = { return 5; 1 } + foo() + } + 1 + } + } +} object TestObjectWithNesting { def run(): Int = { From d1e487473fd509f28daf28dcda856f3c2f1194ec Mon Sep 17 00:00:00 2001 From: Andrew Tulloch Date: Tue, 13 May 2014 17:31:27 -0700 Subject: [PATCH 23/99] SPARK-1791 - SVM implementation does not use threshold parameter Summary: https://issues.apache.org/jira/browse/SPARK-1791 Simple fix, and backward compatible, since - anyone who set the threshold was getting completely wrong answers. - anyone who did not set the threshold had the default 0.0 value for the threshold anyway. Test Plan: Unit test added that is verified to fail under the old implementation, and pass under the new implementation. Reviewers: CC: Author: Andrew Tulloch Closes #725 from ajtulloch/SPARK-1791-SVM and squashes the following commits: 770f55d [Andrew Tulloch] SPARK-1791 - SVM implementation does not use threshold parameter --- .../spark/mllib/classification/SVM.scala | 2 +- .../spark/mllib/classification/SVMSuite.scala | 37 +++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala index e05213536e64a..316ecd713b715 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala @@ -65,7 +65,7 @@ class SVMModel private[mllib] ( intercept: Double) = { val margin = weightMatrix.toBreeze.dot(dataMatrix.toBreeze) + intercept threshold match { - case Some(t) => if (margin < 0) 0.0 else 1.0 + case Some(t) => if (margin < t) 0.0 else 1.0 case None => margin } } diff --git a/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala index 77d6f04b32320..886c71dde3af7 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala @@ -69,6 +69,43 @@ class SVMSuite extends FunSuite with LocalSparkContext { assert(numOffPredictions < input.length / 5) } + test("SVM with threshold") { + val nPoints = 10000 + + // NOTE: Intercept should be small for generating equal 0s and 1s + val A = 0.01 + val B = -1.5 + val C = 1.0 + + val testData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 42) + + val testRDD = sc.parallelize(testData, 2) + testRDD.cache() + + val svm = new SVMWithSGD().setIntercept(true) + svm.optimizer.setStepSize(1.0).setRegParam(1.0).setNumIterations(100) + + val model = svm.run(testRDD) + + val validationData = SVMSuite.generateSVMInput(A, Array[Double](B, C), nPoints, 17) + val validationRDD = sc.parallelize(validationData, 2) + + // Test prediction on RDD. + + var predictions = model.predict(validationRDD.map(_.features)).collect() + assert(predictions.count(_ == 0.0) != predictions.length) + + // High threshold makes all the predictions 0.0 + model.setThreshold(10000.0) + predictions = model.predict(validationRDD.map(_.features)).collect() + assert(predictions.count(_ == 0.0) == predictions.length) + + // Low threshold makes all the predictions 1.0 + model.setThreshold(-10000.0) + predictions = model.predict(validationRDD.map(_.features)).collect() + assert(predictions.count(_ == 1.0) == predictions.length) + } + test("SVM using local random SGD") { val nPoints = 10000 From 5c0dafc2c8734a421206a808b73be67b66264dd7 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Tue, 13 May 2014 18:32:32 -0700 Subject: [PATCH 24/99] [SPARK-1816] LiveListenerBus dies if a listener throws an exception The solution is to wrap a try / catch / log around the posting of each event to each listener. Author: Andrew Or Closes #759 from andrewor14/listener-die and squashes the following commits: aee5107 [Andrew Or] Merge branch 'master' of github.com:apache/spark into listener-die 370939f [Andrew Or] Remove two layers of indirection 422d278 [Andrew Or] Explicitly throw an exception instead of 1 / 0 0df0e2a [Andrew Or] Try/catch and log exceptions when posting events --- .../spark/scheduler/LiveListenerBus.scala | 36 ++++++++++--- .../spark/scheduler/SparkListenerBus.scala | 50 +++++++++++++------ .../scala/org/apache/spark/util/Utils.scala | 2 +- .../spark/scheduler/SparkListenerSuite.scala | 50 +++++++++++++++++-- 4 files changed, 109 insertions(+), 29 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/scheduler/LiveListenerBus.scala b/core/src/main/scala/org/apache/spark/scheduler/LiveListenerBus.scala index dec3316bf7745..36a6e6338faa6 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/LiveListenerBus.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/LiveListenerBus.scala @@ -20,6 +20,7 @@ package org.apache.spark.scheduler import java.util.concurrent.{LinkedBlockingQueue, Semaphore} import org.apache.spark.Logging +import org.apache.spark.util.Utils /** * Asynchronously passes SparkListenerEvents to registered SparkListeners. @@ -42,7 +43,7 @@ private[spark] class LiveListenerBus extends SparkListenerBus with Logging { private val listenerThread = new Thread("SparkListenerBus") { setDaemon(true) - override def run() { + override def run(): Unit = Utils.logUncaughtExceptions { while (true) { eventLock.acquire() // Atomically remove and process this event @@ -77,11 +78,8 @@ private[spark] class LiveListenerBus extends SparkListenerBus with Logging { val eventAdded = eventQueue.offer(event) if (eventAdded) { eventLock.release() - } else if (!queueFullErrorMessageLogged) { - logError("Dropping SparkListenerEvent because no remaining room in event queue. " + - "This likely means one of the SparkListeners is too slow and cannot keep up with the " + - "rate at which tasks are being started by the scheduler.") - queueFullErrorMessageLogged = true + } else { + logQueueFullErrorMessage() } } @@ -96,13 +94,18 @@ private[spark] class LiveListenerBus extends SparkListenerBus with Logging { if (System.currentTimeMillis > finishTime) { return false } - /* Sleep rather than using wait/notify, because this is used only for testing and wait/notify - * add overhead in the general case. */ + /* Sleep rather than using wait/notify, because this is used only for testing and + * wait/notify add overhead in the general case. */ Thread.sleep(10) } true } + /** + * For testing only. Return whether the listener daemon thread is still alive. + */ + def listenerThreadIsAlive: Boolean = synchronized { listenerThread.isAlive } + /** * Return whether the event queue is empty. * @@ -111,6 +114,23 @@ private[spark] class LiveListenerBus extends SparkListenerBus with Logging { */ def queueIsEmpty: Boolean = synchronized { eventQueue.isEmpty } + /** + * Log an error message to indicate that the event queue is full. Do this only once. + */ + private def logQueueFullErrorMessage(): Unit = { + if (!queueFullErrorMessageLogged) { + if (listenerThread.isAlive) { + logError("Dropping SparkListenerEvent because no remaining room in event queue. " + + "This likely means one of the SparkListeners is too slow and cannot keep up with" + + "the rate at which tasks are being started by the scheduler.") + } else { + logError("SparkListenerBus thread is dead! This means SparkListenerEvents have not" + + "been (and will no longer be) propagated to listeners for some time.") + } + queueFullErrorMessageLogged = true + } + } + def stop() { if (!started) { throw new IllegalStateException("Attempted to stop a listener bus that has not yet started!") diff --git a/core/src/main/scala/org/apache/spark/scheduler/SparkListenerBus.scala b/core/src/main/scala/org/apache/spark/scheduler/SparkListenerBus.scala index 0286aac8769b2..ed9fb24bc8ce8 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/SparkListenerBus.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/SparkListenerBus.scala @@ -20,10 +20,13 @@ package org.apache.spark.scheduler import scala.collection.mutable import scala.collection.mutable.ArrayBuffer +import org.apache.spark.Logging +import org.apache.spark.util.Utils + /** * A SparkListenerEvent bus that relays events to its listeners */ -private[spark] trait SparkListenerBus { +private[spark] trait SparkListenerBus extends Logging { // SparkListeners attached to this event bus protected val sparkListeners = new ArrayBuffer[SparkListener] @@ -34,38 +37,53 @@ private[spark] trait SparkListenerBus { } /** - * Post an event to all attached listeners. This does nothing if the event is - * SparkListenerShutdown. + * Post an event to all attached listeners. + * This does nothing if the event is SparkListenerShutdown. */ def postToAll(event: SparkListenerEvent) { event match { case stageSubmitted: SparkListenerStageSubmitted => - sparkListeners.foreach(_.onStageSubmitted(stageSubmitted)) + foreachListener(_.onStageSubmitted(stageSubmitted)) case stageCompleted: SparkListenerStageCompleted => - sparkListeners.foreach(_.onStageCompleted(stageCompleted)) + foreachListener(_.onStageCompleted(stageCompleted)) case jobStart: SparkListenerJobStart => - sparkListeners.foreach(_.onJobStart(jobStart)) + foreachListener(_.onJobStart(jobStart)) case jobEnd: SparkListenerJobEnd => - sparkListeners.foreach(_.onJobEnd(jobEnd)) + foreachListener(_.onJobEnd(jobEnd)) case taskStart: SparkListenerTaskStart => - sparkListeners.foreach(_.onTaskStart(taskStart)) + foreachListener(_.onTaskStart(taskStart)) case taskGettingResult: SparkListenerTaskGettingResult => - sparkListeners.foreach(_.onTaskGettingResult(taskGettingResult)) + foreachListener(_.onTaskGettingResult(taskGettingResult)) case taskEnd: SparkListenerTaskEnd => - sparkListeners.foreach(_.onTaskEnd(taskEnd)) + foreachListener(_.onTaskEnd(taskEnd)) case environmentUpdate: SparkListenerEnvironmentUpdate => - sparkListeners.foreach(_.onEnvironmentUpdate(environmentUpdate)) + foreachListener(_.onEnvironmentUpdate(environmentUpdate)) case blockManagerAdded: SparkListenerBlockManagerAdded => - sparkListeners.foreach(_.onBlockManagerAdded(blockManagerAdded)) + foreachListener(_.onBlockManagerAdded(blockManagerAdded)) case blockManagerRemoved: SparkListenerBlockManagerRemoved => - sparkListeners.foreach(_.onBlockManagerRemoved(blockManagerRemoved)) + foreachListener(_.onBlockManagerRemoved(blockManagerRemoved)) case unpersistRDD: SparkListenerUnpersistRDD => - sparkListeners.foreach(_.onUnpersistRDD(unpersistRDD)) + foreachListener(_.onUnpersistRDD(unpersistRDD)) case applicationStart: SparkListenerApplicationStart => - sparkListeners.foreach(_.onApplicationStart(applicationStart)) + foreachListener(_.onApplicationStart(applicationStart)) case applicationEnd: SparkListenerApplicationEnd => - sparkListeners.foreach(_.onApplicationEnd(applicationEnd)) + foreachListener(_.onApplicationEnd(applicationEnd)) case SparkListenerShutdown => } } + + /** + * Apply the given function to all attached listeners, catching and logging any exception. + */ + private def foreachListener(f: SparkListener => Unit): Unit = { + sparkListeners.foreach { listener => + try { + f(listener) + } catch { + case e: Exception => + logError(s"Listener ${Utils.getFormattedClassName(listener)} threw an exception", e) + } + } + } + } diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 0631e54237923..99ef6dd1fa6e3 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1128,7 +1128,7 @@ private[spark] object Utils extends Logging { } /** - * Executes the given block, printing and re-throwing any uncaught exceptions. + * Execute the given block, logging and re-throwing any uncaught exception. * This is particularly useful for wrapping code that runs in a thread, to ensure * that exceptions are printed, and to avoid having to catch Throwable. */ diff --git a/core/src/test/scala/org/apache/spark/scheduler/SparkListenerSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/SparkListenerSuite.scala index 4e9fd07e68a21..5426e578a9ddd 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/SparkListenerSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/SparkListenerSuite.scala @@ -331,16 +331,47 @@ class SparkListenerSuite extends FunSuite with LocalSparkContext with ShouldMatc } } - def checkNonZeroAvg(m: Traversable[Long], msg: String) { + test("SparkListener moves on if a listener throws an exception") { + val badListener = new BadListener + val jobCounter1 = new BasicJobCounter + val jobCounter2 = new BasicJobCounter + val bus = new LiveListenerBus + + // Propagate events to bad listener first + bus.addListener(badListener) + bus.addListener(jobCounter1) + bus.addListener(jobCounter2) + bus.start() + + // Post events to all listeners, and wait until the queue is drained + (1 to 5).foreach { _ => bus.post(SparkListenerJobEnd(0, JobSucceeded)) } + assert(bus.waitUntilEmpty(WAIT_TIMEOUT_MILLIS)) + + // The exception should be caught, and the event should be propagated to other listeners + assert(bus.listenerThreadIsAlive) + assert(jobCounter1.count === 5) + assert(jobCounter2.count === 5) + } + + /** + * Assert that the given list of numbers has an average that is greater than zero. + */ + private def checkNonZeroAvg(m: Traversable[Long], msg: String) { assert(m.sum / m.size.toDouble > 0.0, msg) } - class BasicJobCounter extends SparkListener { + /** + * A simple listener that counts the number of jobs observed. + */ + private class BasicJobCounter extends SparkListener { var count = 0 override def onJobEnd(job: SparkListenerJobEnd) = count += 1 } - class SaveStageAndTaskInfo extends SparkListener { + /** + * A simple listener that saves all task infos and task metrics. + */ + private class SaveStageAndTaskInfo extends SparkListener { val stageInfos = mutable.Map[StageInfo, Seq[(TaskInfo, TaskMetrics)]]() var taskInfoMetrics = mutable.Buffer[(TaskInfo, TaskMetrics)]() @@ -358,7 +389,10 @@ class SparkListenerSuite extends FunSuite with LocalSparkContext with ShouldMatc } } - class SaveTaskEvents extends SparkListener { + /** + * A simple listener that saves the task indices for all task events. + */ + private class SaveTaskEvents extends SparkListener { val startedTasks = new mutable.HashSet[Int]() val startedGettingResultTasks = new mutable.HashSet[Int]() val endedTasks = new mutable.HashSet[Int]() @@ -377,4 +411,12 @@ class SparkListenerSuite extends FunSuite with LocalSparkContext with ShouldMatc startedGettingResultTasks += taskGettingResult.taskInfo.index } } + + /** + * A simple listener that throws an exception on job end. + */ + private class BadListener extends SparkListener { + override def onJobEnd(jobEnd: SparkListenerJobEnd) = { throw new Exception } + } + } From 753b04dea4b04ba9d0dd0011f00e9d70367e76fc Mon Sep 17 00:00:00 2001 From: Ye Xianjin Date: Tue, 13 May 2014 19:03:51 -0700 Subject: [PATCH 25/99] [SPARK-1527] change rootDir*.getName to rootDir*.getAbsolutePath JIRA issue: [SPARK-1527](https://issues.apache.org/jira/browse/SPARK-1527) getName() only gets the last component of the file path. When deleting test-generated directories, we should pass the generated directory's absolute path to DiskBlockManager. Author: Ye Xianjin This patch had conflicts when merged, resolved by Committer: Patrick Wendell Closes #436 from advancedxy/SPARK-1527 and squashes the following commits: 4678bab [Ye Xianjin] change rootDir*.getname to rootDir*.getAbsolutePath so the temporary directories are deleted when the test is finished. --- .../scala/org/apache/spark/storage/DiskBlockManagerSuite.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala index 2167718fd2428..aaa7714049732 100644 --- a/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/storage/DiskBlockManagerSuite.scala @@ -52,7 +52,7 @@ class DiskBlockManagerSuite extends FunSuite with BeforeAndAfterEach with Before rootDir0.deleteOnExit() rootDir1 = Files.createTempDir() rootDir1.deleteOnExit() - rootDirs = rootDir0.getName + "," + rootDir1.getName + rootDirs = rootDir0.getAbsolutePath + "," + rootDir1.getAbsolutePath println("Created root dirs: " + rootDirs) } From 44233865cf8020741d862d33cc660c88e9315dea Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Tue, 13 May 2014 21:23:51 -0700 Subject: [PATCH 26/99] [SQL] Make it possible to create Java/Python SQLContexts from an existing Scala SQLContext. Author: Michael Armbrust Closes #761 from marmbrus/existingContext and squashes the following commits: 4651051 [Michael Armbrust] Make it possible to create Java/Python SQLContexts from an existing Scala SQLContext. --- python/pyspark/sql.py | 7 +++++-- .../org/apache/spark/sql/api/java/JavaSQLContext.scala | 4 ++-- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 6789d7002b3b7..bbe69e7d8f89b 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -28,7 +28,7 @@ class SQLContext: register L{SchemaRDD}s as tables, execute sql over tables, cache tables, and read parquet files. """ - def __init__(self, sparkContext): + def __init__(self, sparkContext, sqlContext = None): """ Create a new SQLContext. @@ -58,10 +58,13 @@ def __init__(self, sparkContext): self._jvm = self._sc._jvm self._pythonToJavaMap = self._jvm.PythonRDD.pythonToJavaMap + if sqlContext: + self._scala_SQLContext = sqlContext + @property def _ssql_ctx(self): """ - Accessor for the JVM SparkSQL context. Subclasses can overrite this property to provide + Accessor for the JVM SparkSQL context. Subclasses can override this property to provide their own JVM Contexts. """ if not hasattr(self, '_scala_SQLContext'): diff --git a/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSQLContext.scala b/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSQLContext.scala index 57facbe10fc96..6f7d431b9a819 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSQLContext.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSQLContext.scala @@ -33,9 +33,9 @@ import org.apache.spark.util.Utils /** * The entry point for executing Spark SQL queries from a Java program. */ -class JavaSQLContext(sparkContext: JavaSparkContext) { +class JavaSQLContext(val sqlContext: SQLContext) { - val sqlContext = new SQLContext(sparkContext.sc) + def this(sparkContext: JavaSparkContext) = this(new SQLContext(sparkContext.sc)) /** * Executes a query expressed in SQL, returning the result as a JavaSchemaRDD From 92cebada09a7e5a00ab48bcb350a9462949c33eb Mon Sep 17 00:00:00 2001 From: Syed Hashmi Date: Tue, 13 May 2014 21:24:23 -0700 Subject: [PATCH 27/99] [SPARK-1784] Add a new partitioner to allow specifying # of keys per partition This change adds a new partitioner which allows users to specify # of keys per partition. Author: Syed Hashmi Closes #721 from syedhashmi/master and squashes the following commits: 4ca94cc [Syed Hashmi] [SPARK-1784] Add a new partitioner --- .../scala/org/apache/spark/Partitioner.scala | 61 +++++++++++++++++++ .../org/apache/spark/PartitioningSuite.scala | 34 +++++++++++ 2 files changed, 95 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala index 9155159cf6aeb..62747960618a9 100644 --- a/core/src/main/scala/org/apache/spark/Partitioner.scala +++ b/core/src/main/scala/org/apache/spark/Partitioner.scala @@ -156,3 +156,64 @@ class RangePartitioner[K : Ordering : ClassTag, V]( false } } + +/** + * A [[org.apache.spark.Partitioner]] that partitions records into specified bounds + * Default value is 1000. Once all partitions have bounds elements, the partitioner + * allocates 1 element per partition so eventually the smaller partitions are at most + * off by 1 key compared to the larger partitions. + */ +class BoundaryPartitioner[K : Ordering : ClassTag, V]( + partitions: Int, + @transient rdd: RDD[_ <: Product2[K,V]], + private val boundary: Int = 1000) + extends Partitioner { + + // this array keeps track of keys assigned to a partition + // counts[0] refers to # of keys in partition 0 and so on + private val counts: Array[Int] = { + new Array[Int](numPartitions) + } + + def numPartitions = math.abs(partitions) + + /* + * Ideally, this should've been calculated based on # partitions and total keys + * But we are not calling count on RDD here to avoid calling an action. + * User has the flexibility of calling count and passing in any appropriate boundary + */ + def keysPerPartition = boundary + + var currPartition = 0 + + /* + * Pick current partition for the key until we hit the bound for keys / partition, + * start allocating to next partition at that time. + * + * NOTE: In case where we have lets say 2000 keys and user says 3 partitions with 500 + * passed in as boundary, the first 500 will goto P1, 501-1000 go to P2, 1001-1500 go to P3, + * after that, next keys go to one partition at a time. So 1501 goes to P1, 1502 goes to P2, + * 1503 goes to P3 and so on. + */ + def getPartition(key: Any): Int = { + val partition = currPartition + counts(partition) = counts(partition) + 1 + /* + * Since we are filling up a partition before moving to next one (this helps in maintaining + * order of keys, in certain cases, it is possible to end up with empty partitions, like + * 3 partitions, 500 keys / partition and if rdd has 700 keys, 1 partition will be entirely + * empty. + */ + if(counts(currPartition) >= keysPerPartition) + currPartition = (currPartition + 1) % numPartitions + partition + } + + override def equals(other: Any): Boolean = other match { + case r: BoundaryPartitioner[_,_] => + (r.counts.sameElements(counts) && r.boundary == boundary + && r.currPartition == currPartition) + case _ => + false + } +} diff --git a/core/src/test/scala/org/apache/spark/PartitioningSuite.scala b/core/src/test/scala/org/apache/spark/PartitioningSuite.scala index 7c30626a0c421..7d40395803f02 100644 --- a/core/src/test/scala/org/apache/spark/PartitioningSuite.scala +++ b/core/src/test/scala/org/apache/spark/PartitioningSuite.scala @@ -66,6 +66,40 @@ class PartitioningSuite extends FunSuite with SharedSparkContext with PrivateMet assert(descendingP4 != p4) } + test("BoundaryPartitioner equality") { + // Make an RDD where all the elements are the same so that the partition range bounds + // are deterministically all the same. + val rdd = sc.parallelize(1.to(4000)).map(x => (x, x)) + + val p2 = new BoundaryPartitioner(2, rdd, 1000) + val p4 = new BoundaryPartitioner(4, rdd, 1000) + val anotherP4 = new BoundaryPartitioner(4, rdd) + + assert(p2 === p2) + assert(p4 === p4) + assert(p2 != p4) + assert(p4 != p2) + assert(p4 === anotherP4) + assert(anotherP4 === p4) + } + + test("BoundaryPartitioner getPartition") { + val rdd = sc.parallelize(1.to(2000)).map(x => (x, x)) + val partitioner = new BoundaryPartitioner(4, rdd, 500) + 1.to(2000).map { element => { + val partition = partitioner.getPartition(element) + if (element <= 500) { + assert(partition === 0) + } else if (element > 501 && element <= 1000) { + assert(partition === 1) + } else if (element > 1001 && element <= 1500) { + assert(partition === 2) + } else if (element > 1501 && element <= 2000) { + assert(partition === 3) + } + }} + } + test("RangePartitioner getPartition") { val rdd = sc.parallelize(1.to(2000)).map(x => (x, x)) // We have different behaviour of getPartition for partitions with less than 1000 and more than From c33b8dcbf65a3a0c5ee5e65cd1dcdbc7da36aa5f Mon Sep 17 00:00:00 2001 From: larvaboy Date: Tue, 13 May 2014 21:26:08 -0700 Subject: [PATCH 28/99] Implement ApproximateCountDistinct for SparkSql Add the implementation for ApproximateCountDistinct to SparkSql. We use the HyperLogLog algorithm implemented in stream-lib, and do the count in two phases: 1) counting the number of distinct elements in each partitions, and 2) merge the HyperLogLog results from different partitions. A simple serializer and test cases are added as well. Author: larvaboy Closes #737 from larvaboy/master and squashes the following commits: bd8ef3f [larvaboy] Add support of user-provided standard deviation to ApproxCountDistinct. 9ba8360 [larvaboy] Fix alignment and null handling issues. 95b4067 [larvaboy] Add a test case for count distinct and approximate count distinct. f57917d [larvaboy] Add the parser for the approximate count. a2d5d10 [larvaboy] Add ApproximateCountDistinct aggregates and functions. 7ad273a [larvaboy] Add SparkSql serializer for HyperLogLog. 1d9aacf [larvaboy] Fix a minor typo in the toString method of the Count case class. 653542b [larvaboy] Fix a couple of minor typos. --- .../apache/spark/rdd/PairRDDFunctions.scala | 6 +- .../apache/spark/sql/catalyst/SqlParser.scala | 7 ++ .../sql/catalyst/expressions/aggregates.scala | 78 ++++++++++++++++++- .../sql/execution/SparkSqlSerializer.scala | 17 ++++ .../org/apache/spark/sql/SQLQuerySuite.scala | 21 ++++- 5 files changed, 122 insertions(+), 7 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index 5efb4388f6c71..bc6d204434ad8 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -217,7 +217,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) * Return approximate number of distinct values for each key in this RDD. * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in - * more accurate counts but increase the memory footprint and vise versa. Uses the provided + * more accurate counts but increase the memory footprint and vice versa. Uses the provided * Partitioner to partition the output RDD. */ def countApproxDistinctByKey(relativeSD: Double, partitioner: Partitioner): RDD[(K, Long)] = { @@ -232,7 +232,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) * Return approximate number of distinct values for each key in this RDD. * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in - * more accurate counts but increase the memory footprint and vise versa. HashPartitions the + * more accurate counts but increase the memory footprint and vice versa. HashPartitions the * output RDD into numPartitions. * */ @@ -244,7 +244,7 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) * Return approximate number of distinct values for each key this RDD. * The accuracy of approximation can be controlled through the relative standard deviation * (relativeSD) parameter, which also controls the amount of memory used. Lower values result in - * more accurate counts but increase the memory footprint and vise versa. The default value of + * more accurate counts but increase the memory footprint and vice versa. The default value of * relativeSD is 0.05. Hash-partitions the output RDD using the existing partitioner/parallelism * level. */ diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala index b3a3a1ef1b5eb..f2b9b2c1a3ad5 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala @@ -93,6 +93,7 @@ class SqlParser extends StandardTokenParsers with PackratParsers { protected val AND = Keyword("AND") protected val AS = Keyword("AS") protected val ASC = Keyword("ASC") + protected val APPROXIMATE = Keyword("APPROXIMATE") protected val AVG = Keyword("AVG") protected val BY = Keyword("BY") protected val CAST = Keyword("CAST") @@ -318,6 +319,12 @@ class SqlParser extends StandardTokenParsers with PackratParsers { COUNT ~> "(" ~ "*" <~ ")" ^^ { case _ => Count(Literal(1)) } | COUNT ~> "(" ~ expression <~ ")" ^^ { case dist ~ exp => Count(exp) } | COUNT ~> "(" ~> DISTINCT ~> expression <~ ")" ^^ { case exp => CountDistinct(exp :: Nil) } | + APPROXIMATE ~> COUNT ~> "(" ~> DISTINCT ~> expression <~ ")" ^^ { + case exp => ApproxCountDistinct(exp) + } | + APPROXIMATE ~> "(" ~> floatLit ~ ")" ~ COUNT ~ "(" ~ DISTINCT ~ expression <~ ")" ^^ { + case s ~ _ ~ _ ~ _ ~ _ ~ e => ApproxCountDistinct(e, s.toDouble) + } | FIRST ~> "(" ~> expression <~ ")" ^^ { case exp => First(exp) } | AVG ~> "(" ~> expression <~ ")" ^^ { case exp => Average(exp) } | MIN ~> "(" ~> expression <~ ")" ^^ { case exp => Min(exp) } | diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala index 7777d372903e2..5dbaaa3b0ce35 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala @@ -17,6 +17,8 @@ package org.apache.spark.sql.catalyst.expressions +import com.clearspring.analytics.stream.cardinality.HyperLogLog + import org.apache.spark.sql.catalyst.types._ import org.apache.spark.sql.catalyst.trees import org.apache.spark.sql.catalyst.errors.TreeNodeException @@ -146,7 +148,6 @@ case class MaxFunction(expr: Expression, base: AggregateExpression) extends Aggr override def eval(input: Row): Any = currentMax } - case class Count(child: Expression) extends PartialAggregate with trees.UnaryNode[Expression] { override def references = child.references override def nullable = false @@ -166,10 +167,47 @@ case class CountDistinct(expressions: Seq[Expression]) extends AggregateExpressi override def references = expressions.flatMap(_.references).toSet override def nullable = false override def dataType = IntegerType - override def toString = s"COUNT(DISTINCT ${expressions.mkString(",")}})" + override def toString = s"COUNT(DISTINCT ${expressions.mkString(",")})" override def newInstance() = new CountDistinctFunction(expressions, this) } +case class ApproxCountDistinctPartition(child: Expression, relativeSD: Double) + extends AggregateExpression with trees.UnaryNode[Expression] { + override def references = child.references + override def nullable = false + override def dataType = child.dataType + override def toString = s"APPROXIMATE COUNT(DISTINCT $child)" + override def newInstance() = new ApproxCountDistinctPartitionFunction(child, this, relativeSD) +} + +case class ApproxCountDistinctMerge(child: Expression, relativeSD: Double) + extends AggregateExpression with trees.UnaryNode[Expression] { + override def references = child.references + override def nullable = false + override def dataType = IntegerType + override def toString = s"APPROXIMATE COUNT(DISTINCT $child)" + override def newInstance() = new ApproxCountDistinctMergeFunction(child, this, relativeSD) +} + +case class ApproxCountDistinct(child: Expression, relativeSD: Double = 0.05) + extends PartialAggregate with trees.UnaryNode[Expression] { + override def references = child.references + override def nullable = false + override def dataType = IntegerType + override def toString = s"APPROXIMATE COUNT(DISTINCT $child)" + + override def asPartial: SplitEvaluation = { + val partialCount = + Alias(ApproxCountDistinctPartition(child, relativeSD), "PartialApproxCountDistinct")() + + SplitEvaluation( + ApproxCountDistinctMerge(partialCount.toAttribute, relativeSD), + partialCount :: Nil) + } + + override def newInstance() = new CountDistinctFunction(child :: Nil, this) +} + case class Average(child: Expression) extends PartialAggregate with trees.UnaryNode[Expression] { override def references = child.references override def nullable = false @@ -269,6 +307,42 @@ case class CountFunction(expr: Expression, base: AggregateExpression) extends Ag override def eval(input: Row): Any = count } +case class ApproxCountDistinctPartitionFunction( + expr: Expression, + base: AggregateExpression, + relativeSD: Double) + extends AggregateFunction { + def this() = this(null, null, 0) // Required for serialization. + + private val hyperLogLog = new HyperLogLog(relativeSD) + + override def update(input: Row): Unit = { + val evaluatedExpr = expr.eval(input) + if (evaluatedExpr != null) { + hyperLogLog.offer(evaluatedExpr) + } + } + + override def eval(input: Row): Any = hyperLogLog +} + +case class ApproxCountDistinctMergeFunction( + expr: Expression, + base: AggregateExpression, + relativeSD: Double) + extends AggregateFunction { + def this() = this(null, null, 0) // Required for serialization. + + private val hyperLogLog = new HyperLogLog(relativeSD) + + override def update(input: Row): Unit = { + val evaluatedExpr = expr.eval(input) + hyperLogLog.addAll(evaluatedExpr.asInstanceOf[HyperLogLog]) + } + + override def eval(input: Row): Any = hyperLogLog.cardinality() +} + case class SumFunction(expr: Expression, base: AggregateExpression) extends AggregateFunction { def this() = this(null, null) // Required for serialization. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala index 1c6e29b3cdee9..94c2a249ef8f8 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala @@ -21,6 +21,7 @@ import java.nio.ByteBuffer import scala.reflect.ClassTag +import com.clearspring.analytics.stream.cardinality.HyperLogLog import com.esotericsoftware.kryo.io.{Input, Output} import com.esotericsoftware.kryo.{Serializer, Kryo} @@ -44,6 +45,8 @@ private[sql] class SparkSqlSerializer(conf: SparkConf) extends KryoSerializer(co kryo.register(classOf[scala.collection.Map[_,_]], new MapSerializer) kryo.register(classOf[org.apache.spark.sql.catalyst.expressions.GenericRow]) kryo.register(classOf[org.apache.spark.sql.catalyst.expressions.GenericMutableRow]) + kryo.register(classOf[com.clearspring.analytics.stream.cardinality.HyperLogLog], + new HyperLogLogSerializer) kryo.register(classOf[scala.collection.mutable.ArrayBuffer[_]]) kryo.register(classOf[scala.math.BigDecimal], new BigDecimalSerializer) kryo.setReferences(false) @@ -81,6 +84,20 @@ private[sql] class BigDecimalSerializer extends Serializer[BigDecimal] { } } +private[sql] class HyperLogLogSerializer extends Serializer[HyperLogLog] { + def write(kryo: Kryo, output: Output, hyperLogLog: HyperLogLog) { + val bytes = hyperLogLog.getBytes() + output.writeInt(bytes.length) + output.writeBytes(bytes) + } + + def read(kryo: Kryo, input: Input, tpe: Class[HyperLogLog]): HyperLogLog = { + val length = input.readInt() + val bytes = input.readBytes(length) + HyperLogLog.Builder.build(bytes) + } +} + /** * Maps do not have a no arg constructor and so cannot be serialized by default. So, we serialize * them as `Array[(k,v)]`. diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index e966d89c30cf5..524549eb544fc 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -96,8 +96,25 @@ class SQLQuerySuite extends QueryTest { test("count") { checkAnswer( sql("SELECT COUNT(*) FROM testData2"), - testData2.count() - ) + testData2.count()) + } + + test("count distinct") { + checkAnswer( + sql("SELECT COUNT(DISTINCT b) FROM testData2"), + 2) + } + + test("approximate count distinct") { + checkAnswer( + sql("SELECT APPROXIMATE COUNT(DISTINCT a) FROM testData2"), + 3) + } + + test("approximate count distinct with user provided standard deviation") { + checkAnswer( + sql("SELECT APPROXIMATE(0.04) COUNT(DISTINCT a) FROM testData2"), + 3) } // No support for primitive nulls yet. From 7bb9a521f35eb19576c6cc2da3fd385910270e46 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Tue, 13 May 2014 23:24:51 -0700 Subject: [PATCH 29/99] Revert "[SPARK-1784] Add a new partitioner to allow specifying # of keys per partition" This reverts commit 92cebada09a7e5a00ab48bcb350a9462949c33eb. --- .../scala/org/apache/spark/Partitioner.scala | 61 ------------------- .../org/apache/spark/PartitioningSuite.scala | 34 ----------- 2 files changed, 95 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala index 62747960618a9..9155159cf6aeb 100644 --- a/core/src/main/scala/org/apache/spark/Partitioner.scala +++ b/core/src/main/scala/org/apache/spark/Partitioner.scala @@ -156,64 +156,3 @@ class RangePartitioner[K : Ordering : ClassTag, V]( false } } - -/** - * A [[org.apache.spark.Partitioner]] that partitions records into specified bounds - * Default value is 1000. Once all partitions have bounds elements, the partitioner - * allocates 1 element per partition so eventually the smaller partitions are at most - * off by 1 key compared to the larger partitions. - */ -class BoundaryPartitioner[K : Ordering : ClassTag, V]( - partitions: Int, - @transient rdd: RDD[_ <: Product2[K,V]], - private val boundary: Int = 1000) - extends Partitioner { - - // this array keeps track of keys assigned to a partition - // counts[0] refers to # of keys in partition 0 and so on - private val counts: Array[Int] = { - new Array[Int](numPartitions) - } - - def numPartitions = math.abs(partitions) - - /* - * Ideally, this should've been calculated based on # partitions and total keys - * But we are not calling count on RDD here to avoid calling an action. - * User has the flexibility of calling count and passing in any appropriate boundary - */ - def keysPerPartition = boundary - - var currPartition = 0 - - /* - * Pick current partition for the key until we hit the bound for keys / partition, - * start allocating to next partition at that time. - * - * NOTE: In case where we have lets say 2000 keys and user says 3 partitions with 500 - * passed in as boundary, the first 500 will goto P1, 501-1000 go to P2, 1001-1500 go to P3, - * after that, next keys go to one partition at a time. So 1501 goes to P1, 1502 goes to P2, - * 1503 goes to P3 and so on. - */ - def getPartition(key: Any): Int = { - val partition = currPartition - counts(partition) = counts(partition) + 1 - /* - * Since we are filling up a partition before moving to next one (this helps in maintaining - * order of keys, in certain cases, it is possible to end up with empty partitions, like - * 3 partitions, 500 keys / partition and if rdd has 700 keys, 1 partition will be entirely - * empty. - */ - if(counts(currPartition) >= keysPerPartition) - currPartition = (currPartition + 1) % numPartitions - partition - } - - override def equals(other: Any): Boolean = other match { - case r: BoundaryPartitioner[_,_] => - (r.counts.sameElements(counts) && r.boundary == boundary - && r.currPartition == currPartition) - case _ => - false - } -} diff --git a/core/src/test/scala/org/apache/spark/PartitioningSuite.scala b/core/src/test/scala/org/apache/spark/PartitioningSuite.scala index 7d40395803f02..7c30626a0c421 100644 --- a/core/src/test/scala/org/apache/spark/PartitioningSuite.scala +++ b/core/src/test/scala/org/apache/spark/PartitioningSuite.scala @@ -66,40 +66,6 @@ class PartitioningSuite extends FunSuite with SharedSparkContext with PrivateMet assert(descendingP4 != p4) } - test("BoundaryPartitioner equality") { - // Make an RDD where all the elements are the same so that the partition range bounds - // are deterministically all the same. - val rdd = sc.parallelize(1.to(4000)).map(x => (x, x)) - - val p2 = new BoundaryPartitioner(2, rdd, 1000) - val p4 = new BoundaryPartitioner(4, rdd, 1000) - val anotherP4 = new BoundaryPartitioner(4, rdd) - - assert(p2 === p2) - assert(p4 === p4) - assert(p2 != p4) - assert(p4 != p2) - assert(p4 === anotherP4) - assert(anotherP4 === p4) - } - - test("BoundaryPartitioner getPartition") { - val rdd = sc.parallelize(1.to(2000)).map(x => (x, x)) - val partitioner = new BoundaryPartitioner(4, rdd, 500) - 1.to(2000).map { element => { - val partition = partitioner.getPartition(element) - if (element <= 500) { - assert(partition === 0) - } else if (element > 501 && element <= 1000) { - assert(partition === 1) - } else if (element > 1001 && element <= 1500) { - assert(partition === 2) - } else if (element > 1501 && element <= 2000) { - assert(partition === 3) - } - }} - } - test("RangePartitioner getPartition") { val rdd = sc.parallelize(1.to(2000)).map(x => (x, x)) // We have different behaviour of getPartition for partitions with less than 1000 and more than From 6ce0884446d3571fd6e9d967a080a59c657543b1 Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Tue, 13 May 2014 23:27:22 -0700 Subject: [PATCH 30/99] [SQL] Improve column pruning. Fixed a bug that was preventing us from ever pruning beneath Joins. ## TPC-DS Q3 ### Before: ``` Aggregate false, [d_year#12,i_brand#65,i_brand_id#64], [d_year#12,i_brand_id#64 AS brand_id#0,i_brand#65 AS brand#1,SUM(PartialSum#79) AS sum_agg#2] Exchange (HashPartitioning [d_year#12:0,i_brand#65:1,i_brand_id#64:2], 150) Aggregate true, [d_year#12,i_brand#65,i_brand_id#64], [d_year#12,i_brand#65,i_brand_id#64,SUM(CAST(ss_ext_sales_price#49, DoubleType)) AS PartialSum#79] Project [d_year#12:6,i_brand#65:59,i_brand_id#64:58,ss_ext_sales_price#49:43] HashJoin [ss_item_sk#36], [i_item_sk#57], BuildRight Exchange (HashPartitioning [ss_item_sk#36:30], 150) HashJoin [d_date_sk#6], [ss_sold_date_sk#34], BuildRight Exchange (HashPartitioning [d_date_sk#6:0], 150) Filter (d_moy#14:8 = 12) HiveTableScan [d_date_sk#6,d_date_id#7,d_date#8,d_month_seq#9,d_week_seq#10,d_quarter_seq#11,d_year#12,d_dow#13,d_moy#14,d_dom#15,d_qoy#16,d_fy_year#17,d_fy_quarter_seq#18,d_fy_week_seq#19,d_day_name#20,d_quarter_name#21,d_holiday#22,d_weekend#23,d_following_holiday#24,d_first_dom#25,d_last_dom#26,d_same_day_ly#27,d_same_day_lq#28,d_current_day#29,d_current_week#30,d_current_month#31,d_current_quarter#32,d_current_year#33], (MetastoreRelation default, date_dim, Some(dt)), None Exchange (HashPartitioning [ss_sold_date_sk#34:0], 150) HiveTableScan [ss_sold_date_sk#34,ss_sold_time_sk#35,ss_item_sk#36,ss_customer_sk#37,ss_cdemo_sk#38,ss_hdemo_sk#39,ss_addr_sk#40,ss_store_sk#41,ss_promo_sk#42,ss_ticket_number#43,ss_quantity#44,ss_wholesale_cost#45,ss_list_price#46,ss_sales_price#47,ss_ext_discount_amt#48,ss_ext_sales_price#49,ss_ext_wholesale_cost#50,ss_ext_list_price#51,ss_ext_tax#52,ss_coupon_amt#53,ss_net_paid#54,ss_net_paid_inc_tax#55,ss_net_profit#56], (MetastoreRelation default, store_sales, None), None Exchange (HashPartitioning [i_item_sk#57:0], 150) Filter (i_manufact_id#70:13 = 436) HiveTableScan [i_item_sk#57,i_item_id#58,i_rec_start_date#59,i_rec_end_date#60,i_item_desc#61,i_current_price#62,i_wholesale_cost#63,i_brand_id#64,i_brand#65,i_class_id#66,i_class#67,i_category_id#68,i_category#69,i_manufact_id#70,i_manufact#71,i_size#72,i_formulation#73,i_color#74,i_units#75,i_container#76,i_manager_id#77,i_product_name#78], (MetastoreRelation default, item, None), None ``` ### After ``` Aggregate false, [d_year#172,i_brand#225,i_brand_id#224], [d_year#172,i_brand_id#224 AS brand_id#160,i_brand#225 AS brand#161,SUM(PartialSum#239) AS sum_agg#162] Exchange (HashPartitioning [d_year#172:0,i_brand#225:1,i_brand_id#224:2], 150) Aggregate true, [d_year#172,i_brand#225,i_brand_id#224], [d_year#172,i_brand#225,i_brand_id#224,SUM(CAST(ss_ext_sales_price#209, DoubleType)) AS PartialSum#239] Project [d_year#172:1,i_brand#225:5,i_brand_id#224:3,ss_ext_sales_price#209:0] HashJoin [ss_item_sk#196], [i_item_sk#217], BuildRight Exchange (HashPartitioning [ss_item_sk#196:2], 150) Project [ss_ext_sales_price#209:2,d_year#172:1,ss_item_sk#196:3] HashJoin [d_date_sk#166], [ss_sold_date_sk#194], BuildRight Exchange (HashPartitioning [d_date_sk#166:0], 150) Project [d_date_sk#166:0,d_year#172:1] Filter (d_moy#174:2 = 12) HiveTableScan [d_date_sk#166,d_year#172,d_moy#174], (MetastoreRelation default, date_dim, Some(dt)), None Exchange (HashPartitioning [ss_sold_date_sk#194:2], 150) HiveTableScan [ss_ext_sales_price#209,ss_item_sk#196,ss_sold_date_sk#194], (MetastoreRelation default, store_sales, None), None Exchange (HashPartitioning [i_item_sk#217:1], 150) Project [i_brand_id#224:0,i_item_sk#217:1,i_brand#225:2] Filter (i_manufact_id#230:3 = 436) HiveTableScan [i_brand_id#224,i_item_sk#217,i_brand#225,i_manufact_id#230], (MetastoreRelation default, item, None), None ``` Author: Michael Armbrust Closes #729 from marmbrus/fixPruning and squashes the following commits: 5feeff0 [Michael Armbrust] Improve column pruning. --- .../spark/sql/catalyst/optimizer/Optimizer.scala | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala index 3037d45cc6e35..406ffd6801e98 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala @@ -25,13 +25,13 @@ import org.apache.spark.sql.catalyst.types._ object Optimizer extends RuleExecutor[LogicalPlan] { val batches = - Batch("ConstantFolding", Once, + Batch("ConstantFolding", FixedPoint(100), NullPropagation, ConstantFolding, BooleanSimplification, SimplifyFilters, SimplifyCasts) :: - Batch("Filter Pushdown", Once, + Batch("Filter Pushdown", FixedPoint(100), CombineFilters, PushPredicateThroughProject, PushPredicateThroughInnerJoin, @@ -49,17 +49,19 @@ object Optimizer extends RuleExecutor[LogicalPlan] { */ object ColumnPruning extends Rule[LogicalPlan] { def apply(plan: LogicalPlan): LogicalPlan = plan transform { + // Eliminate attributes that are not needed to calculate the specified aggregates. case a @ Aggregate(_, _, child) if (child.outputSet -- a.references).nonEmpty => - // Project away references that are not needed to calculate the required aggregates. a.copy(child = Project(a.references.toSeq, child)) + // Eliminate unneeded attributes from either side of a Join. case Project(projectList, Join(left, right, joinType, condition)) => // Collect the list of off references required either above or to evaluate the condition. val allReferences: Set[Attribute] = projectList.flatMap(_.references).toSet ++ condition.map(_.references).getOrElse(Set.empty) - /** Applies a projection when the child is producing unnecessary attributes */ + + /** Applies a projection only when the child is producing unnecessary attributes */ def prunedChild(c: LogicalPlan) = - if ((allReferences.filter(c.outputSet.contains) -- c.outputSet).nonEmpty) { + if ((c.outputSet -- allReferences.filter(c.outputSet.contains)).nonEmpty) { Project(allReferences.filter(c.outputSet.contains).toSeq, c) } else { c @@ -67,6 +69,7 @@ object ColumnPruning extends Rule[LogicalPlan] { Project(projectList, Join(prunedChild(left), prunedChild(right), joinType, condition)) + // Combine adjacent Projects. case Project(projectList1, Project(projectList2, child)) => // Create a map of Aliases to their values from the child projection. // e.g., 'SELECT ... FROM (SELECT a + b AS c, d ...)' produces Map(c -> Alias(a + b, c)). @@ -83,6 +86,9 @@ object ColumnPruning extends Rule[LogicalPlan] { }).asInstanceOf[Seq[NamedExpression]] Project(substitutedProjection, child) + + // Eliminate no-op Projects + case Project(projectList, child) if(child.output == projectList) => child } } From b22952fa1f21c0b93208846b5e1941a9d2578c6f Mon Sep 17 00:00:00 2001 From: Koert Kuipers Date: Wed, 14 May 2014 00:10:12 -0700 Subject: [PATCH 31/99] SPARK-1801. expose InterruptibleIterator and TaskKilledException in deve... ...loper api Author: Koert Kuipers Closes #764 from koertkuipers/feat-rdd-developerapi and squashes the following commits: 8516dd2 [Koert Kuipers] SPARK-1801. expose InterruptibleIterator and TaskKilledException in developer api --- .../scala/org/apache/spark/InterruptibleIterator.scala | 6 +++++- .../main/scala/org/apache/spark/TaskKilledException.scala | 8 ++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/InterruptibleIterator.scala b/core/src/main/scala/org/apache/spark/InterruptibleIterator.scala index ec11dbbffaaf8..f40baa8e43592 100644 --- a/core/src/main/scala/org/apache/spark/InterruptibleIterator.scala +++ b/core/src/main/scala/org/apache/spark/InterruptibleIterator.scala @@ -17,11 +17,15 @@ package org.apache.spark +import org.apache.spark.annotation.DeveloperApi + /** + * :: DeveloperApi :: * An iterator that wraps around an existing iterator to provide task killing functionality. * It works by checking the interrupted flag in [[TaskContext]]. */ -private[spark] class InterruptibleIterator[+T](val context: TaskContext, val delegate: Iterator[T]) +@DeveloperApi +class InterruptibleIterator[+T](val context: TaskContext, val delegate: Iterator[T]) extends Iterator[T] { def hasNext: Boolean = { diff --git a/core/src/main/scala/org/apache/spark/TaskKilledException.scala b/core/src/main/scala/org/apache/spark/TaskKilledException.scala index cbd6b2866e4f9..ad487c4efb87a 100644 --- a/core/src/main/scala/org/apache/spark/TaskKilledException.scala +++ b/core/src/main/scala/org/apache/spark/TaskKilledException.scala @@ -17,7 +17,11 @@ package org.apache.spark +import org.apache.spark.annotation.DeveloperApi + /** - * Exception for a task getting killed. + * :: DeveloperApi :: + * Exception thrown when a task is explicitly killed (i.e., task failure is expected). */ -private[spark] class TaskKilledException extends RuntimeException +@DeveloperApi +class TaskKilledException extends RuntimeException From 54ae8328bd7d052ba347768cfb02cb5dfdd8045e Mon Sep 17 00:00:00 2001 From: Marcelo Vanzin Date: Wed, 14 May 2014 00:37:57 -0700 Subject: [PATCH 32/99] Fix dep exclusion: avro-ipc, not avro, depends on netty. Author: Marcelo Vanzin Closes #763 from vanzin/netty-dep-hell and squashes the following commits: dfb6ce2 [Marcelo Vanzin] Fix dep exclusion: avro-ipc, not avro, depends on netty. --- pom.xml | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/pom.xml b/pom.xml index 4d4c5f63e44a3..786b6d4984d86 100644 --- a/pom.xml +++ b/pom.xml @@ -496,18 +496,16 @@ org.apache.avro avro ${avro.version} - - - io.netty - netty - - org.apache.avro avro-ipc ${avro.version} + + io.netty + netty + org.mortbay.jetty jetty From 69f750228f3ec8537a93da08e712596fa8004143 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Wed, 14 May 2014 00:54:33 -0700 Subject: [PATCH 33/99] [SPARK-1769] Executor loss causes NPE race condition This PR replaces the Schedulable data structures in Pool.scala with thread-safe ones from java. Note that Scala's `with SynchronizedBuffer` trait is soon to be deprecated in 2.11 because it is ["inherently unreliable"](http://www.scala-lang.org/api/2.11.0/index.html#scala.collection.mutable.SynchronizedBuffer). We should slowly drift away from `SynchronizedBuffer` in other places too. Note that this PR introduces an API-breaking change; `sc.getAllPools` now returns an Array rather than an ArrayBuffer. This is because we want this method to return an immutable copy rather than one may potentially confuse the user if they try to modify the copy, which takes no effect on the original data structure. Author: Andrew Or Closes #762 from andrewor14/pool-npe and squashes the following commits: 383e739 [Andrew Or] JavaConverters -> JavaConversions 3f32981 [Andrew Or] Merge branch 'master' of github.com:apache/spark into pool-npe 769be19 [Andrew Or] Assorted minor changes 2189247 [Andrew Or] Merge branch 'master' of github.com:apache/spark into pool-npe 05ad9e9 [Andrew Or] Fix test - contains is not the same as containsKey 0921ea0 [Andrew Or] var -> val 07d720c [Andrew Or] Synchronize Schedulable data structures --- .../scala/org/apache/spark/SparkContext.scala | 20 +++++++----- .../org/apache/spark/scheduler/Pool.scala | 31 ++++++++++--------- .../apache/spark/scheduler/Schedulable.scala | 6 ++-- .../spark/scheduler/TaskSchedulerImpl.scala | 2 +- .../scheduler/TaskSchedulerImplSuite.scala | 2 +- 5 files changed, 35 insertions(+), 26 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index c43b4fd6d926f..032b3d744c619 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -17,15 +17,17 @@ package org.apache.spark +import scala.language.implicitConversions + import java.io._ import java.net.URI import java.util.concurrent.atomic.AtomicInteger import java.util.{Properties, UUID} import java.util.UUID.randomUUID import scala.collection.{Map, Set} +import scala.collection.JavaConversions._ import scala.collection.generic.Growable -import scala.collection.mutable.{ArrayBuffer, HashMap} -import scala.language.implicitConversions +import scala.collection.mutable.HashMap import scala.reflect.{ClassTag, classTag} import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.Path @@ -836,18 +838,22 @@ class SparkContext(config: SparkConf) extends Logging { } /** - * Return pools for fair scheduler - * TODO(xiajunluan): We should take nested pools into account + * :: DeveloperApi :: + * Return pools for fair scheduler */ - def getAllPools: ArrayBuffer[Schedulable] = { - taskScheduler.rootPool.schedulableQueue + @DeveloperApi + def getAllPools: Seq[Schedulable] = { + // TODO(xiajunluan): We should take nested pools into account + taskScheduler.rootPool.schedulableQueue.toSeq } /** + * :: DeveloperApi :: * Return the pool associated with the given name, if one exists */ + @DeveloperApi def getPoolForName(pool: String): Option[Schedulable] = { - taskScheduler.rootPool.schedulableNameToSchedulable.get(pool) + Option(taskScheduler.rootPool.schedulableNameToSchedulable.get(pool)) } /** diff --git a/core/src/main/scala/org/apache/spark/scheduler/Pool.scala b/core/src/main/scala/org/apache/spark/scheduler/Pool.scala index 187672c4e19e7..174b73221afc0 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/Pool.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/Pool.scala @@ -17,8 +17,10 @@ package org.apache.spark.scheduler +import java.util.concurrent.{ConcurrentHashMap, ConcurrentLinkedQueue} + +import scala.collection.JavaConversions._ import scala.collection.mutable.ArrayBuffer -import scala.collection.mutable.HashMap import org.apache.spark.Logging import org.apache.spark.scheduler.SchedulingMode.SchedulingMode @@ -35,18 +37,15 @@ private[spark] class Pool( extends Schedulable with Logging { - var schedulableQueue = new ArrayBuffer[Schedulable] - var schedulableNameToSchedulable = new HashMap[String, Schedulable] - + val schedulableQueue = new ConcurrentLinkedQueue[Schedulable] + val schedulableNameToSchedulable = new ConcurrentHashMap[String, Schedulable] var weight = initWeight var minShare = initMinShare var runningTasks = 0 - var priority = 0 // A pool's stage id is used to break the tie in scheduling. var stageId = -1 - var name = poolName var parent: Pool = null @@ -60,19 +59,20 @@ private[spark] class Pool( } override def addSchedulable(schedulable: Schedulable) { - schedulableQueue += schedulable - schedulableNameToSchedulable(schedulable.name) = schedulable + require(schedulable != null) + schedulableQueue.add(schedulable) + schedulableNameToSchedulable.put(schedulable.name, schedulable) schedulable.parent = this } override def removeSchedulable(schedulable: Schedulable) { - schedulableQueue -= schedulable - schedulableNameToSchedulable -= schedulable.name + schedulableQueue.remove(schedulable) + schedulableNameToSchedulable.remove(schedulable.name) } override def getSchedulableByName(schedulableName: String): Schedulable = { - if (schedulableNameToSchedulable.contains(schedulableName)) { - return schedulableNameToSchedulable(schedulableName) + if (schedulableNameToSchedulable.containsKey(schedulableName)) { + return schedulableNameToSchedulable.get(schedulableName) } for (schedulable <- schedulableQueue) { val sched = schedulable.getSchedulableByName(schedulableName) @@ -95,11 +95,12 @@ private[spark] class Pool( shouldRevive } - override def getSortedTaskSetQueue(): ArrayBuffer[TaskSetManager] = { + override def getSortedTaskSetQueue: ArrayBuffer[TaskSetManager] = { var sortedTaskSetQueue = new ArrayBuffer[TaskSetManager] - val sortedSchedulableQueue = schedulableQueue.sortWith(taskSetSchedulingAlgorithm.comparator) + val sortedSchedulableQueue = + schedulableQueue.toSeq.sortWith(taskSetSchedulingAlgorithm.comparator) for (schedulable <- sortedSchedulableQueue) { - sortedTaskSetQueue ++= schedulable.getSortedTaskSetQueue() + sortedTaskSetQueue ++= schedulable.getSortedTaskSetQueue } sortedTaskSetQueue } diff --git a/core/src/main/scala/org/apache/spark/scheduler/Schedulable.scala b/core/src/main/scala/org/apache/spark/scheduler/Schedulable.scala index ed24eb6a549dd..a87ef030e69c2 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/Schedulable.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/Schedulable.scala @@ -17,6 +17,8 @@ package org.apache.spark.scheduler +import java.util.concurrent.ConcurrentLinkedQueue + import scala.collection.mutable.ArrayBuffer import org.apache.spark.scheduler.SchedulingMode.SchedulingMode @@ -28,7 +30,7 @@ import org.apache.spark.scheduler.SchedulingMode.SchedulingMode private[spark] trait Schedulable { var parent: Pool // child queues - def schedulableQueue: ArrayBuffer[Schedulable] + def schedulableQueue: ConcurrentLinkedQueue[Schedulable] def schedulingMode: SchedulingMode def weight: Int def minShare: Int @@ -42,5 +44,5 @@ private[spark] trait Schedulable { def getSchedulableByName(name: String): Schedulable def executorLost(executorId: String, host: String): Unit def checkSpeculatableTasks(): Boolean - def getSortedTaskSetQueue(): ArrayBuffer[TaskSetManager] + def getSortedTaskSetQueue: ArrayBuffer[TaskSetManager] } diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala index 5a68f38bc5844..ffd1d9432682b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala @@ -222,7 +222,7 @@ private[spark] class TaskSchedulerImpl( // Build a list of tasks to assign to each worker. val tasks = shuffledOffers.map(o => new ArrayBuffer[TaskDescription](o.cores)) val availableCpus = shuffledOffers.map(o => o.cores).toArray - val sortedTaskSets = rootPool.getSortedTaskSetQueue() + val sortedTaskSets = rootPool.getSortedTaskSetQueue for (taskSet <- sortedTaskSets) { logDebug("parentName: %s, name: %s, runningTasks: %s".format( taskSet.parent.name, taskSet.name, taskSet.runningTasks)) diff --git a/core/src/test/scala/org/apache/spark/scheduler/TaskSchedulerImplSuite.scala b/core/src/test/scala/org/apache/spark/scheduler/TaskSchedulerImplSuite.scala index a8b605c5b212a..7532da88c6065 100644 --- a/core/src/test/scala/org/apache/spark/scheduler/TaskSchedulerImplSuite.scala +++ b/core/src/test/scala/org/apache/spark/scheduler/TaskSchedulerImplSuite.scala @@ -117,7 +117,7 @@ class TaskSchedulerImplSuite extends FunSuite with LocalSparkContext with Loggin } def resourceOffer(rootPool: Pool): Int = { - val taskSetQueue = rootPool.getSortedTaskSetQueue() + val taskSetQueue = rootPool.getSortedTaskSetQueue /* Just for Test*/ for (manager <- taskSetQueue) { logInfo("parentName:%s, parent running tasks:%d, name:%s,runningTasks:%d".format( From 68f28dabe9c7679be82e684385be216319beb610 Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Wed, 14 May 2014 04:17:32 -0700 Subject: [PATCH 34/99] Fixed streaming examples docs to use run-example instead of spark-submit Pretty self-explanatory Author: Tathagata Das Closes #722 from tdas/example-fix and squashes the following commits: 7839979 [Tathagata Das] Minor changes. 0673441 [Tathagata Das] Fixed java docs of java streaming example e687123 [Tathagata Das] Fixed scala style errors. 9b8d112 [Tathagata Das] Fixed streaming examples docs to use run-example instead of spark-submit. --- .../streaming/JavaCustomReceiver.java | 13 ++--- .../streaming/JavaFlumeEventCount.java | 6 +- .../streaming/JavaKafkaWordCount.java | 6 +- .../streaming/JavaNetworkWordCount.java | 13 +++-- .../examples/streaming/ActorWordCount.scala | 6 +- .../examples/streaming/CustomReceiver.scala | 19 +++--- .../examples/streaming/FlumeEventCount.scala | 9 ++- .../examples/streaming/HdfsWordCount.scala | 5 +- .../examples/streaming/KafkaWordCount.scala | 6 +- .../examples/streaming/MQTTWordCount.scala | 10 ++-- .../examples/streaming/NetworkWordCount.scala | 14 +++-- .../RecoverableNetworkWordCount.scala | 7 +-- .../streaming/StatefulNetworkWordCount.scala | 6 +- .../streaming/TwitterPopularTags.scala | 22 ++++++- .../examples/streaming/ZeroMQWordCount.scala | 8 +-- .../clickstream/PageViewGenerator.scala | 10 ++-- .../clickstream/PageViewStream.scala | 7 ++- .../twitter/TwitterInputDStream.scala | 58 +++++++++++-------- 18 files changed, 130 insertions(+), 95 deletions(-) diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java index 7f558f3ee713a..5622df5ce03ff 100644 --- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java @@ -19,6 +19,7 @@ import com.google.common.collect.Lists; +import org.apache.spark.SparkConf; import org.apache.spark.api.java.function.FlatMapFunction; import org.apache.spark.api.java.function.Function2; import org.apache.spark.api.java.function.PairFunction; @@ -48,25 +49,23 @@ * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./run org.apache.spark.examples.streaming.JavaCustomReceiver local[2] localhost 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.JavaCustomReceiver localhost 9999` */ public class JavaCustomReceiver extends Receiver { private static final Pattern SPACE = Pattern.compile(" "); public static void main(String[] args) { - if (args.length < 3) { - System.err.println("Usage: JavaNetworkWordCount \n" + - "In local mode, should be 'local[n]' with n > 1"); + if (args.length < 2) { + System.err.println("Usage: JavaNetworkWordCount "); System.exit(1); } StreamingExamples.setStreamingLogLevels(); // Create the context with a 1 second batch size - JavaStreamingContext ssc = new JavaStreamingContext(args[0], "JavaNetworkWordCount", - new Duration(1000), System.getenv("SPARK_HOME"), - JavaStreamingContext.jarOfClass(JavaNetworkWordCount.class)); + SparkConf sparkConf = new SparkConf().setAppName("JavaCustomReceiver"); + JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(1000)); // Create a input stream with the custom receiver on target ip:port and count the // words in input stream of \n delimited text (eg. generated by 'nc') diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaFlumeEventCount.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaFlumeEventCount.java index 400b68c2215b3..da56637fe891a 100644 --- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaFlumeEventCount.java +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaFlumeEventCount.java @@ -33,10 +33,12 @@ * Your Flume AvroSink should be pointed to this address. * * Usage: JavaFlumeEventCount - * * is the host the Flume receiver will be started on - a receiver * creates a server and listens for flume events. * is the port the Flume receiver will listen on. + * + * To run this example: + * `$ bin/run-example org.apache.spark.examples.streaming.JavaFlumeEventCount ` */ public final class JavaFlumeEventCount { private JavaFlumeEventCount() { @@ -56,7 +58,7 @@ public static void main(String[] args) { Duration batchInterval = new Duration(2000); SparkConf sparkConf = new SparkConf().setAppName("JavaFlumeEventCount"); JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, batchInterval); - JavaReceiverInputDStream flumeStream = FlumeUtils.createStream(ssc, "localhost", port); + JavaReceiverInputDStream flumeStream = FlumeUtils.createStream(ssc, host, port); flumeStream.count(); diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaKafkaWordCount.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaKafkaWordCount.java index 6a74cc50d19ed..16ae9a3319ee2 100644 --- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaKafkaWordCount.java +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaKafkaWordCount.java @@ -40,15 +40,15 @@ /** * Consumes messages from one or more topics in Kafka and does wordcount. + * * Usage: JavaKafkaWordCount * is a list of one or more zookeeper servers that make quorum * is the name of kafka consumer group * is a list of one or more kafka topics to consume from * is the number of threads the kafka consumer should use * - * Example: - * `./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02, \ + * To run this example: + * `$ bin/run-example org.apache.spark.examples.streaming.JavaKafkaWordCount zoo01,zoo02, \ * zoo03 my-consumer-group topic1,topic2 1` */ diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java index e5cbd39f437c2..45bcedebb4117 100644 --- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java @@ -24,7 +24,7 @@ import org.apache.spark.api.java.function.FlatMapFunction; import org.apache.spark.api.java.function.Function2; import org.apache.spark.api.java.function.PairFunction; -import org.apache.spark.examples.streaming.StreamingExamples; +import org.apache.spark.api.java.StorageLevels; import org.apache.spark.streaming.Duration; import org.apache.spark.streaming.api.java.JavaDStream; import org.apache.spark.streaming.api.java.JavaPairDStream; @@ -41,8 +41,7 @@ * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.JavaNetworkWordCount localhost 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.JavaNetworkWordCount localhost 9999` */ public final class JavaNetworkWordCount { private static final Pattern SPACE = Pattern.compile(" "); @@ -54,13 +53,17 @@ public static void main(String[] args) { } StreamingExamples.setStreamingLogLevels(); - SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount"); + // Create the context with a 1 second batch size + SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount"); JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(1000)); // Create a JavaReceiverInputDStream on target ip:port and count the // words in input stream of \n delimited text (eg. generated by 'nc') - JavaReceiverInputDStream lines = ssc.socketTextStream(args[0], Integer.parseInt(args[1])); + // Note that no duplication in storage level only for running locally. + // Replication necessary in distributed scenario for fault tolerance. + JavaReceiverInputDStream lines = ssc.socketTextStream( + args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER); JavaDStream words = lines.flatMap(new FlatMapFunction() { @Override public Iterable call(String x) { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala index e29e16a9c1b17..b433082dce1a2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala @@ -130,11 +130,9 @@ object FeederActor { * and describe the AkkaSystem that Spark Sample feeder is running on. * * To run this example locally, you may run Feeder Actor as - * `./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.FeederActor 127.0.1.1 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.FeederActor 127.0.1.1 9999` * and then run the example - * `./bin/spark-submit examples.jar --class org.apache.spark.examples.streaming.ActorWordCount \ - * 127.0.1.1 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.ActorWordCount 127.0.1.1 9999` */ object ActorWordCount { def main(args: Array[String]) { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala index e317e2d36ae43..6bb659fbd8be8 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala @@ -20,7 +20,7 @@ package org.apache.spark.examples.streaming import java.io.{InputStreamReader, BufferedReader, InputStream} import java.net.Socket -import org.apache.spark.Logging +import org.apache.spark.{SparkConf, Logging} import org.apache.spark.storage.StorageLevel import org.apache.spark.streaming.{Seconds, StreamingContext} import org.apache.spark.streaming.StreamingContext._ @@ -30,32 +30,27 @@ import org.apache.spark.streaming.receiver.Receiver * Custom Receiver that receives data over a socket. Received bytes is interpreted as * text and \n delimited lines are considered as records. They are then counted and printed. * - * Usage: CustomReceiver - * is the Spark master URL. In local mode, should be 'local[n]' with n > 1. - * and of the TCP server that Spark Streaming would connect to receive data. - * * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./run org.apache.spark.examples.streaming.CustomReceiver local[2] localhost 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.CustomReceiver localhost 9999` */ object CustomReceiver { def main(args: Array[String]) { - if (args.length < 3) { - System.err.println("Usage: NetworkWordCount \n" + - "In local mode, should be 'local[n]' with n > 1") + if (args.length < 2) { + System.err.println("Usage: CustomReceiver ") System.exit(1) } StreamingExamples.setStreamingLogLevels() // Create the context with a 1 second batch size - val ssc = new StreamingContext(args(0), "NetworkWordCount", Seconds(1), - System.getenv("SPARK_HOME"), StreamingContext.jarOfClass(this.getClass).toSeq) + val sparkConf = new SparkConf().setAppName("CustomReceiver") + val ssc = new StreamingContext(sparkConf, Seconds(1)) // Create a input stream with the custom receiver on target ip:port and count the // words in input stream of \n delimited text (eg. generated by 'nc') - val lines = ssc.receiverStream(new CustomReceiver(args(1), args(2).toInt)) + val lines = ssc.receiverStream(new CustomReceiver(args(0), args(1).toInt)) val words = lines.flatMap(_.split(" ")) val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _) wordCounts.print() diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala index 38362edac27f8..20e7df7c45b1b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala @@ -31,14 +31,16 @@ import org.apache.spark.util.IntParam * Your Flume AvroSink should be pointed to this address. * * Usage: FlumeEventCount - * * is the host the Flume receiver will be started on - a receiver * creates a server and listens for flume events. * is the port the Flume receiver will listen on. + * + * To run this example: + * `$ bin/run-example org.apache.spark.examples.streaming.FlumeEventCount ` */ object FlumeEventCount { def main(args: Array[String]) { - if (args.length != 3) { + if (args.length < 2) { System.err.println( "Usage: FlumeEventCount ") System.exit(1) @@ -49,8 +51,9 @@ object FlumeEventCount { val Array(host, IntParam(port)) = args val batchInterval = Milliseconds(2000) - val sparkConf = new SparkConf().setAppName("FlumeEventCount") + // Create the context and set the batch size + val sparkConf = new SparkConf().setAppName("FlumeEventCount") val ssc = new StreamingContext(sparkConf, batchInterval) // Create a flume stream diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala index 55ac48cfb6d10..6c24bc3ad09e0 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala @@ -27,8 +27,9 @@ import org.apache.spark.streaming.StreamingContext._ * is the directory that Spark Streaming will use to find and read new text files. * * To run this on your local machine on directory `localdir`, run this example - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.HdfsWordCount localdir` + * $ bin/run-example \ + * org.apache.spark.examples.streaming.HdfsWordCount localdir + * * Then create a text file in `localdir` and the words in the file will get counted. */ object HdfsWordCount { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/KafkaWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/KafkaWordCount.scala index 3af806981f37a..566ba6f911e02 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/KafkaWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/KafkaWordCount.scala @@ -35,9 +35,9 @@ import org.apache.spark.SparkConf * is the number of threads the kafka consumer should use * * Example: - * `./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.KafkaWordCount local[2] zoo01,zoo02,zoo03 \ - * my-consumer-group topic1,topic2 1` + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.KafkaWordCount zoo01,zoo02,zoo03 \ + * my-consumer-group topic1,topic2 1` */ object KafkaWordCount { def main(args: Array[String]) { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/MQTTWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/MQTTWordCount.scala index 3a10daa9ab84a..e4283e04a1b11 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/MQTTWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/MQTTWordCount.scala @@ -75,14 +75,14 @@ object MQTTPublisher { * Example Java code for Mqtt Publisher and Subscriber can be found here * https://bitbucket.org/mkjinesh/mqttclient * Usage: MQTTWordCount -\ * and describe where Mqtt publisher is running. + * and describe where Mqtt publisher is running. * * To run this example locally, you may run publisher as - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.MQTTPublisher tcp://localhost:1883 foo` + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.MQTTPublisher tcp://localhost:1883 foo` * and run the example as - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.MQTTWordCount tcp://localhost:1883 foo` + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.MQTTWordCount tcp://localhost:1883 foo` */ object MQTTWordCount { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala index ad7a199b2c0ab..ae0a08c6cdb1a 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala @@ -23,7 +23,7 @@ import org.apache.spark.streaming.StreamingContext._ import org.apache.spark.storage.StorageLevel /** - * Counts words in text encoded with UTF8 received from the network every second. + * Counts words in UTF8 encoded, '\n' delimited text received from the network every second. * * Usage: NetworkWordCount * and describe the TCP server that Spark Streaming would connect to receive data. @@ -31,8 +31,7 @@ import org.apache.spark.storage.StorageLevel * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.NetworkWordCount localhost 9999` + * `$ bin/run-example org.apache.spark.examples.streaming.NetworkWordCount localhost 9999` */ object NetworkWordCount { def main(args: Array[String]) { @@ -42,13 +41,16 @@ object NetworkWordCount { } StreamingExamples.setStreamingLogLevels() - val sparkConf = new SparkConf().setAppName("NetworkWordCount"); + // Create the context with a 1 second batch size + val sparkConf = new SparkConf().setAppName("NetworkWordCount") val ssc = new StreamingContext(sparkConf, Seconds(1)) - // Create a NetworkInputDStream on target ip:port and count the + // Create a socket stream on target ip:port and count the // words in input stream of \n delimited text (eg. generated by 'nc') - val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_ONLY_SER) + // Note that no duplication in storage level only for running locally. + // Replication necessary in distributed scenario for fault tolerance. + val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER) val words = lines.flatMap(_.split(" ")) val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _) wordCounts.print() diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala index ace785d9fe4c5..6af3a0f33efc2 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala @@ -46,8 +46,7 @@ import org.apache.spark.util.IntParam * * and run the example as * - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.RecoverableNetworkWordCount \ + * `$ ./bin/run-example org.apache.spark.examples.streaming.RecoverableNetworkWordCount \ * localhost 9999 ~/checkpoint/ ~/out` * * If the directory ~/checkpoint/ does not exist (e.g. running for the first time), it will create @@ -57,7 +56,7 @@ import org.apache.spark.util.IntParam * * To run this example in a local standalone cluster with automatic driver recovery, * - * `$ ./spark-class org.apache.spark.deploy.Client -s launch \ + * `$ bin/spark-class org.apache.spark.deploy.Client -s launch \ * \ * org.apache.spark.examples.streaming.RecoverableNetworkWordCount \ * localhost 9999 ~/checkpoint ~/out` @@ -81,7 +80,7 @@ object RecoverableNetworkWordCount { // Create the context with a 1 second batch size val ssc = new StreamingContext(sparkConf, Seconds(1)) - // Create a NetworkInputDStream on target ip:port and count the + // Create a socket stream on target ip:port and count the // words in input stream of \n delimited text (eg. generated by 'nc') val lines = ssc.socketTextStream(ip, port) val words = lines.flatMap(_.split(" ")) diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/StatefulNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/StatefulNetworkWordCount.scala index 5e1415f3cc536..daa1ced63c701 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/StatefulNetworkWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/StatefulNetworkWordCount.scala @@ -31,8 +31,8 @@ import org.apache.spark.streaming.StreamingContext._ * To run this on your local machine, you need to first run a Netcat server * `$ nc -lk 9999` * and then run the example - * `$ ./bin/spark-submit examples.jar - * --class org.apache.spark.examples.streaming.StatefulNetworkWordCount localhost 9999` + * `$ bin/run-example + * org.apache.spark.examples.streaming.StatefulNetworkWordCount localhost 9999` */ object StatefulNetworkWordCount { def main(args: Array[String]) { @@ -51,7 +51,7 @@ object StatefulNetworkWordCount { Some(currentCount + previousCount) } - val sparkConf = new SparkConf().setAppName("NetworkWordCumulativeCountUpdateStateByKey") + val sparkConf = new SparkConf().setAppName("StatefulNetworkWordCount") // Create the context with a 1 second batch size val ssc = new StreamingContext(sparkConf, Seconds(1)) ssc.checkpoint(".") diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala index 1ddff22cb8a42..f55d23ab3924b 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala @@ -28,13 +28,29 @@ import org.apache.spark.SparkConf * stream. The stream is instantiated with credentials and optionally filters supplied by the * command line arguments. * + * Run this on your local machine as + * */ object TwitterPopularTags { def main(args: Array[String]) { + if (args.length < 4) { + System.err.println("Usage: TwitterPopularTags " + + " []") + System.exit(1) + } StreamingExamples.setStreamingLogLevels() - val filters = args + val Array(consumerKey, consumerSecret, accessToken, accessTokenSecret) = args.take(4) + val filters = args.takeRight(args.length - 4) + + // Set the system properties so that Twitter4j library used by twitter stream + // can use them to generat OAuth credentials + System.setProperty("twitter4j.oauth.consumerKey", consumerKey) + System.setProperty("twitter4j.oauth.consumerSecret", consumerSecret) + System.setProperty("twitter4j.oauth.accessToken", accessToken) + System.setProperty("twitter4j.oauth.accessTokenSecret", accessTokenSecret) + val sparkConf = new SparkConf().setAppName("TwitterPopularTags") val ssc = new StreamingContext(sparkConf, Seconds(2)) val stream = TwitterUtils.createStream(ssc, None, filters) @@ -52,13 +68,13 @@ object TwitterPopularTags { // Print popular hashtags topCounts60.foreachRDD(rdd => { - val topList = rdd.take(5) + val topList = rdd.take(10) println("\nPopular topics in last 60 seconds (%s total):".format(rdd.count())) topList.foreach{case (count, tag) => println("%s (%s tweets)".format(tag, count))} }) topCounts10.foreachRDD(rdd => { - val topList = rdd.take(5) + val topList = rdd.take(10) println("\nPopular topics in last 10 seconds (%s total):".format(rdd.count())) topList.foreach{case (count, tag) => println("%s (%s tweets)".format(tag, count))} }) diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/ZeroMQWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/ZeroMQWordCount.scala index 7ade3f1018ee8..79905af381a12 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/ZeroMQWordCount.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/ZeroMQWordCount.scala @@ -68,11 +68,11 @@ object SimpleZeroMQPublisher { * and describe where zeroMq publisher is running. * * To run this example locally, you may run publisher as - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar` + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar` * and run the example as - * `$ ./bin/spark-submit examples.jar \ - * --class org.apache.spark.examples.streaming.ZeroMQWordCount tcp://127.0.1.1:1234 foo` + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.ZeroMQWordCount tcp://127.0.1.1:1234 foo` */ // scalastyle:on object ZeroMQWordCount { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala index 97e0cb92078dc..8402491b62671 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala @@ -40,11 +40,13 @@ object PageView extends Serializable { /** Generates streaming events to simulate page views on a website. * * This should be used in tandem with PageViewStream.scala. Example: - * $ ./bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewGenerator 44444 10 - * $ ./bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewStream errorRatePerZipCode localhost 44444 * - * When running this, you may want to set the root logging level to ERROR in - * conf/log4j.properties to reduce the verbosity of the output. + * To run the generator + * `$ bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewGenerator 44444 10` + * To process the generated stream + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.clickstream.PageViewStream errorRatePerZipCode localhost 44444` + * */ // scalastyle:on object PageViewGenerator { diff --git a/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala b/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala index d30ceffbe29cb..d9b886eff77cc 100644 --- a/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala +++ b/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala @@ -26,8 +26,11 @@ import org.apache.spark.examples.streaming.StreamingExamples * operators available in Spark streaming. * * This should be used in tandem with PageViewStream.scala. Example: - * $ ./bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewGenerator 44444 10 - * $ ./bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewStream errorRatePerZipCode localhost 44444 + * To run the generator + * `$ bin/run-example org.apache.spark.examples.streaming.clickstream.PageViewGenerator 44444 10` + * To process the generated stream + * `$ bin/run-example \ + * org.apache.spark.examples.streaming.clickstream.PageViewStream errorRatePerZipCode localhost 44444` */ // scalastyle:on object PageViewStream { diff --git a/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala index 7bca1407116fa..5ea2e5549d7df 100644 --- a/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala +++ b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/TwitterInputDStream.scala @@ -63,36 +63,48 @@ class TwitterReceiver( storageLevel: StorageLevel ) extends Receiver[Status](storageLevel) with Logging { - var twitterStream: TwitterStream = _ + private var twitterStream: TwitterStream = _ def onStart() { - twitterStream = new TwitterStreamFactory().getInstance(twitterAuth) - twitterStream.addListener(new StatusListener { - def onStatus(status: Status) = { - store(status) - } - // Unimplemented - def onDeletionNotice(statusDeletionNotice: StatusDeletionNotice) {} - def onTrackLimitationNotice(i: Int) {} - def onScrubGeo(l: Long, l1: Long) {} - def onStallWarning(stallWarning: StallWarning) {} - def onException(e: Exception) { - restart("Error receiving tweets", e) - } - }) + try { + val newTwitterStream = new TwitterStreamFactory().getInstance(twitterAuth) + newTwitterStream.addListener(new StatusListener { + def onStatus(status: Status) = { + store(status) + } + // Unimplemented + def onDeletionNotice(statusDeletionNotice: StatusDeletionNotice) {} + def onTrackLimitationNotice(i: Int) {} + def onScrubGeo(l: Long, l1: Long) {} + def onStallWarning(stallWarning: StallWarning) {} + def onException(e: Exception) { + restart("Error receiving tweets", e) + } + }) - val query = new FilterQuery - if (filters.size > 0) { - query.track(filters.toArray) - twitterStream.filter(query) - } else { - twitterStream.sample() + val query = new FilterQuery + if (filters.size > 0) { + query.track(filters.toArray) + newTwitterStream.filter(query) + } else { + newTwitterStream.sample() + } + setTwitterStream(newTwitterStream) + logInfo("Twitter receiver started") + } catch { + case e: Exception => restart("Error starting Twitter stream", e) } - logInfo("Twitter receiver started") } def onStop() { - twitterStream.shutdown() + setTwitterStream(null) logInfo("Twitter receiver stopped") } + + private def setTwitterStream(newTwitterStream: TwitterStream) = synchronized { + if (twitterStream != null) { + twitterStream.shutdown() + } + twitterStream = newTwitterStream + } } From 2e5a7cde223c8bf6d34e46b27ac94a965441584d Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Wed, 14 May 2014 09:38:33 -0700 Subject: [PATCH 35/99] SPARK-1827. LICENSE and NOTICE files need a refresh to contain transitive dependency info LICENSE and NOTICE policy is explained here: http://www.apache.org/dev/licensing-howto.html http://www.apache.org/legal/3party.html This leads to the following changes. First, this change enables two extensions to maven-shade-plugin in assembly/ that will try to include and merge all NOTICE and LICENSE files. This can't hurt. This generates a consolidated NOTICE file that I manually added to NOTICE. Next, a list of all dependencies and their licenses was generated: `mvn ... license:aggregate-add-third-party` to create: `target/generated-sources/license/THIRD-PARTY.txt` Each dependency is listed with one or more licenses. Determine the most-compatible license for each if there is more than one. For "unknown" license dependencies, I manually evaluateD their license. Many are actually Apache projects or components of projects covered already. The only non-trivial one was Colt, which has its own (compatible) license. I ignored Apache-licensed and public domain dependencies as these require no further action (beyond NOTICE above). BSD and MIT licenses (permissive Category A licenses) are evidently supposed to be mentioned in LICENSE, so I added a section without output from the THIRD-PARTY.txt file appropriately. Everything else, Category B licenses, are evidently mentioned in NOTICE (?) Same there. LICENSE contained some license statements for source code that is redistributed. I left this as I think that is the right place to put it. Author: Sean Owen Closes #770 from srowen/SPARK-1827 and squashes the following commits: a764504 [Sean Owen] Add LICENSE and NOTICE info for all transitive dependencies as of 1.0 --- LICENSE | 103 +++++++++ NOTICE | 572 ++++++++++++++++++++++++++++++++++++++++++++++- assembly/pom.xml | 2 + 3 files changed, 671 insertions(+), 6 deletions(-) diff --git a/LICENSE b/LICENSE index 1c1c2c0255fa9..383f079df8c8b 100644 --- a/LICENSE +++ b/LICENSE @@ -428,3 +428,106 @@ LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON A THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +======================================================================== +For colt: +======================================================================== + +Copyright (c) 1999 CERN - European Organization for Nuclear Research. +Permission to use, copy, modify, distribute and sell this software and its documentation for any purpose is hereby granted without fee, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation. CERN makes no representations about the suitability of this software for any purpose. It is provided "as is" without expressed or implied warranty. + +Packages hep.aida.* + +Written by Pavel Binko, Dino Ferrero Merlino, Wolfgang Hoschek, Tony Johnson, Andreas Pfeiffer, and others. Check the FreeHEP home page for more info. Permission to use and/or redistribute this work is granted under the terms of the LGPL License, with the exception that any usage related to military applications is expressly forbidden. The software and documentation made available under the terms of this license are provided with no warranty. + + +======================================================================== +Fo SnapTree: +======================================================================== + +SNAPTREE LICENSE + +Copyright (c) 2009-2012 Stanford University, unless otherwise specified. +All rights reserved. + +This software was developed by the Pervasive Parallelism Laboratory of +Stanford University, California, USA. + +Permission to use, copy, modify, and distribute this software in source +or binary form for any purpose with or without fee is hereby granted, +provided that the following conditions are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + 2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + 3. Neither the name of Stanford University nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + + +THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +SUCH DAMAGE. + + +======================================================================== +BSD-style licenses +======================================================================== + +The following components are provided under a BSD-style license. See project link for details. + + (BSD 3 Clause) core (com.github.fommil.netlib:core:1.1.2 - https://github.com/fommil/netlib-java/core) + (BSD 3-clause style license) jblas (org.jblas:jblas:1.2.3 - http://jblas.org/) + (BSD License) AntLR Parser Generator (antlr:antlr:2.7.7 - http://www.antlr.org/) + (BSD License) Javolution (javolution:javolution:5.5.1 - http://javolution.org) + (BSD licence) ANTLR ST4 4.0.4 (org.antlr:ST4:4.0.4 - http://www.stringtemplate.org) + (BSD licence) ANTLR StringTemplate (org.antlr:stringtemplate:3.2.1 - http://www.stringtemplate.org) + (BSD style) Hamcrest Core (org.hamcrest:hamcrest-core:1.1 - no url defined) + (BSD) JLine (jline:jline:0.9.94 - http://jline.sourceforge.net) + (BSD) ParaNamer Core (com.thoughtworks.paranamer:paranamer:2.3 - http://paranamer.codehaus.org/paranamer) + (BSD) ParaNamer Core (com.thoughtworks.paranamer:paranamer:2.6 - http://paranamer.codehaus.org/paranamer) + (BSD-like) (The BSD License) jline (org.scala-lang:jline:2.10.4 - http://www.scala-lang.org/) + (BSD-like) Scala Actors library (org.scala-lang:scala-actors:2.10.4 - http://www.scala-lang.org/) + (BSD-like) Scala Compiler (org.scala-lang:scala-compiler:2.10.4 - http://www.scala-lang.org/) + (BSD-like) Scala Compiler (org.scala-lang:scala-reflect:2.10.4 - http://www.scala-lang.org/) + (BSD-like) Scala Library (org.scala-lang:scala-library:2.10.4 - http://www.scala-lang.org/) + (BSD-like) Scalap (org.scala-lang:scalap:2.10.4 - http://www.scala-lang.org/) + (BSD-style) scalacheck (org.scalacheck:scalacheck_2.10:1.10.0 - http://www.scalacheck.org) + (BSD-style) spire (org.spire-math:spire_2.10:0.7.1 - http://spire-math.org) + (BSD-style) spire-macros (org.spire-math:spire-macros_2.10:0.7.1 - http://spire-math.org) + (New BSD License) Kryo (com.esotericsoftware.kryo:kryo:2.21 - http://code.google.com/p/kryo/) + (New BSD License) MinLog (com.esotericsoftware.minlog:minlog:1.2 - http://code.google.com/p/minlog/) + (New BSD License) ReflectASM (com.esotericsoftware.reflectasm:reflectasm:1.07 - http://code.google.com/p/reflectasm/) + (New BSD license) Protocol Buffer Java API (com.google.protobuf:protobuf-java:2.5.0 - http://code.google.com/p/protobuf) + (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf) + (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net) + (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net) + (The New BSD License) Py4J (net.sf.py4j:py4j:0.8.1 - http://py4j.sourceforge.net/) + (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/) + (ISC/BSD License) jbcrypt (org.mindrot:jbcrypt:0.3m - http://www.mindrot.org/) + +======================================================================== +MIT licenses +======================================================================== + +The following components are provided under the MIT License. See project link for details. + + (MIT License) JCL 1.1.1 implemented over SLF4J (org.slf4j:jcl-over-slf4j:1.7.5 - http://www.slf4j.org) + (MIT License) JUL to SLF4J bridge (org.slf4j:jul-to-slf4j:1.7.5 - http://www.slf4j.org) + (MIT License) SLF4J API Module (org.slf4j:slf4j-api:1.7.5 - http://www.slf4j.org) + (MIT License) SLF4J LOG4J-12 Binding (org.slf4j:slf4j-log4j12:1.7.5 - http://www.slf4j.org) + (MIT License) pyrolite (org.spark-project:pyrolite:2.0.1 - http://pythonhosted.org/Pyro4/) + (MIT License) scopt (com.github.scopt:scopt_2.10:3.2.0 - https://github.com/scopt/scopt) + (The MIT License) Mockito (org.mockito:mockito-all:1.8.5 - http://www.mockito.org) diff --git a/NOTICE b/NOTICE index 42f6c3a835725..452aef2871652 100644 --- a/NOTICE +++ b/NOTICE @@ -4,11 +4,571 @@ Copyright 2014 The Apache Software Foundation. This product includes software developed at The Apache Software Foundation (http://www.apache.org/). -In addition, this product includes: -- JUnit (http://www.junit.org) is a testing framework for Java. We included it - under the terms of the Eclipse Public License v1.0. +======================================================================== +Common Development and Distribution License 1.0 +======================================================================== -- JTransforms (https://sites.google.com/site/piotrwendykier/software/jtransforms) - provides fast transforms in Java. It is tri-licensed, and we included it under - the terms of the Mozilla Public License v1.1. +The following components are provided under the Common Development and Distribution License 1.0. See project link for details. + + (CDDL 1.0) Glassfish Jasper (org.mortbay.jetty:jsp-2.1:6.1.14 - http://jetty.mortbay.org/project/modules/jsp-2.1) + (CDDL 1.0) Servlet Specification 2.5 API (org.mortbay.jetty:servlet-api-2.5:6.1.14 - http://jetty.mortbay.org/project/modules/servlet-api-2.5) + (COMMON DEVELOPMENT AND DISTRIBUTION LICENSE (CDDL) Version 1.0) (GNU General Public Library) Streaming API for XML (javax.xml.stream:stax-api:1.0-2 - no url defined) + (Common Development and Distribution License (CDDL) v1.0) JavaBeans Activation Framework (JAF) (javax.activation:activation:1.1 - http://java.sun.com/products/javabeans/jaf/index.jsp) + +======================================================================== +Common Development and Distribution License 1.1 +======================================================================== + +The following components are provided under the Common Development and Distribution License 1.1. See project link for details. + + (CDDL 1.1) (GPL2 w/ CPE) JAXB API bundle for GlassFish V3 (javax.xml.bind:jaxb-api:2.2.2 - https://jaxb.dev.java.net/) + (CDDL 1.1) (GPL2 w/ CPE) JAXB RI (com.sun.xml.bind:jaxb-impl:2.2.3-1 - http://jaxb.java.net/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-core (com.sun.jersey:jersey-core:1.8 - https://jersey.dev.java.net/jersey-core/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-core (com.sun.jersey:jersey-core:1.9 - https://jersey.java.net/jersey-core/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-guice (com.sun.jersey.contribs:jersey-guice:1.9 - https://jersey.java.net/jersey-contribs/jersey-guice/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-json (com.sun.jersey:jersey-json:1.8 - https://jersey.dev.java.net/jersey-json/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-json (com.sun.jersey:jersey-json:1.9 - https://jersey.java.net/jersey-json/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-server (com.sun.jersey:jersey-server:1.8 - https://jersey.dev.java.net/jersey-server/) + (CDDL 1.1) (GPL2 w/ CPE) jersey-server (com.sun.jersey:jersey-server:1.9 - https://jersey.java.net/jersey-server/) + +======================================================================== +Common Public License 1.0 +======================================================================== + +The following components are provided under the Common Public 1.0 License. See project link for details. + + (Common Public License Version 1.0) JUnit (junit:junit-dep:4.10 - http://junit.org) + (Common Public License Version 1.0) JUnit (junit:junit:3.8.1 - http://junit.org) + (Common Public License Version 1.0) JUnit (junit:junit:4.8.2 - http://junit.org) + +======================================================================== +Eclipse Public License 1.0 +======================================================================== + +The following components are provided under the Eclipse Public License 1.0. See project link for details. + + (Eclipse Public License - Version 1.0) mqtt-client (org.eclipse.paho:mqtt-client:0.4.0 - http://www.eclipse.org/paho/mqtt-client) + (Eclipse Public License v1.0) Eclipse JDT Core (org.eclipse.jdt:core:3.1.1 - http://www.eclipse.org/jdt/) + +======================================================================== +Mozilla Public License 1.0 +======================================================================== + +The following components are provided under the Mozilla Public License 1.0. See project link for details. + + (GPL) (LGPL) (MPL) JTransforms (com.github.rwl:jtransforms:2.4.0 - http://sourceforge.net/projects/jtransforms/) + (Mozilla Public License Version 1.1) jamon-runtime (org.jamon:jamon-runtime:2.3.1 - http://www.jamon.org/jamon-runtime/) + + + +======================================================================== +NOTICE files +======================================================================== + +The following NOTICEs are pertain to software distributed with this project. + + +// ------------------------------------------------------------------ +// NOTICE file corresponding to the section 4d of The Apache License, +// Version 2.0, in this case for +// ------------------------------------------------------------------ + +Apache Avro +Copyright 2009-2013 The Apache Software Foundation + +This product includes software developed at +The Apache Software Foundation (http://www.apache.org/). + +Apache Commons Codec +Copyright 2002-2009 The Apache Software Foundation + +This product includes software developed by +The Apache Software Foundation (http://www.apache.org/). + +-------------------------------------------------------------------------------- +src/test/org/apache/commons/codec/language/DoubleMetaphoneTest.java contains +test data from http://aspell.sourceforge.net/test/batch0.tab. + +Copyright (C) 2002 Kevin Atkinson (kevina@gnu.org). Verbatim copying +and distribution of this entire article is permitted in any medium, +provided this notice is preserved. +-------------------------------------------------------------------------------- + +Apache HttpComponents HttpClient +Copyright 1999-2011 The Apache Software Foundation + +This project contains annotations derived from JCIP-ANNOTATIONS +Copyright (c) 2005 Brian Goetz and Tim Peierls. See http://www.jcip.net + +Apache HttpComponents HttpCore +Copyright 2005-2011 The Apache Software Foundation + +Curator Recipes +Copyright 2011-2014 The Apache Software Foundation + +Curator Framework +Copyright 2011-2014 The Apache Software Foundation + +Curator Client +Copyright 2011-2014 The Apache Software Foundation + +Apache Geronimo +Copyright 2003-2008 The Apache Software Foundation + +Activation 1.1 +Copyright 2003-2007 The Apache Software Foundation + +Apache Commons Lang +Copyright 2001-2014 The Apache Software Foundation + +This product includes software from the Spring Framework, +under the Apache License 2.0 (see: StringUtils.containsWhitespace()) + +Apache log4j +Copyright 2007 The Apache Software Foundation + +# Compress LZF + +This library contains efficient implementation of LZF compression format, +as well as additional helper classes that build on JDK-provided gzip (deflat) +codec. + +## Licensing + +Library is licensed under Apache License 2.0, as per accompanying LICENSE file. + +## Credit + +Library has been written by Tatu Saloranta (tatu.saloranta@iki.fi). +It was started at Ning, inc., as an official Open Source process used by +platform backend, but after initial versions has been developed outside of +Ning by supporting community. + +Other contributors include: + +* Jon Hartlaub (first versions of streaming reader/writer; unit tests) +* Cedrik Lime: parallel LZF implementation + +Various community members have contributed bug reports, and suggested minor +fixes; these can be found from file "VERSION.txt" in SCM. + +Objenesis +Copyright 2006-2009 Joe Walnes, Henri Tremblay, Leonardo Mesquita + +Apache Commons Net +Copyright 2001-2010 The Apache Software Foundation + + The Netty Project + ================= + +Please visit the Netty web site for more information: + + * http://netty.io/ + +Copyright 2011 The Netty Project + +The Netty Project licenses this file to you under the Apache License, +version 2.0 (the "License"); you may not use this file except in compliance +with the License. You may obtain a copy of the License at: + +http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, WITHOUT +WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the +License for the specific language governing permissions and limitations +under the License. + +Also, please refer to each LICENSE..txt file, which is located in +the 'license' directory of the distribution file, for the license terms of the +components that this product depends on. + +------------------------------------------------------------------------------- +This product contains the extensions to Java Collections Framework which has +been derived from the works by JSR-166 EG, Doug Lea, and Jason T. Greene: + + * LICENSE: + * license/LICENSE.jsr166y.txt (Public Domain) + * HOMEPAGE: + * http://gee.cs.oswego.edu/cgi-bin/viewcvs.cgi/jsr166/ + * http://viewvc.jboss.org/cgi-bin/viewvc.cgi/jbosscache/experimental/jsr166/ + +This product contains a modified version of Robert Harder's Public Domain +Base64 Encoder and Decoder, which can be obtained at: + + * LICENSE: + * license/LICENSE.base64.txt (Public Domain) + * HOMEPAGE: + * http://iharder.sourceforge.net/current/java/base64/ + +This product contains a modified version of 'JZlib', a re-implementation of +zlib in pure Java, which can be obtained at: + + * LICENSE: + * license/LICENSE.jzlib.txt (BSD Style License) + * HOMEPAGE: + * http://www.jcraft.com/jzlib/ + +This product optionally depends on 'Protocol Buffers', Google's data +interchange format, which can be obtained at: + + * LICENSE: + * license/LICENSE.protobuf.txt (New BSD License) + * HOMEPAGE: + * http://code.google.com/p/protobuf/ + +This product optionally depends on 'SLF4J', a simple logging facade for Java, +which can be obtained at: + + * LICENSE: + * license/LICENSE.slf4j.txt (MIT License) + * HOMEPAGE: + * http://www.slf4j.org/ + +This product optionally depends on 'Apache Commons Logging', a logging +framework, which can be obtained at: + + * LICENSE: + * license/LICENSE.commons-logging.txt (Apache License 2.0) + * HOMEPAGE: + * http://commons.apache.org/logging/ + +This product optionally depends on 'Apache Log4J', a logging framework, +which can be obtained at: + + * LICENSE: + * license/LICENSE.log4j.txt (Apache License 2.0) + * HOMEPAGE: + * http://logging.apache.org/log4j/ + +This product optionally depends on 'JBoss Logging', a logging framework, +which can be obtained at: + + * LICENSE: + * license/LICENSE.jboss-logging.txt (GNU LGPL 2.1) + * HOMEPAGE: + * http://anonsvn.jboss.org/repos/common/common-logging-spi/ + +This product optionally depends on 'Apache Felix', an open source OSGi +framework implementation, which can be obtained at: + + * LICENSE: + * license/LICENSE.felix.txt (Apache License 2.0) + * HOMEPAGE: + * http://felix.apache.org/ + +This product optionally depends on 'Webbit', a Java event based +WebSocket and HTTP server: + + * LICENSE: + * license/LICENSE.webbit.txt (BSD License) + * HOMEPAGE: + * https://github.com/joewalnes/webbit + +# Jackson JSON processor + +Jackson is a high-performance, Free/Open Source JSON processing library. +It was originally written by Tatu Saloranta (tatu.saloranta@iki.fi), and has +been in development since 2007. +It is currently developed by a community of developers, as well as supported +commercially by FasterXML.com. + +Jackson core and extension components may be licensed under different licenses. +To find the details that apply to this artifact see the accompanying LICENSE file. +For more information, including possible other licensing options, contact +FasterXML.com (http://fasterxml.com). + +## Credits + +A list of contributors may be found from CREDITS file, which is included +in some artifacts (usually source distributions); but is always available +from the source code management (SCM) system project uses. + +Jackson core and extension components may licensed under different licenses. +To find the details that apply to this artifact see the accompanying LICENSE file. +For more information, including possible other licensing options, contact +FasterXML.com (http://fasterxml.com). + +mesos +Copyright 2014 The Apache Software Foundation + +Apache Thrift +Copyright 2006-2010 The Apache Software Foundation. + + Apache Ant + Copyright 1999-2013 The Apache Software Foundation + + The task is based on code Copyright (c) 2002, Landmark + Graphics Corp that has been kindly donated to the Apache Software + Foundation. + +Apache Commons IO +Copyright 2002-2012 The Apache Software Foundation + +Apache Commons Math +Copyright 2001-2013 The Apache Software Foundation + +=============================================================================== + +The inverse error function implementation in the Erf class is based on CUDA +code developed by Mike Giles, Oxford-Man Institute of Quantitative Finance, +and published in GPU Computing Gems, volume 2, 2010. +=============================================================================== + +The BracketFinder (package org.apache.commons.math3.optimization.univariate) +and PowellOptimizer (package org.apache.commons.math3.optimization.general) +classes are based on the Python code in module "optimize.py" (version 0.5) +developed by Travis E. Oliphant for the SciPy library (http://www.scipy.org/) +Copyright © 2003-2009 SciPy Developers. +=============================================================================== + +The LinearConstraint, LinearObjectiveFunction, LinearOptimizer, +RelationShip, SimplexSolver and SimplexTableau classes in package +org.apache.commons.math3.optimization.linear include software developed by +Benjamin McCann (http://www.benmccann.com) and distributed with +the following copyright: Copyright 2009 Google Inc. +=============================================================================== + +This product includes software developed by the +University of Chicago, as Operator of Argonne National +Laboratory. +The LevenbergMarquardtOptimizer class in package +org.apache.commons.math3.optimization.general includes software +translated from the lmder, lmpar and qrsolv Fortran routines +from the Minpack package +Minpack Copyright Notice (1999) University of Chicago. All rights reserved +=============================================================================== + +The GraggBulirschStoerIntegrator class in package +org.apache.commons.math3.ode.nonstiff includes software translated +from the odex Fortran routine developed by E. Hairer and G. Wanner. +Original source copyright: +Copyright (c) 2004, Ernst Hairer +=============================================================================== + +The EigenDecompositionImpl class in package +org.apache.commons.math3.linear includes software translated +from some LAPACK Fortran routines. Original source copyright: +Copyright (c) 1992-2008 The University of Tennessee. All rights reserved. +=============================================================================== + +The MersenneTwister class in package org.apache.commons.math3.random +includes software translated from the 2002-01-26 version of +the Mersenne-Twister generator written in C by Makoto Matsumoto and Takuji +Nishimura. Original source copyright: +Copyright (C) 1997 - 2002, Makoto Matsumoto and Takuji Nishimura, +All rights reserved +=============================================================================== + +The LocalizedFormatsTest class in the unit tests is an adapted version of +the OrekitMessagesTest class from the orekit library distributed under the +terms of the Apache 2 licence. Original source copyright: +Copyright 2010 CS Systèmes d'Information +=============================================================================== + +The HermiteInterpolator class and its corresponding test have been imported from +the orekit library distributed under the terms of the Apache 2 licence. Original +source copyright: +Copyright 2010-2012 CS Systèmes d'Information +=============================================================================== + +The creation of the package "o.a.c.m.analysis.integration.gauss" was inspired +by an original code donated by Sébastien Brisard. +=============================================================================== + +The complete text of licenses and disclaimers associated with the the original +sources enumerated above at the time of code translation are in the LICENSE.txt +file. + +This product currently only contains code developed by authors +of specific components, as identified by the source code files; +if such notes are missing files have been created by +Tatu Saloranta. + +For additional credits (generally to people who reported problems) +see CREDITS file. + +Apache Commons Lang +Copyright 2001-2011 The Apache Software Foundation + +Apache Commons Compress +Copyright 2002-2012 The Apache Software Foundation + +Apache Commons CLI +Copyright 2001-2009 The Apache Software Foundation + +Google Guice - Extensions - Servlet +Copyright 2006-2011 Google, Inc. + +Google Guice - Core Library +Copyright 2006-2011 Google, Inc. + +Apache Jakarta HttpClient +Copyright 1999-2007 The Apache Software Foundation + +Apache Hive +Copyright 2008-2013 The Apache Software Foundation + +This product includes software developed by The Apache Software +Foundation (http://www.apache.org/). + +This product includes software developed by The JDBM Project +(http://jdbm.sourceforge.net/). + +This product includes/uses ANTLR (http://www.antlr.org/), +Copyright (c) 2003-2011, Terrence Parr. + +This product includes/uses StringTemplate (http://www.stringtemplate.org/), +Copyright (c) 2011, Terrence Parr. + +This product includes/uses ASM (http://asm.ow2.org/), +Copyright (c) 2000-2007 INRIA, France Telecom. + +This product includes/uses org.json (http://www.json.org/java/index.html), +Copyright (c) 2002 JSON.org + +This product includes/uses JLine (http://jline.sourceforge.net/), +Copyright (c) 2002-2006, Marc Prud'hommeaux . + +This product includes/uses SQLLine (http://sqlline.sourceforge.net), +Copyright (c) 2002, 2003, 2004, 2005 Marc Prud'hommeaux . + +This product includes/uses SLF4J (http://www.slf4j.org/), +Copyright (c) 2004-2010 QOS.ch + +This product includes/uses Bootstrap (http://twitter.github.com/bootstrap/), +Copyright (c) 2012 Twitter, Inc. + +This product includes/uses Glyphicons (http://glyphicons.com/), +Copyright (c) 2010 - 2012 Jan Kovarík + +This product includes DataNucleus (http://www.datanucleus.org/) +Copyright 2008-2008 DataNucleus + +This product includes Guava (http://code.google.com/p/guava-libraries/) +Copyright (C) 2006 Google Inc. + +This product includes JavaEWAH (http://code.google.com/p/javaewah/) +Copyright (C) 2011 Google Inc. + +Apache Commons Pool +Copyright 1999-2009 The Apache Software Foundation + +========================================================================= +== NOTICE file corresponding to section 4(d) of the Apache License, == +== Version 2.0, in this case for the DataNucleus distribution. == +========================================================================= + +=================================================================== +This product includes software developed by many individuals, +including the following: +=================================================================== +Erik Bengtson +Andy Jefferson + +=================================================================== +This product has included contributions from some individuals, +including the following: +=================================================================== + +=================================================================== +This product has included contributions from some individuals, +including the following: +=================================================================== +Joerg von Frantzius +Thomas Marti +Barry Haddow +Marco Schulze +Ralph Ullrich +David Ezzio +Brendan de Beer +David Eaves +Martin Taal +Tony Lai +Roland Szabo +Marcus Mennemeier +Xuan Baldauf +Eric Sultan + +=================================================================== +This product also includes software developed by the TJDO project +(http://tjdo.sourceforge.net/). +=================================================================== + +=================================================================== +This product includes software developed by many individuals, +including the following: +=================================================================== +Andy Jefferson +Erik Bengtson +Joerg von Frantzius +Marco Schulze + +=================================================================== +This product has included contributions from some individuals, +including the following: +=================================================================== +Barry Haddow +Ralph Ullrich +David Ezzio +Brendan de Beer +David Eaves +Martin Taal +Tony Lai +Roland Szabo +Anton Troshin (Timesten) + +=================================================================== +This product also includes software developed by the Apache Commons project +(http://commons.apache.org/). +=================================================================== + +Apache Java Data Objects (JDO) +Copyright 2005-2006 The Apache Software Foundation + +========================================================================= +== NOTICE file corresponding to section 4(d) of the Apache License, == +== Version 2.0, in this case for the Apache Derby distribution. == +========================================================================= + +Apache Derby +Copyright 2004-2008 The Apache Software Foundation + +Portions of Derby were originally developed by +International Business Machines Corporation and are +licensed to the Apache Software Foundation under the +"Software Grant and Corporate Contribution License Agreement", +informally known as the "Derby CLA". +The following copyright notice(s) were affixed to portions of the code +with which this file is now or was at one time distributed +and are placed here unaltered. + +(C) Copyright 1997,2004 International Business Machines Corporation. All rights reserved. + +(C) Copyright IBM Corp. 2003. + +The portion of the functionTests under 'nist' was originally +developed by the National Institute of Standards and Technology (NIST), +an agency of the United States Department of Commerce, and adapted by +International Business Machines Corporation in accordance with the NIST +Software Acknowledgment and Redistribution document at +http://www.itl.nist.gov/div897/ctg/sql_form.htm + +Apache Commons Collections +Copyright 2001-2008 The Apache Software Foundation + +Apache Commons Configuration +Copyright 2001-2008 The Apache Software Foundation + +Apache Jakarta Commons Digester +Copyright 2001-2006 The Apache Software Foundation + +Apache Commons BeanUtils +Copyright 2000-2008 The Apache Software Foundation + +Apache Avro Mapred API +Copyright 2009-2013 The Apache Software Foundation + +Apache Avro IPC +Copyright 2009-2013 The Apache Software Foundation diff --git a/assembly/pom.xml b/assembly/pom.xml index 6c4d46aeb67bd..abd8935339992 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -122,6 +122,8 @@ log4j.properties + + From d1d41ccee49a5c093cb61c791c01f64f2076b83e Mon Sep 17 00:00:00 2001 From: Andrew Ash Date: Wed, 14 May 2014 09:45:33 -0700 Subject: [PATCH 36/99] SPARK-1818 Freshen Mesos documentation Place more emphasis on using precompiled binary versions of Spark and Mesos instead of encouraging the reader to compile from source. Author: Andrew Ash Closes #756 from ash211/spark-1818 and squashes the following commits: 7ef3b33 [Andrew Ash] Brief explanation of the interactions between Spark and Mesos e7dea8e [Andrew Ash] Add troubleshooting and debugging section 956362d [Andrew Ash] Don't need to pass spark.executor.uri into the spark shell de3353b [Andrew Ash] Wrap to 100char 7ebf6ef [Andrew Ash] Polish on the section on Mesos Master URLs 3dcc2c1 [Andrew Ash] Use --tgz parameter of make-distribution 41b68ed [Andrew Ash] Period at end of sentence; formatting on :5050 8bf2c53 [Andrew Ash] Update site.MESOS_VERSIOn to match /pom.xml 74f2040 [Andrew Ash] SPARK-1818 Freshen Mesos documentation --- docs/_config.yml | 2 +- docs/running-on-mesos.md | 200 +++++++++++++++++++++++++++++++++------ 2 files changed, 174 insertions(+), 28 deletions(-) diff --git a/docs/_config.yml b/docs/_config.yml index d177e38f884ca..45b78fe724a50 100644 --- a/docs/_config.yml +++ b/docs/_config.yml @@ -7,6 +7,6 @@ SPARK_VERSION: 1.0.0-SNAPSHOT SPARK_VERSION_SHORT: 1.0.0 SCALA_BINARY_VERSION: "2.10" SCALA_VERSION: "2.10.4" -MESOS_VERSION: 0.13.0 +MESOS_VERSION: 0.18.1 SPARK_ISSUE_TRACKER_URL: https://issues.apache.org/jira/browse/SPARK SPARK_GITHUB_URL: https://github.com/apache/spark diff --git a/docs/running-on-mesos.md b/docs/running-on-mesos.md index 68259f0cb8ad1..ef762aa7b8fcc 100644 --- a/docs/running-on-mesos.md +++ b/docs/running-on-mesos.md @@ -3,19 +3,123 @@ layout: global title: Running Spark on Mesos --- -Spark can run on clusters managed by [Apache Mesos](http://mesos.apache.org/). Follow the steps below to install Mesos and Spark: - -1. Download and build Spark using the instructions [here](index.html). **Note:** Don't forget to consider what version of HDFS you might want to use! -2. Download, build, install, and start Mesos {{site.MESOS_VERSION}} on your cluster. You can download the Mesos distribution from a [mirror](http://www.apache.org/dyn/closer.cgi/mesos/{{site.MESOS_VERSION}}/). See the Mesos [Getting Started](http://mesos.apache.org/gettingstarted) page for more information. **Note:** If you want to run Mesos without installing it into the default paths on your system (e.g., if you don't have administrative privileges to install it), you should also pass the `--prefix` option to `configure` to tell it where to install. For example, pass `--prefix=/home/user/mesos`. By default the prefix is `/usr/local`. -3. Create a Spark "distribution" using `make-distribution.sh`. -4. Rename the `dist` directory created from `make-distribution.sh` to `spark-{{site.SPARK_VERSION}}`. -5. Create a `tar` archive: `tar czf spark-{{site.SPARK_VERSION}}.tar.gz spark-{{site.SPARK_VERSION}}` -6. Upload this archive to HDFS or another place accessible from Mesos via `http://`, e.g., [Amazon Simple Storage Service](http://aws.amazon.com/s3): `hadoop fs -put spark-{{site.SPARK_VERSION}}.tar.gz /path/to/spark-{{site.SPARK_VERSION}}.tar.gz` -7. Create a file called `spark-env.sh` in Spark's `conf` directory, by copying `conf/spark-env.sh.template`, and add the following lines to it: - * `export MESOS_NATIVE_LIBRARY=`. This path is usually `/lib/libmesos.so` (where the prefix is `/usr/local` by default, see above). Also, on Mac OS X, the library is called `libmesos.dylib` instead of `libmesos.so`. - * `export SPARK_EXECUTOR_URI=`. - * `export MASTER=mesos://HOST:PORT` where HOST:PORT is the host and port (default: 5050) of your Mesos master (or `zk://...` if using Mesos with ZooKeeper). -8. To run a Spark application against the cluster, when you create your `SparkContext`, pass the string `mesos://HOST:PORT` as the master URL. In addition, you'll need to set the `spark.executor.uri` property. For example: +# Why Mesos + +Spark can run on hardware clusters managed by [Apache Mesos](http://mesos.apache.org/). + +The advantages of deploying Spark with Mesos include: +- dynamic partitioning between Spark and other + [frameworks](https://mesos.apache.org/documentation/latest/mesos-frameworks/) +- scalable partitioning between multiple instances of Spark + +# How it works + +In a standalone cluster deployment, the cluster manager in the below diagram is a Spark master +instance. When using Mesos, the Mesos master replaces the Spark master as the cluster manager. + +

+ Spark cluster components +

+ +Now when a driver creates a job and starts issuing tasks for scheduling, Mesos determines what +machines handle what tasks. Because it takes into account other frameworks when scheduling these +many short-lived tasks, multiple frameworks can coexist on the same cluster without resorting to a +static partitioning of resources. + +To get started, follow the steps below to install Mesos and deploy Spark jobs via Mesos. + + +# Installing Mesos + +Spark {{site.SPARK_VERSION}} is designed for use with Mesos {{site.MESOS_VERSION}} and does not +require any special patches of Mesos. + +If you already have a Mesos cluster running, you can skip this Mesos installation step. + +Otherwise, installing Mesos for Spark is no different than installing Mesos for use by other +frameworks. You can install Mesos using either prebuilt packages or by compiling from source. + +## Prebuilt packages + +The Apache Mesos project only publishes source package releases, no binary releases. But other +third party projects publish binary releases that may be helpful in setting Mesos up. + +One of those is Mesosphere. To install Mesos using the binary releases provided by Mesosphere: + +1. Download Mesos installation package from [downloads page](http://mesosphere.io/downloads/) +2. Follow their instructions for installation and configuration + +The Mesosphere installation documents suggest setting up ZooKeeper to handle Mesos master failover, +but Mesos can be run without ZooKeeper using a single master as well. + +## From source + +To install Mesos directly from the upstream project rather than a third party, install from source. + +1. Download the Mesos distribution from a + [mirror](http://www.apache.org/dyn/closer.cgi/mesos/{{site.MESOS_VERSION}}/) +2. Follow the Mesos [Getting Started](http://mesos.apache.org/gettingstarted) page for compiling and + installing Mesos + +**Note:** If you want to run Mesos without installing it into the default paths on your system +(e.g., if you lack administrative privileges to install it), you should also pass the +`--prefix` option to `configure` to tell it where to install. For example, pass +`--prefix=/home/user/mesos`. By default the prefix is `/usr/local`. + +## Verification + +To verify that the Mesos cluster is ready for Spark, navigate to the Mesos master webui at port +`:5050` Confirm that all expected machines are present in the slaves tab. + + +# Connecting Spark to Mesos + +To use Mesos from Spark, you need a Spark distribution available in a place accessible by Mesos, and +a Spark driver program configured to connect to Mesos. + +## Uploading Spark Distribution + +When Mesos runs a task on a Mesos slave for the first time, that slave must have a distribution of +Spark available for running the Spark Mesos executor backend. A distribution of Spark is just a +compiled binary version of Spark. + +The Spark distribution can be hosted at any Hadoop URI, including HTTP via `http://`, [Amazon Simple +Storage Service](http://aws.amazon.com/s3) via `s3://`, or HDFS via `hdfs:///`. + +To use a precompiled distribution: + +1. Download a Spark distribution from the Spark [download page](https://spark.apache.org/downloads.html) +2. Upload to hdfs/http/s3 + +To host on HDFS, use the Hadoop fs put command: `hadoop fs -put spark-{{site.SPARK_VERSION}}.tar.gz +/path/to/spark-{{site.SPARK_VERSION}}.tar.gz` + + +Or if you are using a custom-compiled version of Spark, you will need to create a distribution using +the `make-distribution.sh` script included in a Spark source tarball/checkout. + +1. Download and build Spark using the instructions [here](index.html) +2. Create a Spark distribution using `make-distribution.sh --tgz`. +3. Upload archive to http/s3/hdfs + + +## Using a Mesos Master URL + +The Master URLs for Mesos are in the form `mesos://host:5050` for a single-master Mesos +cluster, or `zk://host:2181` for a multi-master Mesos cluster using ZooKeeper. + +The driver also needs some configuration in `spark-env.sh` to interact properly with Mesos: + +1. In `spark.env.sh` set some environment variables: + * `export MESOS_NATIVE_LIBRARY=`. This path is typically + `/lib/libmesos.so` where the prefix is `/usr/local` by default. See Mesos installation + instructions above. On Mac OS X, the library is called `libmesos.dylib` instead of + `libmesos.so`. + * `export SPARK_EXECUTOR_URI=`. +2. Also set `spark.executor.uri` to + +Now when starting a Spark application against the cluster, pass a `mesos://` +or `zk://` URL as the master when creating a `SparkContext`. For example: {% highlight scala %} val conf = new SparkConf() @@ -25,31 +129,73 @@ val conf = new SparkConf() val sc = new SparkContext(conf) {% endhighlight %} +When running a shell the `spark.executor.uri` parameter is inherited from `SPARK_EXECUTOR_URI`, so +it does not need to be redundantly passed in as a system property. + +{% highlight bash %} +./bin/spark-shell --master mesos://host:5050 +{% endhighlight %} + + # Mesos Run Modes -Spark can run over Mesos in two modes: "fine-grained" and "coarse-grained". In fine-grained mode, which is the default, -each Spark task runs as a separate Mesos task. This allows multiple instances of Spark (and other frameworks) to share -machines at a very fine granularity, where each application gets more or fewer machines as it ramps up, but it comes with an -additional overhead in launching each task, which may be inappropriate for low-latency applications (e.g. interactive queries or serving web requests). The coarse-grained mode will instead -launch only *one* long-running Spark task on each Mesos machine, and dynamically schedule its own "mini-tasks" within -it. The benefit is much lower startup overhead, but at the cost of reserving the Mesos resources for the complete duration -of the application. +Spark can run over Mesos in two modes: "fine-grained" (default) and "coarse-grained". + +In "fine-grained" mode (default), each Spark task runs as a separate Mesos task. This allows +multiple instances of Spark (and other frameworks) to share machines at a very fine granularity, +where each application gets more or fewer machines as it ramps up and down, but it comes with an +additional overhead in launching each task. This mode may be inappropriate for low-latency +requirements like interactive queries or serving web requests. + +The "coarse-grained" mode will instead launch only *one* long-running Spark task on each Mesos +machine, and dynamically schedule its own "mini-tasks" within it. The benefit is much lower startup +overhead, but at the cost of reserving the Mesos resources for the complete duration of the +application. -To run in coarse-grained mode, set the `spark.mesos.coarse` property in your [SparkConf](configuration.html#spark-properties): +To run in coarse-grained mode, set the `spark.mesos.coarse` property in your +[SparkConf](configuration.html#spark-properties): {% highlight scala %} conf.set("spark.mesos.coarse", "true") {% endhighlight %} -In addition, for coarse-grained mode, you can control the maximum number of resources Spark will acquire. By default, -it will acquire *all* cores in the cluster (that get offered by Mesos), which only makes sense if you run just one -application at a time. You can cap the maximum number of cores using `conf.set("spark.cores.max", "10")` (for example). +In addition, for coarse-grained mode, you can control the maximum number of resources Spark will +acquire. By default, it will acquire *all* cores in the cluster (that get offered by Mesos), which +only makes sense if you run just one application at a time. You can cap the maximum number of cores +using `conf.set("spark.cores.max", "10")` (for example). # Running Alongside Hadoop -You can run Spark and Mesos alongside your existing Hadoop cluster by just launching them as a separate service on the machines. To access Hadoop data from Spark, just use a hdfs:// URL (typically `hdfs://:9000/path`, but you can find the right URL on your Hadoop Namenode's web UI). +You can run Spark and Mesos alongside your existing Hadoop cluster by just launching them as a +separate service on the machines. To access Hadoop data from Spark, a full hdfs:// URL is required +(typically `hdfs://:9000/path`, but you can find the right URL on your Hadoop Namenode web +UI). + +In addition, it is possible to also run Hadoop MapReduce on Mesos for better resource isolation and +sharing between the two. In this case, Mesos will act as a unified scheduler that assigns cores to +either Hadoop or Spark, as opposed to having them share resources via the Linux scheduler on each +node. Please refer to [Hadoop on Mesos](https://github.com/mesos/hadoop). + +In either case, HDFS runs separately from Hadoop MapReduce, without being scheduled through Mesos. + + +# Troubleshooting and Debugging + +A few places to look during debugging: + +- Mesos master on port `:5050` + - Slaves should appear in the slaves tab + - Spark applications should appear in the frameworks tab + - Tasks should appear in the details of a framework + - Check the stdout and stderr of the sandbox of failed tasks +- Mesos logs + - Master and slave logs are both in `/var/log/mesos` by default -In addition, it is possible to also run Hadoop MapReduce on Mesos, to get better resource isolation and sharing between the two. In this case, Mesos will act as a unified scheduler that assigns cores to either Hadoop or Spark, as opposed to having them share resources via the Linux scheduler on each node. Please refer to [Hadoop on Mesos](https://github.com/mesos/hadoop). +And common pitfalls: -In either case, HDFS runs separately from Hadoop MapReduce, without going through Mesos. +- Spark assembly not reachable/accessible + - Slaves need to be able to download the distribution +- Firewall blocking communications + - Check for messages about failed connections + - Temporarily disable firewalls for debugging and then poke appropriate holes From d58cb33ffa9e98a64cecea7b40ce7bfbed145079 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Wed, 14 May 2014 09:51:01 -0700 Subject: [PATCH 37/99] SPARK-1828: Created forked version of hive-exec that doesn't bundle other dependencies See https://issues.apache.org/jira/browse/SPARK-1828 for more information. This is being submitted to Jenkin's for testing. The dependency won't fully propagate in Maven central for a few more hours. Author: Patrick Wendell Closes #767 from pwendell/hive-shaded and squashes the following commits: ea10ac5 [Patrick Wendell] SPARK-1828: Created forked version of hive-exec that doesn't bundle other dependencies --- project/SparkBuild.scala | 6 +++--- sql/hive/pom.xml | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 57b3e22f81713..8d56b40431388 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -489,9 +489,9 @@ object SparkBuild extends Build { name := "spark-hive", javaOptions += "-XX:MaxPermSize=1g", libraryDependencies ++= Seq( - "org.apache.hive" % "hive-metastore" % hiveVersion, - "org.apache.hive" % "hive-exec" % hiveVersion, - "org.apache.hive" % "hive-serde" % hiveVersion + "org.spark-project.hive" % "hive-metastore" % hiveVersion, + "org.spark-project.hive" % "hive-exec" % hiveVersion, + "org.spark-project.hive" % "hive-serde" % hiveVersion ), // Multiple queries rely on the TestHive singleton. See comments there for more details. parallelExecution in Test := false, diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml index 8b32451d76045..9254b70e64a08 100644 --- a/sql/hive/pom.xml +++ b/sql/hive/pom.xml @@ -44,12 +44,12 @@ ${project.version} - org.apache.hive + org.spark-project.hive hive-metastore ${hive.version} - org.apache.hive + org.spark-project.hive hive-exec ${hive.version} @@ -64,7 +64,7 @@ jackson-mapper-asl - org.apache.hive + org.spark-project.hive hive-serde ${hive.version} From 17f3075bc4aa8cbed165f7b367f70e84b1bc8db9 Mon Sep 17 00:00:00 2001 From: Mark Hamstra Date: Wed, 14 May 2014 10:07:25 -0700 Subject: [PATCH 38/99] [SPARK-1620] Handle uncaught exceptions in function run by Akka scheduler If the intended behavior was that uncaught exceptions thrown in functions being run by the Akka scheduler would end up being handled by the default uncaught exception handler set in Executor, and if that behavior is, in fact, correct, then this is a way to accomplish that. I'm not certain, though, that we shouldn't be doing something different to handle uncaught exceptions from some of these scheduled functions. In any event, this PR covers all of the cases I comment on in [SPARK-1620](https://issues.apache.org/jira/browse/SPARK-1620). Author: Mark Hamstra Closes #622 from markhamstra/SPARK-1620 and squashes the following commits: 071d193 [Mark Hamstra] refactored post-SPARK-1772 1a6a35e [Mark Hamstra] another style fix d30eb94 [Mark Hamstra] scalastyle 3573ecd [Mark Hamstra] Use wrapped try/catch in Utils.tryOrExit 8fc0439 [Mark Hamstra] Make functions run by the Akka scheduler use Executor's UncaughtExceptionHandler --- .../apache/spark/deploy/client/AppClient.scala | 18 ++++++++++-------- .../apache/spark/deploy/worker/Worker.scala | 18 ++++++++++-------- .../spark/scheduler/TaskSchedulerImpl.scala | 3 ++- .../apache/spark/storage/BlockManager.scala | 2 +- .../scala/org/apache/spark/util/Utils.scala | 13 +++++++++++++ 5 files changed, 36 insertions(+), 18 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala b/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala index 896913d796604..d38e9e79204c2 100644 --- a/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala +++ b/core/src/main/scala/org/apache/spark/deploy/client/AppClient.scala @@ -30,7 +30,7 @@ import org.apache.spark.{Logging, SparkConf, SparkException} import org.apache.spark.deploy.{ApplicationDescription, ExecutorState} import org.apache.spark.deploy.DeployMessages._ import org.apache.spark.deploy.master.Master -import org.apache.spark.util.AkkaUtils +import org.apache.spark.util.{Utils, AkkaUtils} /** * Interface allowing applications to speak with a Spark deploy cluster. Takes a master URL, @@ -88,13 +88,15 @@ private[spark] class AppClient( var retries = 0 registrationRetryTimer = Some { context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) { - retries += 1 - if (registered) { - registrationRetryTimer.foreach(_.cancel()) - } else if (retries >= REGISTRATION_RETRIES) { - markDead("All masters are unresponsive! Giving up.") - } else { - tryRegisterAllMasters() + Utils.tryOrExit { + retries += 1 + if (registered) { + registrationRetryTimer.foreach(_.cancel()) + } else if (retries >= REGISTRATION_RETRIES) { + markDead("All masters are unresponsive! Giving up.") + } else { + tryRegisterAllMasters() + } } } } diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala index 85d25dc7dbfa4..134624c35a57e 100755 --- a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala @@ -166,14 +166,16 @@ private[spark] class Worker( var retries = 0 registrationRetryTimer = Some { context.system.scheduler.schedule(REGISTRATION_TIMEOUT, REGISTRATION_TIMEOUT) { - retries += 1 - if (registered) { - registrationRetryTimer.foreach(_.cancel()) - } else if (retries >= REGISTRATION_RETRIES) { - logError("All masters are unresponsive! Giving up.") - System.exit(1) - } else { - tryRegisterAllMasters() + Utils.tryOrExit { + retries += 1 + if (registered) { + registrationRetryTimer.foreach(_.cancel()) + } else if (retries >= REGISTRATION_RETRIES) { + logError("All masters are unresponsive! Giving up.") + System.exit(1) + } else { + tryRegisterAllMasters() + } } } } diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala index ffd1d9432682b..649eed213e09a 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala @@ -31,6 +31,7 @@ import scala.util.Random import org.apache.spark._ import org.apache.spark.TaskState.TaskState import org.apache.spark.scheduler.SchedulingMode.SchedulingMode +import org.apache.spark.util.Utils /** * Schedules tasks for multiple types of clusters by acting through a SchedulerBackend. @@ -139,7 +140,7 @@ private[spark] class TaskSchedulerImpl( import sc.env.actorSystem.dispatcher sc.env.actorSystem.scheduler.schedule(SPECULATION_INTERVAL milliseconds, SPECULATION_INTERVAL milliseconds) { - checkSpeculatableTasks() + Utils.tryOrExit { checkSpeculatableTasks() } } } } diff --git a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala index 6d7d4f922e1fa..6534095811907 100644 --- a/core/src/main/scala/org/apache/spark/storage/BlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/BlockManager.scala @@ -155,7 +155,7 @@ private[spark] class BlockManager( BlockManagerWorker.startBlockManagerWorker(this) if (!BlockManager.getDisableHeartBeatsForTesting(conf)) { heartBeatTask = actorSystem.scheduler.schedule(0.seconds, heartBeatFrequency.milliseconds) { - heartBeat() + Utils.tryOrExit { heartBeat() } } } } diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 99ef6dd1fa6e3..d041bfa66a1cd 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -40,6 +40,7 @@ import tachyon.client.{TachyonFile,TachyonFS} import org.apache.spark.{Logging, SecurityManager, SparkConf, SparkException} import org.apache.spark.deploy.SparkHadoopUtil +import org.apache.spark.executor.ExecutorUncaughtExceptionHandler import org.apache.spark.serializer.{DeserializationStream, SerializationStream, SerializerInstance} /** @@ -780,6 +781,18 @@ private[spark] object Utils extends Logging { output.toString } + /** + * Execute a block of code that evaluates to Unit, forwarding any uncaught exceptions to the + * default UncaughtExceptionHandler + */ + def tryOrExit(block: => Unit) { + try { + block + } catch { + case t: Throwable => ExecutorUncaughtExceptionHandler.uncaughtException(t) + } + } + /** * A regular expression to match classes of the "core" Spark API that we want to skip when * finding the call site of a method. From fde82c1549c78f1eebbb21ec34e60befbbff65f5 Mon Sep 17 00:00:00 2001 From: witgo Date: Wed, 14 May 2014 11:19:26 -0700 Subject: [PATCH 39/99] Fix: sbt test throw an java.lang.OutOfMemoryError: PermGen space Author: witgo Closes #773 from witgo/sbt_javaOptions and squashes the following commits: 26c7d38 [witgo] Improve sbt configuration --- .rat-excludes | 5 +++++ project/SparkBuild.scala | 1 + 2 files changed, 6 insertions(+) diff --git a/.rat-excludes b/.rat-excludes index 50766954ef070..689467847d80d 100644 --- a/.rat-excludes +++ b/.rat-excludes @@ -43,3 +43,8 @@ test.out/* .*iml service.properties db.lck +build/* +dist/* +.*out +.*ipr +.*iws diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 8d56b40431388..6adec556322ba 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -183,6 +183,7 @@ object SparkBuild extends Build { javaOptions in Test += "-Dspark.testing=1", javaOptions in Test += "-Dsun.io.serialization.extendedDebugInfo=true", javaOptions in Test ++= System.getProperties.filter(_._1 startsWith "spark").map { case (k,v) => s"-D$k=$v" }.toSeq, + javaOptions in Test ++= "-Xmx3g -XX:PermSize=128M -XX:MaxNewSize=256m -XX:MaxPermSize=1g".split(" ").toSeq, javaOptions += "-Xmx3g", // Show full stack trace and duration in test cases. testOptions in Test += Tests.Argument("-oDF"), From a3315d7f4c7584dae2ee0aa33c6ec9e97b229b48 Mon Sep 17 00:00:00 2001 From: Andrew Ash Date: Wed, 14 May 2014 12:01:14 -0700 Subject: [PATCH 40/99] SPARK-1829 Sub-second durations shouldn't round to "0 s" As "99 ms" up to 99 ms As "0.1 s" from 0.1 s up to 0.9 s https://issues.apache.org/jira/browse/SPARK-1829 Compare the first image to the second here: http://imgur.com/RaLEsSZ,7VTlgfo#0 Author: Andrew Ash Closes #768 from ash211/spark-1829 and squashes the following commits: 1c15b8e [Andrew Ash] SPARK-1829 Format sub-second durations more appropriately --- core/src/main/scala/org/apache/spark/ui/UIUtils.scala | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala index a3d6a1821245b..a43314f48112f 100644 --- a/core/src/main/scala/org/apache/spark/ui/UIUtils.scala +++ b/core/src/main/scala/org/apache/spark/ui/UIUtils.scala @@ -36,7 +36,13 @@ private[spark] object UIUtils extends Logging { def formatDate(timestamp: Long): String = dateFormat.get.format(new Date(timestamp)) def formatDuration(milliseconds: Long): String = { + if (milliseconds < 100) { + return "%d ms".format(milliseconds) + } val seconds = milliseconds.toDouble / 1000 + if (seconds < 1) { + return "%.1f s".format(seconds) + } if (seconds < 60) { return "%.0f s".format(seconds) } From 65533c7ec03e7eedf5cd9756822863ab6f034ec9 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Wed, 14 May 2014 12:53:30 -0700 Subject: [PATCH 41/99] SPARK-1833 - Have an empty SparkContext constructor. This is nicer than relying on new SparkContext(new SparkConf()) Author: Patrick Wendell Closes #774 from pwendell/spark-context and squashes the following commits: ef9f12f [Patrick Wendell] SPARK-1833 - Have an empty SparkContext constructor. --- core/src/main/scala/org/apache/spark/SparkContext.scala | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 032b3d744c619..634c10c33fc86 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -66,6 +66,12 @@ class SparkContext(config: SparkConf) extends Logging { // contains a map from hostname to a list of input format splits on the host. private[spark] var preferredNodeLocationData: Map[String, Set[SplitInfo]] = Map() + /** + * Create a SparkContext that loads settings from system properties (for instance, when + * launching with ./bin/spark-submit). + */ + def this() = this(new SparkConf()) + /** * :: DeveloperApi :: * Alternative constructor for setting preferred locations where Spark will create executors. From 94c6c06ea13032b80610b3f54401d2ef2aa4874a Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Wed, 14 May 2014 14:57:17 -0700 Subject: [PATCH 42/99] [FIX] do not load defaults when testing SparkConf in pyspark The default constructor loads default properties, which can fail the test. Author: Xiangrui Meng Closes #775 from mengxr/pyspark-conf-fix and squashes the following commits: 83ef6c4 [Xiangrui Meng] do not load defaults when testing SparkConf in pyspark --- python/pyspark/conf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/pyspark/conf.py b/python/pyspark/conf.py index 49b68d57ab02c..8eff4a242a529 100644 --- a/python/pyspark/conf.py +++ b/python/pyspark/conf.py @@ -33,7 +33,7 @@ >>> sc.sparkHome == None True ->>> conf = SparkConf() +>>> conf = SparkConf(loadDefaults=False) >>> conf.setSparkHome("/path") >>> conf.get("spark.home") From 601e37198b97ba52e72ac13213c391c932e97b67 Mon Sep 17 00:00:00 2001 From: Jacek Laskowski Date: Wed, 14 May 2014 15:45:52 -0700 Subject: [PATCH 43/99] String interpolation + some other small changes After having been invited to make the change in https://github.com/apache/spark/commit/6bee01dd04ef73c6b829110ebcdd622d521ea8ff#commitcomment-6284165 by @witgo. Author: Jacek Laskowski Closes #748 from jaceklaskowski/sparkenv-string-interpolation and squashes the following commits: be6ebac [Jacek Laskowski] String interpolation + some other small changes --- .../main/scala/org/apache/spark/SparkEnv.scala | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkEnv.scala b/core/src/main/scala/org/apache/spark/SparkEnv.scala index 19d507c0cf860..720151a6b0f84 100644 --- a/core/src/main/scala/org/apache/spark/SparkEnv.scala +++ b/core/src/main/scala/org/apache/spark/SparkEnv.scala @@ -278,10 +278,11 @@ object SparkEnv extends Logging { addedJars: Seq[String], addedFiles: Seq[String]): Map[String, Seq[(String, String)]] = { + import Properties._ val jvmInformation = Seq( - ("Java Version", "%s (%s)".format(Properties.javaVersion, Properties.javaVendor)), - ("Java Home", Properties.javaHome), - ("Scala Version", Properties.versionString) + ("Java Version", s"$javaVersion ($javaVendor)"), + ("Java Home", javaHome), + ("Scala Version", versionString) ).sorted // Spark properties @@ -296,18 +297,15 @@ object SparkEnv extends Logging { // System properties that are not java classpaths val systemProperties = System.getProperties.iterator.toSeq - val otherProperties = systemProperties.filter { case (k, v) => + val otherProperties = systemProperties.filter { case (k, _) => k != "java.class.path" && !k.startsWith("spark.") }.sorted // Class paths including all added jars and files - val classPathProperty = systemProperties.find { case (k, v) => - k == "java.class.path" - }.getOrElse(("", "")) - val classPathEntries = classPathProperty._2 + val classPathEntries = javaClassPath .split(File.pathSeparator) - .filterNot(e => e.isEmpty) - .map(e => (e, "System Classpath")) + .filterNot(_.isEmpty) + .map((_, "System Classpath")) val addedJarsAndFiles = (addedJars ++ addedFiles).map((_, "Added By User")) val classPaths = (addedJarsAndFiles ++ classPathEntries).sorted From e3d72a74ad007c2bf279d6a74cdaca948bdf0ddd Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Wed, 14 May 2014 17:18:30 -0700 Subject: [PATCH 44/99] [SPARK-1696][MLLIB] use alpha in dense dspr It doesn't affect existing code because only `alpha = 1.0` is used in the code. Author: Xiangrui Meng Closes #778 from mengxr/mllib-dspr-fix and squashes the following commits: a37402e [Xiangrui Meng] use alpha in dense dspr --- .../org/apache/spark/mllib/linalg/distributed/RowMatrix.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala index b10857fe7c8a1..07dfadf2f7869 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala @@ -440,7 +440,7 @@ object RowMatrix { val n = v.size v match { case dv: DenseVector => - blas.dspr("U", n, 1.0, dv.values, 1, U) + blas.dspr("U", n, alpha, dv.values, 1, U) case sv: SparseVector => val indices = sv.indices val values = sv.values From 9ad096d55a3d8410f04056ebc87dbd8cba391870 Mon Sep 17 00:00:00 2001 From: andrewor14 Date: Wed, 14 May 2014 17:54:53 -0700 Subject: [PATCH 45/99] [Typo] propertes -> properties Author: andrewor14 Closes #780 from andrewor14/submit-typo and squashes the following commits: e70e057 [andrewor14] propertes -> properties --- core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala index c6d3cbd2e728b..e86182e4c56ce 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala @@ -68,7 +68,7 @@ object SparkSubmit { /** * @return a tuple containing the arguments for the child, a list of classpath - * entries for the child, a list of system propertes, a list of env vars + * entries for the child, a list of system properties, a list of env vars * and the main class for the child */ private[spark] def createLaunchEnv(args: SparkSubmitArguments): (ArrayBuffer[String], From 44165fc91a31e6293a79031c89571e139d2c5356 Mon Sep 17 00:00:00 2001 From: wangfei Date: Wed, 14 May 2014 17:59:11 -0700 Subject: [PATCH 46/99] [SPARK-1826] fix the head notation of package object dsl Author: wangfei Closes #765 from scwf/dslfix and squashes the following commits: d2d1a9d [wangfei] Update package.scala 66ff53b [wangfei] fix the head notation of package object dsl --- .../spark/sql/catalyst/dsl/package.scala | 21 +++++++++++-------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala index 78d3a1d8096af..3cf163f9a9a75 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala @@ -31,26 +31,29 @@ import org.apache.spark.sql.catalyst.types._ * A collection of implicit conversions that create a DSL for constructing catalyst data structures. * * {{{ - * scala> import catalyst.dsl._ + * scala> import org.apache.spark.sql.catalyst.dsl.expressions._ * * // Standard operators are added to expressions. + * scala> import org.apache.spark.sql.catalyst.expressions.Literal * scala> Literal(1) + Literal(1) - * res1: catalyst.expressions.Add = (1 + 1) + * res0: org.apache.spark.sql.catalyst.expressions.Add = (1 + 1) * * // There is a conversion from 'symbols to unresolved attributes. * scala> 'a.attr - * res2: catalyst.analysis.UnresolvedAttribute = 'a + * res1: org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute = 'a * * // These unresolved attributes can be used to create more complicated expressions. * scala> 'a === 'b - * res3: catalyst.expressions.Equals = ('a = 'b) + * res2: org.apache.spark.sql.catalyst.expressions.Equals = ('a = 'b) * * // SQL verbs can be used to construct logical query plans. - * scala> TestRelation('key.int, 'value.string).where('key === 1).select('value).analyze - * res4: catalyst.plans.logical.LogicalPlan = - * Project {value#1} - * Filter (key#0 = 1) - * TestRelation {key#0,value#1} + * scala> import org.apache.spark.sql.catalyst.plans.logical._ + * scala> import org.apache.spark.sql.catalyst.dsl.plans._ + * scala> LocalRelation('key.int, 'value.string).where('key === 1).select('value).analyze + * res3: org.apache.spark.sql.catalyst.plans.logical.LogicalPlan = + * Project [value#3] + * Filter (key#2 = 1) + * LocalRelation [key#2,value#3], [] * }}} */ package object dsl { From 2f639957f0bf70dddf1e698aa9e26007fb58bc67 Mon Sep 17 00:00:00 2001 From: Chen Chao Date: Wed, 14 May 2014 18:20:20 -0700 Subject: [PATCH 47/99] default task number misleading in several places private[streaming] def defaultPartitioner(numPartitions: Int = self.ssc.sc.defaultParallelism){ new HashPartitioner(numPartitions) } it represents that the default task number in Spark Streaming relies on the variable defaultParallelism in SparkContext, which is decided by the config property spark.default.parallelism the property "spark.default.parallelism" refers to https://github.com/apache/spark/pull/389 Author: Chen Chao Closes #766 from CrazyJvm/patch-7 and squashes the following commits: 0b7efba [Chen Chao] Update streaming-programming-guide.md cc5b66c [Chen Chao] default task number misleading in several places --- docs/streaming-programming-guide.md | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/docs/streaming-programming-guide.md b/docs/streaming-programming-guide.md index 939599aa6855b..0c125eb693a8e 100644 --- a/docs/streaming-programming-guide.md +++ b/docs/streaming-programming-guide.md @@ -522,9 +522,9 @@ common ones are as follows. reduceByKey(func, [numTasks]) When called on a DStream of (K, V) pairs, return a new DStream of (K, V) pairs where the values for each key are aggregated using the given reduce function. Note: By default, - this uses Spark's default number of parallel tasks (2 for local machine, 8 for a cluster) to - do the grouping. You can pass an optional numTasks argument to set a different - number of tasks. + this uses Spark's default number of parallel tasks (2 for local mode, and in cluster mode the number + is determined by the config property spark.default.parallelism) to do the grouping. + You can pass an optional numTasks argument to set a different number of tasks. join(otherStream, [numTasks]) @@ -743,8 +743,9 @@ said two parameters - windowLength and slideInterval. When called on a DStream of (K, V) pairs, returns a new DStream of (K, V) pairs where the values for each key are aggregated using the given reduce function func over batches in a sliding window. Note: By default, this uses Spark's default number of - parallel tasks (2 for local machine, 8 for a cluster) to do the grouping. You can pass an optional - numTasks argument to set a different number of tasks. + parallel tasks (2 for local mode, and in cluster mode the number is determined by the config + property spark.default.parallelism) to do the grouping. You can pass an optional + numTasks argument to set a different number of tasks. @@ -956,9 +957,10 @@ before further processing. ### Level of Parallelism in Data Processing Cluster resources maybe under-utilized if the number of parallel tasks used in any stage of the computation is not high enough. For example, for distributed reduce operations like `reduceByKey` -and `reduceByKeyAndWindow`, the default number of parallel tasks is 8. You can pass the level of -parallelism as an argument (see the -[`PairDStreamFunctions`](api/scala/index.html#org.apache.spark.streaming.dstream.PairDStreamFunctions) +and `reduceByKeyAndWindow`, the default number of parallel tasks is decided by the [config property] +(configuration.html#spark-properties) `spark.default.parallelism`. You can pass the level of +parallelism as an argument (see [`PairDStreamFunctions`] +(api/scala/index.html#org.apache.spark.streaming.dstream.PairDStreamFunctions) documentation), or set the [config property](configuration.html#spark-properties) `spark.default.parallelism` to change the default. From ad4e60ee7e2c49c24a9972312915f7f7253c7679 Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Wed, 14 May 2014 21:13:41 -0700 Subject: [PATCH 48/99] [SPARK-1840] SparkListenerBus prints out scary error message when terminated normally Running SparkPi example gave this error. ``` Pi is roughly 3.14374 14/05/14 18:16:19 ERROR Utils: Uncaught exception in thread SparkListenerBus scala.runtime.NonLocalReturnControl$mcV$sp ``` This is due to the catch-all in the SparkListenerBus, which logged control throwable used by scala system Author: Tathagata Das Closes #783 from tdas/controlexception-fix and squashes the following commits: a466c8d [Tathagata Das] Ignored control exceptions when logging all exceptions. --- core/src/main/scala/org/apache/spark/util/Utils.scala | 2 ++ 1 file changed, 2 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index d041bfa66a1cd..388f7222428db 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1149,6 +1149,8 @@ private[spark] object Utils extends Logging { try { f } catch { + case ct: ControlThrowable => + throw ct case t: Throwable => logError(s"Uncaught exception in thread ${Thread.currentThread().getName}", t) throw t From f10de042b8e86adf51b70bae2d8589a5cbf02935 Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Wed, 14 May 2014 21:45:20 -0700 Subject: [PATCH 49/99] Add language tabs and Python version to interactive part of quick-start This is an addition of some stuff that was missed in https://issues.apache.org/jira/browse/SPARK-1567. I've also updated the doc to show submitting the Python application with spark-submit. Author: Matei Zaharia Closes #782 from mateiz/spark-1567-extra and squashes the following commits: 6f8f2aa [Matei Zaharia] tweaks 9ed9874 [Matei Zaharia] tweaks ae67c3e [Matei Zaharia] tweak b303ba3 [Matei Zaharia] tweak 1433a4d [Matei Zaharia] Add language tabs and Python version to interactive part of quick-start guide --- docs/python-programming-guide.md | 2 +- docs/quick-start.md | 151 +++++++++++++++++++++++++++---- 2 files changed, 133 insertions(+), 20 deletions(-) diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index 2ce2c346d7b04..17675acba6bb8 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -121,7 +121,7 @@ IPython also works on a cluster or on multiple cores if you set the `MASTER` env # Standalone Programs PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `bin/spark-submit`. -The Quick Start guide includes a [complete example](quick-start.html#a-standalone-app-in-python) of a standalone Python application. +The Quick Start guide includes a [complete example](quick-start.html#standalone-applications) of a standalone Python application. Code dependencies can be deployed by passing .zip or .egg files in the `--py-files` option of `spark-submit`: diff --git a/docs/quick-start.md b/docs/quick-start.md index a4d01487bb494..33a0df1036424 100644 --- a/docs/quick-start.md +++ b/docs/quick-start.md @@ -6,7 +6,9 @@ title: Quick Start * This will become a table of contents (this text will be scraped). {:toc} -This tutorial provides a quick introduction to using Spark. We will first introduce the API through Spark's interactive Scala shell (don't worry if you don't know Scala -- you will not need much for this), then show how to write standalone applications in Scala, Java, and Python. +This tutorial provides a quick introduction to using Spark. We will first introduce the API through Spark's +interactive shell (in Python or Scala), +then show how to write standalone applications in Java, Scala, and Python. See the [programming guide](scala-programming-guide.html) for a more complete reference. To follow along with this guide, first download a packaged release of Spark from the @@ -17,8 +19,12 @@ you can download a package for any version of Hadoop. ## Basics -Spark's interactive shell provides a simple way to learn the API, as well as a powerful tool to analyze datasets interactively. -Start the shell by running the following in the Spark directory. +Spark's shell provides a simple way to learn the API, as well as a powerful tool to analyze data interactively. +It is available in either Scala (which runs on the Java VM and is thus a good way to use existing Java libraries) +or Python. Start it by running the following in the Spark directory: + +
+
./bin/spark-shell @@ -33,7 +39,7 @@ RDDs have _[actions](scala-programming-guide.html#actions)_, which return values {% highlight scala %} scala> textFile.count() // Number of items in this RDD -res0: Long = 74 +res0: Long = 126 scala> textFile.first() // First item in this RDD res1: String = # Apache Spark @@ -53,12 +59,53 @@ scala> textFile.filter(line => line.contains("Spark")).count() // How many lines res3: Long = 15 {% endhighlight %} +
+
+ + ./bin/pyspark + +Spark's primary abstraction is a distributed collection of items called a Resilient Distributed Dataset (RDD). RDDs can be created from Hadoop InputFormats (such as HDFS files) or by transforming other RDDs. Let's make a new RDD from the text of the README file in the Spark source directory: + +{% highlight python %} +>>> textFile = sc.textFile("README.md") +{% endhighlight %} + +RDDs have _[actions](scala-programming-guide.html#actions)_, which return values, and _[transformations](scala-programming-guide.html#transformations)_, which return pointers to new RDDs. Let's start with a few actions: + +{% highlight python %} +>>> textFile.count() # Number of items in this RDD +126 + +>>> textFile.first() # First item in this RDD +u'# Apache Spark' +{% endhighlight %} + +Now let's use a transformation. We will use the [`filter`](scala-programming-guide.html#transformations) transformation to return a new RDD with a subset of the items in the file. + +{% highlight python %} +>>> linesWithSpark = textFile.filter(lambda line: "Spark" in line) +{% endhighlight %} + +We can chain together transformations and actions: + +{% highlight python %} +>>> textFile.filter(lambda line: "Spark" in line).count() # How many lines contain "Spark"? +15 +{% endhighlight %} + +
+
+ + ## More on RDD Operations RDD actions and transformations can be used for more complex computations. Let's say we want to find the line with the most words: +
+
+ {% highlight scala %} scala> textFile.map(line => line.split(" ").size).reduce((a, b) => if (a > b) a else b) -res4: Long = 16 +res4: Long = 15 {% endhighlight %} This first maps a line to an integer value, creating a new RDD. `reduce` is called on that RDD to find the largest line count. The arguments to `map` and `reduce` are Scala function literals (closures), and can use any language feature or Scala/Java library. For example, we can easily call functions declared elsewhere. We'll use `Math.max()` function to make this code easier to understand: @@ -68,26 +115,69 @@ scala> import java.lang.Math import java.lang.Math scala> textFile.map(line => line.split(" ").size).reduce((a, b) => Math.max(a, b)) -res5: Int = 16 +res5: Int = 15 {% endhighlight %} One common data flow pattern is MapReduce, as popularized by Hadoop. Spark can implement MapReduce flows easily: {% highlight scala %} scala> val wordCounts = textFile.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey((a, b) => a + b) -wordCounts: spark.RDD[(java.lang.String, Int)] = spark.ShuffledAggregatedRDD@71f027b8 +wordCounts: spark.RDD[(String, Int)] = spark.ShuffledAggregatedRDD@71f027b8 {% endhighlight %} Here, we combined the [`flatMap`](scala-programming-guide.html#transformations), [`map`](scala-programming-guide.html#transformations) and [`reduceByKey`](scala-programming-guide.html#transformations) transformations to compute the per-word counts in the file as an RDD of (String, Int) pairs. To collect the word counts in our shell, we can use the [`collect`](scala-programming-guide.html#actions) action: {% highlight scala %} scala> wordCounts.collect() -res6: Array[(java.lang.String, Int)] = Array((need,2), ("",43), (Extra,3), (using,1), (passed,1), (etc.,1), (its,1), (`/usr/local/lib/libmesos.so`,1), (`SCALA_HOME`,1), (option,1), (these,1), (#,1), (`PATH`,,2), (200,1), (To,3),... +res6: Array[(String, Int)] = Array((means,1), (under,2), (this,3), (Because,1), (Python,2), (agree,1), (cluster.,1), ...) {% endhighlight %} +
+
+ +{% highlight python %} +>>> textFile.map(lambda line: len(line.split())).reduce(lambda a, b: a if (a > b) else b) +15 +{% endhighlight %} + +This first maps a line to an integer value, creating a new RDD. `reduce` is called on that RDD to find the largest line count. The arguments to `map` and `reduce` are Python [anonymous functions (lambdas)](https://docs.python.org/2/reference/expressions.html#lambda), +but we can also pass any top-level Python function we want. +For example, we'll define a `max` function to make this code easier to understand: + +{% highlight python %} +>>> def max(a, b): +... if a > b: +... return a +... else: +... return b +... + +>>> textFile.map(lambda line: len(line.split())).reduce(max) +15 +{% endhighlight %} + +One common data flow pattern is MapReduce, as popularized by Hadoop. Spark can implement MapReduce flows easily: + +{% highlight python %} +>>> wordCounts = textFile.flatMap(lambda line: line.split()).map(lambda word: (word, 1)).reduceByKey(lambda a, b: a+b) +{% endhighlight %} + +Here, we combined the [`flatMap`](scala-programming-guide.html#transformations), [`map`](scala-programming-guide.html#transformations) and [`reduceByKey`](scala-programming-guide.html#transformations) transformations to compute the per-word counts in the file as an RDD of (string, int) pairs. To collect the word counts in our shell, we can use the [`collect`](scala-programming-guide.html#actions) action: + +{% highlight python %} +>>> wordCounts.collect() +[(u'and', 9), (u'A', 1), (u'webpage', 1), (u'README', 1), (u'Note', 1), (u'"local"', 1), (u'variable', 1), ...] +{% endhighlight %} + +
+
+ ## Caching Spark also supports pulling data sets into a cluster-wide in-memory cache. This is very useful when data is accessed repeatedly, such as when querying a small "hot" dataset or when running an iterative algorithm like PageRank. As a simple example, let's mark our `linesWithSpark` dataset to be cached: +
+
+ {% highlight scala %} scala> linesWithSpark.cache() res7: spark.RDD[String] = spark.FilteredRDD@17e51082 @@ -99,12 +189,33 @@ scala> linesWithSpark.count() res9: Long = 15 {% endhighlight %} -It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is +It may seem silly to use Spark to explore and cache a 100-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `bin/spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark). -# A Standalone Application +
+
+ +{% highlight python %} +>>> linesWithSpark.cache() + +>>> linesWithSpark.count() +15 + +>>> linesWithSpark.count() +15 +{% endhighlight %} + +It may seem silly to use Spark to explore and cache a 100-line text file. The interesting part is +that these same functions can be used on very large data sets, even when they are striped across +tens or hundreds of nodes. You can also do this interactively by connecting `bin/pyspark` to +a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark). + +
+
+ +# Standalone Applications Now say we wanted to write a standalone application using the Spark API. We will walk through a simple application in both Scala (with SBT), Java (with Maven), and Python. @@ -115,7 +226,7 @@ We'll create a very simple Spark application in Scala. So simple, in fact, that named `SimpleApp.scala`: {% highlight scala %} -/*** SimpleApp.scala ***/ +/* SimpleApp.scala */ import org.apache.spark.SparkContext import org.apache.spark.SparkContext._ import org.apache.spark.SparkConf @@ -194,7 +305,7 @@ This example will use Maven to compile an application jar, but any similar build We'll create a very simple Spark application, `SimpleApp.java`: {% highlight java %} -/*** SimpleApp.java ***/ +/* SimpleApp.java */ import org.apache.spark.api.java.*; import org.apache.spark.SparkConf; import org.apache.spark.api.java.function.Function; @@ -309,16 +420,18 @@ Note that you'll need to replace YOUR_SPARK_HOME with the location where Spark i As with the Scala and Java examples, we use a SparkContext to create RDDs. We can pass Python functions to Spark, which are automatically serialized along with any variables that they reference. -For applications that use custom classes or third-party libraries, we can add those code -dependencies to SparkContext to ensure that they will be available on remote machines; this is -described in more detail in the [Python programming guide](python-programming-guide.html). +For applications that use custom classes or third-party libraries, we can also add code +dependencies to `spark-submit` through its `--py-files` argument by packaging them into a +.zip file (see `spark-submit --help` for details). `SimpleApp` is simple enough that we do not need to specify any code dependencies. -We can run this application using the `bin/pyspark` script: +We can run this application using the `bin/spark-submit` script: {% highlight python %} -$ cd $SPARK_HOME -$ ./bin/pyspark SimpleApp.py +# Use spark-submit to run your application +$ YOUR_SPARK_HOME/bin/spark-submit \ + --master local[4] \ + SimpleApp.py ... Lines with a: 46, Lines with b: 23 {% endhighlight python %} @@ -326,7 +439,7 @@ Lines with a: 46, Lines with b: 23 -# Where to go from here +# Where to Go from Here Congratulations on running your first Spark application! * For an in-depth overview of the API see "Programming Guides" menu section. From 21570b463388194877003318317aafd842800cac Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Wed, 14 May 2014 22:24:04 -0700 Subject: [PATCH 50/99] Documentation: Encourage use of reduceByKey instead of groupByKey. Author: Patrick Wendell Closes #784 from pwendell/group-by-key and squashes the following commits: 9b4505f [Patrick Wendell] Small fix 6347924 [Patrick Wendell] Documentation: Encourage use of reduceByKey instead of groupByKey. --- .../org/apache/spark/api/java/JavaPairRDD.scala | 12 ++++++++++++ .../org/apache/spark/rdd/PairRDDFunctions.scala | 12 ++++++++++++ docs/scala-programming-guide.md | 4 ++++ python/pyspark/rdd.py | 4 ++++ 4 files changed, 32 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala index 554c065358648..4c8f9ed6fbc02 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala @@ -263,6 +263,10 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Allows controlling the * partitioning of the resulting key-value pair RDD by passing a Partitioner. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[JavaPairRDD.reduceByKey]] or [[JavaPairRDD.combineByKey]] + * will provide much better performance. */ def groupByKey(partitioner: Partitioner): JavaPairRDD[K, JIterable[V]] = fromRDD(groupByResultToJava(rdd.groupByKey(partitioner))) @@ -270,6 +274,10 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Hash-partitions the * resulting RDD with into `numPartitions` partitions. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[JavaPairRDD.reduceByKey]] or [[JavaPairRDD.combineByKey]] + * will provide much better performance. */ def groupByKey(numPartitions: Int): JavaPairRDD[K, JIterable[V]] = fromRDD(groupByResultToJava(rdd.groupByKey(numPartitions))) @@ -380,6 +388,10 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Hash-partitions the * resulting RDD with the existing partitioner/parallelism level. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[JavaPairRDD.reduceByKey]] or [[JavaPairRDD.combineByKey]] + * will provide much better performance. */ def groupByKey(): JavaPairRDD[K, JIterable[V]] = fromRDD(groupByResultToJava(rdd.groupByKey())) diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala index bc6d204434ad8..223fef79261d0 100644 --- a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala +++ b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala @@ -264,6 +264,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Allows controlling the * partitioning of the resulting key-value pair RDD by passing a Partitioner. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[PairRDDFunctions.reduceByKey]] or [[PairRDDFunctions.combineByKey]] + * will provide much better performance. */ def groupByKey(partitioner: Partitioner): RDD[(K, Iterable[V])] = { // groupByKey shouldn't use map side combine because map side combine does not @@ -280,6 +284,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Hash-partitions the * resulting RDD with into `numPartitions` partitions. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[PairRDDFunctions.reduceByKey]] or [[PairRDDFunctions.combineByKey]] + * will provide much better performance. */ def groupByKey(numPartitions: Int): RDD[(K, Iterable[V])] = { groupByKey(new HashPartitioner(numPartitions)) @@ -365,6 +373,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)]) /** * Group the values for each key in the RDD into a single sequence. Hash-partitions the * resulting RDD with the existing partitioner/parallelism level. + * + * Note: If you are grouping in order to perform an aggregation (such as a sum or average) over + * each key, using [[PairRDDFunctions.reduceByKey]] or [[PairRDDFunctions.combineByKey]] + * will provide much better performance, */ def groupByKey(): RDD[(K, Iterable[V])] = { groupByKey(defaultPartitioner(self)) diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md index 3ed86e460c01c..edaa7d0639a18 100644 --- a/docs/scala-programming-guide.md +++ b/docs/scala-programming-guide.md @@ -196,6 +196,10 @@ The following tables list the transformations and actions currently supported (s groupByKey([numTasks]) When called on a dataset of (K, V) pairs, returns a dataset of (K, Seq[V]) pairs.
+Note: If you are grouping in order to perform an aggregation (such as a sum or + average) over each key, using `reduceByKey` or `combineByKey` will yield much better + performance. +
Note: By default, if the RDD already has a partitioner, the task number is decided by the partition number of the partitioner, or else relies on the value of spark.default.parallelism if the property is set , otherwise depends on the partition number of the RDD. You can pass an optional numTasks argument to set a different number of tasks. diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 4f74824ba4cf2..07578b8d937fc 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1152,6 +1152,10 @@ def groupByKey(self, numPartitions=None): Group the values for each key in the RDD into a single sequence. Hash-partitions the resulting RDD with into numPartitions partitions. + Note: If you are grouping in order to perform an aggregation (such as a + sum or average) over each key, using reduceByKey will provide much better + performance. + >>> x = sc.parallelize([("a", 1), ("b", 1), ("a", 1)]) >>> map((lambda (x,y): (x, list(y))), sorted(x.groupByKey().collect())) [('a', [1, 1]), ('b', [1])] From 46324279dae2fa803267d788f7c56b0ed643b4c8 Mon Sep 17 00:00:00 2001 From: Prashant Sharma Date: Wed, 14 May 2014 22:24:41 -0700 Subject: [PATCH 51/99] Package docs This is a few changes based on the original patch by @scrapcodes. Author: Prashant Sharma Author: Patrick Wendell Closes #785 from pwendell/package-docs and squashes the following commits: c32b731 [Patrick Wendell] Changes based on Prashant's patch c0463d3 [Prashant Sharma] added eof new line ce8bf73 [Prashant Sharma] Added eof new line to all files. 4c35f2e [Prashant Sharma] SPARK-1563 Add package-info.java and package.scala files for all packages that appear in docs --- .../org/apache/spark/bagel/package-info.java | 21 ++++++++++++++ .../org/apache/spark/bagel/package.scala | 23 +++++++++++++++ .../spark/api/java/function/package-info.java | 23 +++++++++++++++ .../spark/api/java/function/package.scala | 25 +++++++++++++++++ .../apache/spark/annotation/package-info.java | 23 +++++++++++++++ .../org/apache/spark/annotation/package.scala | 25 +++++++++++++++++ .../apache/spark/api/java/package-info.java | 21 ++++++++++++++ .../apache/spark/broadcast/package-info.java | 21 ++++++++++++++ .../org/apache/spark/broadcast/package.scala | 2 +- .../apache/spark/executor/package-info.java | 21 ++++++++++++++ .../org/apache/spark/executor/package.scala | 24 ++++++++++++++++ .../org/apache/spark/io/package-info.java | 21 ++++++++++++++ .../scala/org/apache/spark/io/package.scala | 23 +++++++++++++++ .../apache/spark/metrics/sink/package.scala | 23 +++++++++++++++ .../apache/spark/metrics/source/package.scala | 23 +++++++++++++++ .../org/apache/spark/partial/package.scala | 28 +++++++++++++++++++ .../org/apache/spark/rdd/package-info.java | 21 ++++++++++++++ .../scala/org/apache/spark/rdd/package.scala | 23 +++++++++++++++ .../apache/spark/scheduler/package-info.java | 21 ++++++++++++++ .../org/apache/spark/scheduler/package.scala | 24 ++++++++++++++++ .../apache/spark/serializer/package-info.java | 21 ++++++++++++++ .../org/apache/spark/serializer/package.scala | 25 +++++++++++++++++ .../org/apache/spark/util/package-info.java | 21 ++++++++++++++ .../scala/org/apache/spark/util/package.scala | 23 +++++++++++++++ .../spark/util/random/package-info.java | 21 ++++++++++++++ .../apache/spark/util/random/package.scala | 23 +++++++++++++++ .../spark/streaming/flume/package-info.java | 21 ++++++++++++++ .../spark/streaming/flume/package.scala | 23 +++++++++++++++ .../spark/streaming/kafka/package-info.java | 21 ++++++++++++++ .../spark/streaming/kafka/package.scala | 23 +++++++++++++++ .../spark/streaming/mqtt/package-info.java | 21 ++++++++++++++ .../apache/spark/streaming/mqtt/package.scala | 23 +++++++++++++++ .../spark/streaming/twitter/package-info.java | 21 ++++++++++++++ .../spark/streaming/twitter/package.scala | 23 +++++++++++++++ .../spark/streaming/zeromq/package-info.java | 21 ++++++++++++++ .../spark/streaming/zeromq/package.scala | 23 +++++++++++++++ .../apache/spark/graphx/lib/package-info.java | 21 ++++++++++++++ .../org/apache/spark/graphx/lib/package.scala | 23 +++++++++++++++ .../org/apache/spark/graphx/package-info.java | 22 +++++++++++++++ .../spark/graphx/util/package-info.java | 21 ++++++++++++++ .../apache/spark/graphx/util/package.scala | 23 +++++++++++++++ .../spark/mllib/api/python/package.scala | 25 +++++++++++++++++ .../org/apache/spark/mllib/package-info.java | 21 ++++++++++++++ .../org/apache/spark/mllib/package.scala | 23 +++++++++++++++ .../org/apache/spark/sql/package-info.java | 21 ++++++++++++++ .../apache/spark/sql/hive/package-info.java | 18 ++++++++++++ .../org/apache/spark/sql/hive/package.scala | 20 +++++++++++++ .../streaming/api/java/package-info.java | 21 ++++++++++++++ .../spark/streaming/api/java/package.scala | 23 +++++++++++++++ .../spark/streaming/dstream/package-info.java | 21 ++++++++++++++ .../spark/streaming/dstream/package.scala | 24 ++++++++++++++++ 51 files changed, 1116 insertions(+), 1 deletion(-) create mode 100644 bagel/src/main/scala/org/apache/spark/bagel/package-info.java create mode 100644 bagel/src/main/scala/org/apache/spark/bagel/package.scala create mode 100644 core/src/main/java/org/apache/spark/api/java/function/package-info.java create mode 100644 core/src/main/java/org/apache/spark/api/java/function/package.scala create mode 100644 core/src/main/scala/org/apache/spark/annotation/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/annotation/package.scala create mode 100644 core/src/main/scala/org/apache/spark/api/java/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/broadcast/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/executor/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/executor/package.scala create mode 100644 core/src/main/scala/org/apache/spark/io/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/io/package.scala create mode 100644 core/src/main/scala/org/apache/spark/metrics/sink/package.scala create mode 100644 core/src/main/scala/org/apache/spark/metrics/source/package.scala create mode 100644 core/src/main/scala/org/apache/spark/partial/package.scala create mode 100644 core/src/main/scala/org/apache/spark/rdd/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/rdd/package.scala create mode 100644 core/src/main/scala/org/apache/spark/scheduler/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/scheduler/package.scala create mode 100644 core/src/main/scala/org/apache/spark/serializer/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/serializer/package.scala create mode 100644 core/src/main/scala/org/apache/spark/util/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/util/package.scala create mode 100644 core/src/main/scala/org/apache/spark/util/random/package-info.java create mode 100644 core/src/main/scala/org/apache/spark/util/random/package.scala create mode 100644 external/flume/src/main/scala/org/apache/spark/streaming/flume/package-info.java create mode 100644 external/flume/src/main/scala/org/apache/spark/streaming/flume/package.scala create mode 100644 external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package-info.java create mode 100644 external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package.scala create mode 100644 external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package-info.java create mode 100644 external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package.scala create mode 100644 external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package-info.java create mode 100644 external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package.scala create mode 100644 external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package-info.java create mode 100644 external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package.scala create mode 100644 graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java create mode 100644 graphx/src/main/scala/org/apache/spark/graphx/lib/package.scala create mode 100644 graphx/src/main/scala/org/apache/spark/graphx/package-info.java create mode 100644 graphx/src/main/scala/org/apache/spark/graphx/util/package-info.java create mode 100644 graphx/src/main/scala/org/apache/spark/graphx/util/package.scala create mode 100644 mllib/src/main/scala/org/apache/spark/mllib/api/python/package.scala create mode 100644 mllib/src/main/scala/org/apache/spark/mllib/package-info.java create mode 100644 mllib/src/main/scala/org/apache/spark/mllib/package.scala create mode 100644 sql/catalyst/src/main/scala/org/apache/spark/sql/package-info.java create mode 100644 sql/hive/src/main/scala/org/apache/spark/sql/hive/package-info.java create mode 100644 sql/hive/src/main/scala/org/apache/spark/sql/hive/package.scala create mode 100644 streaming/src/main/scala/org/apache/spark/streaming/api/java/package-info.java create mode 100644 streaming/src/main/scala/org/apache/spark/streaming/api/java/package.scala create mode 100644 streaming/src/main/scala/org/apache/spark/streaming/dstream/package-info.java create mode 100644 streaming/src/main/scala/org/apache/spark/streaming/dstream/package.scala diff --git a/bagel/src/main/scala/org/apache/spark/bagel/package-info.java b/bagel/src/main/scala/org/apache/spark/bagel/package-info.java new file mode 100644 index 0000000000000..81f26f276549f --- /dev/null +++ b/bagel/src/main/scala/org/apache/spark/bagel/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Bagel: An implementation of Pregel in Spark. THIS IS DEPRECATED - use Spark's GraphX library. + */ +package org.apache.spark.bagel; \ No newline at end of file diff --git a/bagel/src/main/scala/org/apache/spark/bagel/package.scala b/bagel/src/main/scala/org/apache/spark/bagel/package.scala new file mode 100644 index 0000000000000..2fb1934579781 --- /dev/null +++ b/bagel/src/main/scala/org/apache/spark/bagel/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Bagel: An implementation of Pregel in Spark. THIS IS DEPRECATED - use Spark's GraphX library. + */ +package object bagel diff --git a/core/src/main/java/org/apache/spark/api/java/function/package-info.java b/core/src/main/java/org/apache/spark/api/java/function/package-info.java new file mode 100644 index 0000000000000..463a42f23342c --- /dev/null +++ b/core/src/main/java/org/apache/spark/api/java/function/package-info.java @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Set of interfaces to represent functions in Spark's Java API. Users create implementations of + * these interfaces to pass functions to various Java API methods for Spark. Please visit Spark's + * Java programming guide for more details. + */ +package org.apache.spark.api.java.function; \ No newline at end of file diff --git a/core/src/main/java/org/apache/spark/api/java/function/package.scala b/core/src/main/java/org/apache/spark/api/java/function/package.scala new file mode 100644 index 0000000000000..7f91de653a64a --- /dev/null +++ b/core/src/main/java/org/apache/spark/api/java/function/package.scala @@ -0,0 +1,25 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.api.java + +/** + * Set of interfaces to represent functions in Spark's Java API. Users create implementations of + * these interfaces to pass functions to various Java API methods for Spark. Please visit Spark's + * Java programming guide for more details. + */ +package object function \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/annotation/package-info.java b/core/src/main/scala/org/apache/spark/annotation/package-info.java new file mode 100644 index 0000000000000..12c7afe6f108a --- /dev/null +++ b/core/src/main/scala/org/apache/spark/annotation/package-info.java @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark annotations to mark an API experimental or intended only for advanced usages by developers. + * This package consist of these annotations, which are used project wide and are reflected in + * Scala and Java docs. + */ +package org.apache.spark.annotation; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/annotation/package.scala b/core/src/main/scala/org/apache/spark/annotation/package.scala new file mode 100644 index 0000000000000..c3f4026a29d44 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/annotation/package.scala @@ -0,0 +1,25 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Spark annotations to mark an API experimental or intended only for advanced usages by developers. + * This package consist of these annotations, which are used project wide and are reflected in + * Scala and Java docs. + */ +package object annotation diff --git a/core/src/main/scala/org/apache/spark/api/java/package-info.java b/core/src/main/scala/org/apache/spark/api/java/package-info.java new file mode 100644 index 0000000000000..10a480fc78e44 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/api/java/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark Java programming APIs. + */ +package org.apache.spark.api.java; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/broadcast/package-info.java b/core/src/main/scala/org/apache/spark/broadcast/package-info.java new file mode 100644 index 0000000000000..1510e6e84c7a8 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/broadcast/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark's broadcast variables, used to broadcast immutable datasets to all nodes. + */ +package org.apache.spark.broadcast; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/broadcast/package.scala b/core/src/main/scala/org/apache/spark/broadcast/package.scala index 01bf88629a7dd..4f2c3c07161a3 100644 --- a/core/src/main/scala/org/apache/spark/broadcast/package.scala +++ b/core/src/main/scala/org/apache/spark/broadcast/package.scala @@ -18,7 +18,7 @@ package org.apache.spark /** - * Package for broadcast variables. See [[broadcast.Broadcast]] for details. + * Spark's broadcast variables, used to broadcast immutable datasets to all nodes. */ package object broadcast { // For package docs only diff --git a/core/src/main/scala/org/apache/spark/executor/package-info.java b/core/src/main/scala/org/apache/spark/executor/package-info.java new file mode 100644 index 0000000000000..dd3b6815fb45f --- /dev/null +++ b/core/src/main/scala/org/apache/spark/executor/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Package for executor components used with various cluster managers. + */ +package org.apache.spark.executor; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/executor/package.scala b/core/src/main/scala/org/apache/spark/executor/package.scala new file mode 100644 index 0000000000000..ef471d761d4b3 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/executor/package.scala @@ -0,0 +1,24 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Executor components used with various cluster managers. + * See [[org.apache.spark.executor.Executor]]. + */ +package object executor diff --git a/core/src/main/scala/org/apache/spark/io/package-info.java b/core/src/main/scala/org/apache/spark/io/package-info.java new file mode 100644 index 0000000000000..bea1bfdb63751 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/io/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * IO codecs used for compression. + */ +package org.apache.spark.io; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/io/package.scala b/core/src/main/scala/org/apache/spark/io/package.scala new file mode 100644 index 0000000000000..f987e66a5dc44 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/io/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * IO codecs used for compression. See [[org.apache.spark.io.CompressionCodec]]. + */ +package object io diff --git a/core/src/main/scala/org/apache/spark/metrics/sink/package.scala b/core/src/main/scala/org/apache/spark/metrics/sink/package.scala new file mode 100644 index 0000000000000..90e3aa70b99ef --- /dev/null +++ b/core/src/main/scala/org/apache/spark/metrics/sink/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.metrics + +/** + * Sinks used in Spark's metrics system. + */ +package object sink diff --git a/core/src/main/scala/org/apache/spark/metrics/source/package.scala b/core/src/main/scala/org/apache/spark/metrics/source/package.scala new file mode 100644 index 0000000000000..1e59fed6f7d7a --- /dev/null +++ b/core/src/main/scala/org/apache/spark/metrics/source/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.metrics + +/** + * Sources used in Spark's metrics system. + */ +package object source diff --git a/core/src/main/scala/org/apache/spark/partial/package.scala b/core/src/main/scala/org/apache/spark/partial/package.scala new file mode 100644 index 0000000000000..62dc5cd25a164 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/partial/package.scala @@ -0,0 +1,28 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * :: Experimental :: + * + * Support for approximate results. This provides convenient api and also implementation for + * approximate calculation. + * + * @see [[org.apache.spark.rdd.RDD.countApprox]] + */ +package object partial diff --git a/core/src/main/scala/org/apache/spark/rdd/package-info.java b/core/src/main/scala/org/apache/spark/rdd/package-info.java new file mode 100644 index 0000000000000..176cc58179fb0 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/rdd/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Provides implementation's of various RDDs. + */ +package org.apache.spark.rdd; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/rdd/package.scala b/core/src/main/scala/org/apache/spark/rdd/package.scala new file mode 100644 index 0000000000000..55fc6e4d2b4df --- /dev/null +++ b/core/src/main/scala/org/apache/spark/rdd/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Provides several RDD implementations. See [[org.apache.spark.rdd.RDD]]. + */ +package object rdd diff --git a/core/src/main/scala/org/apache/spark/scheduler/package-info.java b/core/src/main/scala/org/apache/spark/scheduler/package-info.java new file mode 100644 index 0000000000000..5b4a628d3cee4 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/scheduler/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark's DAG scheduler. + */ +package org.apache.spark.scheduler; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/scheduler/package.scala b/core/src/main/scala/org/apache/spark/scheduler/package.scala new file mode 100644 index 0000000000000..f0dbfc2ac5f48 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/scheduler/package.scala @@ -0,0 +1,24 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Spark's scheduling components. This includes the [[org.apache.spark.scheduler.DAGScheduler]] and + * lower level [[org.apache.spark.scheduler.TaskScheduler]]. + */ +package object scheduler diff --git a/core/src/main/scala/org/apache/spark/serializer/package-info.java b/core/src/main/scala/org/apache/spark/serializer/package-info.java new file mode 100644 index 0000000000000..4c0b73ab36a00 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/serializer/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Pluggable serializers for RDD and shuffle data. + */ +package org.apache.spark.serializer; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/serializer/package.scala b/core/src/main/scala/org/apache/spark/serializer/package.scala new file mode 100644 index 0000000000000..8f09ef6f5b34c --- /dev/null +++ b/core/src/main/scala/org/apache/spark/serializer/package.scala @@ -0,0 +1,25 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Pluggable serializers for RDD and shuffle data. + * + * @see [[org.apache.spark.serializer.Serializer]] + */ +package object serializer diff --git a/core/src/main/scala/org/apache/spark/util/package-info.java b/core/src/main/scala/org/apache/spark/util/package-info.java new file mode 100644 index 0000000000000..819f54ee41a79 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/util/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark utilities. + */ +package org.apache.spark.util; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/util/package.scala b/core/src/main/scala/org/apache/spark/util/package.scala new file mode 100644 index 0000000000000..c7099b85d225f --- /dev/null +++ b/core/src/main/scala/org/apache/spark/util/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Spark utilities. + */ +package object util diff --git a/core/src/main/scala/org/apache/spark/util/random/package-info.java b/core/src/main/scala/org/apache/spark/util/random/package-info.java new file mode 100644 index 0000000000000..62c3762dd11b6 --- /dev/null +++ b/core/src/main/scala/org/apache/spark/util/random/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Utilities for random number generation. + */ +package org.apache.spark.util.random; \ No newline at end of file diff --git a/core/src/main/scala/org/apache/spark/util/random/package.scala b/core/src/main/scala/org/apache/spark/util/random/package.scala new file mode 100644 index 0000000000000..f361125fe2e8a --- /dev/null +++ b/core/src/main/scala/org/apache/spark/util/random/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.util + +/** + * Utilities for random number generation. + */ +package object random diff --git a/external/flume/src/main/scala/org/apache/spark/streaming/flume/package-info.java b/external/flume/src/main/scala/org/apache/spark/streaming/flume/package-info.java new file mode 100644 index 0000000000000..d31aa5f5c096c --- /dev/null +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark streaming receiver for Flume. + */ +package org.apache.spark.streaming.flume; \ No newline at end of file diff --git a/external/flume/src/main/scala/org/apache/spark/streaming/flume/package.scala b/external/flume/src/main/scala/org/apache/spark/streaming/flume/package.scala new file mode 100644 index 0000000000000..9bfab68c4b8b7 --- /dev/null +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * Spark streaming receiver for Flume. + */ +package object flume diff --git a/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package-info.java b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package-info.java new file mode 100644 index 0000000000000..947bae115a620 --- /dev/null +++ b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Kafka receiver for spark streaming. + */ +package org.apache.spark.streaming.kafka; \ No newline at end of file diff --git a/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package.scala b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package.scala new file mode 100644 index 0000000000000..47c5187f8751f --- /dev/null +++ b/external/kafka/src/main/scala/org/apache/spark/streaming/kafka/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * Kafka receiver for spark streaming, + */ +package object kafka diff --git a/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package-info.java b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package-info.java new file mode 100644 index 0000000000000..728e0d8663d01 --- /dev/null +++ b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * MQTT receiver for Spark Streaming. + */ +package org.apache.spark.streaming.mqtt; \ No newline at end of file diff --git a/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package.scala b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package.scala new file mode 100644 index 0000000000000..63d0d138183a9 --- /dev/null +++ b/external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * MQTT receiver for Spark Streaming. + */ +package object mqtt diff --git a/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package-info.java b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package-info.java new file mode 100644 index 0000000000000..258c0950a0aa7 --- /dev/null +++ b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Twitter feed receiver for spark streaming. + */ +package org.apache.spark.streaming.twitter; \ No newline at end of file diff --git a/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package.scala b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package.scala new file mode 100644 index 0000000000000..580e37fa8f814 --- /dev/null +++ b/external/twitter/src/main/scala/org/apache/spark/streaming/twitter/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * Twitter feed receiver for spark streaming. + */ +package object twitter diff --git a/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package-info.java b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package-info.java new file mode 100644 index 0000000000000..587c524e2120f --- /dev/null +++ b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Zeromq receiver for spark streaming. + */ +package org.apache.spark.streaming.zeromq; \ No newline at end of file diff --git a/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package.scala b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package.scala new file mode 100644 index 0000000000000..65e6e57f2c05d --- /dev/null +++ b/external/zeromq/src/main/scala/org/apache/spark/streaming/zeromq/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * Zeromq receiver for spark streaming. + */ +package object zeromq diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java b/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java new file mode 100644 index 0000000000000..49ad7263141ce --- /dev/null +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Internal support for MLLib Python API. + */ +package org.apache.spark.graphx.lib; \ No newline at end of file diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/package.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/package.scala new file mode 100644 index 0000000000000..7cfd617a32a34 --- /dev/null +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.graphx + +/** + * Various analytics functions for graphs. + */ +package object lib diff --git a/graphx/src/main/scala/org/apache/spark/graphx/package-info.java b/graphx/src/main/scala/org/apache/spark/graphx/package-info.java new file mode 100644 index 0000000000000..f659cc518ebd3 --- /dev/null +++ b/graphx/src/main/scala/org/apache/spark/graphx/package-info.java @@ -0,0 +1,22 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * ALPHA COMPONENT + * GraphX is a graph processing framework built on top of Spark. + */ +package org.apache.spark.graphx; \ No newline at end of file diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/package-info.java b/graphx/src/main/scala/org/apache/spark/graphx/util/package-info.java new file mode 100644 index 0000000000000..90cd1d46db177 --- /dev/null +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Collections of utilities used by graphx. + */ +package org.apache.spark.graphx.util; \ No newline at end of file diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/package.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/package.scala new file mode 100644 index 0000000000000..2303541d2e427 --- /dev/null +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.graphx + +/** + * Collections of utilities used by graphx. + */ +package object util diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/package.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/package.scala new file mode 100644 index 0000000000000..87bdc8558aaf5 --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/package.scala @@ -0,0 +1,25 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.mllib.api + +/** + * Internal support for MLLib Python API. + * + * @see [[org.apache.spark.mllib.api.python.PythonMLLibAPI]] + */ +package object python diff --git a/mllib/src/main/scala/org/apache/spark/mllib/package-info.java b/mllib/src/main/scala/org/apache/spark/mllib/package-info.java new file mode 100644 index 0000000000000..4991bc9e972c0 --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Spark's machine learning library. + */ +package org.apache.spark.mllib; \ No newline at end of file diff --git a/mllib/src/main/scala/org/apache/spark/mllib/package.scala b/mllib/src/main/scala/org/apache/spark/mllib/package.scala new file mode 100644 index 0000000000000..5c2b2160c030e --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark + +/** + * Spark's machine learning library. + */ +package object mllib diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/package-info.java b/sql/catalyst/src/main/scala/org/apache/spark/sql/package-info.java new file mode 100644 index 0000000000000..53603614518f5 --- /dev/null +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Allows the execution of relational queries, including those expressed in SQL using Spark. + */ +package org.apache.spark.sql; \ No newline at end of file diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/package-info.java b/sql/hive/src/main/scala/org/apache/spark/sql/hive/package-info.java new file mode 100644 index 0000000000000..8b29fa7d1a8f7 --- /dev/null +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/package-info.java @@ -0,0 +1,18 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.hive; \ No newline at end of file diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/package.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/package.scala new file mode 100644 index 0000000000000..a6c8ed4f7e866 --- /dev/null +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/package.scala @@ -0,0 +1,20 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql + +package object hive diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/package-info.java b/streaming/src/main/scala/org/apache/spark/streaming/api/java/package-info.java new file mode 100644 index 0000000000000..d43d949d76bb3 --- /dev/null +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Java APIs for spark streaming. + */ +package org.apache.spark.streaming.api.java; \ No newline at end of file diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/package.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/package.scala new file mode 100644 index 0000000000000..2479670f2a5bb --- /dev/null +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/package.scala @@ -0,0 +1,23 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.api + +/** + * Spark streaming's Java API. + */ +package object java diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/package-info.java b/streaming/src/main/scala/org/apache/spark/streaming/dstream/package-info.java new file mode 100644 index 0000000000000..05ca2ddffd3c0 --- /dev/null +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/package-info.java @@ -0,0 +1,21 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Various implementations of DStreams. + */ +package org.apache.spark.streaming.dstream; \ No newline at end of file diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/package.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/package.scala new file mode 100644 index 0000000000000..0179b92503e5d --- /dev/null +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/package.scala @@ -0,0 +1,24 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming + +/** + * Various implementations of DStream's. + * @see [[org.apache.spark.streaming.dstream.DStream]] + */ +package object dstream From bae07e36a6e0fb7982405316646b452b4ff06acc Mon Sep 17 00:00:00 2001 From: witgo Date: Wed, 14 May 2014 22:26:26 -0700 Subject: [PATCH 52/99] fix different versions of commons-lang dependency and apache/spark#746 addendum Author: witgo Closes #754 from witgo/commons-lang and squashes the following commits: 3ebab31 [witgo] merge master f3b8fa2 [witgo] merge master 2083fae [witgo] repeat definition 5599cdb [witgo] multiple version of sbt dependency c1b66a1 [witgo] fix different versions of commons-lang dependency --- project/SparkBuild.scala | 12 +++++++----- sql/hive/pom.xml | 8 ++++++++ 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 6adec556322ba..29dcd8678b476 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -318,6 +318,8 @@ object SparkBuild extends Build { val excludeFastutil = ExclusionRule(organization = "it.unimi.dsi") val excludeJruby = ExclusionRule(organization = "org.jruby") val excludeThrift = ExclusionRule(organization = "org.apache.thrift") + val excludeCommonsLang = ExclusionRule(organization = "commons-lang") + val excludeServletApi = ExclusionRule(organization = "javax.servlet", artifact = "servlet-api") def sparkPreviousArtifact(id: String, organization: String = "org.apache.spark", version: String = "0.9.0-incubating", crossVersion: String = "2.10"): Option[sbt.ModuleID] = { @@ -491,7 +493,7 @@ object SparkBuild extends Build { javaOptions += "-XX:MaxPermSize=1g", libraryDependencies ++= Seq( "org.spark-project.hive" % "hive-metastore" % hiveVersion, - "org.spark-project.hive" % "hive-exec" % hiveVersion, + "org.spark-project.hive" % "hive-exec" % hiveVersion excludeAll(excludeCommonsLang, excludeCommonsLogging), "org.spark-project.hive" % "hive-serde" % hiveVersion ), // Multiple queries rely on the TestHive singleton. See comments there for more details. @@ -564,10 +566,10 @@ object SparkBuild extends Build { libraryDependencies ++= Seq( // Exclude rule required for all ? "org.apache.hadoop" % hadoopClient % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm), - "org.apache.hadoop" % "hadoop-yarn-api" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm), - "org.apache.hadoop" % "hadoop-yarn-common" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm), - "org.apache.hadoop" % "hadoop-yarn-client" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm), - "org.apache.hadoop" % "hadoop-yarn-server-web-proxy" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm) + "org.apache.hadoop" % "hadoop-yarn-api" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm, excludeCommonsLogging), + "org.apache.hadoop" % "hadoop-yarn-common" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm, excludeCommonsLogging), + "org.apache.hadoop" % "hadoop-yarn-client" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm, excludeCommonsLogging), + "org.apache.hadoop" % "hadoop-yarn-server-web-proxy" % hadoopVersion excludeAll(excludeJBossNetty, excludeAsm, excludeOldAsm, excludeCommonsLogging, excludeServletApi) ) ) diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml index 9254b70e64a08..4d0b2fa1452a2 100644 --- a/sql/hive/pom.xml +++ b/sql/hive/pom.xml @@ -57,6 +57,10 @@ commons-logging commons-logging + + commons-lang + commons-lang + @@ -76,6 +80,10 @@ commons-logging commons-logging-api + + commons-lang + commons-lang + From 514157f2e4c341378f4a606b66562f39fe3eba5e Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Wed, 14 May 2014 23:48:03 -0700 Subject: [PATCH 53/99] HOTFIX: Don't build Javadoc in Maven when creating releases. Because we've added java package descriptions in some packages that don't have any Java files, running the Javadoc target hits this issue: http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4492654 To fix this I've simply removed the javadoc target when publishing releases. --- dev/create-release/create-release.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/dev/create-release/create-release.sh b/dev/create-release/create-release.sh index c4e74990860b6..c96afe822c6a9 100755 --- a/dev/create-release/create-release.sh +++ b/dev/create-release/create-release.sh @@ -49,16 +49,18 @@ if [[ ! "$@" =~ --package-only ]]; then mvn -Pyarn release:clean mvn -DskipTests \ - -Darguments="-DskipTests=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ + -Darguments="-DskipTests=true -Dmaven.javadoc.skip=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ -Dusername=$GIT_USERNAME -Dpassword=$GIT_PASSWORD \ + -Dmaven.javadoc.skip=true \ -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 \ -Pyarn -Phive -Phadoop-2.2 -Pspark-ganglia-lgpl\ -Dtag=$GIT_TAG -DautoVersionSubmodules=true \ --batch-mode release:prepare mvn -DskipTests \ - -Darguments="-DskipTests=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ + -Darguments="-DskipTests=true -Dmaven.javadoc.skip=true -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -Dgpg.passphrase=${GPG_PASSPHRASE}" \ -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 \ + -Dmaven.javadoc.skip=true \ -Pyarn -Phive -Phadoop-2.2 -Pspark-ganglia-lgpl\ release:perform From 3abe2b734a5578966f671c34f1de34b4446b90f1 Mon Sep 17 00:00:00 2001 From: Andrew Ash Date: Thu, 15 May 2014 11:05:39 -0700 Subject: [PATCH 54/99] SPARK-1846 Ignore logs directory in RAT checks https://issues.apache.org/jira/browse/SPARK-1846 Author: Andrew Ash Closes #793 from ash211/SPARK-1846 and squashes the following commits: 3f50db5 [Andrew Ash] SPARK-1846 Ignore logs directory in RAT checks --- .rat-excludes | 1 + 1 file changed, 1 insertion(+) diff --git a/.rat-excludes b/.rat-excludes index 689467847d80d..15589702c5599 100644 --- a/.rat-excludes +++ b/.rat-excludes @@ -48,3 +48,4 @@ dist/* .*out .*ipr .*iws +logs From db8cc6f28abe4326cea6f53feb604920e4867a27 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Thu, 15 May 2014 11:20:21 -0700 Subject: [PATCH 55/99] [SPARK-1845] [SQL] Use AllScalaRegistrar for SparkSqlSerializer to register serializers of ... ...Scala collections. When I execute `orderBy` or `limit` for `SchemaRDD` including `ArrayType` or `MapType`, `SparkSqlSerializer` throws the following exception: ``` com.esotericsoftware.kryo.KryoException: Class cannot be created (missing no-arg constructor): scala.collection.immutable.$colon$colon ``` or ``` com.esotericsoftware.kryo.KryoException: Class cannot be created (missing no-arg constructor): scala.collection.immutable.Vector ``` or ``` com.esotericsoftware.kryo.KryoException: Class cannot be created (missing no-arg constructor): scala.collection.immutable.HashMap$HashTrieMap ``` and so on. This is because registrations of serializers for each concrete collections are missing in `SparkSqlSerializer`. I believe it should use `AllScalaRegistrar`. `AllScalaRegistrar` covers a lot of serializers for concrete classes of `Seq`, `Map` for `ArrayType`, `MapType`. Author: Takuya UESHIN Closes #790 from ueshin/issues/SPARK-1845 and squashes the following commits: d1ed992 [Takuya UESHIN] Use AllScalaRegistrar for SparkSqlSerializer to register serializers of Scala collections. --- .../sql/execution/SparkSqlSerializer.scala | 28 ++--------------- .../org/apache/spark/sql/DslQuerySuite.scala | 24 +++++++++++++++ .../org/apache/spark/sql/SQLQuerySuite.scala | 30 +++++++++++++++++++ .../scala/org/apache/spark/sql/TestData.scala | 10 +++++++ 4 files changed, 66 insertions(+), 26 deletions(-) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala index 94c2a249ef8f8..34b355e906695 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlSerializer.scala @@ -24,6 +24,7 @@ import scala.reflect.ClassTag import com.clearspring.analytics.stream.cardinality.HyperLogLog import com.esotericsoftware.kryo.io.{Input, Output} import com.esotericsoftware.kryo.{Serializer, Kryo} +import com.twitter.chill.AllScalaRegistrar import org.apache.spark.{SparkEnv, SparkConf} import org.apache.spark.serializer.KryoSerializer @@ -35,22 +36,14 @@ private[sql] class SparkSqlSerializer(conf: SparkConf) extends KryoSerializer(co val kryo = new Kryo() kryo.setRegistrationRequired(false) kryo.register(classOf[MutablePair[_, _]]) - kryo.register(classOf[Array[Any]]) - // This is kinda hacky... - kryo.register(classOf[scala.collection.immutable.Map$Map1], new MapSerializer) - kryo.register(classOf[scala.collection.immutable.Map$Map2], new MapSerializer) - kryo.register(classOf[scala.collection.immutable.Map$Map3], new MapSerializer) - kryo.register(classOf[scala.collection.immutable.Map$Map4], new MapSerializer) - kryo.register(classOf[scala.collection.immutable.Map[_,_]], new MapSerializer) - kryo.register(classOf[scala.collection.Map[_,_]], new MapSerializer) kryo.register(classOf[org.apache.spark.sql.catalyst.expressions.GenericRow]) kryo.register(classOf[org.apache.spark.sql.catalyst.expressions.GenericMutableRow]) kryo.register(classOf[com.clearspring.analytics.stream.cardinality.HyperLogLog], new HyperLogLogSerializer) - kryo.register(classOf[scala.collection.mutable.ArrayBuffer[_]]) kryo.register(classOf[scala.math.BigDecimal], new BigDecimalSerializer) kryo.setReferences(false) kryo.setClassLoader(Utils.getSparkClassLoader) + new AllScalaRegistrar().apply(kryo) kryo } } @@ -97,20 +90,3 @@ private[sql] class HyperLogLogSerializer extends Serializer[HyperLogLog] { HyperLogLog.Builder.build(bytes) } } - -/** - * Maps do not have a no arg constructor and so cannot be serialized by default. So, we serialize - * them as `Array[(k,v)]`. - */ -private[sql] class MapSerializer extends Serializer[Map[_,_]] { - def write(kryo: Kryo, output: Output, map: Map[_,_]) { - kryo.writeObject(output, map.flatMap(e => Seq(e._1, e._2)).toArray) - } - - def read(kryo: Kryo, input: Input, tpe: Class[Map[_,_]]): Map[_,_] = { - kryo.readObject(input, classOf[Array[Any]]) - .sliding(2,2) - .map { case Array(k,v) => (k,v) } - .toMap - } -} diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala index 92a707ea57504..f43e98d614094 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DslQuerySuite.scala @@ -69,12 +69,36 @@ class DslQuerySuite extends QueryTest { checkAnswer( testData2.orderBy('a.desc, 'b.asc), Seq((3,1), (3,2), (2,1), (2,2), (1,1), (1,2))) + + checkAnswer( + arrayData.orderBy(GetItem('data, 0).asc), + arrayData.collect().sortBy(_.data(0)).toSeq) + + checkAnswer( + arrayData.orderBy(GetItem('data, 0).desc), + arrayData.collect().sortBy(_.data(0)).reverse.toSeq) + + checkAnswer( + mapData.orderBy(GetItem('data, 1).asc), + mapData.collect().sortBy(_.data(1)).toSeq) + + checkAnswer( + mapData.orderBy(GetItem('data, 1).desc), + mapData.collect().sortBy(_.data(1)).reverse.toSeq) } test("limit") { checkAnswer( testData.limit(10), testData.take(10).toSeq) + + checkAnswer( + arrayData.limit(1), + arrayData.take(1).toSeq) + + checkAnswer( + mapData.limit(1), + mapData.take(1).toSeq) } test("average") { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index 524549eb544fc..189dccd5253e5 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -85,6 +85,36 @@ class SQLQuerySuite extends QueryTest { checkAnswer( sql("SELECT * FROM testData2 ORDER BY a DESC, b ASC"), Seq((3,1), (3,2), (2,1), (2,2), (1,1), (1,2))) + + checkAnswer( + sql("SELECT * FROM arrayData ORDER BY data[0] ASC"), + arrayData.collect().sortBy(_.data(0)).toSeq) + + checkAnswer( + sql("SELECT * FROM arrayData ORDER BY data[0] DESC"), + arrayData.collect().sortBy(_.data(0)).reverse.toSeq) + + checkAnswer( + sql("SELECT * FROM mapData ORDER BY data[1] ASC"), + mapData.collect().sortBy(_.data(1)).toSeq) + + checkAnswer( + sql("SELECT * FROM mapData ORDER BY data[1] DESC"), + mapData.collect().sortBy(_.data(1)).reverse.toSeq) + } + + test("limit") { + checkAnswer( + sql("SELECT * FROM testData LIMIT 10"), + testData.take(10).toSeq) + + checkAnswer( + sql("SELECT * FROM arrayData LIMIT 1"), + arrayData.collect().take(1).toSeq) + + checkAnswer( + sql("SELECT * FROM mapData LIMIT 1"), + mapData.collect().take(1).toSeq) } test("average") { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/TestData.scala b/sql/core/src/test/scala/org/apache/spark/sql/TestData.scala index aa71e274f7f4b..1aca3872524d7 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/TestData.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/TestData.scala @@ -74,6 +74,16 @@ object TestData { ArrayData(Seq(2,3,4), Seq(Seq(2,3,4))) :: Nil) arrayData.registerAsTable("arrayData") + case class MapData(data: Map[Int, String]) + val mapData = + TestSQLContext.sparkContext.parallelize( + MapData(Map(1 -> "a1", 2 -> "b1", 3 -> "c1", 4 -> "d1", 5 -> "e1")) :: + MapData(Map(1 -> "a2", 2 -> "b2", 3 -> "c2", 4 -> "d2")) :: + MapData(Map(1 -> "a3", 2 -> "b3", 3 -> "c3")) :: + MapData(Map(1 -> "a4", 2 -> "b4")) :: + MapData(Map(1 -> "a5")) :: Nil) + mapData.registerAsTable("mapData") + case class StringData(s: String) val repeatedData = TestSQLContext.sparkContext.parallelize(List.fill(2)(StringData("test"))) From 94c9d6f59859ebc77fae112c2c42c64b7a4d7f83 Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Thu, 15 May 2014 11:21:33 -0700 Subject: [PATCH 56/99] [SPARK-1819] [SQL] Fix GetField.nullable. `GetField.nullable` should be `true` not only when `field.nullable` is `true` but also when `child.nullable` is `true`. Author: Takuya UESHIN Closes #757 from ueshin/issues/SPARK-1819 and squashes the following commits: 8781a11 [Takuya UESHIN] Modify a test to use named parameters. 5bfc77d [Takuya UESHIN] Fix GetField.nullable. --- .../sql/catalyst/expressions/complexTypes.scala | 2 +- .../expressions/ExpressionEvaluationSuite.scala | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala index 195ca2eb3d589..b6aeae92f8bec 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypes.scala @@ -74,7 +74,7 @@ case class GetField(child: Expression, fieldName: String) extends UnaryExpressio type EvaluatedType = Any def dataType = field.dataType - override def nullable = field.nullable + override def nullable = child.nullable || field.nullable override def foldable = child.foldable protected def structType = child.dataType match { diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala index 344d8a304fc11..1132a30b42767 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionEvaluationSuite.scala @@ -364,6 +364,19 @@ class ExpressionEvaluationSuite extends FunSuite { checkEvaluation(GetField(BoundReference(2, AttributeReference("c", typeS)()), "a"), "aa", row) checkEvaluation(GetField(Literal(null, typeS), "a"), null, row) + + val typeS_notNullable = StructType( + StructField("a", StringType, nullable = false) + :: StructField("b", StringType, nullable = false) :: Nil + ) + + assert(GetField(BoundReference(2, + AttributeReference("c", typeS)()), "a").nullable === true) + assert(GetField(BoundReference(2, + AttributeReference("c", typeS_notNullable, nullable = false)()), "a").nullable === false) + + assert(GetField(Literal(null, typeS), "a").nullable === true) + assert(GetField(Literal(null, typeS_notNullable), "a").nullable === true) } test("arithmetic") { From d52761d67f42ad4d2ff02d96f0675fb3ab709f38 Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Thu, 15 May 2014 11:59:59 -0700 Subject: [PATCH 57/99] [SPARK-1741][MLLIB] add predict(JavaRDD) to RegressionModel, ClassificationModel, and KMeans `model.predict` returns a RDD of Scala primitive type (Int/Double), which is recognized as Object in Java. Adding predict(JavaRDD) could make life easier for Java users. Added tests for KMeans, LinearRegression, and NaiveBayes. Will update examples after https://github.com/apache/spark/pull/653 gets merged. cc: @srowen Author: Xiangrui Meng Closes #670 from mengxr/predict-javardd and squashes the following commits: b77ccd8 [Xiangrui Meng] Merge branch 'master' into predict-javardd 43caac9 [Xiangrui Meng] add predict(JavaRDD) to RegressionModel, ClassificationModel, and KMeans --- .../classification/ClassificationModel.scala | 11 +++++++++- .../spark/mllib/clustering/KMeansModel.scala | 5 +++++ .../mllib/regression/RegressionModel.scala | 11 +++++++++- .../classification/JavaNaiveBayesSuite.java | 16 ++++++++++++++ .../mllib/clustering/JavaKMeansSuite.java | 14 +++++++++++++ .../regression/JavaLinearRegressionSuite.java | 21 +++++++++++++++++++ 6 files changed, 76 insertions(+), 2 deletions(-) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/ClassificationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/ClassificationModel.scala index 6332301e30cbd..b7a1d90d24d72 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/ClassificationModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/ClassificationModel.scala @@ -17,9 +17,10 @@ package org.apache.spark.mllib.classification +import org.apache.spark.annotation.Experimental +import org.apache.spark.api.java.JavaRDD import org.apache.spark.mllib.linalg.Vector import org.apache.spark.rdd.RDD -import org.apache.spark.annotation.Experimental /** * :: Experimental :: @@ -43,4 +44,12 @@ trait ClassificationModel extends Serializable { * @return predicted category from the trained model */ def predict(testData: Vector): Double + + /** + * Predict values for examples stored in a JavaRDD. + * @param testData JavaRDD representing data points to be predicted + * @return a JavaRDD[java.lang.Double] where each entry contains the corresponding prediction + */ + def predict(testData: JavaRDD[Vector]): JavaRDD[java.lang.Double] = + predict(testData.rdd).toJavaRDD().asInstanceOf[JavaRDD[java.lang.Double]] } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala index ce14b06241932..fba21aefaaacd 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansModel.scala @@ -17,6 +17,7 @@ package org.apache.spark.mllib.clustering +import org.apache.spark.api.java.JavaRDD import org.apache.spark.rdd.RDD import org.apache.spark.SparkContext._ import org.apache.spark.mllib.linalg.Vector @@ -40,6 +41,10 @@ class KMeansModel private[mllib] (val clusterCenters: Array[Vector]) extends Ser points.map(p => KMeans.findClosest(centersWithNorm, new BreezeVectorWithNorm(p))._1) } + /** Maps given points to their cluster indices. */ + def predict(points: JavaRDD[Vector]): JavaRDD[java.lang.Integer] = + predict(points.rdd).toJavaRDD().asInstanceOf[JavaRDD[java.lang.Integer]] + /** * Return the K-means cost (sum of squared distances of points to their nearest center) for this * model on the given data. diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala index b27e158b43f9a..64b02f7a6e7a9 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala @@ -17,9 +17,10 @@ package org.apache.spark.mllib.regression +import org.apache.spark.annotation.Experimental +import org.apache.spark.api.java.JavaRDD import org.apache.spark.rdd.RDD import org.apache.spark.mllib.linalg.Vector -import org.apache.spark.annotation.Experimental @Experimental trait RegressionModel extends Serializable { @@ -38,4 +39,12 @@ trait RegressionModel extends Serializable { * @return Double prediction from the trained model */ def predict(testData: Vector): Double + + /** + * Predict values for examples stored in a JavaRDD. + * @param testData JavaRDD representing data points to be predicted + * @return a JavaRDD[java.lang.Double] where each entry contains the corresponding prediction + */ + def predict(testData: JavaRDD[Vector]): JavaRDD[java.lang.Double] = + predict(testData.rdd).toJavaRDD().asInstanceOf[JavaRDD[java.lang.Double]] } diff --git a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java index c80b1134ed1b2..743a43a139c0c 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/classification/JavaNaiveBayesSuite.java @@ -19,6 +19,8 @@ import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.mllib.linalg.Vector; import org.apache.spark.mllib.linalg.Vectors; import org.apache.spark.mllib.regression.LabeledPoint; import org.junit.After; @@ -87,4 +89,18 @@ public void runUsingStaticMethods() { int numAccurate2 = validatePrediction(POINTS, model2); Assert.assertEquals(POINTS.size(), numAccurate2); } + + @Test + public void testPredictJavaRDD() { + JavaRDD examples = sc.parallelize(POINTS, 2).cache(); + NaiveBayesModel model = NaiveBayes.train(examples.rdd()); + JavaRDD vectors = examples.map(new Function() { + @Override + public Vector call(LabeledPoint v) throws Exception { + return v.features(); + }}); + JavaRDD predictions = model.predict(vectors); + // Should be able to get the first prediction. + predictions.first(); + } } diff --git a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java index 49a614bd90cab..0c916ca378034 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/clustering/JavaKMeansSuite.java @@ -88,4 +88,18 @@ public void runKMeansUsingConstructor() { .run(data.rdd()); assertEquals(expectedCenter, model.clusterCenters()[0]); } + + @Test + public void testPredictJavaRDD() { + List points = Lists.newArrayList( + Vectors.dense(1.0, 2.0, 6.0), + Vectors.dense(1.0, 3.0, 0.0), + Vectors.dense(1.0, 4.0, 6.0) + ); + JavaRDD data = sc.parallelize(points, 2); + KMeansModel model = new KMeans().setK(1).setMaxIterations(5).run(data.rdd()); + JavaRDD predictions = model.predict(data); + // Should be able to get the first prediction. + predictions.first(); + } } diff --git a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLinearRegressionSuite.java b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLinearRegressionSuite.java index 7151e553512b3..6dc6877691036 100644 --- a/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLinearRegressionSuite.java +++ b/mllib/src/test/java/org/apache/spark/mllib/regression/JavaLinearRegressionSuite.java @@ -25,8 +25,10 @@ import org.junit.Before; import org.junit.Test; +import org.apache.spark.api.java.function.Function; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.mllib.linalg.Vector; import org.apache.spark.mllib.util.LinearDataGenerator; public class JavaLinearRegressionSuite implements Serializable { @@ -92,4 +94,23 @@ public void runLinearRegressionUsingStaticMethods() { Assert.assertTrue(numAccurate > nPoints * 4.0 / 5.0); } + @Test + public void testPredictJavaRDD() { + int nPoints = 100; + double A = 0.0; + double[] weights = {10, 10}; + JavaRDD testRDD = sc.parallelize( + LinearDataGenerator.generateLinearInputAsList(A, weights, nPoints, 42, 0.1), 2).cache(); + LinearRegressionWithSGD linSGDImpl = new LinearRegressionWithSGD(); + LinearRegressionModel model = linSGDImpl.run(testRDD.rdd()); + JavaRDD vectors = testRDD.map(new Function() { + @Override + public Vector call(LabeledPoint v) throws Exception { + return v.features(); + } + }); + JavaRDD predictions = model.predict(vectors); + // Should be able to get the first prediction. + predictions.first(); + } } From 08e7606a964e3d1ac1d565f33651ff0035c75044 Mon Sep 17 00:00:00 2001 From: Sandy Ryza Date: Thu, 15 May 2014 16:35:39 -0700 Subject: [PATCH 58/99] SPARK-1851. Upgrade Avro dependency to 1.7.6 so Spark can read Avro file... ...s Author: Sandy Ryza Closes #795 from sryza/sandy-spark-1851 and squashes the following commits: 79c8227 [Sandy Ryza] SPARK-1851. Upgrade Avro dependency to 1.7.6 so Spark can read Avro files --- pom.xml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pom.xml b/pom.xml index 786b6d4984d86..5df7036585b75 100644 --- a/pom.xml +++ b/pom.xml @@ -129,7 +129,7 @@ 8.1.14.v20131031 0.3.6 3.0.0 - 1.7.4 + 1.7.6 0.7.1 64m From e66e31be51f396c8f6b7a45119b8b31c4d8cdf79 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stevo=20Slavi=C4=87?= Date: Thu, 15 May 2014 16:44:14 -0700 Subject: [PATCH 59/99] SPARK-1803 Replaced colon in filenames with a dash MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch replaces colon in several filenames with dash to make these filenames Windows compatible. Author: Stevo Slavić Author: Stevo Slavic Closes #739 from sslavic/SPARK-1803 and squashes the following commits: 3ec66eb [Stevo Slavic] Removed extra empty line which was causing test to fail b967cc3 [Stevo Slavić] Aligned tests and names of test resources 2b12776 [Stevo Slavić] Fixed a typo in file name 1c5dfff [Stevo Slavić] Replaced colon in file name with dash 8f5bf7f [Stevo Slavić] Replaced colon in file name with dash c5b5083 [Stevo Slavić] Replaced colon in file name with dash a49801f [Stevo Slavić] Replaced colon in file name with dash 401d99e [Stevo Slavić] Replaced colon in file name with dash 40a9621 [Stevo Slavić] Replaced colon in file name with dash 4774580 [Stevo Slavić] Replaced colon in file name with dash 004f8bb [Stevo Slavić] Replaced colon in file name with dash d6a3e2c [Stevo Slavić] Replaced colon in file name with dash b585126 [Stevo Slavić] Replaced colon in file name with dash 028e48a [Stevo Slavić] Replaced colon in file name with dash ece0507 [Stevo Slavić] Replaced colon in file name with dash 84f5d2f [Stevo Slavić] Replaced colon in file name with dash 2fc7854 [Stevo Slavić] Replaced colon in file name with dash 9e1467d [Stevo Slavić] Replaced colon in file name with dash --- ...y test-0-cb0737d268260da971487a8ac5e3d8be} | 0 ...y test-0-c89dcddb8539bae211ea28cd1e695e35} | 0 ...y test-0-9589ac54d6de575083765ee64051ebaa} | 0 ...y test-0-d6d2726928df920ab99078015b8ff494} | 0 ...ry test-0-cfe78c68302bd143d989c383c3b0477} | 0 ...y test-0-358525951e893ed9686c46bf1f7447ee} | 0 ...y test-0-d9d50146537344742300ce7b52c18c91} | 0 ...y test-0-c25cdafe7d85c42a9d9cd559d88a6049} | 0 ...y test-0-63ab78355dbc6fa0d7619c8a35b0f7a7} | 0 ...y test-0-3adc3a7f76b2abd059904ba81a595db3} | 0 ...y test-0-681332efaff7b12e3ca12d9f021cd344} | 0 ...y test-0-3893ec7a86062215d9f817f1495a69bb} | 0 ...y test-0-75148567b91227053f728d72f7dc7c10} | 0 ...y test-0-4e4d2651e1e6e3c224242078d0201190} | 0 ...y test-0-b6e59464383591f02408f8765ac6a5d5} | 0 .../sql/hive/execution/PruningSuite.scala | 30 +++++++++---------- 16 files changed, 15 insertions(+), 15 deletions(-) rename sql/hive/src/test/resources/golden/{Column pruning: filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be => Column pruning - filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35 => Column pruning - non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa => Column pruning - projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494 => Column pruning - simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477 => Column pruning - with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee => Column pruning - with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91 => Column pruning - with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91} (100%) rename sql/hive/src/test/resources/golden/{Column pruning: without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049 => Column pruning - without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7 => Partition pruning - all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3 => Partition pruning - left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3} (100%) rename sql/hive/src/test/resources/golden/{Partiton pruning: non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344 => Partition pruning - non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb => Partition pruning - non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10 => Partition pruning - pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190 => Partition pruning - with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190} (100%) rename sql/hive/src/test/resources/golden/{Partition pruning: with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5 => Partition pruning - with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5} (100%) diff --git a/sql/hive/src/test/resources/golden/Column pruning: filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be b/sql/hive/src/test/resources/golden/Column pruning - filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be rename to sql/hive/src/test/resources/golden/Column pruning - filter alias in-lining - query test-0-cb0737d268260da971487a8ac5e3d8be diff --git a/sql/hive/src/test/resources/golden/Column pruning: non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35 b/sql/hive/src/test/resources/golden/Column pruning - non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35 similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35 rename to sql/hive/src/test/resources/golden/Column pruning - non-trivial top project with aliases - query test-0-c89dcddb8539bae211ea28cd1e695e35 diff --git a/sql/hive/src/test/resources/golden/Column pruning: projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa b/sql/hive/src/test/resources/golden/Column pruning - projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa rename to sql/hive/src/test/resources/golden/Column pruning - projects alias substituting - query test-0-9589ac54d6de575083765ee64051ebaa diff --git a/sql/hive/src/test/resources/golden/Column pruning: simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494 b/sql/hive/src/test/resources/golden/Column pruning - simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494 similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494 rename to sql/hive/src/test/resources/golden/Column pruning - simple top project without aliases - query test-0-d6d2726928df920ab99078015b8ff494 diff --git a/sql/hive/src/test/resources/golden/Column pruning: with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477 b/sql/hive/src/test/resources/golden/Column pruning - with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477 similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477 rename to sql/hive/src/test/resources/golden/Column pruning - with multiple projects - query test-0-cfe78c68302bd143d989c383c3b0477 diff --git a/sql/hive/src/test/resources/golden/Column pruning: with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee b/sql/hive/src/test/resources/golden/Column pruning - with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee rename to sql/hive/src/test/resources/golden/Column pruning - with non-partitioned table - query test-0-358525951e893ed9686c46bf1f7447ee diff --git a/sql/hive/src/test/resources/golden/Column pruning: with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91 b/sql/hive/src/test/resources/golden/Column pruning - with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91 similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91 rename to sql/hive/src/test/resources/golden/Column pruning - with partitioned table - query test-0-d9d50146537344742300ce7b52c18c91 diff --git a/sql/hive/src/test/resources/golden/Column pruning: without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049 b/sql/hive/src/test/resources/golden/Column pruning - without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049 similarity index 100% rename from sql/hive/src/test/resources/golden/Column pruning: without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049 rename to sql/hive/src/test/resources/golden/Column pruning - without filters - query test-0-c25cdafe7d85c42a9d9cd559d88a6049 diff --git a/sql/hive/src/test/resources/golden/Partition pruning: all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7 b/sql/hive/src/test/resources/golden/Partition pruning - all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7 similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7 rename to sql/hive/src/test/resources/golden/Partition pruning - all partitions pruned - query test-0-63ab78355dbc6fa0d7619c8a35b0f7a7 diff --git a/sql/hive/src/test/resources/golden/Partition pruning: left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3 b/sql/hive/src/test/resources/golden/Partition pruning - left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3 similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3 rename to sql/hive/src/test/resources/golden/Partition pruning - left only 1 partition - query test-0-3adc3a7f76b2abd059904ba81a595db3 diff --git a/sql/hive/src/test/resources/golden/Partiton pruning: non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344 b/sql/hive/src/test/resources/golden/Partition pruning - non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344 similarity index 100% rename from sql/hive/src/test/resources/golden/Partiton pruning: non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344 rename to sql/hive/src/test/resources/golden/Partition pruning - non-partitioned table - query test-0-681332efaff7b12e3ca12d9f021cd344 diff --git a/sql/hive/src/test/resources/golden/Partition pruning: non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb b/sql/hive/src/test/resources/golden/Partition pruning - non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb rename to sql/hive/src/test/resources/golden/Partition pruning - non-partitioned, non-trivial project - query test-0-3893ec7a86062215d9f817f1495a69bb diff --git a/sql/hive/src/test/resources/golden/Partition pruning: pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10 b/sql/hive/src/test/resources/golden/Partition pruning - pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10 similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10 rename to sql/hive/src/test/resources/golden/Partition pruning - pruning with both column key and partition key - query test-0-75148567b91227053f728d72f7dc7c10 diff --git a/sql/hive/src/test/resources/golden/Partition pruning: with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190 b/sql/hive/src/test/resources/golden/Partition pruning - with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190 similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190 rename to sql/hive/src/test/resources/golden/Partition pruning - with filter on int partition key - query test-0-4e4d2651e1e6e3c224242078d0201190 diff --git a/sql/hive/src/test/resources/golden/Partition pruning: with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5 b/sql/hive/src/test/resources/golden/Partition pruning - with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5 similarity index 100% rename from sql/hive/src/test/resources/golden/Partition pruning: with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5 rename to sql/hive/src/test/resources/golden/Partition pruning - with filter on string partition key - query test-0-b6e59464383591f02408f8765ac6a5d5 diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruningSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruningSuite.scala index 25eca397462f7..34434449a0d77 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruningSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruningSuite.scala @@ -28,7 +28,7 @@ import scala.collection.JavaConversions._ class PruningSuite extends HiveComparisonTest { // Column pruning tests - createPruningTest("Column pruning: with partitioned table", + createPruningTest("Column pruning - with partitioned table", "SELECT key FROM srcpart WHERE ds = '2008-04-08' LIMIT 3", Seq("key"), Seq("key"), @@ -36,43 +36,43 @@ class PruningSuite extends HiveComparisonTest { Seq("2008-04-08", "11"), Seq("2008-04-08", "12"))) - createPruningTest("Column pruning: with non-partitioned table", + createPruningTest("Column pruning - with non-partitioned table", "SELECT key FROM src WHERE key > 10 LIMIT 3", Seq("key"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: with multiple projects", + createPruningTest("Column pruning - with multiple projects", "SELECT c1 FROM (SELECT key AS c1 FROM src WHERE key > 10) t1 LIMIT 3", Seq("c1"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: projects alias substituting", + createPruningTest("Column pruning - projects alias substituting", "SELECT c1 AS c2 FROM (SELECT key AS c1 FROM src WHERE key > 10) t1 LIMIT 3", Seq("c2"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: filter alias in-lining", + createPruningTest("Column pruning - filter alias in-lining", "SELECT c1 FROM (SELECT key AS c1 FROM src WHERE key > 10) t1 WHERE c1 < 100 LIMIT 3", Seq("c1"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: without filters", + createPruningTest("Column pruning - without filters", "SELECT c1 FROM (SELECT key AS c1 FROM src) t1 LIMIT 3", Seq("c1"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: simple top project without aliases", + createPruningTest("Column pruning - simple top project without aliases", "SELECT key FROM (SELECT key FROM src WHERE key > 10) t1 WHERE key < 100 LIMIT 3", Seq("key"), Seq("key"), Seq.empty) - createPruningTest("Column pruning: non-trivial top project with aliases", + createPruningTest("Column pruning - non-trivial top project with aliases", "SELECT c1 * 2 AS double FROM (SELECT key AS c1 FROM src WHERE key > 10) t1 LIMIT 3", Seq("double"), Seq("key"), @@ -80,19 +80,19 @@ class PruningSuite extends HiveComparisonTest { // Partition pruning tests - createPruningTest("Partition pruning: non-partitioned, non-trivial project", + createPruningTest("Partition pruning - non-partitioned, non-trivial project", "SELECT key * 2 AS double FROM src WHERE value IS NOT NULL", Seq("double"), Seq("key", "value"), Seq.empty) - createPruningTest("Partiton pruning: non-partitioned table", + createPruningTest("Partition pruning - non-partitioned table", "SELECT value FROM src WHERE key IS NOT NULL", Seq("value"), Seq("value", "key"), Seq.empty) - createPruningTest("Partition pruning: with filter on string partition key", + createPruningTest("Partition pruning - with filter on string partition key", "SELECT value, hr FROM srcpart1 WHERE ds = '2008-04-08'", Seq("value", "hr"), Seq("value", "hr"), @@ -100,7 +100,7 @@ class PruningSuite extends HiveComparisonTest { Seq("2008-04-08", "11"), Seq("2008-04-08", "12"))) - createPruningTest("Partition pruning: with filter on int partition key", + createPruningTest("Partition pruning - with filter on int partition key", "SELECT value, hr FROM srcpart1 WHERE hr < 12", Seq("value", "hr"), Seq("value", "hr"), @@ -108,20 +108,20 @@ class PruningSuite extends HiveComparisonTest { Seq("2008-04-08", "11"), Seq("2008-04-09", "11"))) - createPruningTest("Partition pruning: left only 1 partition", + createPruningTest("Partition pruning - left only 1 partition", "SELECT value, hr FROM srcpart1 WHERE ds = '2008-04-08' AND hr < 12", Seq("value", "hr"), Seq("value", "hr"), Seq( Seq("2008-04-08", "11"))) - createPruningTest("Partition pruning: all partitions pruned", + createPruningTest("Partition pruning - all partitions pruned", "SELECT value, hr FROM srcpart1 WHERE ds = '2014-01-27' AND hr = 11", Seq("value", "hr"), Seq("value", "hr"), Seq.empty) - createPruningTest("Partition pruning: pruning with both column key and partition key", + createPruningTest("Partition pruning - pruning with both column key and partition key", "SELECT value, hr FROM srcpart1 WHERE value IS NOT NULL AND hr < 12", Seq("value", "hr"), Seq("value", "hr"), From a4aafe5f9fb191533400caeafddf04986492c95f Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Thu, 15 May 2014 16:50:42 -0700 Subject: [PATCH 60/99] [SQL] Fix tiny/small ints from HiveMetastore. Author: Michael Armbrust Closes #797 from marmbrus/smallInt and squashes the following commits: 2db9dae [Michael Armbrust] Fix tiny/small ints from HiveMetastore. --- .../org/apache/spark/sql/hive/HiveMetastoreCatalog.scala | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala index fa30f596f8c67..636c4f7b93190 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala @@ -183,7 +183,8 @@ object HiveMetastoreTypes extends RegexParsers { "string" ^^^ StringType | "float" ^^^ FloatType | "int" ^^^ IntegerType | - "tinyint" ^^^ ShortType | + "tinyint" ^^^ ByteType | + "smallint" ^^^ ShortType | "double" ^^^ DoubleType | "bigint" ^^^ LongType | "binary" ^^^ BinaryType | @@ -227,7 +228,8 @@ object HiveMetastoreTypes extends RegexParsers { case StringType => "string" case FloatType => "float" case IntegerType => "int" - case ShortType =>"tinyint" + case ByteType => "tinyint" + case ShortType => "smallint" case DoubleType => "double" case LongType => "bigint" case BinaryType => "binary" From e1e3416c4e5f6f32983597d74866dbb809cf6a5e Mon Sep 17 00:00:00 2001 From: Prashant Sharma Date: Thu, 15 May 2014 16:58:37 -0700 Subject: [PATCH 61/99] Fixes a misplaced comment. Fixes a misplaced comment from #785. @pwendell Author: Prashant Sharma Closes #788 from ScrapCodes/patch-1 and squashes the following commits: 3ef6a69 [Prashant Sharma] Update package-info.java 67d9461 [Prashant Sharma] Update package-info.java --- .../main/scala/org/apache/spark/graphx/lib/package-info.java | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java b/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java index 49ad7263141ce..e987ee8560ff7 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/package-info.java @@ -16,6 +16,6 @@ */ /** - * Internal support for MLLib Python API. + * Various analytics functions for graphs. */ -package org.apache.spark.graphx.lib; \ No newline at end of file +package org.apache.spark.graphx.lib; From 94c5139607ec876782e594012a108ebf55fa97db Mon Sep 17 00:00:00 2001 From: Huajian Mao Date: Thu, 15 May 2014 18:20:16 -0700 Subject: [PATCH 62/99] Typos in Spark Author: Huajian Mao Closes #798 from huajianmao/patch-1 and squashes the following commits: 208a454 [Huajian Mao] A typo in Task 1b515af [Huajian Mao] A typo in the message --- core/src/main/scala/org/apache/spark/scheduler/Task.scala | 2 +- .../scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/scheduler/Task.scala b/core/src/main/scala/org/apache/spark/scheduler/Task.scala index 2ca3479c80efc..5871edeb856ad 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/Task.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/Task.scala @@ -33,7 +33,7 @@ import org.apache.spark.util.ByteBufferInputStream * - [[org.apache.spark.scheduler.ResultTask]] * * A Spark job consists of one or more stages. The very last stage in a job consists of multiple - * ResultTask's, while earlier stages consist of ShuffleMapTasks. A ResultTask executes the task + * ResultTasks, while earlier stages consist of ShuffleMapTasks. A ResultTask executes the task * and sends the task output back to the driver application. A ShuffleMapTask executes the task * and divides the task output to multiple buckets (based on the task's partitioner). * diff --git a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala index 649eed213e09a..17292b4c15b8b 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala @@ -105,7 +105,7 @@ private[spark] class TaskSchedulerImpl( SchedulingMode.withName(schedulingModeConf.toUpperCase) } catch { case e: java.util.NoSuchElementException => - throw new SparkException(s"Urecognized spark.scheduler.mode: $schedulingModeConf") + throw new SparkException(s"Unrecognized spark.scheduler.mode: $schedulingModeConf") } // This is a var so that we can reset it for testing purposes. From bb98ecafce196ecc5bc3a1e4cc9264df7b752c6a Mon Sep 17 00:00:00 2001 From: Aaron Davidson Date: Thu, 15 May 2014 21:37:58 -0700 Subject: [PATCH 63/99] SPARK-1860: Do not cleanup application work/ directories by default This causes an unrecoverable error for applications that are running for longer than 7 days that have jars added to the SparkContext, as the jars are cleaned up even though the application is still running. Author: Aaron Davidson Closes #800 from aarondav/shitty-defaults and squashes the following commits: a573fbb [Aaron Davidson] SPARK-1860: Do not cleanup application work/ directories by default --- .../main/scala/org/apache/spark/deploy/worker/Worker.scala | 2 +- docs/configuration.md | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala index 134624c35a57e..fb9cc116cd08b 100755 --- a/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/Worker.scala @@ -65,7 +65,7 @@ private[spark] class Worker( val REGISTRATION_TIMEOUT = 20.seconds val REGISTRATION_RETRIES = 3 - val CLEANUP_ENABLED = conf.getBoolean("spark.worker.cleanup.enabled", true) + val CLEANUP_ENABLED = conf.getBoolean("spark.worker.cleanup.enabled", false) // How often worker will clean up old app folders val CLEANUP_INTERVAL_MILLIS = conf.getLong("spark.worker.cleanup.interval", 60 * 30) * 1000 // TTL for app folders/data; after TTL expires it will be cleaned up diff --git a/docs/configuration.md b/docs/configuration.md index 2eed96f704a4f..f89040d714773 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -390,10 +390,11 @@ Apart from these, the following properties are also available, and may be useful spark.worker.cleanup.enabled - true + false Enable periodic cleanup of worker / application directories. Note that this only affects standalone - mode, as YARN works differently. + mode, as YARN works differently. Applications directories are cleaned up regardless of whether + the application is still running. From a20fea98811d98958567780815fcf0d4fb4e28d4 Mon Sep 17 00:00:00 2001 From: Cheng Hao Date: Thu, 15 May 2014 22:12:34 -0700 Subject: [PATCH 64/99] [Spark-1461] Deferred Expression Evaluation (short-circuit evaluation) This patch unify the foldable & nullable interface for Expression. 1) Deterministic-less UDF (like Rand()) can not be folded. 2) Short-circut will significantly improves the performance in Expression Evaluation, however, the stateful UDF should not be ignored in a short-circuit evaluation(e.g. in expression: col1 > 0 and row_sequence() < 1000, row_sequence() can not be ignored even if col1 > 0 is false) I brought an concept of DeferredObject from Hive, which has 2 kinds of children classes (EagerResult / DeferredResult), the former requires triggering the evaluation before it's created, while the later trigger the evaluation when first called its get() method. Author: Cheng Hao Closes #446 from chenghao-intel/expression_deferred_evaluation and squashes the following commits: d2729de [Cheng Hao] Fix the codestyle issues a08f09c [Cheng Hao] fix bug in or/and short-circuit evaluation af2236b [Cheng Hao] revert the short-circuit expression evaluation for IF b7861d2 [Cheng Hao] Add Support for Deferred Expression Evaluation --- .../sql/catalyst/expressions/predicates.scala | 47 +++++++++++++------ .../org/apache/spark/sql/hive/hiveUdfs.scala | 28 ++++++++--- 2 files changed, 53 insertions(+), 22 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala index 6ee479939d25c..d111578530506 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala @@ -98,13 +98,19 @@ case class And(left: Expression, right: Expression) extends BinaryPredicate { override def eval(input: Row): Any = { val l = left.eval(input) - val r = right.eval(input) - if (l == false || r == false) { - false - } else if (l == null || r == null ) { - null + if (l == false) { + false } else { - true + val r = right.eval(input) + if (r == false) { + false + } else { + if (l != null && r != null) { + true + } else { + null + } + } } } } @@ -114,13 +120,19 @@ case class Or(left: Expression, right: Expression) extends BinaryPredicate { override def eval(input: Row): Any = { val l = left.eval(input) - val r = right.eval(input) - if (l == true || r == true) { + if (l == true) { true - } else if (l == null || r == null) { - null } else { - false + val r = right.eval(input) + if (r == true) { + true + } else { + if (l != null && r != null) { + false + } else { + null + } + } } } } @@ -133,8 +145,12 @@ case class Equals(left: Expression, right: Expression) extends BinaryComparison def symbol = "=" override def eval(input: Row): Any = { val l = left.eval(input) - val r = right.eval(input) - if (l == null || r == null) null else l == r + if (l == null) { + null + } else { + val r = right.eval(input) + if (r == null) null else l == r + } } } @@ -162,7 +178,7 @@ case class If(predicate: Expression, trueValue: Expression, falseValue: Expressi extends Expression { def children = predicate :: trueValue :: falseValue :: Nil - def nullable = trueValue.nullable || falseValue.nullable + override def nullable = trueValue.nullable || falseValue.nullable def references = children.flatMap(_.references).toSet override lazy val resolved = childrenResolved && trueValue.dataType == falseValue.dataType def dataType = { @@ -175,8 +191,9 @@ case class If(predicate: Expression, trueValue: Expression, falseValue: Expressi } type EvaluatedType = Any + override def eval(input: Row): Any = { - if (predicate.eval(input).asInstanceOf[Boolean]) { + if (true == predicate.eval(input)) { trueValue.eval(input) } else { falseValue.eval(input) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala index d50e2c65b7b36..572902042337f 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala @@ -248,17 +248,31 @@ private[hive] case class HiveGenericUdf(name: String, children: Seq[Expression]) isUDFDeterministic && children.foldLeft(true)((prev, n) => prev && n.foldable) } + protected lazy val deferedObjects = Array.fill[DeferredObject](children.length)({ + new DeferredObjectAdapter + }) + + // Adapter from Catalyst ExpressionResult to Hive DeferredObject + class DeferredObjectAdapter extends DeferredObject { + private var func: () => Any = _ + def set(func: () => Any) { + this.func = func + } + override def prepare(i: Int) = {} + override def get(): AnyRef = wrap(func()) + } + val dataType: DataType = inspectorToDataType(returnInspector) override def eval(input: Row): Any = { returnInspector // Make sure initialized. - val args = children.map { v => - new DeferredObject { - override def prepare(i: Int) = {} - override def get(): AnyRef = wrap(v.eval(input)) - } - }.toArray - unwrap(function.evaluate(args)) + var i = 0 + while (i < children.length) { + val idx = i + deferedObjects(i).asInstanceOf[DeferredObjectAdapter].set(() => {children(idx).eval(input)}) + i += 1 + } + unwrap(function.evaluate(deferedObjects)) } } From 17702e280c4b0b030870962fcb3d50c3085ae862 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Thu, 15 May 2014 23:31:43 -0700 Subject: [PATCH 65/99] SPARK-1862: Support for MapR in the Maven build. Author: Patrick Wendell Closes #803 from pwendell/mapr-support and squashes the following commits: 8df60e4 [Patrick Wendell] SPARK-1862: Support for MapR in the Maven build. --- pom.xml | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) diff --git a/pom.xml b/pom.xml index 5df7036585b75..088d4cacb8bb5 100644 --- a/pom.xml +++ b/pom.xml @@ -123,6 +123,7 @@ 2.4.1 ${hadoop.version} 0.94.6 + 3.4.5 0.12.0 1.4.3 1.2.3 @@ -194,6 +195,17 @@ false + + mapr-repo + MapR Repository + http://repository.mapr.com/maven + + true + + + false + + @@ -490,6 +502,14 @@ commons-logging commons-logging + + org.mortbay.jetty + servlet-api-2.5 + + + junit + junit + @@ -979,6 +999,20 @@ + + mapr + + false + + + 1.0.3-mapr-3.0.3 + 2.3.0-mapr-4.0.0-beta + 0.94.17-mapr-1403 + 0.94.17-mapr-1403 + 3.4.5-mapr-1401 + + + hadoop-provided @@ -1024,7 +1058,7 @@ org.apache.zookeeper zookeeper - 3.4.5 + ${zookeeper.version} provided From e304eb998e3b2a44dc1f773cd75211679f217661 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Thu, 15 May 2014 23:33:27 -0700 Subject: [PATCH 66/99] HOTFIX: Duplication of hbase version --- pom.xml | 1 - 1 file changed, 1 deletion(-) diff --git a/pom.xml b/pom.xml index 088d4cacb8bb5..86264d1132ec4 100644 --- a/pom.xml +++ b/pom.xml @@ -1008,7 +1008,6 @@ 1.0.3-mapr-3.0.3 2.3.0-mapr-4.0.0-beta 0.94.17-mapr-1403 - 0.94.17-mapr-1403 3.4.5-mapr-1401 From fa6de408a131a3e84350a60af74a92c323dfc5eb Mon Sep 17 00:00:00 2001 From: Zhen Peng Date: Fri, 16 May 2014 11:37:18 -0700 Subject: [PATCH 67/99] bugfix: overflow of graphx Edge compare function Author: Zhen Peng Closes #769 from zhpengg/bugfix-graphx-edge-compare and squashes the following commits: 8a978ff [Zhen Peng] add ut for graphx Edge.lexicographicOrdering.compare 413c258 [Zhen Peng] there maybe a overflow for two Long's substraction --- .../scala/org/apache/spark/graphx/Edge.scala | 10 ++++- .../org/apache/spark/graphx/EdgeSuite.scala | 39 +++++++++++++++++++ 2 files changed, 47 insertions(+), 2 deletions(-) create mode 100644 graphx/src/test/scala/org/apache/spark/graphx/EdgeSuite.scala diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala b/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala index 580faa0866789..7e842ec4cc82f 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala @@ -56,7 +56,13 @@ case class Edge[@specialized(Char, Int, Boolean, Byte, Long, Float, Double) ED] object Edge { private[graphx] def lexicographicOrdering[ED] = new Ordering[Edge[ED]] { - override def compare(a: Edge[ED], b: Edge[ED]): Int = - (if (a.srcId != b.srcId) a.srcId - b.srcId else a.dstId - b.dstId).toInt + override def compare(a: Edge[ED], b: Edge[ED]): Int = { + if (a.srcId == b.srcId) { + if (a.dstId == b.dstId) 0 + else if (a.dstId < b.dstId) -1 + else 1 + } else if (a.srcId < b.srcId) -1 + else 1 + } } } diff --git a/graphx/src/test/scala/org/apache/spark/graphx/EdgeSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/EdgeSuite.scala new file mode 100644 index 0000000000000..5a2c73b414279 --- /dev/null +++ b/graphx/src/test/scala/org/apache/spark/graphx/EdgeSuite.scala @@ -0,0 +1,39 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.graphx + +import org.scalatest.FunSuite + +class EdgeSuite extends FunSuite { + test ("compare") { + // decending order + val testEdges: Array[Edge[Int]] = Array( + Edge(0x7FEDCBA987654321L, -0x7FEDCBA987654321L, 1), + Edge(0x2345L, 0x1234L, 1), + Edge(0x1234L, 0x5678L, 1), + Edge(0x1234L, 0x2345L, 1), + Edge(-0x7FEDCBA987654321L, 0x7FEDCBA987654321L, 1) + ) + // to ascending order + val sortedEdges = testEdges.sorted(Edge.lexicographicOrdering[Int]) + + for (i <- 0 until testEdges.length) { + assert(sortedEdges(i) == testEdges(testEdges.length - i - 1)) + } + } +} From 032d6632ad4ab88c97c9e568b63169a114220a02 Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Fri, 16 May 2014 11:47:00 -0700 Subject: [PATCH 68/99] [SQL] Implement between in hql Author: Michael Armbrust Closes #804 from marmbrus/between and squashes the following commits: ae24672 [Michael Armbrust] add golden answer. d9997ef [Michael Armbrust] Implement between in hql. 9bd4433 [Michael Armbrust] Better error on parse failures. --- .../scala/org/apache/spark/sql/hive/HiveQl.scala | 16 ++++++++++++++++ .../between-0-df3cf89fcf2ef64199a582fae14a3321 | 1 + .../sql/hive/execution/HiveQuerySuite.scala | 4 ++++ 3 files changed, 21 insertions(+) create mode 100644 sql/hive/src/test/resources/golden/between-0-df3cf89fcf2ef64199a582fae14a3321 diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 1f688fe1117fe..93b9057a23816 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -233,6 +233,11 @@ private[hive] object HiveQl { } } catch { case e: Exception => throw new ParseException(sql, e) + case e: NotImplementedError => sys.error( + s""" + |Unsupported language features in query: $sql + |${dumpTree(getAst(sql))} + """.stripMargin) } } @@ -865,6 +870,17 @@ private[hive] object HiveQl { IsNull(nodeToExpr(child)) case Token("TOK_FUNCTION", Token("IN", Nil) :: value :: list) => In(nodeToExpr(value), list.map(nodeToExpr)) + case Token("TOK_FUNCTION", + Token("between", Nil) :: + Token("KW_FALSE", Nil) :: + target :: + minValue :: + maxValue :: Nil) => + + val targetExpression = nodeToExpr(target) + And( + GreaterThanOrEqual(targetExpression, nodeToExpr(minValue)), + LessThanOrEqual(targetExpression, nodeToExpr(maxValue))) /* Boolean Logic */ case Token(AND(), left :: right:: Nil) => And(nodeToExpr(left), nodeToExpr(right)) diff --git a/sql/hive/src/test/resources/golden/between-0-df3cf89fcf2ef64199a582fae14a3321 b/sql/hive/src/test/resources/golden/between-0-df3cf89fcf2ef64199a582fae14a3321 new file mode 100644 index 0000000000000..dcd1d8643e3cb --- /dev/null +++ b/sql/hive/src/test/resources/golden/between-0-df3cf89fcf2ef64199a582fae14a3321 @@ -0,0 +1 @@ +2 val_2 diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 87a92d83383ab..1a2b2f89182ae 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -24,6 +24,10 @@ import org.apache.spark.sql.hive.test.TestHive._ */ class HiveQuerySuite extends HiveComparisonTest { + createQueryTest("between", + "SELECT * FROM src WHERE key between 1 and 2" + ) + test("Query expressed in SQL") { assert(sql("SELECT 1").collect() === Array(Seq(1))) } From 40d6acd6ba2feccc600301f5c47d4f90157138b1 Mon Sep 17 00:00:00 2001 From: Andre Schumacher Date: Fri, 16 May 2014 13:41:41 -0700 Subject: [PATCH 69/99] SPARK-1487 [SQL] Support record filtering via predicate pushdown in Parquet Simple filter predicates such as LessThan, GreaterThan, etc., where one side is a literal and the other one a NamedExpression are now pushed down to the underlying ParquetTableScan. Here are some results for a microbenchmark with a simple schema of six fields of different types where most records failed the test: | Uncompressed | Compressed -------------| ------------- | ------------- File size | 10 GB | 2 GB Speedup | 2 | 1.8 Since mileage may vary I added a new option to SparkConf: `org.apache.spark.sql.parquet.filter.pushdown` Default value would be `true` and setting it to `false` disables the pushdown. When most rows are expected to pass the filter or when there are few fields performance can be better when pushdown is disabled. The default should fit situations with a reasonable number of (possibly nested) fields where not too many records on average pass the filter. Because of an issue with Parquet ([see here](https://github.com/Parquet/parquet-mr/issues/371])) currently only predicates on non-nullable attributes are pushed down. If one would know that for a given table no optional fields have missing values one could also allow overriding this. Author: Andre Schumacher Closes #511 from AndreSchumacher/parquet_filter and squashes the following commits: 16bfe83 [Andre Schumacher] Removing leftovers from merge during rebase 7b304ca [Andre Schumacher] Fixing formatting c36d5cb [Andre Schumacher] Scalastyle 3da98db [Andre Schumacher] Second round of review feedback 7a78265 [Andre Schumacher] Fixing broken formatting in ParquetFilter a86553b [Andre Schumacher] First round of code review feedback b0f7806 [Andre Schumacher] Optimizing imports in ParquetTestData 85fea2d [Andre Schumacher] Adding SparkConf setting to disable filter predicate pushdown f0ad3cf [Andre Schumacher] Undoing changes not needed for this PR 210e9cb [Andre Schumacher] Adding disjunctive filter predicates a93a588 [Andre Schumacher] Adding unit test for filtering 6d22666 [Andre Schumacher] Extending ParquetFilters 93e8192 [Andre Schumacher] First commit Parquet record filtering --- .../spark/sql/execution/SparkStrategies.scala | 31 +- .../spark/sql/parquet/ParquetFilters.scala | 436 ++++++++++++++++++ .../sql/parquet/ParquetTableOperations.scala | 90 +++- .../spark/sql/parquet/ParquetTestData.scala | 90 +++- .../spark/sql/parquet/ParquetQuerySuite.scala | 135 +++++- 5 files changed, 731 insertions(+), 51 deletions(-) create mode 100644 sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala index f763106da4e0e..394a59700dbaf 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala @@ -140,12 +140,35 @@ private[sql] abstract class SparkStrategies extends QueryPlanner[SparkPlan] { InsertIntoParquetTable(relation, planLater(child), overwrite=true)(sparkContext) :: Nil case logical.InsertIntoTable(table: ParquetRelation, partition, child, overwrite) => InsertIntoParquetTable(table, planLater(child), overwrite)(sparkContext) :: Nil - case PhysicalOperation(projectList, filters, relation: ParquetRelation) => - // TODO: Should be pushing down filters as well. + case PhysicalOperation(projectList, filters: Seq[Expression], relation: ParquetRelation) => { + val remainingFilters = + if (sparkContext.conf.getBoolean(ParquetFilters.PARQUET_FILTER_PUSHDOWN_ENABLED, true)) { + filters.filter { + // Note: filters cannot be pushed down to Parquet if they contain more complex + // expressions than simple "Attribute cmp Literal" comparisons. Here we remove + // all filters that have been pushed down. Note that a predicate such as + // "(A AND B) OR C" can result in "A OR C" being pushed down. + filter => + val recordFilter = ParquetFilters.createFilter(filter) + if (!recordFilter.isDefined) { + // First case: the pushdown did not result in any record filter. + true + } else { + // Second case: a record filter was created; here we are conservative in + // the sense that even if "A" was pushed and we check for "A AND B" we + // still want to keep "A AND B" in the higher-level filter, not just "B". + !ParquetFilters.findExpression(recordFilter.get, filter).isDefined + } + } + } else { + filters + } pruneFilterProject( projectList, - filters, - ParquetTableScan(_, relation, None)(sparkContext)) :: Nil + remainingFilters, + ParquetTableScan(_, relation, filters)(sparkContext)) :: Nil + } + case _ => Nil } } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala new file mode 100644 index 0000000000000..052b0a9196717 --- /dev/null +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala @@ -0,0 +1,436 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.parquet + +import org.apache.hadoop.conf.Configuration + +import parquet.filter._ +import parquet.filter.ColumnPredicates._ +import parquet.column.ColumnReader + +import com.google.common.io.BaseEncoding + +import org.apache.spark.sql.catalyst.types._ +import org.apache.spark.sql.catalyst.expressions.{Predicate => CatalystPredicate} +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.execution.SparkSqlSerializer + +object ParquetFilters { + val PARQUET_FILTER_DATA = "org.apache.spark.sql.parquet.row.filter" + // set this to false if pushdown should be disabled + val PARQUET_FILTER_PUSHDOWN_ENABLED = "spark.sql.hints.parquetFilterPushdown" + + def createRecordFilter(filterExpressions: Seq[Expression]): UnboundRecordFilter = { + val filters: Seq[CatalystFilter] = filterExpressions.collect { + case (expression: Expression) if createFilter(expression).isDefined => + createFilter(expression).get + } + if (filters.length > 0) filters.reduce(AndRecordFilter.and) else null + } + + def createFilter(expression: Expression): Option[CatalystFilter] = { + def createEqualityFilter( + name: String, + literal: Literal, + predicate: CatalystPredicate) = literal.dataType match { + case BooleanType => + ComparisonFilter.createBooleanFilter(name, literal.value.asInstanceOf[Boolean], predicate) + case IntegerType => + ComparisonFilter.createIntFilter( + name, + (x: Int) => x == literal.value.asInstanceOf[Int], + predicate) + case LongType => + ComparisonFilter.createLongFilter( + name, + (x: Long) => x == literal.value.asInstanceOf[Long], + predicate) + case DoubleType => + ComparisonFilter.createDoubleFilter( + name, + (x: Double) => x == literal.value.asInstanceOf[Double], + predicate) + case FloatType => + ComparisonFilter.createFloatFilter( + name, + (x: Float) => x == literal.value.asInstanceOf[Float], + predicate) + case StringType => + ComparisonFilter.createStringFilter(name, literal.value.asInstanceOf[String], predicate) + } + def createLessThanFilter( + name: String, + literal: Literal, + predicate: CatalystPredicate) = literal.dataType match { + case IntegerType => + ComparisonFilter.createIntFilter( + name, + (x: Int) => x < literal.value.asInstanceOf[Int], + predicate) + case LongType => + ComparisonFilter.createLongFilter( + name, + (x: Long) => x < literal.value.asInstanceOf[Long], + predicate) + case DoubleType => + ComparisonFilter.createDoubleFilter( + name, + (x: Double) => x < literal.value.asInstanceOf[Double], + predicate) + case FloatType => + ComparisonFilter.createFloatFilter( + name, + (x: Float) => x < literal.value.asInstanceOf[Float], + predicate) + } + def createLessThanOrEqualFilter( + name: String, + literal: Literal, + predicate: CatalystPredicate) = literal.dataType match { + case IntegerType => + ComparisonFilter.createIntFilter( + name, + (x: Int) => x <= literal.value.asInstanceOf[Int], + predicate) + case LongType => + ComparisonFilter.createLongFilter( + name, + (x: Long) => x <= literal.value.asInstanceOf[Long], + predicate) + case DoubleType => + ComparisonFilter.createDoubleFilter( + name, + (x: Double) => x <= literal.value.asInstanceOf[Double], + predicate) + case FloatType => + ComparisonFilter.createFloatFilter( + name, + (x: Float) => x <= literal.value.asInstanceOf[Float], + predicate) + } + // TODO: combine these two types somehow? + def createGreaterThanFilter( + name: String, + literal: Literal, + predicate: CatalystPredicate) = literal.dataType match { + case IntegerType => + ComparisonFilter.createIntFilter( + name, + (x: Int) => x > literal.value.asInstanceOf[Int], + predicate) + case LongType => + ComparisonFilter.createLongFilter( + name, + (x: Long) => x > literal.value.asInstanceOf[Long], + predicate) + case DoubleType => + ComparisonFilter.createDoubleFilter( + name, + (x: Double) => x > literal.value.asInstanceOf[Double], + predicate) + case FloatType => + ComparisonFilter.createFloatFilter( + name, + (x: Float) => x > literal.value.asInstanceOf[Float], + predicate) + } + def createGreaterThanOrEqualFilter( + name: String, + literal: Literal, + predicate: CatalystPredicate) = literal.dataType match { + case IntegerType => + ComparisonFilter.createIntFilter( + name, (x: Int) => x >= literal.value.asInstanceOf[Int], + predicate) + case LongType => + ComparisonFilter.createLongFilter( + name, + (x: Long) => x >= literal.value.asInstanceOf[Long], + predicate) + case DoubleType => + ComparisonFilter.createDoubleFilter( + name, + (x: Double) => x >= literal.value.asInstanceOf[Double], + predicate) + case FloatType => + ComparisonFilter.createFloatFilter( + name, + (x: Float) => x >= literal.value.asInstanceOf[Float], + predicate) + } + + /** + * TODO: we currently only filter on non-nullable (Parquet REQUIRED) attributes until + * https://github.com/Parquet/parquet-mr/issues/371 + * has been resolved. + */ + expression match { + case p @ Or(left: Expression, right: Expression) + if createFilter(left).isDefined && createFilter(right).isDefined => { + // If either side of this Or-predicate is empty then this means + // it contains a more complex comparison than between attribute and literal + // (e.g., it contained a CAST). The only safe thing to do is then to disregard + // this disjunction, which could be contained in a conjunction. If it stands + // alone then it is also safe to drop it, since a Null return value of this + // function is interpreted as having no filters at all. + val leftFilter = createFilter(left).get + val rightFilter = createFilter(right).get + Some(new OrFilter(leftFilter, rightFilter)) + } + case p @ And(left: Expression, right: Expression) => { + // This treats nested conjunctions; since either side of the conjunction + // may contain more complex filter expressions we may actually generate + // strictly weaker filter predicates in the process. + val leftFilter = createFilter(left) + val rightFilter = createFilter(right) + (leftFilter, rightFilter) match { + case (None, Some(filter)) => Some(filter) + case (Some(filter), None) => Some(filter) + case (_, _) => + Some(new AndFilter(leftFilter.get, rightFilter.get)) + } + } + case p @ Equals(left: Literal, right: NamedExpression) if !right.nullable => + Some(createEqualityFilter(right.name, left, p)) + case p @ Equals(left: NamedExpression, right: Literal) if !left.nullable => + Some(createEqualityFilter(left.name, right, p)) + case p @ LessThan(left: Literal, right: NamedExpression) if !right.nullable => + Some(createLessThanFilter(right.name, left, p)) + case p @ LessThan(left: NamedExpression, right: Literal) if !left.nullable => + Some(createLessThanFilter(left.name, right, p)) + case p @ LessThanOrEqual(left: Literal, right: NamedExpression) if !right.nullable => + Some(createLessThanOrEqualFilter(right.name, left, p)) + case p @ LessThanOrEqual(left: NamedExpression, right: Literal) if !left.nullable => + Some(createLessThanOrEqualFilter(left.name, right, p)) + case p @ GreaterThan(left: Literal, right: NamedExpression) if !right.nullable => + Some(createGreaterThanFilter(right.name, left, p)) + case p @ GreaterThan(left: NamedExpression, right: Literal) if !left.nullable => + Some(createGreaterThanFilter(left.name, right, p)) + case p @ GreaterThanOrEqual(left: Literal, right: NamedExpression) if !right.nullable => + Some(createGreaterThanOrEqualFilter(right.name, left, p)) + case p @ GreaterThanOrEqual(left: NamedExpression, right: Literal) if !left.nullable => + Some(createGreaterThanOrEqualFilter(left.name, right, p)) + case _ => None + } + } + + /** + * Note: Inside the Hadoop API we only have access to `Configuration`, not to + * [[org.apache.spark.SparkContext]], so we cannot use broadcasts to convey + * the actual filter predicate. + */ + def serializeFilterExpressions(filters: Seq[Expression], conf: Configuration): Unit = { + if (filters.length > 0) { + val serialized: Array[Byte] = SparkSqlSerializer.serialize(filters) + val encoded: String = BaseEncoding.base64().encode(serialized) + conf.set(PARQUET_FILTER_DATA, encoded) + } + } + + /** + * Note: Inside the Hadoop API we only have access to `Configuration`, not to + * [[org.apache.spark.SparkContext]], so we cannot use broadcasts to convey + * the actual filter predicate. + */ + def deserializeFilterExpressions(conf: Configuration): Seq[Expression] = { + val data = conf.get(PARQUET_FILTER_DATA) + if (data != null) { + val decoded: Array[Byte] = BaseEncoding.base64().decode(data) + SparkSqlSerializer.deserialize(decoded) + } else { + Seq() + } + } + + /** + * Try to find the given expression in the tree of filters in order to + * determine whether it is safe to remove it from the higher level filters. Note + * that strictly speaking we could stop the search whenever an expression is found + * that contains this expression as subexpression (e.g., when searching for "a" + * and "(a or c)" is found) but we don't care about optimizations here since the + * filter tree is assumed to be small. + * + * @param filter The [[org.apache.spark.sql.parquet.CatalystFilter]] to expand + * and search + * @param expression The expression to look for + * @return An optional [[org.apache.spark.sql.parquet.CatalystFilter]] that + * contains the expression. + */ + def findExpression( + filter: CatalystFilter, + expression: Expression): Option[CatalystFilter] = filter match { + case f @ OrFilter(_, leftFilter, rightFilter, _) => + if (f.predicate == expression) { + Some(f) + } else { + val left = findExpression(leftFilter, expression) + if (left.isDefined) left else findExpression(rightFilter, expression) + } + case f @ AndFilter(_, leftFilter, rightFilter, _) => + if (f.predicate == expression) { + Some(f) + } else { + val left = findExpression(leftFilter, expression) + if (left.isDefined) left else findExpression(rightFilter, expression) + } + case f @ ComparisonFilter(_, _, predicate) => + if (predicate == expression) Some(f) else None + case _ => None + } +} + +abstract private[parquet] class CatalystFilter( + @transient val predicate: CatalystPredicate) extends UnboundRecordFilter + +private[parquet] case class ComparisonFilter( + val columnName: String, + private var filter: UnboundRecordFilter, + @transient override val predicate: CatalystPredicate) + extends CatalystFilter(predicate) { + override def bind(readers: java.lang.Iterable[ColumnReader]): RecordFilter = { + filter.bind(readers) + } +} + +private[parquet] case class OrFilter( + private var filter: UnboundRecordFilter, + @transient val left: CatalystFilter, + @transient val right: CatalystFilter, + @transient override val predicate: Or) + extends CatalystFilter(predicate) { + def this(l: CatalystFilter, r: CatalystFilter) = + this( + OrRecordFilter.or(l, r), + l, + r, + Or(l.predicate, r.predicate)) + + override def bind(readers: java.lang.Iterable[ColumnReader]): RecordFilter = { + filter.bind(readers) + } +} + +private[parquet] case class AndFilter( + private var filter: UnboundRecordFilter, + @transient val left: CatalystFilter, + @transient val right: CatalystFilter, + @transient override val predicate: And) + extends CatalystFilter(predicate) { + def this(l: CatalystFilter, r: CatalystFilter) = + this( + AndRecordFilter.and(l, r), + l, + r, + And(l.predicate, r.predicate)) + + override def bind(readers: java.lang.Iterable[ColumnReader]): RecordFilter = { + filter.bind(readers) + } +} + +private[parquet] object ComparisonFilter { + def createBooleanFilter( + columnName: String, + value: Boolean, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToBoolean( + new BooleanPredicateFunction { + def functionToApply(input: Boolean): Boolean = input == value + } + )), + predicate) + + def createStringFilter( + columnName: String, + value: String, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToString ( + new ColumnPredicates.PredicateFunction[String] { + def functionToApply(input: String): Boolean = input == value + } + )), + predicate) + + def createIntFilter( + columnName: String, + func: Int => Boolean, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToInteger( + new IntegerPredicateFunction { + def functionToApply(input: Int) = func(input) + } + )), + predicate) + + def createLongFilter( + columnName: String, + func: Long => Boolean, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToLong( + new LongPredicateFunction { + def functionToApply(input: Long) = func(input) + } + )), + predicate) + + def createDoubleFilter( + columnName: String, + func: Double => Boolean, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToDouble( + new DoublePredicateFunction { + def functionToApply(input: Double) = func(input) + } + )), + predicate) + + def createFloatFilter( + columnName: String, + func: Float => Boolean, + predicate: CatalystPredicate): CatalystFilter = + new ComparisonFilter( + columnName, + ColumnRecordFilter.column( + columnName, + ColumnPredicates.applyFunctionToFloat( + new FloatPredicateFunction { + def functionToApply(input: Float) = func(input) + } + )), + predicate) +} diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala index f825ca3c028ef..65ba1246fbf9a 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala @@ -27,26 +27,27 @@ import org.apache.hadoop.mapreduce._ import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat => NewFileInputFormat} import org.apache.hadoop.mapreduce.lib.output.{FileOutputFormat => NewFileOutputFormat, FileOutputCommitter} -import parquet.hadoop.{ParquetInputFormat, ParquetOutputFormat} +import parquet.hadoop.{ParquetRecordReader, ParquetInputFormat, ParquetOutputFormat} +import parquet.hadoop.api.ReadSupport import parquet.hadoop.util.ContextUtil import parquet.io.InvalidRecordException import parquet.schema.MessageType -import org.apache.spark.{SerializableWritable, SparkContext, TaskContext} +import org.apache.spark.{Logging, SerializableWritable, SparkContext, TaskContext} import org.apache.spark.rdd.RDD import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression, Row} import org.apache.spark.sql.execution.{LeafNode, SparkPlan, UnaryNode} /** * Parquet table scan operator. Imports the file that backs the given - * [[ParquetRelation]] as a RDD[Row]. + * [[org.apache.spark.sql.parquet.ParquetRelation]] as a ``RDD[Row]``. */ case class ParquetTableScan( // note: output cannot be transient, see // https://issues.apache.org/jira/browse/SPARK-1367 output: Seq[Attribute], relation: ParquetRelation, - columnPruningPred: Option[Expression])( + columnPruningPred: Seq[Expression])( @transient val sc: SparkContext) extends LeafNode { @@ -62,18 +63,30 @@ case class ParquetTableScan( for (path <- fileList if !path.getName.startsWith("_")) { NewFileInputFormat.addInputPath(job, path) } + + // Store Parquet schema in `Configuration` conf.set( RowReadSupport.PARQUET_ROW_REQUESTED_SCHEMA, ParquetTypesConverter.convertFromAttributes(output).toString) - // TODO: think about adding record filters - /* Comments regarding record filters: it would be nice to push down as much filtering - to Parquet as possible. However, currently it seems we cannot pass enough information - to materialize an (arbitrary) Catalyst [[Predicate]] inside Parquet's - ``FilteredRecordReader`` (via Configuration, for example). Simple - filter-rows-by-column-values however should be supported. - */ - sc.newAPIHadoopRDD(conf, classOf[ParquetInputFormat[Row]], classOf[Void], classOf[Row]) - .map(_._2) + + // Store record filtering predicate in `Configuration` + // Note 1: the input format ignores all predicates that cannot be expressed + // as simple column predicate filters in Parquet. Here we just record + // the whole pruning predicate. + // Note 2: you can disable filter predicate pushdown by setting + // "spark.sql.hints.parquetFilterPushdown" to false inside SparkConf. + if (columnPruningPred.length > 0 && + sc.conf.getBoolean(ParquetFilters.PARQUET_FILTER_PUSHDOWN_ENABLED, true)) { + ParquetFilters.serializeFilterExpressions(columnPruningPred, conf) + } + + sc.newAPIHadoopRDD( + conf, + classOf[org.apache.spark.sql.parquet.FilteringParquetRowInputFormat], + classOf[Void], + classOf[Row]) + .map(_._2) + .filter(_ != null) // Parquet's record filters may produce null values } override def otherCopyArgs = sc :: Nil @@ -184,10 +197,19 @@ case class InsertIntoParquetTable( override def otherCopyArgs = sc :: Nil - // based on ``saveAsNewAPIHadoopFile`` in [[PairRDDFunctions]] - // TODO: Maybe PairRDDFunctions should use Product2 instead of Tuple2? - // .. then we could use the default one and could use [[MutablePair]] - // instead of ``Tuple2`` + /** + * Stores the given Row RDD as a Hadoop file. + * + * Note: We cannot use ``saveAsNewAPIHadoopFile`` from [[org.apache.spark.rdd.PairRDDFunctions]] + * together with [[org.apache.spark.util.MutablePair]] because ``PairRDDFunctions`` uses + * ``Tuple2`` and not ``Product2``. Also, we want to allow appending files to an existing + * directory and need to determine which was the largest written file index before starting to + * write. + * + * @param rdd The [[org.apache.spark.rdd.RDD]] to writer + * @param path The directory to write to. + * @param conf A [[org.apache.hadoop.conf.Configuration]]. + */ private def saveAsHadoopFile( rdd: RDD[Row], path: String, @@ -244,8 +266,10 @@ case class InsertIntoParquetTable( } } -// TODO: this will be able to append to directories it created itself, not necessarily -// to imported ones +/** + * TODO: this will be able to append to directories it created itself, not necessarily + * to imported ones. + */ private[parquet] class AppendingParquetOutputFormat(offset: Int) extends parquet.hadoop.ParquetOutputFormat[Row] { // override to accept existing directories as valid output directory @@ -262,6 +286,30 @@ private[parquet] class AppendingParquetOutputFormat(offset: Int) } } +/** + * We extend ParquetInputFormat in order to have more control over which + * RecordFilter we want to use. + */ +private[parquet] class FilteringParquetRowInputFormat + extends parquet.hadoop.ParquetInputFormat[Row] with Logging { + override def createRecordReader( + inputSplit: InputSplit, + taskAttemptContext: TaskAttemptContext): RecordReader[Void, Row] = { + val readSupport: ReadSupport[Row] = new RowReadSupport() + + val filterExpressions = + ParquetFilters.deserializeFilterExpressions(ContextUtil.getConfiguration(taskAttemptContext)) + if (filterExpressions.length > 0) { + logInfo(s"Pushing down predicates for RecordFilter: ${filterExpressions.mkString(", ")}") + new ParquetRecordReader[Row]( + readSupport, + ParquetFilters.createRecordFilter(filterExpressions)) + } else { + new ParquetRecordReader[Row](readSupport) + } + } +} + private[parquet] object FileSystemHelper { def listFiles(pathStr: String, conf: Configuration): Seq[Path] = { val origPath = new Path(pathStr) @@ -278,7 +326,9 @@ private[parquet] object FileSystemHelper { fs.listStatus(path).map(_.getPath) } - // finds the maximum taskid in the output file names at the given path + /** + * Finds the maximum taskid in the output file names at the given path. + */ def findMaxTaskId(pathStr: String, conf: Configuration): Int = { val files = FileSystemHelper.listFiles(pathStr, conf) // filename pattern is part-r-.parquet diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTestData.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTestData.scala index f37976f7313c1..46c7172985642 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTestData.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTestData.scala @@ -19,15 +19,34 @@ package org.apache.spark.sql.parquet import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.Path -import org.apache.hadoop.mapreduce.Job +import parquet.example.data.{GroupWriter, Group} +import parquet.example.data.simple.SimpleGroup import parquet.hadoop.ParquetWriter -import parquet.hadoop.util.ContextUtil +import parquet.hadoop.api.WriteSupport +import parquet.hadoop.api.WriteSupport.WriteContext +import parquet.io.api.RecordConsumer import parquet.schema.{MessageType, MessageTypeParser} -import org.apache.spark.sql.catalyst.expressions.GenericRow import org.apache.spark.util.Utils +// Write support class for nested groups: ParquetWriter initializes GroupWriteSupport +// with an empty configuration (it is after all not intended to be used in this way?) +// and members are private so we need to make our own in order to pass the schema +// to the writer. +private class TestGroupWriteSupport(schema: MessageType) extends WriteSupport[Group] { + var groupWriter: GroupWriter = null + override def prepareForWrite(recordConsumer: RecordConsumer): Unit = { + groupWriter = new GroupWriter(recordConsumer, schema) + } + override def init(configuration: Configuration): WriteContext = { + new WriteContext(schema, new java.util.HashMap[String, String]()) + } + override def write(record: Group) { + groupWriter.write(record) + } +} + private[sql] object ParquetTestData { val testSchema = @@ -43,7 +62,7 @@ private[sql] object ParquetTestData { // field names for test assertion error messages val testSchemaFieldNames = Seq( "myboolean:Boolean", - "mtint:Int", + "myint:Int", "mystring:String", "mylong:Long", "myfloat:Float", @@ -58,6 +77,18 @@ private[sql] object ParquetTestData { |} """.stripMargin + val testFilterSchema = + """ + |message myrecord { + |required boolean myboolean; + |required int32 myint; + |required binary mystring; + |required int64 mylong; + |required float myfloat; + |required double mydouble; + |} + """.stripMargin + // field names for test assertion error messages val subTestSchemaFieldNames = Seq( "myboolean:Boolean", @@ -65,36 +96,57 @@ private[sql] object ParquetTestData { ) val testDir = Utils.createTempDir() + val testFilterDir = Utils.createTempDir() lazy val testData = new ParquetRelation(testDir.toURI.toString) def writeFile() = { testDir.delete val path: Path = new Path(new Path(testDir.toURI), new Path("part-r-0.parquet")) - val job = new Job() - val configuration: Configuration = ContextUtil.getConfiguration(job) val schema: MessageType = MessageTypeParser.parseMessageType(testSchema) + val writeSupport = new TestGroupWriteSupport(schema) + val writer = new ParquetWriter[Group](path, writeSupport) - val writeSupport = new RowWriteSupport() - writeSupport.setSchema(schema, configuration) - val writer = new ParquetWriter(path, writeSupport) for(i <- 0 until 15) { - val data = new Array[Any](6) + val record = new SimpleGroup(schema) if (i % 3 == 0) { - data.update(0, true) + record.add(0, true) } else { - data.update(0, false) + record.add(0, false) } if (i % 5 == 0) { - data.update(1, 5) + record.add(1, 5) + } + record.add(2, "abc") + record.add(3, i.toLong << 33) + record.add(4, 2.5F) + record.add(5, 4.5D) + writer.write(record) + } + writer.close() + } + + def writeFilterFile(records: Int = 200) = { + // for microbenchmark use: records = 300000000 + testFilterDir.delete + val path: Path = new Path(new Path(testFilterDir.toURI), new Path("part-r-0.parquet")) + val schema: MessageType = MessageTypeParser.parseMessageType(testFilterSchema) + val writeSupport = new TestGroupWriteSupport(schema) + val writer = new ParquetWriter[Group](path, writeSupport) + + for(i <- 0 to records) { + val record = new SimpleGroup(schema) + if (i % 4 == 0) { + record.add(0, true) } else { - data.update(1, null) // optional + record.add(0, false) } - data.update(2, "abc") - data.update(3, i.toLong << 33) - data.update(4, 2.5F) - data.update(5, 4.5D) - writer.write(new GenericRow(data.toArray)) + record.add(1, i) + record.add(2, i.toString) + record.add(3, i.toLong) + record.add(4, i.toFloat + 0.5f) + record.add(5, i.toDouble + 0.5d) + writer.write(record) } writer.close() } diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala index ff1677eb8a480..65f4c17aeee3a 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetQuerySuite.scala @@ -17,25 +17,25 @@ package org.apache.spark.sql.parquet -import java.io.File - import org.scalatest.{BeforeAndAfterAll, FunSuite} import org.apache.hadoop.fs.{Path, FileSystem} import org.apache.hadoop.mapreduce.Job import parquet.hadoop.ParquetFileWriter -import parquet.schema.MessageTypeParser import parquet.hadoop.util.ContextUtil +import parquet.schema.MessageTypeParser import org.apache.spark.sql._ import org.apache.spark.sql.catalyst.util.getTempFilePath -import org.apache.spark.sql.catalyst.expressions.{AttributeReference, Row} +import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.test.TestSQLContext import org.apache.spark.sql.TestData +import org.apache.spark.sql.SchemaRDD +import org.apache.spark.sql.catalyst.expressions.Row +import org.apache.spark.sql.catalyst.expressions.Equals +import org.apache.spark.sql.catalyst.types.IntegerType import org.apache.spark.util.Utils -import org.apache.spark.sql.catalyst.types.{StringType, IntegerType, DataType} -import org.apache.spark.sql.{parquet, SchemaRDD} // Implicits import org.apache.spark.sql.test.TestSQLContext._ @@ -64,12 +64,16 @@ class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { override def beforeAll() { ParquetTestData.writeFile() + ParquetTestData.writeFilterFile() testRDD = parquetFile(ParquetTestData.testDir.toString) testRDD.registerAsTable("testsource") + parquetFile(ParquetTestData.testFilterDir.toString) + .registerAsTable("testfiltersource") } override def afterAll() { Utils.deleteRecursively(ParquetTestData.testDir) + Utils.deleteRecursively(ParquetTestData.testFilterDir) // here we should also unregister the table?? } @@ -120,7 +124,7 @@ class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { val scanner = new ParquetTableScan( ParquetTestData.testData.output, ParquetTestData.testData, - None)(TestSQLContext.sparkContext) + Seq())(TestSQLContext.sparkContext) val projected = scanner.pruneColumns(ParquetTypesConverter .convertToAttributes(MessageTypeParser .parseMessageType(ParquetTestData.subTestSchema))) @@ -196,7 +200,6 @@ class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { assert(true) } - test("insert (appending) to same table via Scala API") { sql("INSERT INTO testsource SELECT * FROM testsource").collect() val double_rdd = sql("SELECT * FROM testsource").collect() @@ -239,5 +242,121 @@ class ParquetQuerySuite extends QueryTest with FunSuite with BeforeAndAfterAll { Utils.deleteRecursively(file) assert(true) } + + test("create RecordFilter for simple predicates") { + val attribute1 = new AttributeReference("first", IntegerType, false)() + val predicate1 = new Equals(attribute1, new Literal(1, IntegerType)) + val filter1 = ParquetFilters.createFilter(predicate1) + assert(filter1.isDefined) + assert(filter1.get.predicate == predicate1, "predicates do not match") + assert(filter1.get.isInstanceOf[ComparisonFilter]) + val cmpFilter1 = filter1.get.asInstanceOf[ComparisonFilter] + assert(cmpFilter1.columnName == "first", "column name incorrect") + + val predicate2 = new LessThan(attribute1, new Literal(4, IntegerType)) + val filter2 = ParquetFilters.createFilter(predicate2) + assert(filter2.isDefined) + assert(filter2.get.predicate == predicate2, "predicates do not match") + assert(filter2.get.isInstanceOf[ComparisonFilter]) + val cmpFilter2 = filter2.get.asInstanceOf[ComparisonFilter] + assert(cmpFilter2.columnName == "first", "column name incorrect") + + val predicate3 = new And(predicate1, predicate2) + val filter3 = ParquetFilters.createFilter(predicate3) + assert(filter3.isDefined) + assert(filter3.get.predicate == predicate3, "predicates do not match") + assert(filter3.get.isInstanceOf[AndFilter]) + + val predicate4 = new Or(predicate1, predicate2) + val filter4 = ParquetFilters.createFilter(predicate4) + assert(filter4.isDefined) + assert(filter4.get.predicate == predicate4, "predicates do not match") + assert(filter4.get.isInstanceOf[OrFilter]) + + val attribute2 = new AttributeReference("second", IntegerType, false)() + val predicate5 = new GreaterThan(attribute1, attribute2) + val badfilter = ParquetFilters.createFilter(predicate5) + assert(badfilter.isDefined === false) + } + + test("test filter by predicate pushdown") { + for(myval <- Seq("myint", "mylong", "mydouble", "myfloat")) { + println(s"testing field $myval") + val query1 = sql(s"SELECT * FROM testfiltersource WHERE $myval < 150 AND $myval >= 100") + assert( + query1.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + val result1 = query1.collect() + assert(result1.size === 50) + assert(result1(0)(1) === 100) + assert(result1(49)(1) === 149) + val query2 = sql(s"SELECT * FROM testfiltersource WHERE $myval > 150 AND $myval <= 200") + assert( + query2.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + val result2 = query2.collect() + assert(result2.size === 50) + if (myval == "myint" || myval == "mylong") { + assert(result2(0)(1) === 151) + assert(result2(49)(1) === 200) + } else { + assert(result2(0)(1) === 150) + assert(result2(49)(1) === 199) + } + } + for(myval <- Seq("myint", "mylong")) { + val query3 = sql(s"SELECT * FROM testfiltersource WHERE $myval > 190 OR $myval < 10") + assert( + query3.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + val result3 = query3.collect() + assert(result3.size === 20) + assert(result3(0)(1) === 0) + assert(result3(9)(1) === 9) + assert(result3(10)(1) === 191) + assert(result3(19)(1) === 200) + } + for(myval <- Seq("mydouble", "myfloat")) { + val result4 = + if (myval == "mydouble") { + val query4 = sql(s"SELECT * FROM testfiltersource WHERE $myval > 190.5 OR $myval < 10.0") + assert( + query4.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + query4.collect() + } else { + // CASTs are problematic. Here myfloat will be casted to a double and it seems there is + // currently no way to specify float constants in SqlParser? + sql(s"SELECT * FROM testfiltersource WHERE $myval > 190.5 OR $myval < 10").collect() + } + assert(result4.size === 20) + assert(result4(0)(1) === 0) + assert(result4(9)(1) === 9) + assert(result4(10)(1) === 191) + assert(result4(19)(1) === 200) + } + val query5 = sql(s"SELECT * FROM testfiltersource WHERE myboolean = true AND myint < 40") + assert( + query5.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + val booleanResult = query5.collect() + assert(booleanResult.size === 10) + for(i <- 0 until 10) { + if (!booleanResult(i).getBoolean(0)) { + fail(s"Boolean value in result row $i not true") + } + if (booleanResult(i).getInt(1) != i * 4) { + fail(s"Int value in result row $i should be ${4*i}") + } + } + val query6 = sql("SELECT * FROM testfiltersource WHERE mystring = \"100\"") + assert( + query6.queryExecution.executedPlan(0)(0).isInstanceOf[ParquetTableScan], + "Top operator should be ParquetTableScan after pushdown") + val stringResult = query6.collect() + assert(stringResult.size === 1) + assert(stringResult(0).getString(2) == "100", "stringvalue incorrect") + assert(stringResult(0).getInt(1) === 100) + } } From fed6303f29250bd5e656dbdd731b38938c933a61 Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Fri, 16 May 2014 17:35:05 -0700 Subject: [PATCH 70/99] Tweaks to Mesos docs - Mention Apache downloads first - Shorten some wording Author: Matei Zaharia Closes #806 from mateiz/doc-update and squashes the following commits: d9345cd [Matei Zaharia] typo a179f8d [Matei Zaharia] Tweaks to Mesos docs --- docs/running-on-mesos.md | 71 +++++++++++++++++++--------------------- 1 file changed, 34 insertions(+), 37 deletions(-) diff --git a/docs/running-on-mesos.md b/docs/running-on-mesos.md index ef762aa7b8fcc..df8687f81f3ef 100644 --- a/docs/running-on-mesos.md +++ b/docs/running-on-mesos.md @@ -3,16 +3,15 @@ layout: global title: Running Spark on Mesos --- -# Why Mesos - Spark can run on hardware clusters managed by [Apache Mesos](http://mesos.apache.org/). The advantages of deploying Spark with Mesos include: + - dynamic partitioning between Spark and other [frameworks](https://mesos.apache.org/documentation/latest/mesos-frameworks/) - scalable partitioning between multiple instances of Spark -# How it works +# How it Works In a standalone cluster deployment, the cluster manager in the below diagram is a Spark master instance. When using Mesos, the Mesos master replaces the Spark master as the cluster manager. @@ -37,11 +36,25 @@ require any special patches of Mesos. If you already have a Mesos cluster running, you can skip this Mesos installation step. Otherwise, installing Mesos for Spark is no different than installing Mesos for use by other -frameworks. You can install Mesos using either prebuilt packages or by compiling from source. +frameworks. You can install Mesos either from source or using prebuilt packages. + +## From Source + +To install Apache Mesos from source, follow these steps: + +1. Download a Mesos release from a + [mirror](http://www.apache.org/dyn/closer.cgi/mesos/{{site.MESOS_VERSION}}/) +2. Follow the Mesos [Getting Started](http://mesos.apache.org/gettingstarted) page for compiling and + installing Mesos + +**Note:** If you want to run Mesos without installing it into the default paths on your system +(e.g., if you lack administrative privileges to install it), pass the +`--prefix` option to `configure` to tell it where to install. For example, pass +`--prefix=/home/me/mesos`. By default the prefix is `/usr/local`. -## Prebuilt packages +## Third-Party Packages -The Apache Mesos project only publishes source package releases, no binary releases. But other +The Apache Mesos project only publishes source releases, not binary packages. But other third party projects publish binary releases that may be helpful in setting Mesos up. One of those is Mesosphere. To install Mesos using the binary releases provided by Mesosphere: @@ -52,20 +65,6 @@ One of those is Mesosphere. To install Mesos using the binary releases provided The Mesosphere installation documents suggest setting up ZooKeeper to handle Mesos master failover, but Mesos can be run without ZooKeeper using a single master as well. -## From source - -To install Mesos directly from the upstream project rather than a third party, install from source. - -1. Download the Mesos distribution from a - [mirror](http://www.apache.org/dyn/closer.cgi/mesos/{{site.MESOS_VERSION}}/) -2. Follow the Mesos [Getting Started](http://mesos.apache.org/gettingstarted) page for compiling and - installing Mesos - -**Note:** If you want to run Mesos without installing it into the default paths on your system -(e.g., if you lack administrative privileges to install it), you should also pass the -`--prefix` option to `configure` to tell it where to install. For example, pass -`--prefix=/home/user/mesos`. By default the prefix is `/usr/local`. - ## Verification To verify that the Mesos cluster is ready for Spark, navigate to the Mesos master webui at port @@ -74,32 +73,30 @@ To verify that the Mesos cluster is ready for Spark, navigate to the Mesos maste # Connecting Spark to Mesos -To use Mesos from Spark, you need a Spark distribution available in a place accessible by Mesos, and +To use Mesos from Spark, you need a Spark binary package available in a place accessible by Mesos, and a Spark driver program configured to connect to Mesos. -## Uploading Spark Distribution - -When Mesos runs a task on a Mesos slave for the first time, that slave must have a distribution of -Spark available for running the Spark Mesos executor backend. A distribution of Spark is just a -compiled binary version of Spark. +## Uploading Spark Package -The Spark distribution can be hosted at any Hadoop URI, including HTTP via `http://`, [Amazon Simple -Storage Service](http://aws.amazon.com/s3) via `s3://`, or HDFS via `hdfs:///`. +When Mesos runs a task on a Mesos slave for the first time, that slave must have a Spark binary +package for running the Spark Mesos executor backend. +The Spark package can be hosted at any Hadoop-accessible URI, including HTTP via `http://`, +[Amazon Simple Storage Service](http://aws.amazon.com/s3) via `s3n://`, or HDFS via `hdfs://`. -To use a precompiled distribution: +To use a precompiled package: -1. Download a Spark distribution from the Spark [download page](https://spark.apache.org/downloads.html) +1. Download a Spark binary package from the Spark [download page](https://spark.apache.org/downloads.html) 2. Upload to hdfs/http/s3 To host on HDFS, use the Hadoop fs put command: `hadoop fs -put spark-{{site.SPARK_VERSION}}.tar.gz /path/to/spark-{{site.SPARK_VERSION}}.tar.gz` -Or if you are using a custom-compiled version of Spark, you will need to create a distribution using +Or if you are using a custom-compiled version of Spark, you will need to create a package using the `make-distribution.sh` script included in a Spark source tarball/checkout. 1. Download and build Spark using the instructions [here](index.html) -2. Create a Spark distribution using `make-distribution.sh --tgz`. +2. Create a binary package using `make-distribution.sh --tgz`. 3. Upload archive to http/s3/hdfs @@ -115,8 +112,8 @@ The driver also needs some configuration in `spark-env.sh` to interact properly `/lib/libmesos.so` where the prefix is `/usr/local` by default. See Mesos installation instructions above. On Mac OS X, the library is called `libmesos.dylib` instead of `libmesos.so`. - * `export SPARK_EXECUTOR_URI=`. -2. Also set `spark.executor.uri` to + * `export SPARK_EXECUTOR_URI=`. +2. Also set `spark.executor.uri` to ``. Now when starting a Spark application against the cluster, pass a `mesos://` or `zk://` URL as the master when creating a `SparkContext`. For example: @@ -129,7 +126,7 @@ val conf = new SparkConf() val sc = new SparkContext(conf) {% endhighlight %} -When running a shell the `spark.executor.uri` parameter is inherited from `SPARK_EXECUTOR_URI`, so +When running a shell, the `spark.executor.uri` parameter is inherited from `SPARK_EXECUTOR_URI`, so it does not need to be redundantly passed in as a system property. {% highlight bash %} @@ -168,7 +165,7 @@ using `conf.set("spark.cores.max", "10")` (for example). # Running Alongside Hadoop You can run Spark and Mesos alongside your existing Hadoop cluster by just launching them as a -separate service on the machines. To access Hadoop data from Spark, a full hdfs:// URL is required +separate service on the machines. To access Hadoop data from Spark, a full `hdfs://` URL is required (typically `hdfs://:9000/path`, but you can find the right URL on your Hadoop Namenode web UI). @@ -195,7 +192,7 @@ A few places to look during debugging: And common pitfalls: - Spark assembly not reachable/accessible - - Slaves need to be able to download the distribution + - Slaves must be able to download the Spark binary package from the `http://`, `hdfs://` or `s3n://` URL you gave - Firewall blocking communications - Check for messages about failed connections - Temporarily disable firewalls for debugging and then poke appropriate holes From a80a6a139e729ee3f81ec4f0028e084d2d9f7e82 Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Fri, 16 May 2014 20:25:10 -0700 Subject: [PATCH 71/99] SPARK-1864 Look in spark conf instead of system properties when propagating configuration to executors. Author: Michael Armbrust Closes #808 from marmbrus/confClasspath and squashes the following commits: 4c31d57 [Michael Armbrust] Look in spark conf instead of system properties when propagating configuration to executors. --- .../scheduler/cluster/SparkDeploySchedulerBackend.scala | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala index 933f6e0571518..9768670855f80 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala @@ -46,12 +46,13 @@ private[spark] class SparkDeploySchedulerBackend( CoarseGrainedSchedulerBackend.ACTOR_NAME) val args = Seq(driverUrl, "{{EXECUTOR_ID}}", "{{HOSTNAME}}", "{{CORES}}", "{{WORKER_URL}}") val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions") - val classPathEntries = sys.props.get("spark.executor.extraClassPath").toSeq.flatMap { cp => - cp.split(java.io.File.pathSeparator) - } - val libraryPathEntries = sys.props.get("spark.executor.extraLibraryPath").toSeq.flatMap { cp => + val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath").toSeq.flatMap { cp => cp.split(java.io.File.pathSeparator) } + val libraryPathEntries = + sc.conf.getOption("spark.executor.extraLibraryPath").toSeq.flatMap { cp => + cp.split(java.io.File.pathSeparator) + } val command = Command( "org.apache.spark.executor.CoarseGrainedExecutorBackend", args, sc.executorEnvs, From c0ab85d7320cea90e6331fb03a70349bc804c1b1 Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Fri, 16 May 2014 21:42:14 -0700 Subject: [PATCH 72/99] Version bump of spark-ec2 scripts This will allow us to change things in spark-ec2 related to the 1.0 release. Author: Patrick Wendell Closes #809 from pwendell/spark-ec2 and squashes the following commits: 59117fb [Patrick Wendell] Version bump of spark-ec2 scripts --- ec2/spark_ec2.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py index 0a8d6ca5d7519..4c5a99f5f6b2e 100755 --- a/ec2/spark_ec2.py +++ b/ec2/spark_ec2.py @@ -443,7 +443,7 @@ def setup_cluster(conn, master_nodes, slave_nodes, opts, deploy_ssh_key): # NOTE: We should clone the repository before running deploy_files to # prevent ec2-variables.sh from being overwritten - ssh(master, opts, "rm -rf spark-ec2 && git clone https://github.com/mesos/spark-ec2.git -b v2") + ssh(master, opts, "rm -rf spark-ec2 && git clone https://github.com/mesos/spark-ec2.git -b v3") print "Deploying files to master..." deploy_files(conn, "deploy.generic", opts, master_nodes, slave_nodes, modules) From 4b8ec6fcfd7a7ef0857d5b21917183c181301c95 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Fri, 16 May 2014 22:34:38 -0700 Subject: [PATCH 73/99] [SPARK-1808] Route bin/pyspark through Spark submit **Problem.** For `bin/pyspark`, there is currently no other way to specify Spark configuration properties other than through `SPARK_JAVA_OPTS` in `conf/spark-env.sh`. However, this mechanism is supposedly deprecated. Instead, it needs to pick up configurations explicitly specified in `conf/spark-defaults.conf`. **Solution.** Have `bin/pyspark` invoke `bin/spark-submit`, like all of its counterparts in Scala land (i.e. `bin/spark-shell`, `bin/run-example`). This has the additional benefit of making the invocation of all the user facing Spark scripts consistent. **Details.** `bin/pyspark` inherently handles two cases: (1) running python applications and (2) running the python shell. For (1), Spark submit already handles running python applications. For cases in which `bin/pyspark` is given a python file, we can simply call pass the file directly to Spark submit and let it handle the rest. For case (2), `bin/pyspark` starts a python process as before, which launches the JVM as a sub-process. The existing code already provides a code path to do this. All we needed to change is to use `bin/spark-submit` instead of `spark-class` to launch the JVM. This requires modifications to Spark submit to handle the pyspark shell as a special case. This has been tested locally (OSX and Windows 7), on a standalone cluster, and on a YARN cluster. Running IPython also works as before, except now it takes in Spark submit arguments too. Author: Andrew Or Closes #799 from andrewor14/pyspark-submit and squashes the following commits: bf37e36 [Andrew Or] Minor changes 01066fa [Andrew Or] bin/pyspark for Windows c8cb3bf [Andrew Or] Handle perverse app names (with escaped quotes) 1866f85 [Andrew Or] Windows is not cooperating 456d844 [Andrew Or] Guard against shlex hanging if PYSPARK_SUBMIT_ARGS is not set 7eebda8 [Andrew Or] Merge branch 'master' of github.com:apache/spark into pyspark-submit b7ba0d8 [Andrew Or] Address a few comments (minor) 06eb138 [Andrew Or] Use shlex instead of writing our own parser 05879fa [Andrew Or] Merge branch 'master' of github.com:apache/spark into pyspark-submit a823661 [Andrew Or] Fix --die-on-broken-pipe not propagated properly 6fba412 [Andrew Or] Deal with quotes + address various comments fe4c8a7 [Andrew Or] Update --help for bin/pyspark afe47bf [Andrew Or] Fix spark shell f04aaa4 [Andrew Or] Merge branch 'master' of github.com:apache/spark into pyspark-submit a371d26 [Andrew Or] Route bin/pyspark through Spark submit --- bin/pyspark | 35 ++++++++++-- bin/pyspark2.cmd | 21 ++++++- bin/spark-shell | 6 +- bin/spark-shell.cmd | 2 +- .../apache/spark/deploy/PythonRunner.scala | 2 +- .../org/apache/spark/deploy/SparkSubmit.scala | 55 ++++++++++++++----- .../spark/deploy/SparkSubmitArguments.scala | 6 +- .../scala/org/apache/spark/util/Utils.scala | 2 +- python/pyspark/java_gateway.py | 10 ++-- python/pyspark/shell.py | 2 +- 10 files changed, 107 insertions(+), 34 deletions(-) diff --git a/bin/pyspark b/bin/pyspark index 10e35e0f1734e..9e1364e44c8c4 100755 --- a/bin/pyspark +++ b/bin/pyspark @@ -25,6 +25,12 @@ export SPARK_HOME="$FWDIR" SCALA_VERSION=2.10 +if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then + echo "Usage: ./bin/pyspark [options]" + ./bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 + exit 0 +fi + # Exit if the user hasn't compiled Spark if [ ! -f "$FWDIR/RELEASE" ]; then # Exit if the user hasn't compiled Spark @@ -52,13 +58,34 @@ export PYTHONPATH=$SPARK_HOME/python/lib/py4j-0.8.1-src.zip:$PYTHONPATH export OLD_PYTHONSTARTUP=$PYTHONSTARTUP export PYTHONSTARTUP=$FWDIR/python/pyspark/shell.py +# If IPython options are specified, assume user wants to run IPython if [ -n "$IPYTHON_OPTS" ]; then IPYTHON=1 fi -# Only use ipython if no command line arguments were provided [SPARK-1134] -if [[ "$IPYTHON" = "1" && $# = 0 ]] ; then - exec ipython $IPYTHON_OPTS +# Build up arguments list manually to preserve quotes and backslashes. +# We export Spark submit arguments as an environment variable because shell.py must run as a +# PYTHONSTARTUP script, which does not take in arguments. This is required for IPython notebooks. + +PYSPARK_SUBMIT_ARGS="" +whitespace="[[:space:]]" +for i in "$@"; do + if [[ $i =~ \" ]]; then i=$(echo $i | sed 's/\"/\\\"/g'); fi + if [[ $i =~ $whitespace ]]; then i=\"$i\"; fi + PYSPARK_SUBMIT_ARGS="$PYSPARK_SUBMIT_ARGS $i" +done +export PYSPARK_SUBMIT_ARGS + +# If a python file is provided, directly run spark-submit. +if [[ "$1" =~ \.py$ ]]; then + echo -e "\nWARNING: Running python applications through ./bin/pyspark is deprecated as of Spark 1.0." 1>&2 + echo -e "Use ./bin/spark-submit \n" 1>&2 + exec $FWDIR/bin/spark-submit "$@" else - exec "$PYSPARK_PYTHON" "$@" + # Only use ipython if no command line arguments were provided [SPARK-1134] + if [[ "$IPYTHON" = "1" ]]; then + exec ipython $IPYTHON_OPTS + else + exec "$PYSPARK_PYTHON" + fi fi diff --git a/bin/pyspark2.cmd b/bin/pyspark2.cmd index d7cfd5eec501c..0ef9eea95342e 100644 --- a/bin/pyspark2.cmd +++ b/bin/pyspark2.cmd @@ -31,7 +31,7 @@ set FOUND_JAR=0 for %%d in ("%FWDIR%assembly\target\scala-%SCALA_VERSION%\spark-assembly*hadoop*.jar") do ( set FOUND_JAR=1 ) -if "%FOUND_JAR%"=="0" ( +if [%FOUND_JAR%] == [0] ( echo Failed to find Spark assembly JAR. echo You need to build Spark with sbt\sbt assembly before running this program. goto exit @@ -42,15 +42,30 @@ rem Load environment variables from conf\spark-env.cmd, if it exists if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd" rem Figure out which Python to use. -if "x%PYSPARK_PYTHON%"=="x" set PYSPARK_PYTHON=python +if [%PYSPARK_PYTHON%] == [] set PYSPARK_PYTHON=python set PYTHONPATH=%FWDIR%python;%PYTHONPATH% set PYTHONPATH=%FWDIR%python\lib\py4j-0.8.1-src.zip;%PYTHONPATH% set OLD_PYTHONSTARTUP=%PYTHONSTARTUP% set PYTHONSTARTUP=%FWDIR%python\pyspark\shell.py +set PYSPARK_SUBMIT_ARGS=%* echo Running %PYSPARK_PYTHON% with PYTHONPATH=%PYTHONPATH% -"%PYSPARK_PYTHON%" %* +rem Check whether the argument is a file +for /f %%i in ('echo %1^| findstr /R "\.py"') do ( + set PYTHON_FILE=%%i +) + +if [%PYTHON_FILE%] == [] ( + %PYSPARK_PYTHON% +) else ( + echo. + echo WARNING: Running python applications through ./bin/pyspark.cmd is deprecated as of Spark 1.0. + echo Use ./bin/spark-submit ^ + echo. + "%FWDIR%\bin\spark-submit.cmd" %PYSPARK_SUBMIT_ARGS% +) + :exit diff --git a/bin/spark-shell b/bin/spark-shell index 7f03349c5e910..c158683ab3f99 100755 --- a/bin/spark-shell +++ b/bin/spark-shell @@ -28,7 +28,7 @@ esac # Enter posix mode for bash set -o posix -if [[ "$@" == *--help* ]]; then +if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then echo "Usage: ./bin/spark-shell [options]" ./bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 exit 0 @@ -46,11 +46,11 @@ function main(){ # (see https://github.com/sbt/sbt/issues/562). stty -icanon min 1 -echo > /dev/null 2>&1 export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix" - $FWDIR/bin/spark-submit spark-internal "$@" --class org.apache.spark.repl.Main + $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main stty icanon echo > /dev/null 2>&1 else export SPARK_SUBMIT_OPTS - $FWDIR/bin/spark-submit spark-internal "$@" --class org.apache.spark.repl.Main + $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main fi } diff --git a/bin/spark-shell.cmd b/bin/spark-shell.cmd index ca0c722c926f5..4b9708a8c03f3 100755 --- a/bin/spark-shell.cmd +++ b/bin/spark-shell.cmd @@ -19,4 +19,4 @@ rem set SPARK_HOME=%~dp0.. -cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-internal %* --class org.apache.spark.repl.Main +cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-shell %* --class org.apache.spark.repl.Main diff --git a/core/src/main/scala/org/apache/spark/deploy/PythonRunner.scala b/core/src/main/scala/org/apache/spark/deploy/PythonRunner.scala index e20d4486c8f0c..2dfa02bd26f13 100644 --- a/core/src/main/scala/org/apache/spark/deploy/PythonRunner.scala +++ b/core/src/main/scala/org/apache/spark/deploy/PythonRunner.scala @@ -42,7 +42,7 @@ object PythonRunner { // Build up a PYTHONPATH that includes the Spark assembly JAR (where this class is), the // python directories in SPARK_HOME (if set), and any files in the pyFiles argument val pathElements = new ArrayBuffer[String] - pathElements ++= pyFiles.split(",") + pathElements ++= Option(pyFiles).getOrElse("").split(",") pathElements += PythonUtils.sparkPythonPath pathElements += sys.env.getOrElse("PYTHONPATH", "") val pythonPath = PythonUtils.mergePythonPaths(pathElements: _*) diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala index e86182e4c56ce..a99b2176e2b5e 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala @@ -41,10 +41,10 @@ object SparkSubmit { private var clusterManager: Int = LOCAL /** - * A special jar name that indicates the class being run is inside of Spark itself, - * and therefore no user jar is needed. + * Special primary resource names that represent shells rather than application jars. */ - private val RESERVED_JAR_NAME = "spark-internal" + private val SPARK_SHELL = "spark-shell" + private val PYSPARK_SHELL = "pyspark-shell" def main(args: Array[String]) { val appArgs = new SparkSubmitArguments(args) @@ -71,8 +71,8 @@ object SparkSubmit { * entries for the child, a list of system properties, a list of env vars * and the main class for the child */ - private[spark] def createLaunchEnv(args: SparkSubmitArguments): (ArrayBuffer[String], - ArrayBuffer[String], Map[String, String], String) = { + private[spark] def createLaunchEnv(args: SparkSubmitArguments) + : (ArrayBuffer[String], ArrayBuffer[String], Map[String, String], String) = { if (args.master.startsWith("local")) { clusterManager = LOCAL } else if (args.master.startsWith("yarn")) { @@ -121,24 +121,30 @@ object SparkSubmit { printErrorAndExit("Cannot currently run driver on the cluster in Mesos") } - // If we're running a Python app, set the Java class to run to be our PythonRunner, add - // Python files to deployment list, and pass the main file and Python path to PythonRunner + // If we're running a python app, set the main class to our specific python runner if (isPython) { if (deployOnCluster) { printErrorAndExit("Cannot currently run Python driver programs on cluster") } - args.mainClass = "org.apache.spark.deploy.PythonRunner" - args.files = mergeFileLists(args.files, args.pyFiles, args.primaryResource) + if (args.primaryResource == PYSPARK_SHELL) { + args.mainClass = "py4j.GatewayServer" + args.childArgs = ArrayBuffer("--die-on-broken-pipe", "0") + } else { + // If a python file is provided, add it to the child arguments and list of files to deploy. + // Usage: PythonAppRunner
[app arguments] + args.mainClass = "org.apache.spark.deploy.PythonRunner" + args.childArgs = ArrayBuffer(args.primaryResource, args.pyFiles) ++ args.childArgs + args.files = mergeFileLists(args.files, args.primaryResource) + } val pyFiles = Option(args.pyFiles).getOrElse("") - args.childArgs = ArrayBuffer(args.primaryResource, pyFiles) ++ args.childArgs - args.primaryResource = RESERVED_JAR_NAME + args.files = mergeFileLists(args.files, pyFiles) sysProps("spark.submit.pyFiles") = pyFiles } // If we're deploying into YARN, use yarn.Client as a wrapper around the user class if (!deployOnCluster) { childMainClass = args.mainClass - if (args.primaryResource != RESERVED_JAR_NAME) { + if (isUserJar(args.primaryResource)) { childClasspath += args.primaryResource } } else if (clusterManager == YARN) { @@ -219,7 +225,7 @@ object SparkSubmit { // For python files, the primary resource is already distributed as a regular file if (!isYarnCluster && !isPython) { var jars = sysProps.get("spark.jars").map(x => x.split(",").toSeq).getOrElse(Seq()) - if (args.primaryResource != RESERVED_JAR_NAME) { + if (isUserJar(args.primaryResource)) { jars = jars ++ Seq(args.primaryResource) } sysProps.put("spark.jars", jars.mkString(",")) @@ -293,7 +299,7 @@ object SparkSubmit { } private def addJarToClasspath(localJar: String, loader: ExecutorURLClassLoader) { - val localJarFile = new File(new URI(localJar).getPath()) + val localJarFile = new File(new URI(localJar).getPath) if (!localJarFile.exists()) { printWarning(s"Jar $localJar does not exist, skipping.") } @@ -302,6 +308,27 @@ object SparkSubmit { loader.addURL(url) } + /** + * Return whether the given primary resource represents a user jar. + */ + private def isUserJar(primaryResource: String): Boolean = { + !isShell(primaryResource) && !isPython(primaryResource) + } + + /** + * Return whether the given primary resource represents a shell. + */ + private def isShell(primaryResource: String): Boolean = { + primaryResource == SPARK_SHELL || primaryResource == PYSPARK_SHELL + } + + /** + * Return whether the given primary resource requires running python. + */ + private[spark] def isPython(primaryResource: String): Boolean = { + primaryResource.endsWith(".py") || primaryResource == PYSPARK_SHELL + } + /** * Merge a sequence of comma-separated file lists, some of which may be null to indicate * no files, into a single comma-separated string. diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala index 2d327aa3fb27f..264d4544cd31c 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala @@ -298,11 +298,13 @@ private[spark] class SparkSubmitArguments(args: Seq[String]) { case v => primaryResource = v inSparkOpts = false - isPython = v.endsWith(".py") + isPython = SparkSubmit.isPython(v) parse(tail) } } else { - childArgs += value + if (!value.isEmpty) { + childArgs += value + } parse(tail) } diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 388f7222428db..0c7cff019fce1 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -1101,7 +1101,7 @@ private[spark] object Utils extends Logging { * Strip the directory from a path name */ def stripDirectory(path: String): String = { - path.split(File.separator).last + new File(path).getName } /** diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py index 3d0936fdca911..91ae8263f66b8 100644 --- a/python/pyspark/java_gateway.py +++ b/python/pyspark/java_gateway.py @@ -18,12 +18,12 @@ import os import sys import signal +import shlex import platform from subprocess import Popen, PIPE from threading import Thread from py4j.java_gateway import java_import, JavaGateway, GatewayClient - def launch_gateway(): SPARK_HOME = os.environ["SPARK_HOME"] @@ -34,9 +34,11 @@ def launch_gateway(): # Launch the Py4j gateway using Spark's run command so that we pick up the # proper classpath and settings from spark-env.sh on_windows = platform.system() == "Windows" - script = "./bin/spark-class.cmd" if on_windows else "./bin/spark-class" - command = [os.path.join(SPARK_HOME, script), "py4j.GatewayServer", - "--die-on-broken-pipe", "0"] + script = "./bin/spark-submit.cmd" if on_windows else "./bin/spark-submit" + submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS") + submit_args = submit_args if submit_args is not None else "" + submit_args = shlex.split(submit_args) + command = [os.path.join(SPARK_HOME, script), "pyspark-shell"] + submit_args if not on_windows: # Don't send ctrl-c / SIGINT to the Java gateway: def preexec_func(): diff --git a/python/pyspark/shell.py b/python/pyspark/shell.py index d172d588bfbd8..ebd714db7a918 100644 --- a/python/pyspark/shell.py +++ b/python/pyspark/shell.py @@ -40,7 +40,7 @@ if os.environ.get("SPARK_EXECUTOR_URI"): SparkContext.setSystemProperty("spark.executor.uri", os.environ["SPARK_EXECUTOR_URI"]) -sc = SparkContext(os.environ.get("MASTER", "local[*]"), "PySparkShell", pyFiles=add_files) +sc = SparkContext(appName="PySparkShell", pyFiles=add_files) print("""Welcome to ____ __ From cf6cbe9f76c3b322a968c836d039fc5b70d4ce43 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Fri, 16 May 2014 22:36:23 -0700 Subject: [PATCH 74/99] [SPARK-1824] Remove from Python examples A recent PR (#552) fixed this for all Scala / Java examples. We need to do it for python too. Note that this blocks on #799, which makes `bin/pyspark` go through Spark submit. With only the changes in this PR, the only way to run these examples is through Spark submit. Once #799 goes in, you can use `bin/pyspark` to run them too. For example, ``` bin/pyspark examples/src/main/python/pi.py 100 --master local-cluster[4,1,512] ``` Author: Andrew Or Closes #802 from andrewor14/python-examples and squashes the following commits: cf50b9f [Andrew Or] De-indent python comments (minor) 50f80b1 [Andrew Or] Remove pyFiles from SparkContext construction c362f69 [Andrew Or] Update docs to use spark-submit for python applications 7072c6a [Andrew Or] Merge branch 'master' of github.com:apache/spark into python-examples 427a5f0 [Andrew Or] Update docs d32072c [Andrew Or] Remove from examples + update usages --- docs/index.md | 11 ++++--- docs/python-programming-guide.md | 32 ++++++++++--------- examples/src/main/python/als.py | 18 +++++------ examples/src/main/python/kmeans.py | 12 +++---- .../src/main/python/logistic_regression.py | 10 +++--- examples/src/main/python/mllib/kmeans.py | 10 +++--- .../main/python/mllib/logistic_regression.py | 10 +++--- examples/src/main/python/pagerank.py | 10 +++--- examples/src/main/python/pi.py | 10 +++--- examples/src/main/python/sort.py | 8 ++--- .../src/main/python/transitive_closure.py | 10 +++--- examples/src/main/python/wordcount.py | 8 ++--- 12 files changed, 77 insertions(+), 72 deletions(-) diff --git a/docs/index.md b/docs/index.md index 48182a27d28ae..c9b10376cc809 100644 --- a/docs/index.md +++ b/docs/index.md @@ -43,12 +43,15 @@ The `--master` option specifies the locally with one thread, or `local[N]` to run locally with N threads. You should start by using `local` for testing. For a full list of options, run Spark shell with the `--help` option. -Spark also provides a Python interface. To run an example Spark application written in Python, use -`bin/pyspark [params]`. For example, +Spark also provides a Python interface. To run Spark interactively in a Python interpreter, use +`bin/pyspark`. As in Spark shell, you can also pass in the `--master` option to configure your +master URL. - ./bin/pyspark examples/src/main/python/pi.py local[2] 10 + ./bin/pyspark --master local[2] -or simply `bin/pyspark` without any arguments to run Spark interactively in a python interpreter. +Example applications are also provided in Python. For example, + + ./bin/spark-submit examples/src/main/python/pi.py 10 # Launching on a Cluster diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index 17675acba6bb8..b686bee1aebe2 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -60,13 +60,9 @@ By default, PySpark requires `python` to be available on the system `PATH` and u All of PySpark's library dependencies, including [Py4J](http://py4j.sourceforge.net/), are bundled with PySpark and automatically imported. -Standalone PySpark applications should be run using the `bin/spark-submit` script, which automatically -configures the Java and Python environment for running Spark. - - # Interactive Use -The `bin/pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options: +The `bin/pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line: {% highlight bash %} $ sbt/sbt assembly @@ -83,20 +79,24 @@ The Python shell can be used explore data interactively and is a simple way to l {% endhighlight %} By default, the `bin/pyspark` shell creates SparkContext that runs applications locally on all of -your machine's logical cores. -To connect to a non-local cluster, or to specify a number of cores, set the `MASTER` environment variable. -For example, to use the `bin/pyspark` shell with a [standalone Spark cluster](spark-standalone.html): +your machine's logical cores. To connect to a non-local cluster, or to specify a number of cores, +set the `--master` flag. For example, to use the `bin/pyspark` shell with a +[standalone Spark cluster](spark-standalone.html): {% highlight bash %} -$ MASTER=spark://IP:PORT ./bin/pyspark +$ ./bin/pyspark --master spark://1.2.3.4:7077 {% endhighlight %} Or, to use exactly four cores on the local machine: {% highlight bash %} -$ MASTER=local[4] ./bin/pyspark +$ ./bin/pyspark --master local[4] {% endhighlight %} +Under the hood `bin/pyspark` is a wrapper around the +[Spark submit script](cluster-overview.html#launching-applications-with-spark-submit), so these +two scripts share the same list of options. For a complete list of options, run `bin/pyspark` with +the `--help` option. ## IPython @@ -115,13 +115,14 @@ the [IPython Notebook](http://ipython.org/notebook.html) with PyLab graphing sup $ IPYTHON_OPTS="notebook --pylab inline" ./bin/pyspark {% endhighlight %} -IPython also works on a cluster or on multiple cores if you set the `MASTER` environment variable. +IPython also works on a cluster or on multiple cores if you set the `--master` flag. # Standalone Programs -PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `bin/spark-submit`. -The Quick Start guide includes a [complete example](quick-start.html#standalone-applications) of a standalone Python application. +PySpark can also be used from standalone Python scripts by creating a SparkContext in your script +and running the script using `bin/spark-submit`. The Quick Start guide includes a +[complete example](quick-start.html#standalone-applications) of a standalone Python application. Code dependencies can be deployed by passing .zip or .egg files in the `--py-files` option of `spark-submit`: @@ -138,6 +139,7 @@ You can set [configuration properties](configuration.html#spark-properties) by p {% highlight python %} from pyspark import SparkConf, SparkContext conf = (SparkConf() + .setMaster("local") .setAppName("My app") .set("spark.executor.memory", "1g")) sc = SparkContext(conf = conf) @@ -164,6 +166,6 @@ some example applications. PySpark also includes several sample programs in the [`examples/src/main/python` folder](https://github.com/apache/spark/tree/master/examples/src/main/python). You can run them by passing the files to `pyspark`; e.g.: - ./bin/spark-submit examples/src/main/python/wordcount.py local[2] README.md + ./bin/spark-submit examples/src/main/python/wordcount.py README.md -Each program prints usage help when run without arguments. +Each program prints usage help when run without the sufficient arguments. diff --git a/examples/src/main/python/als.py b/examples/src/main/python/als.py index 01552dc1d449e..f0b46cd28b7aa 100755 --- a/examples/src/main/python/als.py +++ b/examples/src/main/python/als.py @@ -46,15 +46,15 @@ def update(i, vec, mat, ratings): return np.linalg.solve(XtX, Xty) if __name__ == "__main__": - if len(sys.argv) < 2: - print >> sys.stderr, "Usage: als " - exit(-1) - sc = SparkContext(sys.argv[1], "PythonALS", pyFiles=[realpath(__file__)]) - M = int(sys.argv[2]) if len(sys.argv) > 2 else 100 - U = int(sys.argv[3]) if len(sys.argv) > 3 else 500 - F = int(sys.argv[4]) if len(sys.argv) > 4 else 10 - ITERATIONS = int(sys.argv[5]) if len(sys.argv) > 5 else 5 - slices = int(sys.argv[6]) if len(sys.argv) > 6 else 2 + """ + Usage: als [M] [U] [F] [iterations] [slices]" + """ + sc = SparkContext(appName="PythonALS") + M = int(sys.argv[1]) if len(sys.argv) > 1 else 100 + U = int(sys.argv[2]) if len(sys.argv) > 2 else 500 + F = int(sys.argv[3]) if len(sys.argv) > 3 else 10 + ITERATIONS = int(sys.argv[4]) if len(sys.argv) > 4 else 5 + slices = int(sys.argv[5]) if len(sys.argv) > 5 else 2 print "Running ALS with M=%d, U=%d, F=%d, iters=%d, slices=%d\n" % \ (M, U, F, ITERATIONS, slices) diff --git a/examples/src/main/python/kmeans.py b/examples/src/main/python/kmeans.py index e3596488faf9e..fc16586c28a46 100755 --- a/examples/src/main/python/kmeans.py +++ b/examples/src/main/python/kmeans.py @@ -45,14 +45,14 @@ def closestPoint(p, centers): if __name__ == "__main__": - if len(sys.argv) < 5: - print >> sys.stderr, "Usage: kmeans " + if len(sys.argv) != 4: + print >> sys.stderr, "Usage: kmeans " exit(-1) - sc = SparkContext(sys.argv[1], "PythonKMeans") - lines = sc.textFile(sys.argv[2]) + sc = SparkContext(appName="PythonKMeans") + lines = sc.textFile(sys.argv[1]) data = lines.map(parseVector).cache() - K = int(sys.argv[3]) - convergeDist = float(sys.argv[4]) + K = int(sys.argv[2]) + convergeDist = float(sys.argv[3]) kPoints = data.takeSample(False, K, 1) tempDist = 1.0 diff --git a/examples/src/main/python/logistic_regression.py b/examples/src/main/python/logistic_regression.py index fe5373cf799b1..0f22d0b32319e 100755 --- a/examples/src/main/python/logistic_regression.py +++ b/examples/src/main/python/logistic_regression.py @@ -47,12 +47,12 @@ def readPointBatch(iterator): return [matrix] if __name__ == "__main__": - if len(sys.argv) != 4: - print >> sys.stderr, "Usage: logistic_regression " + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: logistic_regression " exit(-1) - sc = SparkContext(sys.argv[1], "PythonLR", pyFiles=[realpath(__file__)]) - points = sc.textFile(sys.argv[2]).mapPartitions(readPointBatch).cache() - iterations = int(sys.argv[3]) + sc = SparkContext(appName="PythonLR") + points = sc.textFile(sys.argv[1]).mapPartitions(readPointBatch).cache() + iterations = int(sys.argv[2]) # Initialize w to a random value w = 2 * np.random.ranf(size=D) - 1 diff --git a/examples/src/main/python/mllib/kmeans.py b/examples/src/main/python/mllib/kmeans.py index dec82ff34fbac..b308132c9aeeb 100755 --- a/examples/src/main/python/mllib/kmeans.py +++ b/examples/src/main/python/mllib/kmeans.py @@ -33,12 +33,12 @@ def parseVector(line): if __name__ == "__main__": - if len(sys.argv) < 4: - print >> sys.stderr, "Usage: kmeans " + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: kmeans " exit(-1) - sc = SparkContext(sys.argv[1], "KMeans") - lines = sc.textFile(sys.argv[2]) + sc = SparkContext(appName="KMeans") + lines = sc.textFile(sys.argv[1]) data = lines.map(parseVector) - k = int(sys.argv[3]) + k = int(sys.argv[2]) model = KMeans.train(data, k) print "Final centers: " + str(model.clusterCenters) diff --git a/examples/src/main/python/mllib/logistic_regression.py b/examples/src/main/python/mllib/logistic_regression.py index 8631051d00ff2..6e0f7a4ee5a81 100755 --- a/examples/src/main/python/mllib/logistic_regression.py +++ b/examples/src/main/python/mllib/logistic_regression.py @@ -39,12 +39,12 @@ def parsePoint(line): if __name__ == "__main__": - if len(sys.argv) != 4: - print >> sys.stderr, "Usage: logistic_regression " + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: logistic_regression " exit(-1) - sc = SparkContext(sys.argv[1], "PythonLR") - points = sc.textFile(sys.argv[2]).map(parsePoint) - iterations = int(sys.argv[3]) + sc = SparkContext(appName="PythonLR") + points = sc.textFile(sys.argv[1]).map(parsePoint) + iterations = int(sys.argv[2]) model = LogisticRegressionWithSGD.train(points, iterations) print "Final weights: " + str(model.weights) print "Final intercept: " + str(model.intercept) diff --git a/examples/src/main/python/pagerank.py b/examples/src/main/python/pagerank.py index cd774cf3a319f..d350fa46fa49a 100755 --- a/examples/src/main/python/pagerank.py +++ b/examples/src/main/python/pagerank.py @@ -36,19 +36,19 @@ def parseNeighbors(urls): if __name__ == "__main__": - if len(sys.argv) < 3: - print >> sys.stderr, "Usage: pagerank " + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: pagerank " exit(-1) # Initialize the spark context. - sc = SparkContext(sys.argv[1], "PythonPageRank") + sc = SparkContext(appName="PythonPageRank") # Loads in input file. It should be in format of: # URL neighbor URL # URL neighbor URL # URL neighbor URL # ... - lines = sc.textFile(sys.argv[2], 1) + lines = sc.textFile(sys.argv[1], 1) # Loads all URLs from input file and initialize their neighbors. links = lines.map(lambda urls: parseNeighbors(urls)).distinct().groupByKey().cache() @@ -57,7 +57,7 @@ def parseNeighbors(urls): ranks = links.map(lambda (url, neighbors): (url, 1.0)) # Calculates and updates URL ranks continuously using PageRank algorithm. - for iteration in xrange(int(sys.argv[3])): + for iteration in xrange(int(sys.argv[2])): # Calculates URL contributions to the rank of other URLs. contribs = links.join(ranks).flatMap(lambda (url, (urls, rank)): computeContribs(urls, rank)) diff --git a/examples/src/main/python/pi.py b/examples/src/main/python/pi.py index ab0645fc2f326..234720b55fa49 100755 --- a/examples/src/main/python/pi.py +++ b/examples/src/main/python/pi.py @@ -23,11 +23,11 @@ if __name__ == "__main__": - if len(sys.argv) == 1: - print >> sys.stderr, "Usage: pi []" - exit(-1) - sc = SparkContext(sys.argv[1], "PythonPi") - slices = int(sys.argv[2]) if len(sys.argv) > 2 else 2 + """ + Usage: pi [slices] + """ + sc = SparkContext(appName="PythonPi") + slices = int(sys.argv[1]) if len(sys.argv) > 1 else 2 n = 100000 * slices def f(_): x = random() * 2 - 1 diff --git a/examples/src/main/python/sort.py b/examples/src/main/python/sort.py index 5de20a6d98f43..4913ee926aa03 100755 --- a/examples/src/main/python/sort.py +++ b/examples/src/main/python/sort.py @@ -21,11 +21,11 @@ if __name__ == "__main__": - if len(sys.argv) < 3: - print >> sys.stderr, "Usage: sort " + if len(sys.argv) != 2: + print >> sys.stderr, "Usage: sort " exit(-1) - sc = SparkContext(sys.argv[1], "PythonSort") - lines = sc.textFile(sys.argv[2], 1) + sc = SparkContext(appName="PythonSort") + lines = sc.textFile(sys.argv[1], 1) sortedCount = lines.flatMap(lambda x: x.split(' ')) \ .map(lambda x: (int(x), 1)) \ .sortByKey(lambda x: x) diff --git a/examples/src/main/python/transitive_closure.py b/examples/src/main/python/transitive_closure.py index 744cce6651607..8698369b13d84 100755 --- a/examples/src/main/python/transitive_closure.py +++ b/examples/src/main/python/transitive_closure.py @@ -36,11 +36,11 @@ def generateGraph(): if __name__ == "__main__": - if len(sys.argv) == 1: - print >> sys.stderr, "Usage: transitive_closure []" - exit(-1) - sc = SparkContext(sys.argv[1], "PythonTransitiveClosure") - slices = int(sys.argv[2]) if len(sys.argv) > 2 else 2 + """ + Usage: transitive_closure [slices] + """ + sc = SparkContext(appName="PythonTransitiveClosure") + slices = int(sys.argv[1]) if len(sys.argv) > 1 else 2 tc = sc.parallelize(generateGraph(), slices).cache() # Linear transitive closure: each round grows paths by one edge, diff --git a/examples/src/main/python/wordcount.py b/examples/src/main/python/wordcount.py index b9139b9d76520..dcc095fdd0ed9 100755 --- a/examples/src/main/python/wordcount.py +++ b/examples/src/main/python/wordcount.py @@ -22,11 +22,11 @@ if __name__ == "__main__": - if len(sys.argv) < 3: - print >> sys.stderr, "Usage: wordcount " + if len(sys.argv) != 2: + print >> sys.stderr, "Usage: wordcount " exit(-1) - sc = SparkContext(sys.argv[1], "PythonWordCount") - lines = sc.textFile(sys.argv[2], 1) + sc = SparkContext(appName="PythonWordCount") + lines = sc.textFile(sys.argv[1], 1) counts = lines.flatMap(lambda x: x.split(' ')) \ .map(lambda x: (x, 1)) \ .reduceByKey(add) From 442808a7482b81c8de887c901b424683da62022e Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Fri, 16 May 2014 22:58:47 -0700 Subject: [PATCH 75/99] Make deprecation warning less severe Just a small change. I think it's good not to scare people who are using the old options. Author: Patrick Wendell Closes #810 from pwendell/warnings and squashes the following commits: cb8a311 [Patrick Wendell] Make deprecation warning less severe --- core/src/main/scala/org/apache/spark/SparkConf.scala | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkConf.scala b/core/src/main/scala/org/apache/spark/SparkConf.scala index 800616622d7bf..8ce4b91cae8ae 100644 --- a/core/src/main/scala/org/apache/spark/SparkConf.scala +++ b/core/src/main/scala/org/apache/spark/SparkConf.scala @@ -238,10 +238,10 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging { // Check for legacy configs sys.env.get("SPARK_JAVA_OPTS").foreach { value => - val error = + val warning = s""" |SPARK_JAVA_OPTS was detected (set to '$value'). - |This has undefined behavior when running on a cluster and is deprecated in Spark 1.0+. + |This is deprecated in Spark 1.0+. | |Please instead use: | - ./spark-submit with conf/spark-defaults.conf to set defaults for an application @@ -249,7 +249,7 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging { | - spark.executor.extraJavaOptions to set -X options for executors | - SPARK_DAEMON_JAVA_OPTS to set java options for standalone daemons (master or worker) """.stripMargin - logError(error) + logWarning(warning) for (key <- Seq(executorOptsKey, driverOptsKey)) { if (getOption(key).isDefined) { @@ -262,16 +262,16 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging { } sys.env.get("SPARK_CLASSPATH").foreach { value => - val error = + val warning = s""" |SPARK_CLASSPATH was detected (set to '$value'). - | This has undefined behavior when running on a cluster and is deprecated in Spark 1.0+. + |This is deprecated in Spark 1.0+. | |Please instead use: | - ./spark-submit with --driver-class-path to augment the driver classpath | - spark.executor.extraClassPath to augment the executor classpath """.stripMargin - logError(error) + logWarning(warning) for (key <- Seq(executorClasspathKey, driverClassPathKey)) { if (getOption(key).isDefined) { From ebcd2d68897f423614d0629758240da97dca4a12 Mon Sep 17 00:00:00 2001 From: Neville Li Date: Sun, 18 May 2014 13:31:23 -0700 Subject: [PATCH 76/99] Fix spark-submit path in spark-shell & pyspark Author: Neville Li Closes #812 from nevillelyh/neville/v1.0 and squashes the following commits: 0dc33ed [Neville Li] Fix spark-submit path in pyspark becec64 [Neville Li] Fix spark-submit path in spark-shell --- bin/pyspark | 2 +- bin/spark-shell | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/bin/pyspark b/bin/pyspark index 9e1364e44c8c4..3908ffe79939b 100755 --- a/bin/pyspark +++ b/bin/pyspark @@ -27,7 +27,7 @@ SCALA_VERSION=2.10 if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then echo "Usage: ./bin/pyspark [options]" - ./bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 + $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 exit 0 fi diff --git a/bin/spark-shell b/bin/spark-shell index c158683ab3f99..850e9507ec38f 100755 --- a/bin/spark-shell +++ b/bin/spark-shell @@ -28,15 +28,15 @@ esac # Enter posix mode for bash set -o posix +## Global script variables +FWDIR="$(cd `dirname $0`/..; pwd)" + if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then echo "Usage: ./bin/spark-shell [options]" - ./bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 + $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2 exit 0 fi -## Global script variables -FWDIR="$(cd `dirname $0`/..; pwd)" - function main(){ if $cygwin; then # Workaround for issue involving JLine and Cygwin From 4ce479324bdcf603806fc90b5b0f4968c6de690e Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Sun, 18 May 2014 16:51:53 -0700 Subject: [PATCH 77/99] SPARK-1873: Add README.md file when making distributions Author: Patrick Wendell Closes #818 from pwendell/reamde and squashes the following commits: 4020b11 [Patrick Wendell] SPARK-1873: Add README.md file when making distributions --- make-distribution.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/make-distribution.sh b/make-distribution.sh index 7a08d6b9151c4..1c89027d68bed 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -191,6 +191,7 @@ fi mkdir "$DISTDIR"/conf cp "$FWDIR"/conf/*.template "$DISTDIR"/conf cp "$FWDIR"/conf/slaves "$DISTDIR"/conf +cp "$FWDIR/README.md" "$DISTDIR" cp -r "$FWDIR/bin" "$DISTDIR" cp -r "$FWDIR/python" "$DISTDIR" cp -r "$FWDIR/sbin" "$DISTDIR" From df0aa8353ab6d3b19d838c6fa95a93a64948309f Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Sun, 18 May 2014 17:00:57 -0700 Subject: [PATCH 78/99] [WIP][SPARK-1871][MLLIB] Improve MLlib guide for v1.0 Some improvements to MLlib guide: 1. [SPARK-1872] Update API links for unidoc. 2. [SPARK-1783] Added `page.displayTitle` to the global layout. If it is defined, use it instead of `page.title` for title display. 3. Add more Java/Python examples. Author: Xiangrui Meng Closes #816 from mengxr/mllib-doc and squashes the following commits: ec2e407 [Xiangrui Meng] format scala example for ALS cd9f40b [Xiangrui Meng] add a paragraph to summarize distributed matrix types 4617f04 [Xiangrui Meng] add python example to loadLibSVMFile and fix Java example d6509c2 [Xiangrui Meng] [SPARK-1783] update mllib titles 561fdc0 [Xiangrui Meng] add a displayTitle option to global layout 195d06f [Xiangrui Meng] add Java example for summary stats and minor fix 9f1ff89 [Xiangrui Meng] update java api links in mllib-basics 7dad18e [Xiangrui Meng] update java api links in NB 3a0f4a6 [Xiangrui Meng] api/pyspark -> api/python 35bdeb9 [Xiangrui Meng] api/mllib -> api/scala e4afaa8 [Xiangrui Meng] explicity state what might change --- docs/_layouts/global.html | 6 +- docs/mllib-basics.md | 125 +++++++++++++++++-------- docs/mllib-clustering.md | 5 +- docs/mllib-collaborative-filtering.md | 29 +++--- docs/mllib-decision-tree.md | 3 +- docs/mllib-dimensionality-reduction.md | 3 +- docs/mllib-guide.md | 19 ++-- docs/mllib-linear-methods.md | 21 +++-- docs/mllib-naive-bayes.md | 21 +++-- docs/mllib-optimization.md | 11 ++- 10 files changed, 153 insertions(+), 90 deletions(-) diff --git a/docs/_layouts/global.html b/docs/_layouts/global.html index 8b543de574622..fb808129bb65d 100755 --- a/docs/_layouts/global.html +++ b/docs/_layouts/global.html @@ -114,7 +114,11 @@
-

{{ page.title }}

+ {% if page.displayTitle %} +

{{ page.displayTitle }}

+ {% else %} +

{{ page.title }}

+ {% endif %} {{ content }} diff --git a/docs/mllib-basics.md b/docs/mllib-basics.md index aa9321a547097..5796e16e8f99c 100644 --- a/docs/mllib-basics.md +++ b/docs/mllib-basics.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Basics +title: Basics - MLlib +displayTitle: MLlib - Basics --- * Table of contents @@ -26,11 +27,11 @@ of the vector.
The base class of local vectors is -[`Vector`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector), and we provide two -implementations: [`DenseVector`](api/mllib/index.html#org.apache.spark.mllib.linalg.DenseVector) and -[`SparseVector`](api/mllib/index.html#org.apache.spark.mllib.linalg.SparseVector). We recommend +[`Vector`](api/scala/index.html#org.apache.spark.mllib.linalg.Vector), and we provide two +implementations: [`DenseVector`](api/scala/index.html#org.apache.spark.mllib.linalg.DenseVector) and +[`SparseVector`](api/scala/index.html#org.apache.spark.mllib.linalg.SparseVector). We recommend using the factory methods implemented in -[`Vectors`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector) to create local vectors. +[`Vectors`](api/scala/index.html#org.apache.spark.mllib.linalg.Vector) to create local vectors. {% highlight scala %} import org.apache.spark.mllib.linalg.{Vector, Vectors} @@ -53,11 +54,11 @@ Scala imports `scala.collection.immutable.Vector` by default, so you have to imp
The base class of local vectors is -[`Vector`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector), and we provide two -implementations: [`DenseVector`](api/mllib/index.html#org.apache.spark.mllib.linalg.DenseVector) and -[`SparseVector`](api/mllib/index.html#org.apache.spark.mllib.linalg.SparseVector). We recommend +[`Vector`](api/java/org/apache/spark/mllib/linalg/Vector.html), and we provide two +implementations: [`DenseVector`](api/java/org/apache/spark/mllib/linalg/DenseVector.html) and +[`SparseVector`](api/java/org/apache/spark/mllib/linalg/SparseVector.html). We recommend using the factory methods implemented in -[`Vectors`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector) to create local vectors. +[`Vectors`](api/java/org/apache/spark/mllib/linalg/Vector.html) to create local vectors. {% highlight java %} import org.apache.spark.mllib.linalg.Vector; @@ -78,13 +79,13 @@ MLlib recognizes the following types as dense vectors: and the following as sparse vectors: -* MLlib's [`SparseVector`](api/pyspark/pyspark.mllib.linalg.SparseVector-class.html). +* MLlib's [`SparseVector`](api/python/pyspark.mllib.linalg.SparseVector-class.html). * SciPy's [`csc_matrix`](http://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csc_matrix.html#scipy.sparse.csc_matrix) with a single column We recommend using NumPy arrays over lists for efficiency, and using the factory methods implemented -in [`Vectors`](api/pyspark/pyspark.mllib.linalg.Vectors-class.html) to create sparse vectors. +in [`Vectors`](api/python/pyspark.mllib.linalg.Vectors-class.html) to create sparse vectors. {% highlight python %} import numpy as np @@ -117,7 +118,7 @@ For multiclass classification, labels should be class indices staring from zero:
A labeled point is represented by the case class -[`LabeledPoint`](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint). +[`LabeledPoint`](api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint). {% highlight scala %} import org.apache.spark.mllib.linalg.Vectors @@ -134,7 +135,7 @@ val neg = LabeledPoint(0.0, Vectors.sparse(3, Array(0, 2), Array(1.0, 3.0)))
A labeled point is represented by -[`LabeledPoint`](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint). +[`LabeledPoint`](api/java/org/apache/spark/mllib/regression/LabeledPoint.html). {% highlight java %} import org.apache.spark.mllib.linalg.Vectors; @@ -151,7 +152,7 @@ LabeledPoint neg = new LabeledPoint(1.0, Vectors.sparse(3, new int[] {0, 2}, new
A labeled point is represented by -[`LabeledPoint`](api/pyspark/pyspark.mllib.regression.LabeledPoint-class.html). +[`LabeledPoint`](api/python/pyspark.mllib.regression.LabeledPoint-class.html). {% highlight python %} from pyspark.mllib.linalg import SparseVector @@ -184,7 +185,7 @@ After loading, the feature indices are converted to zero-based.
-[`MLUtils.loadLibSVMFile`](api/mllib/index.html#org.apache.spark.mllib.util.MLUtils$) reads training +[`MLUtils.loadLibSVMFile`](api/scala/index.html#org.apache.spark.mllib.util.MLUtils$) reads training examples stored in LIBSVM format. {% highlight scala %} @@ -192,20 +193,32 @@ import org.apache.spark.mllib.regression.LabeledPoint import org.apache.spark.mllib.util.MLUtils import org.apache.spark.rdd.RDD -val training: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt") +val examples: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt") {% endhighlight %}
-[`MLUtils.loadLibSVMFile`](api/mllib/index.html#org.apache.spark.mllib.util.MLUtils$) reads training +[`MLUtils.loadLibSVMFile`](api/java/org/apache/spark/mllib/util/MLUtils.html) reads training examples stored in LIBSVM format. {% highlight java %} import org.apache.spark.mllib.regression.LabeledPoint; import org.apache.spark.mllib.util.MLUtils; -import org.apache.spark.rdd.RDDimport; +import org.apache.spark.api.java.JavaRDD; + +JavaRDD examples = + MLUtils.loadLibSVMFile(jsc.sc(), "mllib/data/sample_libsvm_data.txt").toJavaRDD(); +{% endhighlight %} +
+ +
+[`MLUtils.loadLibSVMFile`](api/python/pyspark.mllib.util.MLUtils-class.html) reads training +examples stored in LIBSVM format. -RDD training = MLUtils.loadLibSVMFile(jsc, "mllib/data/sample_libsvm_data.txt"); +{% highlight python %} +from pyspark.mllib.util import MLUtils + +examples = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt") {% endhighlight %}
@@ -227,10 +240,10 @@ We are going to add sparse matrix in the next release.
The base class of local matrices is -[`Matrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.Matrix), and we provide one -implementation: [`DenseMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.DenseMatrix). +[`Matrix`](api/scala/index.html#org.apache.spark.mllib.linalg.Matrix), and we provide one +implementation: [`DenseMatrix`](api/scala/index.html#org.apache.spark.mllib.linalg.DenseMatrix). Sparse matrix will be added in the next release. We recommend using the factory methods implemented -in [`Matrices`](api/mllib/index.html#org.apache.spark.mllib.linalg.Matrices) to create local +in [`Matrices`](api/scala/index.html#org.apache.spark.mllib.linalg.Matrices) to create local matrices. {% highlight scala %} @@ -244,10 +257,10 @@ val dm: Matrix = Matrices.dense(3, 2, Array(1.0, 3.0, 5.0, 2.0, 4.0, 6.0))
The base class of local matrices is -[`Matrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.Matrix), and we provide one -implementation: [`DenseMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.DenseMatrix). +[`Matrix`](api/java/org/apache/spark/mllib/linalg/Matrix.html), and we provide one +implementation: [`DenseMatrix`](api/java/org/apache/spark/mllib/linalg/DenseMatrix.html). Sparse matrix will be added in the next release. We recommend using the factory methods implemented -in [`Matrices`](api/mllib/index.html#org.apache.spark.mllib.linalg.Matrices) to create local +in [`Matrices`](api/java/org/apache/spark/mllib/linalg/Matrices.html) to create local matrices. {% highlight java %} @@ -269,6 +282,15 @@ and distributed matrices. Converting a distributed matrix to a different format global shuffle, which is quite expensive. We implemented three types of distributed matrices in this release and will add more types in the future. +The basic type is called `RowMatrix`. A `RowMatrix` is a row-oriented distributed +matrix without meaningful row indices, e.g., a collection of feature vectors. +It is backed by an RDD of its rows, where each row is a local vector. +We assume that the number of columns is not huge for a `RowMatrix`. +An `IndexedRowMatrix` is similar to a `RowMatrix` but with row indices, +which can be used for identifying rows and joins. +A `CoordinateMatrix` is a distributed matrix stored in [coordinate list (COO)](https://en.wikipedia.org/wiki/Sparse_matrix) format, +backed by an RDD of its entries. + ***Note*** The underlying RDDs of a distributed matrix must be deterministic, because we cache the matrix size. @@ -284,7 +306,7 @@ limited by the integer range but it should be much smaller in practice.
-A [`RowMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.RowMatrix) can be +A [`RowMatrix`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.RowMatrix) can be created from an `RDD[Vector]` instance. Then we can compute its column summary statistics. {% highlight scala %} @@ -303,7 +325,7 @@ val n = mat.numCols()
-A [`RowMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.RowMatrix) can be +A [`RowMatrix`](api/java/org/apache/spark/mllib/linalg/distributed/RowMatrix.html) can be created from a `JavaRDD` instance. Then we can compute its column summary statistics. {% highlight java %} @@ -333,8 +355,8 @@ which could be faster if the rows are sparse.
-`RowMatrix#computeColumnSummaryStatistics` returns an instance of -[`MultivariateStatisticalSummary`](api/mllib/index.html#org.apache.spark.mllib.stat.MultivariateStatisticalSummary), +[`RowMatrix#computeColumnSummaryStatistics`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.RowMatrix) returns an instance of +[`MultivariateStatisticalSummary`](api/scala/index.html#org.apache.spark.mllib.stat.MultivariateStatisticalSummary), which contains the column-wise max, min, mean, variance, and number of nonzeros, as well as the total count. @@ -355,6 +377,31 @@ println(summary.numNonzeros) // number of nonzeros in each column val cov: Matrix = mat.computeCovariance() {% endhighlight %}
+ +
+ +[`RowMatrix#computeColumnSummaryStatistics`](api/java/org/apache/spark/mllib/linalg/distributed/RowMatrix.html#computeColumnSummaryStatistics()) returns an instance of +[`MultivariateStatisticalSummary`](api/java/org/apache/spark/mllib/stat/MultivariateStatisticalSummary.html), +which contains the column-wise max, min, mean, variance, and number of nonzeros, as well as the +total count. + +{% highlight java %} +import org.apache.spark.mllib.linalg.Matrix; +import org.apache.spark.mllib.linalg.distributed.RowMatrix; +import org.apache.spark.mllib.stat.MultivariateStatisticalSummary; + +RowMatrix mat = ... // a RowMatrix + +// Compute column summary statistics. +MultivariateStatisticalSummary summary = mat.computeColumnSummaryStatistics(); +System.out.println(summary.mean()); // a dense vector containing the mean value for each column +System.out.println(summary.variance()); // column-wise variance +System.out.println(summary.numNonzeros()); // number of nonzeros in each column + +// Compute the covariance matrix. +Matrix cov = mat.computeCovariance(); +{% endhighlight %} +
### IndexedRowMatrix @@ -366,9 +413,9 @@ an RDD of indexed rows, which each row is represented by its index (long-typed)
An -[`IndexedRowMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix) +[`IndexedRowMatrix`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix) can be created from an `RDD[IndexedRow]` instance, where -[`IndexedRow`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRow) is a +[`IndexedRow`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRow) is a wrapper over `(Long, Vector)`. An `IndexedRowMatrix` can be converted to a `RowMatrix` by dropping its row indices. @@ -391,9 +438,9 @@ val rowMat: RowMatrix = mat.toRowMatrix()
An -[`IndexedRowMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix) +[`IndexedRowMatrix`](api/java/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.html) can be created from an `JavaRDD` instance, where -[`IndexedRow`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.IndexedRow) is a +[`IndexedRow`](api/java/org/apache/spark/mllib/linalg/distributed/IndexedRow.html) is a wrapper over `(long, Vector)`. An `IndexedRowMatrix` can be converted to a `RowMatrix` by dropping its row indices. @@ -427,9 +474,9 @@ dimensions of the matrix are huge and the matrix is very sparse.
A -[`CoordinateMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.CoordinateMatrix) +[`CoordinateMatrix`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.CoordinateMatrix) can be created from an `RDD[MatrixEntry]` instance, where -[`MatrixEntry`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.MatrixEntry) is a +[`MatrixEntry`](api/scala/index.html#org.apache.spark.mllib.linalg.distributed.MatrixEntry) is a wrapper over `(Long, Long, Double)`. A `CoordinateMatrix` can be converted to a `IndexedRowMatrix` with sparse rows by calling `toIndexedRowMatrix`. In this release, we do not provide other computation for `CoordinateMatrix`. @@ -453,13 +500,13 @@ val indexedRowMatrix = mat.toIndexedRowMatrix()
A -[`CoordinateMatrix`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.CoordinateMatrix) +[`CoordinateMatrix`](api/java/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.html) can be created from a `JavaRDD` instance, where -[`MatrixEntry`](api/mllib/index.html#org.apache.spark.mllib.linalg.distributed.MatrixEntry) is a +[`MatrixEntry`](api/java/org/apache/spark/mllib/linalg/distributed/MatrixEntry.html) is a wrapper over `(long, long, double)`. A `CoordinateMatrix` can be converted to a `IndexedRowMatrix` with sparse rows by calling `toIndexedRowMatrix`. -{% highlight scala %} +{% highlight java %} import org.apache.spark.api.java.JavaRDD; import org.apache.spark.mllib.linalg.distributed.CoordinateMatrix; import org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix; @@ -467,7 +514,7 @@ import org.apache.spark.mllib.linalg.distributed.MatrixEntry; JavaRDD entries = ... // a JavaRDD of matrix entries // Create a CoordinateMatrix from a JavaRDD. -CoordinateMatrix mat = new CoordinateMatrix(entries); +CoordinateMatrix mat = new CoordinateMatrix(entries.rdd()); // Get its size. long m = mat.numRows(); diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md index 276868fa8490d..429cdf8d40cec 100644 --- a/docs/mllib-clustering.md +++ b/docs/mllib-clustering.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Clustering +title: Clustering - MLlib +displayTitle: MLlib - Clustering --- * Table of contents @@ -40,7 +41,7 @@ a given dataset, the algorithm returns the best clustering result). Following code snippets can be executed in `spark-shell`. In the following example after loading and parsing data, we use the -[`KMeans`](api/mllib/index.html#org.apache.spark.mllib.clustering.KMeans) object to cluster the data +[`KMeans`](api/scala/index.html#org.apache.spark.mllib.clustering.KMeans) object to cluster the data into two clusters. The number of desired clusters is passed to the algorithm. We then compute Within Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasing *k*. In fact the optimal *k* is usually one where there is an "elbow" in the WSSSE graph. diff --git a/docs/mllib-collaborative-filtering.md b/docs/mllib-collaborative-filtering.md index f486c56e55907..d51002f015670 100644 --- a/docs/mllib-collaborative-filtering.md +++ b/docs/mllib-collaborative-filtering.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Collaborative Filtering +title: Collaborative Filtering - MLlib +displayTitle: MLlib - Collaborative Filtering --- * Table of contents @@ -48,7 +49,7 @@ user for an item.
In the following example we load rating data. Each row consists of a user, a product and a rating. -We use the default [ALS.train()](api/mllib/index.html#org.apache.spark.mllib.recommendation.ALS$) +We use the default [ALS.train()](api/scala/index.html#org.apache.spark.mllib.recommendation.ALS$) method which assumes ratings are explicit. We evaluate the recommendation model by measuring the Mean Squared Error of rating prediction. @@ -58,9 +59,9 @@ import org.apache.spark.mllib.recommendation.Rating // Load and parse the data val data = sc.textFile("mllib/data/als/test.data") -val ratings = data.map(_.split(',') match { - case Array(user, item, rate) => Rating(user.toInt, item.toInt, rate.toDouble) -}) +val ratings = data.map(_.split(',') match { case Array(user, item, rate) => + Rating(user.toInt, item.toInt, rate.toDouble) + }) // Build the recommendation model using ALS val rank = 10 @@ -68,15 +69,19 @@ val numIterations = 20 val model = ALS.train(ratings, rank, numIterations, 0.01) // Evaluate the model on rating data -val usersProducts = ratings.map{ case Rating(user, product, rate) => (user, product)} -val predictions = model.predict(usersProducts).map{ - case Rating(user, product, rate) => ((user, product), rate) +val usersProducts = ratings.map { case Rating(user, product, rate) => + (user, product) } -val ratesAndPreds = ratings.map{ - case Rating(user, product, rate) => ((user, product), rate) +val predictions = + model.predict(usersProducts).map { case Rating(user, product, rate) => + ((user, product), rate) + } +val ratesAndPreds = ratings.map { case Rating(user, product, rate) => + ((user, product), rate) }.join(predictions) -val MSE = ratesAndPreds.map{ - case ((user, product), (r1, r2)) => math.pow((r1- r2), 2) +val MSE = ratesAndPreds.map { case ((user, product), (r1, r2)) => + val err = (r1 - r2) + err * err }.mean() println("Mean Squared Error = " + MSE) {% endhighlight %} diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md index acf0feff42a8d..3002a66a4fdb3 100644 --- a/docs/mllib-decision-tree.md +++ b/docs/mllib-decision-tree.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Decision Tree +title: Decision Tree - MLlib +displayTitle: MLlib - Decision Tree --- * Table of contents diff --git a/docs/mllib-dimensionality-reduction.md b/docs/mllib-dimensionality-reduction.md index ab24663cfe258..e3608075fbb13 100644 --- a/docs/mllib-dimensionality-reduction.md +++ b/docs/mllib-dimensionality-reduction.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Dimensionality Reduction +title: Dimensionality Reduction - MLlib +displayTitle: MLlib - Dimensionality Reduction --- * Table of contents diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 842ca5c8c6d8a..640ca83085387 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -27,8 +27,9 @@ filtering, dimensionality reduction, as well as underlying optimization primitiv * stochastic gradient descent * limited-memory BFGS (L-BFGS) -MLlib is currently a *beta* component under active development. -The APIs may change in the future releases, and we will provide migration guide between releases. +MLlib is a new component under active development. +The APIs marked `Experimental`/`DeveloperApi` may change in future releases, +and we will provide migration guide between releases. ## Dependencies @@ -61,9 +62,9 @@ take advantage of sparsity in both storage and computation.
We used to represent a feature vector by `Array[Double]`, which is replaced by -[`Vector`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector) in v1.0. Algorithms that used +[`Vector`](api/scala/index.html#org.apache.spark.mllib.linalg.Vector) in v1.0. Algorithms that used to accept `RDD[Array[Double]]` now take -`RDD[Vector]`. [`LabeledPoint`](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint) +`RDD[Vector]`. [`LabeledPoint`](api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint) is now a wrapper of `(Double, Vector)` instead of `(Double, Array[Double])`. Converting `Array[Double]` to `Vector` is straightforward: @@ -74,7 +75,7 @@ val array: Array[Double] = ... // a double array val vector: Vector = Vectors.dense(array) // a dense vector {% endhighlight %} -[`Vectors`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vectors$) provides factory methods to create sparse vectors. +[`Vectors`](api/scala/index.html#org.apache.spark.mllib.linalg.Vectors$) provides factory methods to create sparse vectors. *Note*. Scala imports `scala.collection.immutable.Vector` by default, so you have to import `org.apache.spark.mllib.linalg.Vector` explicitly to use MLlib's `Vector`. @@ -83,9 +84,9 @@ val vector: Vector = Vectors.dense(array) // a dense vector
We used to represent a feature vector by `double[]`, which is replaced by -[`Vector`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vector) in v1.0. Algorithms that used +[`Vector`](api/scala/index.html#org.apache.spark.mllib.linalg.Vector) in v1.0. Algorithms that used to accept `RDD` now take -`RDD`. [`LabeledPoint`](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint) +`RDD`. [`LabeledPoint`](api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint) is now a wrapper of `(double, Vector)` instead of `(double, double[])`. Converting `double[]` to `Vector` is straightforward: @@ -97,7 +98,7 @@ double[] array = ... // a double array Vector vector = Vectors.dense(array); // a dense vector {% endhighlight %} -[`Vectors`](api/mllib/index.html#org.apache.spark.mllib.linalg.Vectors$) provides factory methods to +[`Vectors`](api/scala/index.html#org.apache.spark.mllib.linalg.Vectors$) provides factory methods to create sparse vectors.
@@ -106,7 +107,7 @@ create sparse vectors. We used to represent a labeled feature vector in a NumPy array, where the first entry corresponds to the label and the rest are features. This representation is replaced by class -[`LabeledPoint`](api/pyspark/pyspark.mllib.regression.LabeledPoint-class.html), which takes both +[`LabeledPoint`](api/python/pyspark.mllib.regression.LabeledPoint-class.html), which takes both dense and sparse feature vectors. {% highlight python %} diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md index eff617d8641e2..4dfbebbcd04b7 100644 --- a/docs/mllib-linear-methods.md +++ b/docs/mllib-linear-methods.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Linear Methods +title: Linear Methods - MLlib +displayTitle: MLlib - Linear Methods --- * Table of contents @@ -233,7 +234,7 @@ val modelL1 = svmAlg.run(training) {% endhighlight %} Similarly, you can use replace `SVMWithSGD` by -[`LogisticRegressionWithSGD`](api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD). +[`LogisticRegressionWithSGD`](api/scala/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD).
@@ -328,8 +329,8 @@ println("training Mean Squared Error = " + MSE) {% endhighlight %} Similarly you can use -[`RidgeRegressionWithSGD`](api/mllib/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD) -and [`LassoWithSGD`](api/mllib/index.html#org.apache.spark.mllib.regression.LassoWithSGD). +[`RidgeRegressionWithSGD`](api/scala/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD) +and [`LassoWithSGD`](api/scala/index.html#org.apache.spark.mllib.regression.LassoWithSGD).
@@ -380,11 +381,11 @@ all three possible regularizations (none, L1 or L2). Algorithms are all implemented in Scala: -* [SVMWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.SVMWithSGD) -* [LogisticRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD) -* [LinearRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.LinearRegressionWithSGD) -* [RidgeRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD) -* [LassoWithSGD](api/mllib/index.html#org.apache.spark.mllib.regression.LassoWithSGD) +* [SVMWithSGD](api/scala/index.html#org.apache.spark.mllib.classification.SVMWithSGD) +* [LogisticRegressionWithSGD](api/scala/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD) +* [LinearRegressionWithSGD](api/scala/index.html#org.apache.spark.mllib.regression.LinearRegressionWithSGD) +* [RidgeRegressionWithSGD](api/scala/index.html#org.apache.spark.mllib.regression.RidgeRegressionWithSGD) +* [LassoWithSGD](api/scala/index.html#org.apache.spark.mllib.regression.LassoWithSGD) Python calls the Scala implementation via -[PythonMLLibAPI](api/mllib/index.html#org.apache.spark.mllib.api.python.PythonMLLibAPI). +[PythonMLLibAPI](api/scala/index.html#org.apache.spark.mllib.api.python.PythonMLLibAPI). diff --git a/docs/mllib-naive-bayes.md b/docs/mllib-naive-bayes.md index c47508b7daa2d..4b3a7cab32118 100644 --- a/docs/mllib-naive-bayes.md +++ b/docs/mllib-naive-bayes.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Naive Bayes +title: Naive Bayes - MLlib +displayTitle: MLlib - Naive Bayes --- Naive Bayes is a simple multiclass classification algorithm with the assumption of independence @@ -27,11 +28,11 @@ sparsity. Since the training data is only used once, it is not necessary to cach
-[NaiveBayes](api/mllib/index.html#org.apache.spark.mllib.classification.NaiveBayes$) implements +[NaiveBayes](api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayes$) implements multinomial naive Bayes. It takes an RDD of -[LabeledPoint](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint) and an optional +[LabeledPoint](api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint) and an optional smoothing parameter `lambda` as input, and output a -[NaiveBayesModel](api/mllib/index.html#org.apache.spark.mllib.classification.NaiveBayesModel), which +[NaiveBayesModel](api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayesModel), which can be used for evaluation and prediction. {% highlight scala %} @@ -59,11 +60,11 @@ val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test
-[NaiveBayes](api/mllib/index.html#org.apache.spark.mllib.classification.NaiveBayes$) implements +[NaiveBayes](api/java/org/apache/spark/mllib/classification/NaiveBayes.html) implements multinomial naive Bayes. It takes a Scala RDD of -[LabeledPoint](api/mllib/index.html#org.apache.spark.mllib.regression.LabeledPoint) and an +[LabeledPoint](api/java/org/apache/spark/mllib/regression/LabeledPoint.html) and an optionally smoothing parameter `lambda` as input, and output a -[NaiveBayesModel](api/mllib/index.html#org.apache.spark.mllib.classification.NaiveBayesModel), which +[NaiveBayesModel](api/java/org/apache/spark/mllib/classification/NaiveBayesModel.html), which can be used for evaluation and prediction. {% highlight java %} @@ -102,11 +103,11 @@ double accuracy = 1.0 * predictionAndLabel.filter(new Function -[NaiveBayes](api/pyspark/pyspark.mllib.classification.NaiveBayes-class.html) implements multinomial +[NaiveBayes](api/python/pyspark.mllib.classification.NaiveBayes-class.html) implements multinomial naive Bayes. It takes an RDD of -[LabeledPoint](api/pyspark/pyspark.mllib.regression.LabeledPoint-class.html) and an optionally +[LabeledPoint](api/python/pyspark.mllib.regression.LabeledPoint-class.html) and an optionally smoothing parameter `lambda` as input, and output a -[NaiveBayesModel](api/pyspark/pyspark.mllib.classification.NaiveBayesModel-class.html), which can be +[NaiveBayesModel](api/python/pyspark.mllib.classification.NaiveBayesModel-class.html), which can be used for evaluation and prediction. diff --git a/docs/mllib-optimization.md b/docs/mllib-optimization.md index aa0dec2130593..a22980d03a2f0 100644 --- a/docs/mllib-optimization.md +++ b/docs/mllib-optimization.md @@ -1,6 +1,7 @@ --- layout: global -title: MLlib - Optimization +title: Optimization - MLlib +displayTitle: MLlib - Optimization --- * Table of contents @@ -170,17 +171,17 @@ each iteration, to compute the gradient direction. Available algorithms for gradient descent: -* [GradientDescent.runMiniBatchSGD](api/mllib/index.html#org.apache.spark.mllib.optimization.GradientDescent) +* [GradientDescent.runMiniBatchSGD](api/scala/index.html#org.apache.spark.mllib.optimization.GradientDescent) ### L-BFGS L-BFGS is currently only a low-level optimization primitive in `MLlib`. If you want to use L-BFGS in various ML algorithms such as Linear Regression, and Logistic Regression, you have to pass the gradient of objective function, and updater into optimizer yourself instead of using the training APIs like -[LogisticRegressionWithSGD](api/mllib/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD). +[LogisticRegressionWithSGD](api/scala/index.html#org.apache.spark.mllib.classification.LogisticRegressionWithSGD). See the example below. It will be addressed in the next release. The L1 regularization by using -[L1Updater](api/mllib/index.html#org.apache.spark.mllib.optimization.L1Updater) will not work since the +[L1Updater](api/scala/index.html#org.apache.spark.mllib.optimization.L1Updater) will not work since the soft-thresholding logic in L1Updater is designed for gradient descent. See the developer's note. The L-BFGS method @@ -274,4 +275,4 @@ the actual gradient descent step. However, we're able to take the gradient and loss of objective function of regularization for L-BFGS by ignoring the part of logic only for gradient decent such as adaptive step size stuff. We will refactorize this into regularizer to replace updater to separate the logic between -regularization and step update later. \ No newline at end of file +regularization and step update later. From 7b70a7071894dd90ea1d0091542b3e13e7ef8d3a Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Mon, 19 May 2014 15:02:35 -0700 Subject: [PATCH 79/99] [SPARK-1876] Windows fixes to deal with latest distribution layout changes - Look for JARs in the right place - Launch examples the same way as on Unix - Load datanucleus JARs if they exist - Don't attempt to parse local paths as URIs in SparkSubmit, since paths with C:\ are not valid URIs - Also fixed POM exclusion rules for datanucleus (it wasn't properly excluding it, whereas SBT was) Author: Matei Zaharia Closes #819 from mateiz/win-fixes and squashes the following commits: d558f96 [Matei Zaharia] Fix comment 228577b [Matei Zaharia] Review comments d3b71c7 [Matei Zaharia] Properly exclude datanucleus files in Maven assembly 144af84 [Matei Zaharia] Update Windows scripts to match latest binary package layout --- README.md | 7 +-- assembly/pom.xml | 2 +- bin/compute-classpath.cmd | 24 ++++++++- bin/run-example | 23 ++++----- bin/run-example2.cmd | 51 ++++++++++++++----- bin/spark-class2.cmd | 2 + .../org/apache/spark/deploy/SparkSubmit.scala | 2 +- 7 files changed, 81 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index 9c2e32b90f162..6211a5889a3f5 100644 --- a/README.md +++ b/README.md @@ -9,13 +9,14 @@ You can find the latest Spark documentation, including a programming guide, on the project webpage at . This README file only contains basic setup instructions. - ## Building Spark Spark is built on Scala 2.10. To build Spark and its example programs, run: ./sbt/sbt assembly +(You do not need to do this if you downloaded a pre-built package.) + ## Interactive Scala Shell The easiest way to start using Spark is through the Scala shell: @@ -41,9 +42,9 @@ And run the following command, which should also return 1000: Spark also comes with several sample programs in the `examples` directory. To run one of them, use `./bin/run-example [params]`. For example: - ./bin/run-example org.apache.spark.examples.SparkLR + ./bin/run-example SparkPi -will run the Logistic Regression example locally. +will run the Pi example locally. You can set the MASTER environment variable when running examples to submit examples to a cluster. This can be a mesos:// or spark:// URL, diff --git a/assembly/pom.xml b/assembly/pom.xml index abd8935339992..963357b9ab167 100644 --- a/assembly/pom.xml +++ b/assembly/pom.xml @@ -96,7 +96,7 @@ *:* - org.datanucleus:* + org/datanucleus/** META-INF/*.SF META-INF/*.DSA META-INF/*.RSA diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd index 065553eb31939..58710cd1bd548 100644 --- a/bin/compute-classpath.cmd +++ b/bin/compute-classpath.cmd @@ -20,6 +20,13 @@ rem rem This script computes Spark's classpath and prints it to stdout; it's used by both the "run" rem script and the ExecutorRunner in standalone cluster mode. +rem If we're called from spark-class2.cmd, it already set enabledelayedexpansion and setting +rem it here would stop us from affecting its copy of the CLASSPATH variable; otherwise we +rem need to set it here because we use !datanucleus_jars! below. +if "%DONT_PRINT_CLASSPATH%"=="1" goto skip_delayed_expansion +setlocal enabledelayedexpansion +:skip_delayed_expansion + set SCALA_VERSION=2.10 rem Figure out where the Spark framework is installed @@ -31,7 +38,7 @@ if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd" rem Build up classpath set CLASSPATH=%FWDIR%conf if exist "%FWDIR%RELEASE" ( - for %%d in ("%FWDIR%jars\spark-assembly*.jar") do ( + for %%d in ("%FWDIR%lib\spark-assembly*.jar") do ( set ASSEMBLY_JAR=%%d ) ) else ( @@ -42,6 +49,21 @@ if exist "%FWDIR%RELEASE" ( set CLASSPATH=%CLASSPATH%;%ASSEMBLY_JAR% +rem When Hive support is needed, Datanucleus jars must be included on the classpath. +rem Datanucleus jars do not work if only included in the uber jar as plugin.xml metadata is lost. +rem Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is +rem built with Hive, so look for them there. +if exist "%FWDIR%RELEASE" ( + set datanucleus_dir=%FWDIR%lib +) else ( + set datanucleus_dir=%FWDIR%lib_managed\jars +) +set "datanucleus_jars=" +for %%d in ("%datanucleus_dir%\datanucleus-*.jar") do ( + set datanucleus_jars=!datanucleus_jars!;%%d +) +set CLASSPATH=%CLASSPATH%;%datanucleus_jars% + set SPARK_CLASSES=%FWDIR%core\target\scala-%SCALA_VERSION%\classes set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%repl\target\scala-%SCALA_VERSION%\classes set SPARK_CLASSES=%SPARK_CLASSES%;%FWDIR%mllib\target\scala-%SCALA_VERSION%\classes diff --git a/bin/run-example b/bin/run-example index 146951ac0ee56..7caab31daef39 100755 --- a/bin/run-example +++ b/bin/run-example @@ -23,6 +23,16 @@ FWDIR="$(cd `dirname $0`/..; pwd)" export SPARK_HOME="$FWDIR" EXAMPLES_DIR="$FWDIR"/examples +if [ -n "$1" ]; then + EXAMPLE_CLASS="$1" + shift +else + echo "Usage: ./bin/run-example [example-args]" + echo " - set MASTER=XX to use a specific master" + echo " - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)" + exit 1 +fi + if [ -f "$FWDIR/RELEASE" ]; then export SPARK_EXAMPLES_JAR=`ls "$FWDIR"/lib/spark-examples-*hadoop*.jar` elif [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar ]; then @@ -37,17 +47,6 @@ fi EXAMPLE_MASTER=${MASTER:-"local[*]"} -if [ -n "$1" ]; then - EXAMPLE_CLASS="$1" - shift -else - echo "usage: ./bin/run-example [example-args]" - echo " - set MASTER=XX to use a specific master" - echo " - can use abbreviated example class name (e.g. SparkPi, mllib.MovieLensALS)" - echo - exit -1 -fi - if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS" fi @@ -55,5 +54,5 @@ fi ./bin/spark-submit \ --master $EXAMPLE_MASTER \ --class $EXAMPLE_CLASS \ - $SPARK_EXAMPLES_JAR \ + "$SPARK_EXAMPLES_JAR" \ "$@" diff --git a/bin/run-example2.cmd b/bin/run-example2.cmd index 40abb9af74246..eadedd7fa61ff 100644 --- a/bin/run-example2.cmd +++ b/bin/run-example2.cmd @@ -30,7 +30,9 @@ if exist "%FWDIR%conf\spark-env.cmd" call "%FWDIR%conf\spark-env.cmd" rem Test that an argument was given if not "x%1"=="x" goto arg_given - echo Usage: run-example ^ [^] + echo Usage: run-example ^ [example-args] + echo - set MASTER=XX to use a specific master + echo - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression) goto exit :arg_given @@ -38,8 +40,14 @@ set EXAMPLES_DIR=%FWDIR%examples rem Figure out the JAR file that our examples were packaged into. set SPARK_EXAMPLES_JAR= -for %%d in ("%EXAMPLES_DIR%\target\scala-%SCALA_VERSION%\spark-examples*assembly*.jar") do ( - set SPARK_EXAMPLES_JAR=%%d +if exist "%FWDIR%RELEASE" ( + for %%d in ("%FWDIR%lib\spark-examples*.jar") do ( + set SPARK_EXAMPLES_JAR=%%d + ) +) else ( + for %%d in ("%EXAMPLES_DIR%\target\scala-%SCALA_VERSION%\spark-examples*.jar") do ( + set SPARK_EXAMPLES_JAR=%%d + ) ) if "x%SPARK_EXAMPLES_JAR%"=="x" ( echo Failed to find Spark examples assembly JAR. @@ -47,15 +55,34 @@ if "x%SPARK_EXAMPLES_JAR%"=="x" ( goto exit ) -rem Compute Spark classpath using external script -set DONT_PRINT_CLASSPATH=1 -call "%FWDIR%bin\compute-classpath.cmd" -set DONT_PRINT_CLASSPATH=0 -set CLASSPATH=%SPARK_EXAMPLES_JAR%;%CLASSPATH% +rem Set master from MASTER environment variable if given +if "x%MASTER%"=="x" ( + set EXAMPLE_MASTER=local[*] +) else ( + set EXAMPLE_MASTER=%MASTER% +) + +rem If the EXAMPLE_CLASS does not start with org.apache.spark.examples, add that +set EXAMPLE_CLASS=%1 +set PREFIX=%EXAMPLE_CLASS:~0,25% +if not %PREFIX%==org.apache.spark.examples ( + set EXAMPLE_CLASS=org.apache.spark.examples.%EXAMPLE_CLASS% +) + +rem Get the tail of the argument list, to skip the first one. This is surprisingly +rem complicated on Windows. +set "ARGS=" +:top +shift +if "%~1" neq "" ( + set ARGS=%ARGS% "%~1" + goto :top +) +if defined ARGS set ARGS=%ARGS:~1% -rem Figure out where java is. -set RUNNER=java -if not "x%JAVA_HOME%"=="x" set RUNNER=%JAVA_HOME%\bin\java +call "%FWDIR%bin\spark-submit.cmd" ^ + --master %EXAMPLE_MASTER% ^ + --class %EXAMPLE_CLASS% ^ + "%SPARK_EXAMPLES_JAR%" %ARGS% -"%RUNNER%" -cp "%CLASSPATH%" %JAVA_OPTS% %* :exit diff --git a/bin/spark-class2.cmd b/bin/spark-class2.cmd index 4302c1b6b7ff4..266edd9fa9835 100755 --- a/bin/spark-class2.cmd +++ b/bin/spark-class2.cmd @@ -17,6 +17,8 @@ rem See the License for the specific language governing permissions and rem limitations under the License. rem +setlocal enabledelayedexpansion + set SCALA_VERSION=2.10 rem Figure out where the Spark framework is installed diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala index a99b2176e2b5e..c54331c00fab8 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala @@ -299,7 +299,7 @@ object SparkSubmit { } private def addJarToClasspath(localJar: String, loader: ExecutorURLClassLoader) { - val localJarFile = new File(new URI(localJar).getPath) + val localJarFile = new File(localJar) if (!localJarFile.exists()) { printWarning(s"Jar $localJar does not exist, skipping.") } From 1811ba8ccb580979aa2e12019e6a82805f09ab53 Mon Sep 17 00:00:00 2001 From: zsxwing Date: Mon, 19 May 2014 16:41:31 -0700 Subject: [PATCH 80/99] SPARK-1878: Fix the incorrect initialization order JIRA: https://issues.apache.org/jira/browse/SPARK-1878 Author: zsxwing Closes #822 from zsxwing/SPARK-1878 and squashes the following commits: 4a47e27 [zsxwing] SPARK-1878: Fix the incorrect initialization order --- .../spark/streaming/api/java/JavaStreamingContext.scala | 6 +++--- .../test/java/org/apache/spark/streaming/JavaAPISuite.java | 4 ++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala index 75a3e9334e6d5..18605cac7006c 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/api/java/JavaStreamingContext.scala @@ -142,12 +142,12 @@ class JavaStreamingContext(val ssc: StreamingContext) { */ def this(path: String, hadoopConf: Configuration) = this(new StreamingContext(path, hadoopConf)) - @deprecated("use sparkContext", "0.9.0") - val sc: JavaSparkContext = sparkContext - /** The underlying SparkContext */ val sparkContext = new JavaSparkContext(ssc.sc) + @deprecated("use sparkContext", "0.9.0") + val sc: JavaSparkContext = sparkContext + /** * Create an input stream from network source hostname:port. Data is received using * a TCP socket and the receive bytes is interpreted as UTF8 encoded \n delimited diff --git a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java index ce58cb12a4564..4efeb8dfbe1ad 100644 --- a/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java +++ b/streaming/src/test/java/org/apache/spark/streaming/JavaAPISuite.java @@ -55,6 +55,10 @@ public void equalIterable(Iterable a, Iterable b) { equalIterator(a.iterator(), b.iterator()); } + @Test + public void testInitialization() { + Assert.assertNotNull(ssc.sc()); + } @SuppressWarnings("unchecked") @Test From 5af99d7617ba3b9fbfdb345ef9571b7dd41f45a1 Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Mon, 19 May 2014 18:42:28 -0700 Subject: [PATCH 81/99] SPARK-1879. Increase MaxPermSize since some of our builds have many classes See https://issues.apache.org/jira/browse/SPARK-1879 -- builds with Hadoop2 and Hive ran out of PermGen space in spark-shell, when those things added up with the Scala compiler. Note that users can still override it by setting their own Java options with this change. Their options will come later in the command string than the -XX:MaxPermSize=128m. Author: Matei Zaharia Closes #823 from mateiz/spark-1879 and squashes the following commits: 6bc0ee8 [Matei Zaharia] Increase MaxPermSize to 128m since some of our builds have lots of classes --- bin/spark-class | 4 ++-- bin/spark-class2.cmd | 4 ++-- .../scala/org/apache/spark/deploy/worker/CommandUtils.scala | 4 +++- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/bin/spark-class b/bin/spark-class index 6480ccb58d6aa..2e57295fd0234 100755 --- a/bin/spark-class +++ b/bin/spark-class @@ -99,14 +99,14 @@ else fi # Set JAVA_OPTS to be able to load native libraries and to set heap size -JAVA_OPTS="$OUR_JAVA_OPTS" +JAVA_OPTS="-XX:MaxPermSize=128m $OUR_JAVA_OPTS" JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM" # Load extra JAVA_OPTS from conf/java-opts, if it exists if [ -e "$FWDIR/conf/java-opts" ] ; then JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`" fi export JAVA_OPTS -# Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in ExecutorRunner.scala! +# Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala! if [ ! -f "$FWDIR/RELEASE" ]; then # Exit if the user hasn't compiled Spark diff --git a/bin/spark-class2.cmd b/bin/spark-class2.cmd index 266edd9fa9835..e420eb409e529 100755 --- a/bin/spark-class2.cmd +++ b/bin/spark-class2.cmd @@ -77,8 +77,8 @@ rem All drivers use SPARK_JAVA_OPTS + SPARK_DRIVER_MEMORY. The repl also uses SP ) rem Set JAVA_OPTS to be able to load native libraries and to set heap size -set JAVA_OPTS=%OUR_JAVA_OPTS% -Djava.library.path=%SPARK_LIBRARY_PATH% -Xms%OUR_JAVA_MEM% -Xmx%OUR_JAVA_MEM% -rem Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in ExecutorRunner.scala! +set JAVA_OPTS=-XX:MaxPermSize=128m %OUR_JAVA_OPTS% -Djava.library.path=%SPARK_LIBRARY_PATH% -Xms%OUR_JAVA_MEM% -Xmx%OUR_JAVA_MEM% +rem Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala! rem Test whether the user has built Spark if exist "%FWDIR%RELEASE" goto skip_build_test diff --git a/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala b/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala index c7f0f244ea2fc..4af5bc3afad6c 100644 --- a/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala +++ b/core/src/main/scala/org/apache/spark/deploy/worker/CommandUtils.scala @@ -65,6 +65,8 @@ object CommandUtils extends Logging { Seq() } + val permGenOpt = Seq("-XX:MaxPermSize=128m") + // Figure out our classpath with the external compute-classpath script val ext = if (System.getProperty("os.name").startsWith("Windows")) ".cmd" else ".sh" val classPath = Utils.executeAndGetOutput( @@ -73,7 +75,7 @@ object CommandUtils extends Logging { val userClassPath = command.classPathEntries ++ Seq(classPath) Seq("-cp", userClassPath.filterNot(_.isEmpty).mkString(File.pathSeparator)) ++ - libraryOpts ++ extraOpts ++ workerLocalOpts ++ memoryOpts + permGenOpt ++ libraryOpts ++ extraOpts ++ workerLocalOpts ++ memoryOpts } /** Spawn a thread that will redirect a given stream to a file */ From 6a2c5c610c259f62cb12d8cfc18bf59cdb334bb2 Mon Sep 17 00:00:00 2001 From: witgo Date: Mon, 19 May 2014 19:40:29 -0700 Subject: [PATCH 82/99] [SPARK-1875]NoClassDefFoundError: StringUtils when building with hadoop 1.x and hive Author: witgo Closes #824 from witgo/SPARK-1875_commons-lang-2.6 and squashes the following commits: ef7231d [witgo] review commit ead3c3b [witgo] SPARK-1875:NoClassDefFoundError: StringUtils when building against Hadoop 1 --- project/SparkBuild.scala | 3 +-- sql/hive/pom.xml | 8 -------- 2 files changed, 1 insertion(+), 10 deletions(-) diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 29dcd8678b476..b9d92340ff75b 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -318,7 +318,6 @@ object SparkBuild extends Build { val excludeFastutil = ExclusionRule(organization = "it.unimi.dsi") val excludeJruby = ExclusionRule(organization = "org.jruby") val excludeThrift = ExclusionRule(organization = "org.apache.thrift") - val excludeCommonsLang = ExclusionRule(organization = "commons-lang") val excludeServletApi = ExclusionRule(organization = "javax.servlet", artifact = "servlet-api") def sparkPreviousArtifact(id: String, organization: String = "org.apache.spark", @@ -493,7 +492,7 @@ object SparkBuild extends Build { javaOptions += "-XX:MaxPermSize=1g", libraryDependencies ++= Seq( "org.spark-project.hive" % "hive-metastore" % hiveVersion, - "org.spark-project.hive" % "hive-exec" % hiveVersion excludeAll(excludeCommonsLang, excludeCommonsLogging), + "org.spark-project.hive" % "hive-exec" % hiveVersion excludeAll(excludeCommonsLogging), "org.spark-project.hive" % "hive-serde" % hiveVersion ), // Multiple queries rely on the TestHive singleton. See comments there for more details. diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml index 4d0b2fa1452a2..9254b70e64a08 100644 --- a/sql/hive/pom.xml +++ b/sql/hive/pom.xml @@ -57,10 +57,6 @@ commons-logging commons-logging - - commons-lang - commons-lang - @@ -80,10 +76,6 @@ commons-logging commons-logging-api - - commons-lang - commons-lang - From b0ce22e071da4cc62ec5e29abf7b1299b8e4a6b0 Mon Sep 17 00:00:00 2001 From: Aaron Davidson Date: Mon, 19 May 2014 20:55:26 -0700 Subject: [PATCH 83/99] SPARK-1689: Spark application should die when removed by Master scheduler.error() will mask the error if there are active tasks. Being removed is a cataclysmic event for Spark applications, and should probably be treated as such. Author: Aaron Davidson Closes #832 from aarondav/i-love-u and squashes the following commits: 9f1200f [Aaron Davidson] SPARK-1689: Spark application should die when removed by Master --- .../spark/scheduler/cluster/SparkDeploySchedulerBackend.scala | 2 ++ 1 file changed, 2 insertions(+) diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala index 9768670855f80..9c07b3f7b695a 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/cluster/SparkDeploySchedulerBackend.scala @@ -88,6 +88,8 @@ private[spark] class SparkDeploySchedulerBackend( if (!stopping) { logError("Application has been killed. Reason: " + reason) scheduler.error(reason) + // Ensure the application terminates, as we can no longer run jobs. + sc.stop() } } From bcb9dce6f444a977c714117811bce0c54b417650 Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Mon, 19 May 2014 21:29:33 -0700 Subject: [PATCH 84/99] [SPARK-1874][MLLIB] Clean up MLlib sample data 1. Added synthetic datasets for `MovieLensALS`, `LinearRegression`, `BinaryClassification`. 2. Embedded instructions in the help message of those example apps. Per discussion with Matei on the JIRA page, new example data is under `data/mllib`. Author: Xiangrui Meng Closes #833 from mengxr/mllib-sample-data and squashes the following commits: 59f0a18 [Xiangrui Meng] add sample binary classification data 3c2f92f [Xiangrui Meng] add linear regression data 050f1ca [Xiangrui Meng] add a sample dataset for MovieLensALS example --- .../sample_binary_classification_data.txt | 100 ++ data/mllib/sample_linear_regression_data.txt | 501 ++++++ data/mllib/sample_movielens_data.txt | 1501 +++++++++++++++++ .../examples/mllib/BinaryClassification.scala | 12 +- .../examples/mllib/LinearRegression.scala | 11 +- .../spark/examples/mllib/MovieLensALS.scala | 15 + 6 files changed, 2138 insertions(+), 2 deletions(-) create mode 100644 data/mllib/sample_binary_classification_data.txt create mode 100755 data/mllib/sample_linear_regression_data.txt create mode 100644 data/mllib/sample_movielens_data.txt diff --git a/data/mllib/sample_binary_classification_data.txt b/data/mllib/sample_binary_classification_data.txt new file mode 100644 index 0000000000000..861c70cde7fd2 --- /dev/null +++ b/data/mllib/sample_binary_classification_data.txt @@ -0,0 +1,100 @@ +0 128:51 129:159 130:253 131:159 132:50 155:48 156:238 157:252 158:252 159:252 160:237 182:54 183:227 184:253 185:252 186:239 187:233 188:252 189:57 190:6 208:10 209:60 210:224 211:252 212:253 213:252 214:202 215:84 216:252 217:253 218:122 236:163 237:252 238:252 239:252 240:253 241:252 242:252 243:96 244:189 245:253 246:167 263:51 264:238 265:253 266:253 267:190 268:114 269:253 270:228 271:47 272:79 273:255 274:168 290:48 291:238 292:252 293:252 294:179 295:12 296:75 297:121 298:21 301:253 302:243 303:50 317:38 318:165 319:253 320:233 321:208 322:84 329:253 330:252 331:165 344:7 345:178 346:252 347:240 348:71 349:19 350:28 357:253 358:252 359:195 372:57 373:252 374:252 375:63 385:253 386:252 387:195 400:198 401:253 402:190 413:255 414:253 415:196 427:76 428:246 429:252 430:112 441:253 442:252 443:148 455:85 456:252 457:230 458:25 467:7 468:135 469:253 470:186 471:12 483:85 484:252 485:223 494:7 495:131 496:252 497:225 498:71 511:85 512:252 513:145 521:48 522:165 523:252 524:173 539:86 540:253 541:225 548:114 549:238 550:253 551:162 567:85 568:252 569:249 570:146 571:48 572:29 573:85 574:178 575:225 576:253 577:223 578:167 579:56 595:85 596:252 597:252 598:252 599:229 600:215 601:252 602:252 603:252 604:196 605:130 623:28 624:199 625:252 626:252 627:253 628:252 629:252 630:233 631:145 652:25 653:128 654:252 655:253 656:252 657:141 658:37 +1 159:124 160:253 161:255 162:63 186:96 187:244 188:251 189:253 190:62 214:127 215:251 216:251 217:253 218:62 241:68 242:236 243:251 244:211 245:31 246:8 268:60 269:228 270:251 271:251 272:94 296:155 297:253 298:253 299:189 323:20 324:253 325:251 326:235 327:66 350:32 351:205 352:253 353:251 354:126 378:104 379:251 380:253 381:184 382:15 405:80 406:240 407:251 408:193 409:23 432:32 433:253 434:253 435:253 436:159 460:151 461:251 462:251 463:251 464:39 487:48 488:221 489:251 490:251 491:172 515:234 516:251 517:251 518:196 519:12 543:253 544:251 545:251 546:89 570:159 571:255 572:253 573:253 574:31 597:48 598:228 599:253 600:247 601:140 602:8 625:64 626:251 627:253 628:220 653:64 654:251 655:253 656:220 681:24 682:193 683:253 684:220 +1 125:145 126:255 127:211 128:31 152:32 153:237 154:253 155:252 156:71 180:11 181:175 182:253 183:252 184:71 209:144 210:253 211:252 212:71 236:16 237:191 238:253 239:252 240:71 264:26 265:221 266:253 267:252 268:124 269:31 293:125 294:253 295:252 296:252 297:108 322:253 323:252 324:252 325:108 350:255 351:253 352:253 353:108 378:253 379:252 380:252 381:108 406:253 407:252 408:252 409:108 434:253 435:252 436:252 437:108 462:255 463:253 464:253 465:170 490:253 491:252 492:252 493:252 494:42 518:149 519:252 520:252 521:252 522:144 546:109 547:252 548:252 549:252 550:144 575:218 576:253 577:253 578:255 579:35 603:175 604:252 605:252 606:253 607:35 631:73 632:252 633:252 634:253 635:35 659:31 660:211 661:252 662:253 663:35 +1 153:5 154:63 155:197 181:20 182:254 183:230 184:24 209:20 210:254 211:254 212:48 237:20 238:254 239:255 240:48 265:20 266:254 267:254 268:57 293:20 294:254 295:254 296:108 321:16 322:239 323:254 324:143 350:178 351:254 352:143 378:178 379:254 380:143 406:178 407:254 408:162 434:178 435:254 436:240 462:113 463:254 464:240 490:83 491:254 492:245 493:31 518:79 519:254 520:246 521:38 547:214 548:254 549:150 575:144 576:241 577:8 603:144 604:240 605:2 631:144 632:254 633:82 659:230 660:247 661:40 687:168 688:209 689:31 +1 152:1 153:168 154:242 155:28 180:10 181:228 182:254 183:100 209:190 210:254 211:122 237:83 238:254 239:162 265:29 266:254 267:248 268:25 293:29 294:255 295:254 296:103 321:29 322:254 323:254 324:109 349:29 350:254 351:254 352:109 377:29 378:254 379:254 380:109 405:29 406:255 407:254 408:109 433:29 434:254 435:254 436:109 461:29 462:254 463:254 464:63 489:29 490:254 491:254 492:28 517:29 518:254 519:254 520:28 545:29 546:254 547:254 548:35 573:29 574:254 575:254 576:109 601:6 602:212 603:254 604:109 630:203 631:254 632:178 658:155 659:254 660:190 686:32 687:199 688:104 +0 130:64 131:253 132:255 133:63 157:96 158:205 159:251 160:253 161:205 162:111 163:4 184:96 185:189 186:251 187:251 188:253 189:251 190:251 191:31 209:16 210:64 211:223 212:244 213:251 214:251 215:211 216:213 217:251 218:251 219:31 236:80 237:181 238:251 239:253 240:251 241:251 242:251 243:94 244:96 245:251 246:251 247:31 263:92 264:253 265:253 266:253 267:255 268:253 269:253 270:253 271:95 272:96 273:253 274:253 275:31 290:92 291:236 292:251 293:243 294:220 295:233 296:251 297:251 298:243 299:82 300:96 301:251 302:251 303:31 317:80 318:253 319:251 320:251 321:188 323:96 324:251 325:251 326:109 328:96 329:251 330:251 331:31 344:96 345:240 346:253 347:243 348:188 349:42 351:96 352:204 353:109 354:4 356:12 357:197 358:251 359:31 372:221 373:251 374:253 375:121 379:36 380:23 385:190 386:251 387:31 399:48 400:234 401:253 413:191 414:253 415:31 426:44 427:221 428:251 429:251 440:12 441:197 442:251 443:31 454:190 455:251 456:251 457:251 468:96 469:251 470:251 471:31 482:190 483:251 484:251 485:113 495:40 496:234 497:251 498:219 499:23 510:190 511:251 512:251 513:94 522:40 523:217 524:253 525:231 526:47 538:191 539:253 540:253 541:253 548:12 549:174 550:253 551:253 552:219 553:39 566:67 567:236 568:251 569:251 570:191 571:190 572:111 573:72 574:190 575:191 576:197 577:251 578:243 579:121 580:39 595:63 596:236 597:251 598:253 599:251 600:251 601:251 602:251 603:253 604:251 605:188 606:94 624:27 625:129 626:253 627:251 628:251 629:251 630:251 631:229 632:168 633:15 654:95 655:212 656:251 657:211 658:94 659:59 +1 159:121 160:254 161:136 186:13 187:230 188:253 189:248 190:99 213:4 214:118 215:253 216:253 217:225 218:42 241:61 242:253 243:253 244:253 245:74 268:32 269:206 270:253 271:253 272:186 273:9 296:211 297:253 298:253 299:239 300:69 324:254 325:253 326:253 327:133 351:142 352:255 353:253 354:186 355:8 378:149 379:229 380:254 381:207 382:21 405:54 406:229 407:253 408:254 409:105 433:152 434:254 435:254 436:213 437:26 460:112 461:251 462:253 463:253 464:26 487:29 488:212 489:253 490:250 491:149 514:36 515:214 516:253 517:253 518:137 542:75 543:253 544:253 545:253 546:59 570:93 571:253 572:253 573:189 574:17 598:224 599:253 600:253 601:84 625:43 626:235 627:253 628:126 629:1 653:99 654:248 655:253 656:119 682:225 683:235 684:49 +1 100:166 101:222 102:55 128:197 129:254 130:218 131:5 155:29 156:249 157:254 158:254 159:9 183:45 184:254 185:254 186:174 187:2 210:4 211:164 212:254 213:254 214:85 238:146 239:254 240:254 241:254 242:85 265:101 266:245 267:254 268:254 269:254 270:85 292:97 293:248 294:254 295:204 296:254 297:254 298:85 315:12 316:59 317:98 318:151 319:237 320:254 321:254 322:109 323:35 324:254 325:254 326:85 343:41 344:216 345:254 346:254 347:239 348:153 349:37 350:4 351:32 352:254 353:254 354:85 372:7 373:44 374:44 375:30 379:32 380:254 381:254 382:96 407:19 408:230 409:254 410:174 436:197 437:254 438:110 464:197 465:254 466:85 492:197 493:253 494:63 515:37 516:54 517:54 518:45 519:26 520:84 521:221 522:84 523:21 524:31 525:162 526:78 540:6 541:41 542:141 543:244 544:254 545:254 546:248 547:236 548:254 549:254 550:254 551:233 552:239 553:254 554:138 567:23 568:167 569:254 570:254 571:254 572:254 573:229 574:228 575:185 576:138 577:138 578:138 579:138 580:138 581:138 582:44 595:113 596:254 597:254 598:254 599:179 600:64 601:5 623:32 624:209 625:183 626:97 +0 155:53 156:255 157:253 158:253 159:253 160:124 183:180 184:253 185:251 186:251 187:251 188:251 189:145 190:62 209:32 210:217 211:241 212:253 213:251 214:251 215:251 216:251 217:253 218:107 237:37 238:251 239:251 240:253 241:251 242:251 243:251 244:251 245:253 246:107 265:166 266:251 267:251 268:253 269:251 270:96 271:148 272:251 273:253 274:107 291:73 292:253 293:253 294:253 295:253 296:130 299:110 300:253 301:255 302:108 319:73 320:251 321:251 322:251 323:251 327:109 328:251 329:253 330:107 347:202 348:251 349:251 350:251 351:225 354:6 355:129 356:251 357:253 358:107 375:150 376:251 377:251 378:251 379:71 382:115 383:251 384:251 385:253 386:107 403:253 404:251 405:251 406:173 407:20 410:217 411:251 412:251 413:253 414:107 430:182 431:255 432:253 433:216 438:218 439:253 440:253 441:182 457:63 458:221 459:253 460:251 461:215 465:84 466:236 467:251 468:251 469:77 485:109 486:251 487:253 488:251 489:215 492:11 493:160 494:251 495:251 496:96 513:109 514:251 515:253 516:251 517:137 520:150 521:251 522:251 523:251 524:71 541:109 542:251 543:253 544:251 545:35 547:130 548:253 549:251 550:251 551:173 552:20 569:110 570:253 571:255 572:253 573:98 574:150 575:253 576:255 577:253 578:164 597:109 598:251 599:253 600:251 601:251 602:251 603:251 604:253 605:251 606:35 625:93 626:241 627:253 628:251 629:251 630:251 631:251 632:216 633:112 634:5 654:103 655:253 656:251 657:251 658:251 659:251 683:124 684:251 685:225 686:71 687:71 +0 128:73 129:253 130:227 131:73 132:21 156:73 157:251 158:251 159:251 160:174 182:16 183:166 184:228 185:251 186:251 187:251 188:122 210:62 211:220 212:253 213:251 214:251 215:251 216:251 217:79 238:79 239:231 240:253 241:251 242:251 243:251 244:251 245:232 246:77 264:145 265:253 266:253 267:253 268:255 269:253 270:253 271:253 272:253 273:255 274:108 292:144 293:251 294:251 295:251 296:253 297:168 298:107 299:169 300:251 301:253 302:189 303:20 318:27 319:89 320:236 321:251 322:235 323:215 324:164 325:15 326:6 327:129 328:251 329:253 330:251 331:35 345:47 346:211 347:253 348:251 349:251 350:142 354:37 355:251 356:251 357:253 358:251 359:35 373:109 374:251 375:253 376:251 377:251 378:142 382:11 383:148 384:251 385:253 386:251 387:164 400:11 401:150 402:253 403:255 404:211 405:25 410:11 411:150 412:253 413:255 414:211 415:25 428:140 429:251 430:251 431:253 432:107 438:37 439:251 440:251 441:211 442:46 456:190 457:251 458:251 459:253 460:128 461:5 466:37 467:251 468:251 469:51 484:115 485:251 486:251 487:253 488:188 489:20 492:32 493:109 494:129 495:251 496:173 497:103 512:217 513:251 514:251 515:201 516:30 520:73 521:251 522:251 523:251 524:71 540:166 541:253 542:253 543:255 544:149 545:73 546:150 547:253 548:255 549:253 550:253 551:143 568:140 569:251 570:251 571:253 572:251 573:251 574:251 575:251 576:253 577:251 578:230 579:61 596:190 597:251 598:251 599:253 600:251 601:251 602:251 603:251 604:242 605:215 606:55 624:21 625:189 626:251 627:253 628:251 629:251 630:251 631:173 632:103 653:31 654:200 655:253 656:251 657:96 658:71 659:20 +1 155:178 156:255 157:105 182:6 183:188 184:253 185:216 186:14 210:14 211:202 212:253 213:253 214:23 238:12 239:199 240:253 241:128 242:6 266:42 267:253 268:253 269:158 294:42 295:253 296:253 297:158 322:155 323:253 324:253 325:158 350:160 351:253 352:253 353:147 378:160 379:253 380:253 381:41 405:17 406:225 407:253 408:235 409:31 433:24 434:253 435:253 436:176 461:24 462:253 463:253 464:176 489:24 490:253 491:253 492:176 517:24 518:253 519:253 520:176 545:24 546:253 547:253 548:162 573:46 574:253 575:253 576:59 601:142 602:253 603:253 604:59 629:142 630:253 631:253 632:59 657:142 658:253 659:202 660:8 685:87 686:253 687:139 +0 154:46 155:105 156:254 157:254 158:254 159:254 160:255 161:239 162:41 180:37 181:118 182:222 183:254 184:253 185:253 186:253 187:253 188:253 189:253 190:211 191:54 207:14 208:200 209:253 210:253 211:254 212:253 213:253 214:253 215:253 216:253 217:253 218:253 219:116 233:16 234:160 235:236 236:253 237:253 238:253 239:254 240:253 241:253 242:246 243:229 244:253 245:253 246:253 247:116 261:99 262:253 263:253 264:253 265:253 266:253 267:254 268:253 269:253 270:213 271:99 272:253 273:253 274:253 275:116 288:25 289:194 290:253 291:253 292:253 293:253 294:131 295:97 296:169 297:253 298:93 299:99 300:253 301:253 302:253 303:116 316:206 317:253 318:253 319:251 320:233 321:127 322:9 324:18 325:38 326:3 327:15 328:171 329:253 330:253 331:116 343:55 344:240 345:253 346:253 347:233 355:31 356:186 357:253 358:253 359:116 371:176 372:253 373:253 374:253 375:127 383:99 384:253 385:253 386:253 387:116 399:176 400:253 401:253 402:131 403:9 411:99 412:253 413:253 414:253 415:116 426:119 427:254 428:254 429:232 430:75 440:158 441:254 442:254 443:117 454:118 455:253 456:253 457:154 468:156 469:253 470:253 471:116 482:118 483:253 484:253 485:154 496:156 497:253 498:253 499:116 509:46 510:222 511:253 512:253 513:154 522:7 523:116 524:246 525:253 526:180 527:9 538:118 539:253 540:253 541:154 550:116 551:253 552:253 553:253 554:174 566:118 567:253 568:253 569:154 577:110 578:246 579:253 580:253 581:240 582:67 594:118 595:253 596:253 597:238 598:215 599:49 600:20 601:20 602:20 603:66 604:215 605:241 606:253 607:245 608:233 609:64 622:82 623:229 624:253 625:253 626:253 627:253 628:253 629:253 630:253 631:254 632:253 633:253 634:240 635:107 651:176 652:253 653:253 654:253 655:253 656:253 657:253 658:253 659:254 660:253 661:253 662:108 679:40 680:239 681:253 682:253 683:253 684:253 685:253 686:253 687:254 688:161 689:57 690:4 +0 152:56 153:105 154:220 155:254 156:63 178:18 179:166 180:233 181:253 182:253 183:253 184:236 185:209 186:209 187:209 188:77 189:18 206:84 207:253 208:253 209:253 210:253 211:253 212:254 213:253 214:253 215:253 216:253 217:172 218:8 233:57 234:238 235:253 236:253 237:253 238:253 239:253 240:254 241:253 242:253 243:253 244:253 245:253 246:119 260:14 261:238 262:253 263:253 264:253 265:253 266:253 267:253 268:179 269:196 270:253 271:253 272:253 273:253 274:238 275:12 288:33 289:253 290:253 291:253 292:253 293:253 294:248 295:134 297:18 298:83 299:237 300:253 301:253 302:253 303:14 316:164 317:253 318:253 319:253 320:253 321:253 322:128 327:57 328:119 329:214 330:253 331:94 343:57 344:248 345:253 346:253 347:253 348:126 349:14 350:4 357:179 358:253 359:248 360:56 371:175 372:253 373:253 374:240 375:190 376:28 385:179 386:253 387:253 388:173 399:209 400:253 401:253 402:178 413:92 414:253 415:253 416:208 427:211 428:254 429:254 430:179 442:135 443:255 444:209 455:209 456:253 457:253 458:90 470:134 471:253 472:208 483:209 484:253 485:253 486:178 497:2 498:142 499:253 500:208 511:209 512:253 513:253 514:214 515:35 525:30 526:253 527:253 528:208 539:165 540:253 541:253 542:253 543:215 544:36 553:163 554:253 555:253 556:164 567:18 568:172 569:253 570:253 571:253 572:214 573:127 574:7 580:72 581:232 582:253 583:171 584:17 596:8 597:182 598:253 599:253 600:253 601:253 602:162 603:56 607:64 608:240 609:253 610:253 611:14 625:7 626:173 627:253 628:253 629:253 630:253 631:245 632:241 633:239 634:239 635:246 636:253 637:225 638:14 639:1 654:18 655:59 656:138 657:224 658:253 659:253 660:254 661:253 662:253 663:253 664:240 665:96 685:37 686:104 687:192 688:255 689:253 690:253 691:182 692:73 +1 130:7 131:176 132:254 133:224 158:51 159:253 160:253 161:223 185:4 186:170 187:253 188:253 189:214 213:131 214:253 215:253 216:217 217:39 241:209 242:253 243:253 244:134 268:75 269:240 270:253 271:239 272:26 296:184 297:253 298:245 299:63 323:142 324:255 325:253 326:185 350:62 351:229 352:254 353:242 354:73 377:54 378:229 379:253 380:254 381:105 405:152 406:254 407:254 408:213 409:26 432:32 433:243 434:253 435:253 436:115 459:2 460:142 461:253 462:253 463:155 487:30 488:253 489:253 490:232 491:55 515:75 516:253 517:253 518:164 542:72 543:232 544:253 545:189 546:17 570:224 571:253 572:253 573:163 597:43 598:235 599:253 600:253 601:195 602:21 625:28 626:231 627:253 628:253 629:184 630:14 654:225 655:253 656:253 657:75 +0 155:21 156:176 157:253 158:253 159:124 182:105 183:176 184:251 185:251 186:251 187:251 188:105 208:58 209:217 210:241 211:253 212:251 213:251 214:251 215:251 216:243 217:113 218:5 235:63 236:231 237:251 238:251 239:253 240:251 241:251 242:251 243:251 244:253 245:251 246:113 263:144 264:251 265:251 266:251 267:253 268:251 269:251 270:251 271:251 272:253 273:251 274:215 290:125 291:253 292:253 293:253 294:253 295:255 296:253 297:253 298:253 299:253 300:255 301:253 302:227 303:42 318:253 319:251 320:251 321:251 322:251 323:253 324:251 325:251 326:251 327:251 328:253 329:251 330:251 331:142 345:27 346:253 347:251 348:251 349:235 350:241 351:253 352:251 353:246 354:137 355:35 356:98 357:251 358:251 359:236 360:61 372:47 373:211 374:253 375:251 376:235 377:82 378:103 379:253 380:251 381:137 384:73 385:251 386:251 387:251 388:71 399:27 400:211 401:251 402:253 403:251 404:86 407:72 408:71 409:10 412:73 413:251 414:251 415:173 416:20 427:89 428:253 429:253 430:255 431:253 432:35 440:73 441:253 442:253 443:253 444:72 454:84 455:236 456:251 457:251 458:253 459:251 460:138 468:73 469:251 470:251 471:251 472:71 481:63 482:236 483:251 484:251 485:251 486:227 487:251 488:246 489:138 490:11 494:16 495:37 496:228 497:251 498:246 499:137 500:10 509:73 510:251 511:251 512:251 513:173 514:42 515:142 516:142 517:142 518:41 522:109 523:251 524:253 525:251 526:137 537:73 538:251 539:251 540:173 541:20 549:27 550:211 551:251 552:253 553:147 554:10 565:73 566:253 567:253 568:143 575:21 576:176 577:253 578:253 579:253 593:73 594:251 595:251 596:205 597:144 603:176 604:251 605:251 606:188 607:107 621:62 622:236 623:251 624:251 625:251 626:218 627:217 628:217 629:217 630:217 631:253 632:230 633:189 634:20 650:83 651:158 652:251 653:251 654:253 655:251 656:251 657:251 658:251 659:253 660:107 679:37 680:251 681:251 682:253 683:251 684:251 685:251 686:122 687:72 688:30 +1 151:68 152:45 153:131 154:131 155:131 156:101 157:68 158:92 159:44 187:19 188:170 211:29 212:112 213:89 215:40 216:222 239:120 240:254 241:251 242:127 243:40 244:222 267:197 268:254 269:254 270:91 271:40 272:222 294:64 295:247 296:254 297:236 298:50 299:40 300:107 322:184 323:254 324:254 325:91 327:6 328:14 350:203 351:254 352:254 353:71 377:23 378:218 379:254 380:254 381:71 405:113 406:254 407:255 408:239 409:53 433:210 434:254 435:254 436:195 460:62 461:242 462:254 463:241 464:88 468:28 488:86 489:254 490:254 491:189 495:28 496:104 516:106 517:254 518:254 519:168 523:40 524:91 544:216 545:254 546:245 547:51 551:35 552:80 572:216 573:254 574:102 599:55 600:239 601:254 602:52 627:166 628:254 629:210 630:23 655:223 656:252 657:104 683:223 684:169 +0 125:29 126:170 127:255 128:255 129:141 151:29 152:198 153:255 154:255 155:255 156:226 157:255 158:86 178:141 179:255 180:255 181:170 182:29 184:86 185:255 186:255 187:141 204:29 205:226 206:255 207:198 208:57 213:226 214:255 215:255 216:226 217:114 231:29 232:255 233:255 234:114 241:141 242:170 243:114 244:255 245:255 246:141 259:226 260:255 261:170 269:29 270:57 273:141 274:255 275:226 286:57 287:255 288:170 302:114 303:255 304:198 314:226 315:255 331:170 332:255 333:57 342:255 343:226 360:255 361:170 370:255 371:170 388:114 389:198 398:255 399:226 416:86 417:255 426:198 427:255 444:86 445:255 454:114 455:255 456:57 472:86 473:255 482:29 483:255 484:226 500:141 501:255 511:170 512:255 513:170 528:226 529:198 539:29 540:226 541:255 542:170 555:29 556:255 557:114 568:29 569:226 570:255 571:141 582:57 583:226 584:226 598:141 599:255 600:255 601:170 602:86 607:29 608:86 609:226 610:255 611:226 612:29 627:86 628:198 629:255 630:255 631:255 632:255 633:255 634:255 635:255 636:255 637:255 638:141 639:29 657:29 658:114 659:170 660:170 661:170 662:170 663:170 664:86 +0 153:203 154:254 155:252 156:252 157:252 158:214 159:51 160:20 180:62 181:221 182:252 183:250 184:250 185:250 186:252 187:250 188:160 189:20 207:62 208:211 209:250 210:252 211:250 212:250 213:250 214:252 215:250 216:250 217:49 234:41 235:221 236:250 237:250 238:252 239:250 240:250 241:250 242:252 243:250 244:128 245:10 262:254 263:252 264:252 265:252 266:254 267:252 268:252 269:252 270:254 271:252 272:252 273:90 290:150 291:190 292:250 293:250 294:252 295:250 296:250 297:169 298:171 299:250 300:250 301:250 302:82 318:31 319:191 320:250 321:250 322:252 323:189 324:100 325:20 326:172 327:250 328:250 329:250 330:80 346:213 347:250 348:250 349:250 350:212 351:29 354:252 355:250 356:250 357:250 374:92 375:252 376:252 377:252 382:51 383:252 384:252 385:252 386:203 401:82 402:252 403:250 404:250 405:169 410:132 411:250 412:250 413:250 414:121 428:92 429:231 430:252 431:250 432:159 433:20 438:252 439:250 440:250 441:250 456:30 457:211 458:252 459:250 460:221 461:40 466:90 467:250 468:250 469:250 470:163 484:31 485:213 486:254 487:232 488:80 494:92 495:252 496:252 497:212 498:163 512:151 513:250 514:252 515:149 522:252 523:250 524:250 525:49 540:60 541:221 542:252 543:210 544:60 550:252 551:250 552:250 553:49 569:202 570:252 571:250 572:221 573:40 576:123 577:202 578:252 579:250 580:250 581:49 596:123 597:243 598:255 599:252 600:252 601:252 602:254 603:252 604:252 605:252 606:254 607:252 608:100 625:121 626:171 627:250 628:250 629:250 630:252 631:250 632:250 633:250 634:252 635:250 636:100 654:20 655:160 656:250 657:250 658:252 659:250 660:250 661:250 662:252 663:189 664:40 683:20 684:170 685:250 686:252 687:250 688:128 689:49 690:49 691:29 +1 98:64 99:191 100:70 125:68 126:243 127:253 128:249 129:63 152:30 153:223 154:253 155:253 156:247 157:41 179:73 180:238 181:253 182:253 183:253 184:242 206:73 207:236 208:253 209:253 210:253 211:253 212:242 234:182 235:253 236:253 237:191 238:247 239:253 240:149 262:141 263:253 264:143 265:86 266:249 267:253 268:122 290:9 291:36 292:7 293:14 294:233 295:253 296:122 322:230 323:253 324:122 350:230 351:253 352:122 378:231 379:255 380:123 406:230 407:253 408:52 433:61 434:245 435:253 461:98 462:253 463:253 468:35 469:12 489:98 490:253 491:253 494:9 495:142 496:233 497:146 517:190 518:253 519:253 520:128 521:7 522:99 523:253 524:253 525:180 544:29 545:230 546:253 547:253 548:252 549:210 550:253 551:253 552:253 553:140 571:28 572:207 573:253 574:253 575:253 576:254 577:253 578:253 579:235 580:70 581:9 599:126 600:253 601:253 602:253 603:253 604:254 605:253 606:168 607:19 627:79 628:253 629:253 630:201 631:190 632:132 633:63 634:5 +1 125:26 126:240 127:72 153:25 154:238 155:208 182:209 183:226 184:14 210:209 211:254 212:43 238:175 239:254 240:128 266:63 267:254 268:204 294:107 295:254 296:204 322:88 323:254 324:204 350:55 351:254 352:204 378:126 379:254 380:204 406:126 407:254 408:189 434:169 435:254 436:121 462:209 463:254 464:193 490:209 491:254 492:111 517:22 518:235 519:254 520:37 545:137 546:254 547:227 548:16 573:205 574:255 575:185 601:205 602:254 603:125 629:205 630:254 631:125 657:111 658:212 659:43 +0 155:62 156:91 157:213 158:255 159:228 160:91 161:12 182:70 183:230 184:253 185:253 186:253 187:253 188:253 189:152 190:7 210:246 211:253 212:253 213:253 214:253 215:253 216:253 217:253 218:106 237:21 238:247 239:253 240:253 241:253 242:253 243:253 244:253 245:208 246:24 265:156 266:253 267:253 268:253 269:253 270:253 271:253 272:253 273:195 292:88 293:238 294:253 295:253 296:253 297:221 298:253 299:253 300:253 301:195 320:230 321:253 322:253 323:253 324:198 325:40 326:177 327:253 328:253 329:195 346:56 347:156 348:251 349:253 350:189 351:182 352:15 354:86 355:240 356:253 357:210 358:28 374:213 375:253 376:253 377:156 378:3 383:205 384:253 385:253 386:106 401:121 402:252 403:253 404:135 405:3 411:46 412:253 413:253 414:106 428:28 429:212 430:253 431:248 432:23 439:42 440:253 441:253 442:106 456:197 457:253 458:234 459:70 467:42 468:253 469:253 470:106 483:11 484:202 485:253 486:187 495:58 496:253 497:210 498:27 511:107 512:253 513:253 514:40 522:53 523:227 524:253 525:195 539:107 540:253 541:253 542:40 549:47 550:227 551:253 552:231 553:58 567:107 568:253 569:253 570:40 575:5 576:131 577:222 578:253 579:231 580:59 595:14 596:204 597:253 598:226 599:222 600:73 601:58 602:58 603:170 604:253 605:253 606:227 607:58 624:197 625:253 626:253 627:253 628:253 629:253 630:253 631:253 632:253 633:238 634:58 652:33 653:179 654:241 655:253 656:253 657:253 658:253 659:250 660:116 661:14 682:75 683:179 684:253 685:151 686:89 687:86 +1 157:42 158:228 159:253 160:253 185:144 186:251 187:251 188:251 212:89 213:236 214:251 215:235 216:215 239:79 240:253 241:251 242:251 243:142 267:180 268:253 269:251 270:251 271:142 294:32 295:202 296:255 297:253 298:216 322:109 323:251 324:253 325:251 326:112 349:6 350:129 351:251 352:253 353:127 354:5 377:37 378:251 379:251 380:253 381:107 405:166 406:251 407:251 408:201 409:30 432:42 433:228 434:253 435:253 460:144 461:251 462:251 463:147 487:63 488:236 489:251 490:251 491:71 515:150 516:251 517:251 518:204 519:41 543:253 544:251 545:251 546:142 571:255 572:253 573:164 598:105 599:253 600:251 601:35 626:180 627:253 628:251 629:35 654:180 655:253 656:251 657:35 682:180 683:253 684:251 685:35 +1 128:62 129:254 130:213 156:102 157:253 158:252 159:102 160:20 184:102 185:254 186:253 187:254 188:50 212:102 213:253 214:252 215:253 216:50 240:102 241:254 242:253 243:254 244:50 268:142 269:253 270:252 271:253 272:50 295:51 296:253 297:254 298:253 299:224 300:20 323:132 324:252 325:253 326:252 327:162 351:173 352:253 353:254 354:253 355:102 378:82 379:253 380:252 381:253 382:252 383:61 406:203 407:254 408:253 409:254 410:233 433:41 434:243 435:253 436:252 437:253 438:111 461:132 462:253 463:254 464:253 465:203 488:41 489:253 490:252 491:253 492:252 493:40 515:11 516:213 517:254 518:253 519:254 520:151 543:92 544:252 545:253 546:252 547:192 548:50 570:21 571:214 572:253 573:255 574:253 575:41 598:142 599:253 600:252 601:253 602:171 625:113 626:253 627:255 628:253 629:203 630:40 653:30 654:131 655:233 656:111 +0 154:28 155:195 156:254 157:254 158:254 159:254 160:254 161:255 162:61 181:6 182:191 183:253 184:253 185:253 186:253 187:253 188:253 189:253 190:60 208:26 209:190 210:253 211:253 212:253 213:253 214:240 215:191 216:242 217:253 218:60 235:15 236:187 237:253 238:253 239:253 240:253 241:253 242:200 244:211 245:253 246:60 262:22 263:66 264:253 265:253 266:253 267:253 268:241 269:209 270:44 271:23 272:218 273:253 274:60 290:124 291:253 292:253 293:253 294:253 295:253 296:182 299:131 300:253 301:253 302:60 318:38 319:217 320:253 321:253 322:244 323:111 324:37 327:131 328:253 329:253 330:60 346:124 347:253 348:253 349:253 350:165 354:22 355:182 356:253 357:253 358:60 374:124 375:253 376:253 377:240 378:45 382:53 383:253 384:253 385:249 386:58 401:16 402:168 403:253 404:216 405:45 410:53 411:253 412:253 413:138 429:159 430:253 431:253 432:147 438:53 439:253 440:253 441:138 456:136 457:252 458:253 459:227 460:5 466:53 467:253 468:243 469:101 484:140 485:253 486:253 487:124 494:156 495:253 496:218 511:13 512:164 513:253 514:142 515:5 521:32 522:233 523:253 524:218 539:62 540:253 541:253 542:130 548:37 549:203 550:253 551:253 552:127 567:62 568:253 569:253 570:147 571:36 572:36 573:36 574:36 575:151 576:222 577:253 578:245 579:127 580:8 595:34 596:202 597:253 598:253 599:253 600:253 601:253 602:253 603:253 604:253 605:253 606:200 624:140 625:253 626:253 627:253 628:253 629:253 630:253 631:253 632:248 633:235 634:65 652:87 653:173 654:253 655:253 656:253 657:253 658:253 659:253 660:182 681:14 682:78 683:96 684:253 685:253 686:253 687:137 688:56 +0 123:8 124:76 125:202 126:254 127:255 128:163 129:37 130:2 150:13 151:182 152:253 153:253 154:253 155:253 156:253 157:253 158:23 177:15 178:179 179:253 180:253 181:212 182:91 183:218 184:253 185:253 186:179 187:109 205:105 206:253 207:253 208:160 209:35 210:156 211:253 212:253 213:253 214:253 215:250 216:113 232:19 233:212 234:253 235:253 236:88 237:121 238:253 239:233 240:128 241:91 242:245 243:253 244:248 245:114 260:104 261:253 262:253 263:110 264:2 265:142 266:253 267:90 270:26 271:199 272:253 273:248 274:63 287:1 288:173 289:253 290:253 291:29 293:84 294:228 295:39 299:72 300:251 301:253 302:215 303:29 315:36 316:253 317:253 318:203 319:13 328:82 329:253 330:253 331:170 343:36 344:253 345:253 346:164 356:11 357:198 358:253 359:184 360:6 371:36 372:253 373:253 374:82 385:138 386:253 387:253 388:35 399:128 400:253 401:253 402:47 413:48 414:253 415:253 416:35 427:154 428:253 429:253 430:47 441:48 442:253 443:253 444:35 455:102 456:253 457:253 458:99 469:48 470:253 471:253 472:35 483:36 484:253 485:253 486:164 496:16 497:208 498:253 499:211 500:17 511:32 512:244 513:253 514:175 515:4 524:44 525:253 526:253 527:156 540:171 541:253 542:253 543:29 551:30 552:217 553:253 554:188 555:19 568:171 569:253 570:253 571:59 578:60 579:217 580:253 581:253 582:70 596:78 597:253 598:253 599:231 600:48 604:26 605:128 606:249 607:253 608:244 609:94 610:15 624:8 625:151 626:253 627:253 628:234 629:101 630:121 631:219 632:229 633:253 634:253 635:201 636:80 653:38 654:232 655:253 656:253 657:253 658:253 659:253 660:253 661:253 662:201 663:66 +0 127:68 128:254 129:255 130:254 131:107 153:11 154:176 155:230 156:253 157:253 158:253 159:212 180:28 181:197 182:253 183:253 184:253 185:253 186:253 187:229 188:107 189:14 208:194 209:253 210:253 211:253 212:253 213:253 214:253 215:253 216:253 217:53 235:69 236:241 237:253 238:253 239:253 240:253 241:241 242:186 243:253 244:253 245:195 262:10 263:161 264:253 265:253 266:253 267:246 268:40 269:57 270:231 271:253 272:253 273:195 290:140 291:253 292:253 293:253 294:253 295:154 297:25 298:253 299:253 300:253 301:195 318:213 319:253 320:253 321:253 322:135 323:8 325:3 326:128 327:253 328:253 329:195 345:77 346:238 347:253 348:253 349:253 350:7 354:116 355:253 356:253 357:195 372:11 373:165 374:253 375:253 376:231 377:70 378:1 382:78 383:237 384:253 385:195 400:33 401:253 402:253 403:253 404:182 411:200 412:253 413:195 428:98 429:253 430:253 431:253 432:24 439:42 440:253 441:195 456:197 457:253 458:253 459:253 460:24 467:163 468:253 469:195 484:197 485:253 486:253 487:189 488:13 494:53 495:227 496:253 497:121 512:197 513:253 514:253 515:114 521:21 522:227 523:253 524:231 525:27 540:197 541:253 542:253 543:114 547:5 548:131 549:143 550:253 551:231 552:59 568:197 569:253 570:253 571:236 572:73 573:58 574:217 575:223 576:253 577:253 578:253 579:174 596:197 597:253 598:253 599:253 600:253 601:253 602:253 603:253 604:253 605:253 606:253 607:48 624:149 625:253 626:253 627:253 628:253 629:253 630:253 631:253 632:253 633:182 634:15 635:3 652:12 653:168 654:253 655:253 656:253 657:253 658:253 659:248 660:89 661:23 +1 157:85 158:255 159:103 160:1 185:205 186:253 187:253 188:30 213:205 214:253 215:253 216:30 240:44 241:233 242:253 243:244 244:27 268:135 269:253 270:253 271:100 296:153 297:253 298:240 299:76 323:12 324:208 325:253 326:166 351:69 352:253 353:253 354:142 378:14 379:110 380:253 381:235 382:33 406:63 407:223 408:235 409:130 434:186 435:253 436:235 437:37 461:17 462:145 463:253 464:231 465:35 489:69 490:220 491:231 492:123 516:18 517:205 518:253 519:176 520:27 543:17 544:125 545:253 546:185 547:39 571:71 572:214 573:231 574:41 599:167 600:253 601:225 602:33 626:72 627:205 628:207 629:14 653:30 654:249 655:233 656:49 681:32 682:253 683:89 +1 126:94 127:132 154:250 155:250 156:4 182:250 183:254 184:95 210:250 211:254 212:95 238:250 239:254 240:95 266:250 267:254 268:95 294:250 295:254 296:95 322:250 323:254 324:95 350:250 351:254 352:95 378:250 379:254 380:95 405:77 406:254 407:250 408:19 433:96 434:254 435:249 461:53 462:253 463:252 464:43 490:250 491:251 492:32 517:85 518:254 519:249 545:96 546:254 547:249 573:83 574:254 575:250 576:14 602:250 603:254 604:95 630:250 631:255 632:95 658:132 659:254 660:95 +1 124:32 125:253 126:31 152:32 153:251 154:149 180:32 181:251 182:188 208:32 209:251 210:188 236:32 237:251 238:228 239:59 264:32 265:253 266:253 267:95 292:28 293:236 294:251 295:114 321:127 322:251 323:251 349:127 350:251 351:251 377:48 378:232 379:251 406:223 407:253 408:159 434:221 435:251 436:158 462:142 463:251 464:158 490:64 491:251 492:242 493:55 518:64 519:251 520:253 521:161 546:64 547:253 548:255 549:221 574:16 575:181 576:253 577:220 603:79 604:253 605:236 606:63 632:213 633:251 634:126 660:96 661:251 662:126 +1 129:39 130:254 131:255 132:254 133:140 157:136 158:253 159:253 160:228 161:67 184:6 185:227 186:253 187:253 188:58 211:29 212:188 213:253 214:253 215:253 216:17 239:95 240:253 241:253 242:253 243:157 244:8 266:3 267:107 268:253 269:253 270:245 271:77 294:29 295:253 296:253 297:240 298:100 322:141 323:253 324:253 325:215 349:129 350:248 351:253 352:253 353:215 377:151 378:253 379:253 380:253 381:144 405:151 406:253 407:253 408:253 409:27 431:3 432:102 433:242 434:253 435:253 436:110 437:3 459:97 460:253 461:253 462:253 463:214 464:55 487:207 488:253 489:253 490:253 491:158 515:67 516:253 517:253 518:253 519:158 543:207 544:253 545:253 546:240 547:88 571:207 572:253 573:253 574:224 598:32 599:217 600:253 601:253 602:224 626:141 627:253 628:253 629:253 630:133 654:36 655:219 656:253 657:140 658:10 +0 123:59 124:55 149:71 150:192 151:254 152:250 153:147 154:17 176:123 177:247 178:253 179:254 180:253 181:253 182:196 183:79 184:176 185:175 186:175 187:124 188:48 203:87 204:247 205:247 206:176 207:95 208:102 209:117 210:243 211:237 212:192 213:232 214:253 215:253 216:245 217:152 218:6 230:23 231:229 232:253 233:138 238:219 239:58 241:95 242:118 243:80 244:230 245:254 246:196 247:30 258:120 259:254 260:205 261:8 266:114 272:38 273:255 274:254 275:155 276:5 286:156 287:253 288:92 301:61 302:235 303:253 304:102 314:224 315:253 316:78 330:117 331:253 332:196 333:18 342:254 343:253 344:78 358:9 359:211 360:253 361:73 370:254 371:253 372:78 387:175 388:253 389:155 398:194 399:254 400:101 415:79 416:254 417:155 426:112 427:253 428:211 429:9 443:73 444:251 445:200 454:41 455:241 456:253 457:87 471:25 472:240 473:253 483:147 484:253 485:227 486:47 499:94 500:253 501:200 511:5 512:193 513:253 514:230 515:76 527:175 528:253 529:155 540:31 541:219 542:254 543:255 544:126 545:18 553:14 554:149 555:254 556:244 557:45 569:21 570:158 571:254 572:253 573:226 574:162 575:118 576:96 577:20 578:20 579:73 580:118 581:224 582:253 583:247 584:85 598:30 599:155 600:253 601:253 602:253 603:253 604:254 605:253 606:253 607:253 608:253 609:254 610:247 611:84 627:5 628:27 629:117 630:206 631:244 632:229 633:213 634:213 635:213 636:176 637:117 638:32 659:45 660:23 +1 128:58 129:139 156:247 157:247 158:25 183:121 184:253 185:156 186:3 211:133 212:253 213:145 238:11 239:227 240:253 241:145 266:7 267:189 268:253 269:145 294:35 295:252 296:253 297:145 322:146 323:252 324:253 325:131 350:146 351:252 352:253 353:13 378:146 379:252 380:253 381:13 406:147 407:253 408:255 409:13 434:146 435:252 436:253 437:13 462:146 463:252 464:253 465:13 490:146 491:252 492:253 493:13 517:22 518:230 519:252 520:221 521:9 545:22 546:230 547:252 548:133 574:146 575:252 576:133 602:146 603:252 604:120 630:146 631:252 658:146 659:252 +1 129:28 130:247 131:255 132:165 156:47 157:221 158:252 159:252 160:164 184:177 185:252 186:252 187:252 188:164 212:177 213:252 214:252 215:223 216:78 240:177 241:252 242:252 243:197 267:114 268:236 269:252 270:235 271:42 294:5 295:148 296:252 297:252 298:230 321:14 322:135 323:252 324:252 325:252 326:230 349:78 350:252 351:252 352:252 353:252 354:162 377:78 378:252 379:252 380:252 381:252 382:9 405:78 406:252 407:252 408:252 409:252 410:9 432:32 433:200 434:252 435:252 436:252 437:105 438:3 459:10 460:218 461:252 462:252 463:252 464:105 465:8 487:225 488:252 489:252 490:252 491:240 492:69 514:44 515:237 516:252 517:252 518:228 519:85 541:59 542:218 543:252 544:252 545:225 546:93 568:65 569:208 570:252 571:252 572:252 573:175 596:133 597:252 598:252 599:252 600:225 601:68 624:133 625:252 626:252 627:244 628:54 652:133 653:252 654:252 655:48 +0 156:13 157:6 181:10 182:77 183:145 184:253 185:190 186:67 207:11 208:77 209:193 210:252 211:252 212:253 213:252 214:238 215:157 216:71 217:26 233:10 234:78 235:193 236:252 237:252 238:252 239:252 240:253 241:252 242:252 243:252 244:252 245:228 246:128 247:49 248:5 259:6 260:78 261:194 262:252 263:252 264:252 265:252 266:252 267:252 268:253 269:217 270:192 271:232 272:252 273:252 274:252 275:252 276:135 277:3 286:4 287:147 288:252 289:252 290:252 291:252 292:252 293:252 294:252 295:252 296:175 297:26 299:40 300:145 301:235 302:252 303:252 304:252 305:104 314:208 315:252 316:252 317:252 318:252 319:252 320:252 321:133 322:48 323:48 329:71 330:236 331:252 332:252 333:230 342:253 343:185 344:170 345:252 346:252 347:252 348:173 349:22 358:102 359:252 360:252 361:252 370:24 371:141 372:243 373:252 374:252 375:186 376:5 386:8 387:220 388:252 389:252 398:70 399:247 400:252 401:252 402:165 403:37 414:81 415:251 416:252 417:194 426:255 427:253 428:253 429:251 430:69 441:39 442:231 443:253 444:253 445:127 454:253 455:252 456:249 457:127 468:6 469:147 470:252 471:252 472:190 473:5 482:253 483:252 484:216 495:7 496:145 497:252 498:252 499:252 500:69 510:253 511:252 512:223 513:16 522:25 523:185 524:252 525:252 526:252 527:107 528:8 538:167 539:252 540:252 541:181 542:18 549:105 550:191 551:252 552:252 553:235 554:151 555:10 566:37 567:221 568:252 569:252 570:210 571:193 572:96 573:73 574:130 575:188 576:194 577:227 578:252 579:252 580:235 581:128 595:97 596:220 597:252 598:252 599:252 600:252 601:252 602:252 603:252 604:253 605:252 606:252 607:236 608:70 624:40 625:174 626:252 627:252 628:252 629:252 630:252 631:252 632:253 633:197 634:138 635:29 653:5 654:23 655:116 656:143 657:143 658:143 659:143 660:24 661:10 +0 127:28 128:164 129:254 130:233 131:148 132:11 154:3 155:164 156:254 157:234 158:225 159:254 160:204 182:91 183:254 184:235 185:48 186:32 187:166 188:251 189:92 208:33 209:111 210:214 211:205 212:49 215:24 216:216 217:210 235:34 236:217 237:254 238:254 239:211 244:87 245:237 246:43 262:34 263:216 264:254 265:254 266:252 267:243 268:61 272:38 273:248 274:182 290:171 291:254 292:184 293:205 294:175 295:36 301:171 302:227 317:28 318:234 319:190 320:13 321:193 322:157 329:124 330:238 331:26 345:140 346:254 347:131 349:129 350:157 357:124 358:254 359:95 373:201 374:238 375:56 377:70 378:103 385:124 386:254 387:148 400:62 401:255 402:210 413:150 414:254 415:122 428:86 429:254 430:201 431:15 440:28 441:237 442:246 443:44 456:128 457:254 458:143 468:34 469:243 470:227 484:62 485:254 486:210 496:58 497:249 498:179 512:30 513:240 514:210 524:207 525:254 526:64 541:216 542:231 543:34 551:129 552:248 553:170 554:9 569:131 570:254 571:170 577:17 578:129 579:248 580:225 581:24 597:50 598:245 599:245 600:184 601:106 602:106 603:106 604:133 605:231 606:254 607:244 608:53 626:67 627:249 628:254 629:254 630:254 631:254 632:254 633:251 634:193 635:40 655:38 656:157 657:248 658:166 659:166 660:139 661:57 +0 129:105 130:255 131:219 132:67 133:67 134:52 156:20 157:181 158:253 159:253 160:253 161:253 162:226 163:69 182:4 183:129 184:206 185:253 186:253 187:253 188:253 189:253 190:253 191:130 209:9 210:141 211:253 212:253 213:253 214:253 215:253 216:253 217:253 218:253 219:166 220:20 237:134 238:253 239:253 240:253 241:253 242:253 243:253 244:253 245:253 246:253 247:253 248:65 262:2 263:83 264:207 265:246 266:253 267:253 268:253 269:253 270:253 271:249 272:234 273:247 274:253 275:253 276:65 290:83 291:253 292:253 293:253 294:253 295:253 296:189 297:253 298:253 299:205 301:179 302:253 303:253 304:65 317:85 318:234 319:253 320:253 321:253 322:253 323:157 324:26 325:164 326:151 327:83 329:179 330:253 331:253 332:65 344:65 345:237 346:253 347:253 348:253 349:67 350:36 351:14 353:15 354:12 357:179 358:253 359:253 360:65 371:4 372:141 373:253 374:253 375:221 376:158 377:23 385:179 386:253 387:253 388:65 399:129 400:253 401:253 402:241 403:62 412:72 413:226 414:253 415:175 416:24 426:119 427:247 428:253 429:253 430:206 439:8 440:134 441:253 442:253 443:130 454:132 455:253 456:253 457:194 458:27 467:125 468:253 469:253 470:253 471:130 481:45 482:213 483:253 484:253 485:112 493:70 494:170 495:247 496:253 497:253 498:89 499:43 509:67 510:253 511:253 512:196 513:55 514:9 520:8 521:131 522:253 523:253 524:253 525:86 526:1 537:67 538:253 539:253 540:253 541:253 542:129 546:43 547:114 548:134 549:253 550:253 551:231 552:139 553:41 565:20 566:167 567:253 568:253 569:253 570:247 571:179 572:179 573:179 574:206 575:253 576:253 577:253 578:253 579:72 594:103 595:240 596:253 597:253 598:253 599:253 600:253 601:253 602:253 603:253 604:244 605:119 606:8 607:1 623:107 624:253 625:253 626:253 627:253 628:253 629:253 630:253 631:175 632:111 651:3 652:121 653:253 654:253 655:253 656:253 657:253 658:182 659:24 +0 125:22 126:183 127:252 128:254 129:252 130:252 131:252 132:76 151:85 152:85 153:168 154:250 155:250 156:252 157:250 158:250 159:250 160:250 161:71 163:43 164:85 165:14 178:107 179:252 180:250 181:250 182:250 183:250 184:252 185:250 186:250 187:250 188:250 189:210 191:127 192:250 193:146 205:114 206:237 207:252 208:250 209:250 210:250 211:250 212:252 213:250 214:250 215:250 216:250 217:210 219:127 220:250 221:250 232:107 233:237 234:250 235:252 236:250 237:250 238:250 239:74 240:41 241:41 242:41 243:41 244:217 245:34 247:127 248:250 249:250 259:15 260:148 261:252 262:252 263:254 264:238 265:105 275:128 276:252 277:252 286:15 287:140 288:250 289:250 290:250 291:167 292:111 303:127 304:250 305:250 314:43 315:250 316:250 317:250 318:250 331:127 332:250 333:250 342:183 343:250 344:250 345:250 346:110 358:57 359:210 360:250 361:250 370:252 371:250 372:250 373:110 374:7 386:85 387:250 388:250 389:250 398:254 399:252 400:252 401:83 414:86 415:252 416:252 417:217 426:252 427:250 428:250 429:138 430:14 441:15 442:140 443:250 444:250 445:41 454:252 455:250 456:250 457:250 458:41 469:43 470:250 471:250 472:250 473:41 482:252 483:250 484:250 485:250 486:181 497:183 498:250 499:250 500:250 501:41 510:76 511:250 512:250 513:250 514:250 524:177 525:252 526:250 527:250 528:110 529:7 538:36 539:224 540:252 541:252 542:252 543:219 544:43 545:43 546:43 547:7 549:15 550:43 551:183 552:252 553:255 554:252 555:126 567:85 568:250 569:250 570:250 571:252 572:250 573:250 574:250 575:111 576:86 577:140 578:250 579:250 580:250 581:252 582:222 583:83 595:42 596:188 597:250 598:250 599:252 600:250 601:250 602:250 603:250 604:252 605:250 606:250 607:250 608:250 609:126 610:83 624:127 625:250 626:250 627:252 628:250 629:250 630:250 631:250 632:252 633:250 634:250 635:137 636:83 652:21 653:41 654:217 655:252 656:250 657:250 658:250 659:250 660:217 661:41 662:41 663:14 +1 155:114 156:206 157:25 183:238 184:252 185:55 211:222 212:252 213:55 239:113 240:252 241:55 267:113 268:252 269:55 295:255 296:253 297:56 323:253 324:176 325:6 350:32 351:253 352:233 353:43 378:140 379:253 380:195 381:19 406:140 407:253 408:167 433:29 434:253 435:141 461:29 462:252 463:140 489:29 490:252 491:140 517:29 518:252 519:140 545:29 546:252 547:140 573:169 574:253 575:79 601:169 602:252 628:76 629:234 630:141 656:197 657:233 658:37 684:197 685:223 +1 127:73 128:253 129:253 130:63 155:115 156:252 157:252 158:144 183:217 184:252 185:252 186:144 210:63 211:237 212:252 213:252 214:144 238:109 239:252 240:252 241:252 266:109 267:252 268:252 269:252 294:109 295:252 296:252 297:252 322:191 323:252 324:252 325:252 349:145 350:255 351:253 352:253 353:253 376:32 377:237 378:253 379:252 380:252 381:210 404:37 405:252 406:253 407:252 408:252 409:108 432:37 433:252 434:253 435:252 436:252 437:108 460:21 461:207 462:255 463:253 464:253 465:108 489:144 490:253 491:252 492:252 493:108 516:27 517:221 518:253 519:252 520:252 521:108 544:16 545:190 546:253 547:252 548:252 549:108 573:145 574:255 575:253 576:253 577:253 601:144 602:253 603:252 604:252 605:210 629:144 630:253 631:252 632:252 633:108 657:62 658:253 659:252 660:252 661:108 +1 120:85 121:253 122:132 123:9 147:82 148:241 149:251 150:251 151:128 175:175 176:251 177:251 178:251 179:245 180:121 203:13 204:204 205:251 206:251 207:251 208:245 209:107 232:39 233:251 234:251 235:251 236:251 237:167 238:22 260:15 261:155 262:251 263:251 264:251 265:251 266:177 289:15 290:157 291:248 292:251 293:251 294:251 295:165 319:214 320:251 321:251 322:251 323:212 324:78 325:24 347:109 348:251 349:251 350:251 351:253 352:251 353:170 354:10 375:5 376:57 377:162 378:251 379:253 380:251 381:251 382:18 405:106 406:239 407:255 408:253 409:253 410:213 434:105 435:253 436:251 437:251 438:230 439:72 463:253 464:251 465:251 466:251 467:221 468:67 491:72 492:251 493:251 494:251 495:251 496:96 519:36 520:199 521:251 522:251 523:251 524:155 525:15 548:45 549:204 550:251 551:251 552:251 553:157 577:161 578:249 579:251 580:251 581:248 582:147 606:233 607:251 608:251 609:251 610:173 634:233 635:251 636:251 637:251 638:173 662:53 663:131 664:251 665:251 666:173 +1 126:15 127:200 128:255 129:90 154:42 155:254 156:254 157:173 182:42 183:254 184:254 185:199 210:26 211:237 212:254 213:221 214:12 239:213 240:254 241:231 242:17 267:213 268:254 269:199 295:213 296:254 297:199 323:213 324:254 325:96 350:20 351:232 352:254 353:33 378:84 379:254 380:229 381:17 406:168 407:254 408:203 433:8 434:217 435:254 436:187 461:84 462:254 463:254 464:48 489:195 490:254 491:254 492:37 516:20 517:233 518:254 519:212 520:4 544:132 545:254 546:254 547:82 571:9 572:215 573:254 574:254 575:116 576:46 599:55 600:254 601:254 602:254 603:254 604:121 627:113 628:254 629:254 630:254 631:254 632:40 655:12 656:163 657:254 658:185 659:58 660:1 +0 182:32 183:57 184:57 185:57 186:57 187:57 188:57 189:57 208:67 209:185 210:229 211:252 212:252 213:252 214:253 215:252 216:252 217:252 218:185 219:66 234:13 235:188 236:246 237:252 238:253 239:252 240:252 241:252 242:241 243:139 244:177 245:252 246:253 247:246 248:187 249:13 261:26 262:255 263:253 264:244 265:175 266:101 274:126 275:244 276:253 277:153 288:82 289:243 290:253 291:214 292:81 303:169 304:252 305:252 315:19 316:215 317:252 318:206 319:56 331:169 332:252 333:252 343:157 344:252 345:252 346:13 359:169 360:252 361:151 370:41 371:253 372:253 373:128 386:92 387:253 388:206 389:13 398:166 399:252 400:196 401:9 414:216 415:252 416:142 426:253 427:252 428:168 441:89 442:253 443:208 444:13 454:253 455:252 456:68 468:38 469:225 470:253 471:96 482:254 483:253 484:56 495:45 496:229 497:253 498:151 510:253 511:252 512:81 522:70 523:225 524:252 525:227 538:216 539:252 540:168 548:29 549:134 550:253 551:252 552:186 553:31 566:91 567:252 568:243 569:125 573:51 574:114 575:113 576:210 577:252 578:253 579:151 580:19 595:157 596:253 597:253 598:254 599:253 600:253 601:253 602:254 603:253 604:244 605:175 606:51 623:19 624:122 625:196 626:197 627:221 628:196 629:196 630:197 631:121 632:56 655:25 +0 127:42 128:235 129:255 130:84 153:15 154:132 155:208 156:253 157:253 158:171 159:108 180:6 181:177 182:253 183:253 184:253 185:253 186:253 187:242 188:110 208:151 209:253 210:253 211:253 212:253 213:253 214:253 215:253 216:139 235:48 236:208 237:253 238:253 239:253 240:253 241:253 242:253 243:253 244:139 263:85 264:253 265:253 266:253 267:253 268:236 269:156 270:184 271:253 272:148 273:6 290:7 291:141 292:253 293:253 294:253 295:253 296:27 298:170 299:253 300:253 301:74 318:19 319:253 320:253 321:253 322:253 323:253 324:27 326:170 327:253 328:253 329:74 345:16 346:186 347:253 348:253 349:253 350:242 351:105 352:4 354:170 355:253 356:253 357:94 358:1 373:141 374:253 375:253 376:253 377:242 378:100 382:170 383:253 384:253 385:253 386:8 401:141 402:253 403:253 404:253 405:224 410:170 411:253 412:253 413:253 414:8 428:12 429:158 430:253 431:253 432:230 433:51 438:18 439:237 440:253 441:253 442:8 456:76 457:253 458:253 459:218 460:61 467:236 468:253 469:253 470:8 484:76 485:253 486:253 487:168 495:110 496:253 497:132 498:3 512:76 513:253 514:253 515:168 521:20 522:174 523:239 524:147 525:5 539:5 540:155 541:253 542:253 543:168 548:102 549:170 550:253 551:253 552:139 567:3 568:128 569:253 570:253 571:228 572:179 573:179 574:179 575:179 576:245 577:253 578:253 579:219 580:41 596:76 597:253 598:253 599:253 600:253 601:253 602:253 603:253 604:253 605:253 606:253 607:163 624:39 625:199 626:253 627:253 628:253 629:253 630:253 631:253 632:253 633:253 634:170 635:9 653:36 654:219 655:253 656:253 657:253 658:253 659:253 660:224 661:65 662:22 +1 156:202 157:253 158:69 184:253 185:252 186:121 212:253 213:252 214:69 240:253 241:252 242:69 267:106 268:253 269:231 270:37 295:179 296:255 297:196 322:17 323:234 324:253 325:92 350:93 351:252 352:253 353:92 378:93 379:252 380:253 381:92 406:93 407:252 408:232 409:8 434:208 435:253 436:116 462:207 463:252 464:116 490:207 491:252 492:32 517:57 518:244 519:252 545:122 546:252 547:252 573:185 574:253 575:253 601:184 602:252 603:252 629:101 630:252 631:252 657:13 658:173 659:252 660:43 686:9 687:232 688:116 +1 156:73 157:253 158:253 159:253 160:124 184:73 185:251 186:251 187:251 188:251 212:99 213:251 214:251 215:251 216:225 240:253 241:251 242:251 243:251 244:71 266:79 267:180 268:253 269:251 270:251 271:173 272:20 294:110 295:253 296:255 297:253 298:216 322:109 323:251 324:253 325:251 326:215 350:109 351:251 352:253 353:251 354:215 378:109 379:251 380:253 381:251 382:137 406:109 407:251 408:253 409:251 410:35 433:37 434:253 435:253 436:255 437:253 438:35 461:140 462:251 463:251 464:253 465:168 466:15 488:125 489:246 490:251 491:251 492:190 493:15 516:144 517:251 518:251 519:251 520:180 543:53 544:221 545:251 546:251 547:251 548:51 571:125 572:253 573:253 574:253 575:201 598:105 599:253 600:251 601:251 602:188 603:30 626:180 627:253 628:251 629:251 630:142 654:180 655:253 656:251 657:235 658:82 682:180 683:253 684:251 685:215 +1 124:111 125:255 126:48 152:162 153:253 154:237 155:63 180:206 181:253 182:253 183:183 208:87 209:217 210:253 211:205 237:90 238:253 239:238 240:60 265:37 266:225 267:253 268:89 294:206 295:253 296:159 322:206 323:253 324:226 350:206 351:253 352:226 378:206 379:253 380:226 406:206 407:253 408:226 434:206 435:253 436:226 462:206 463:253 464:226 490:206 491:253 492:226 518:206 519:253 520:237 521:45 546:206 547:253 548:253 549:109 574:173 575:253 576:253 577:109 602:69 603:253 604:253 605:109 630:64 631:248 632:253 633:109 659:112 660:253 661:109 +0 99:70 100:255 101:165 102:114 127:122 128:253 129:253 130:253 131:120 155:165 156:253 157:253 158:253 159:234 160:52 183:99 184:253 185:253 186:253 187:253 188:228 189:26 209:60 210:168 211:238 212:202 213:174 214:253 215:253 216:253 217:127 235:91 236:81 237:1 238:215 239:128 240:28 241:12 242:181 243:253 244:253 245:175 246:3 262:18 263:204 264:253 265:77 270:7 271:253 272:253 273:253 274:54 289:54 290:248 291:253 292:253 293:143 298:1 299:127 300:253 301:253 302:188 317:104 318:253 319:253 320:253 321:20 327:81 328:249 329:253 330:191 345:192 346:253 347:253 348:218 349:5 356:203 357:253 358:208 359:21 372:56 373:237 374:253 375:250 376:100 384:104 385:253 386:253 387:75 400:76 401:253 402:253 403:224 412:119 413:253 414:253 415:75 428:80 429:253 430:253 431:103 439:4 440:241 441:253 442:218 443:32 456:213 457:253 458:253 459:103 467:125 468:253 469:253 470:191 484:213 485:253 486:253 487:103 494:3 495:176 496:253 497:253 498:135 512:213 513:253 514:253 515:103 521:9 522:162 523:253 524:253 525:226 526:37 540:179 541:253 542:253 543:135 548:46 549:157 550:253 551:253 552:253 553:63 568:23 569:188 570:253 571:249 572:179 573:179 574:179 575:179 576:233 577:253 578:253 579:233 580:156 581:10 597:51 598:235 599:253 600:253 601:253 602:253 603:253 604:253 605:251 606:232 607:120 626:16 627:124 628:253 629:253 630:253 631:253 632:152 633:104 +1 124:29 125:197 126:255 127:84 152:85 153:251 154:253 155:83 180:86 181:253 182:254 183:253 208:85 209:251 210:253 211:251 236:86 237:253 238:254 239:253 240:169 264:85 265:251 266:253 267:251 268:168 292:86 293:253 294:254 295:253 296:169 320:28 321:196 322:253 323:251 324:168 349:169 350:254 351:253 352:169 377:168 378:253 379:251 380:168 405:169 406:254 407:253 408:169 433:168 434:253 435:251 436:168 462:254 463:253 464:254 465:139 490:253 491:251 492:253 493:251 518:254 519:253 520:254 521:253 522:57 546:253 547:251 548:253 549:251 550:168 574:198 575:253 576:254 577:253 578:114 602:85 603:251 604:253 605:251 630:85 631:253 632:254 633:253 658:28 659:83 660:196 661:83 +1 159:31 160:210 161:253 162:163 187:198 188:252 189:252 190:162 213:10 214:86 215:242 216:252 217:252 218:66 241:164 242:252 243:252 244:252 245:188 246:8 268:53 269:242 270:252 271:252 272:225 273:14 296:78 297:252 298:252 299:252 300:204 323:56 324:231 325:252 326:252 327:212 328:35 351:157 352:252 353:252 354:252 355:37 377:8 378:132 379:253 380:252 381:252 382:230 383:24 405:45 406:252 407:253 408:252 409:154 410:55 427:7 428:55 433:107 434:253 435:255 436:228 437:53 454:15 455:24 456:23 460:110 461:242 462:252 463:228 464:59 482:57 483:83 487:88 488:247 489:252 490:252 491:140 514:15 515:189 516:252 517:252 518:252 542:74 543:252 544:252 545:238 546:90 570:178 571:252 572:252 573:189 597:40 598:217 599:252 600:252 601:59 625:75 626:252 627:252 628:252 629:85 630:61 653:62 654:239 655:252 656:156 657:14 682:178 683:252 684:14 +1 131:159 132:255 133:122 158:167 159:228 160:253 161:121 185:64 186:236 187:251 188:205 189:110 212:48 213:158 214:251 215:251 216:178 217:39 240:190 241:251 242:251 243:251 267:96 268:253 269:253 270:253 271:153 295:194 296:251 297:251 298:211 299:74 322:80 323:174 324:251 325:251 326:140 327:47 349:16 350:181 351:253 352:251 353:219 354:23 377:64 378:251 379:253 380:251 381:204 382:19 405:223 406:253 407:255 408:233 409:48 431:20 432:174 433:244 434:251 435:253 436:109 437:31 459:96 460:189 461:251 462:251 463:126 464:31 486:24 487:106 488:251 489:235 490:188 491:100 514:96 515:251 516:251 517:228 518:59 542:255 543:253 544:253 545:213 546:36 569:100 570:253 571:251 572:251 573:85 574:23 596:32 597:127 598:253 599:235 600:126 601:15 624:104 625:251 626:253 627:240 628:79 652:83 653:193 654:253 655:220 +0 153:92 154:191 155:178 156:253 157:242 158:141 159:104 160:29 180:26 181:253 182:252 183:252 184:252 185:253 186:252 187:252 188:252 189:108 190:19 206:57 207:123 208:222 209:253 210:252 211:252 212:252 213:168 214:224 215:252 216:252 217:253 218:84 233:176 234:243 235:252 236:252 237:253 238:252 239:252 240:252 242:19 243:153 244:252 245:253 246:209 247:25 259:10 260:128 261:255 262:253 263:244 264:225 265:114 266:194 267:253 268:178 272:163 273:254 274:253 275:168 287:85 288:252 289:253 290:189 291:56 294:19 295:133 296:9 300:38 301:253 302:252 303:168 314:19 315:191 316:252 317:194 318:19 329:253 330:252 331:234 332:22 342:107 343:252 344:252 345:13 357:253 358:252 359:252 360:128 370:169 371:253 372:241 385:141 386:253 387:253 388:140 397:19 398:225 399:252 400:139 413:66 414:252 415:252 416:139 425:29 426:252 427:252 428:52 441:29 442:252 443:252 444:139 453:29 454:252 455:252 456:28 469:29 470:252 471:252 472:40 481:141 482:253 483:253 484:91 497:154 498:253 499:168 509:66 510:252 511:252 512:165 525:253 526:252 527:168 537:19 538:224 539:252 540:252 552:126 553:253 554:252 555:80 566:169 567:252 568:252 569:214 570:38 579:126 580:249 581:253 582:151 583:6 594:26 595:223 596:253 597:254 598:253 599:128 600:29 604:13 605:41 606:216 607:253 608:253 609:226 610:38 623:122 624:252 625:253 626:252 627:252 628:252 629:169 630:169 631:169 632:206 633:253 634:252 635:252 636:202 637:38 651:19 652:56 653:168 654:224 655:252 656:252 657:253 658:252 659:252 660:252 661:253 662:233 663:130 664:6 682:94 683:139 684:190 685:153 686:252 687:164 688:139 689:28 690:22 +1 128:53 129:250 130:255 131:25 156:167 157:253 158:253 159:25 182:3 183:123 184:247 185:253 186:253 187:25 210:9 211:253 212:253 213:253 214:253 215:25 238:9 239:253 240:253 241:253 242:253 243:25 266:9 267:253 268:253 269:253 270:180 271:13 294:9 295:253 296:253 297:253 298:104 322:9 323:253 324:253 325:253 326:104 350:15 351:253 352:253 353:253 354:104 378:184 379:253 380:253 381:228 382:68 406:184 407:253 408:253 409:182 433:103 434:251 435:253 436:253 437:12 461:106 462:253 463:253 464:253 465:8 488:24 489:238 490:253 491:253 492:253 493:8 516:27 517:253 518:253 519:253 520:253 521:8 544:27 545:253 546:253 547:253 548:253 549:8 572:27 573:253 574:253 575:253 576:177 577:4 600:160 601:253 602:253 603:253 604:87 628:202 629:253 630:253 631:219 632:54 656:81 657:253 658:247 659:51 +0 122:63 123:176 124:253 125:253 126:159 127:113 128:63 150:140 151:253 152:252 153:252 154:252 155:252 156:241 157:100 158:66 177:54 178:227 179:253 180:252 181:252 182:252 183:252 184:253 185:252 186:239 187:181 188:57 204:38 205:224 206:252 207:253 208:226 209:246 210:252 211:252 212:253 213:252 214:252 215:252 216:252 217:108 218:3 232:57 233:252 234:252 235:253 236:27 237:88 238:112 239:112 240:112 241:112 242:142 243:252 244:252 245:253 246:152 247:31 260:198 261:253 262:253 263:79 270:32 271:153 272:253 273:255 274:253 275:196 287:76 288:246 289:252 290:127 299:3 300:106 301:253 302:252 303:214 304:28 315:194 316:252 317:252 318:112 329:143 330:252 331:252 332:193 343:225 344:252 345:217 346:37 357:38 358:234 359:252 360:223 370:63 371:240 372:252 373:84 386:146 387:252 388:223 398:114 399:253 400:228 401:47 414:147 415:253 416:253 417:112 426:159 427:252 428:195 442:225 443:252 444:252 445:112 454:253 455:252 456:195 470:225 471:252 472:230 473:25 482:159 483:252 484:202 485:10 497:92 498:243 499:252 500:208 510:113 511:252 512:252 513:161 524:79 525:253 526:252 527:220 528:37 538:114 539:253 540:253 541:253 542:174 543:63 550:26 551:128 552:253 553:255 554:253 555:133 566:12 567:228 568:252 569:252 570:252 571:241 572:100 573:85 574:76 576:85 577:131 578:231 579:252 580:252 581:253 582:129 583:6 595:97 596:208 597:252 598:252 599:253 600:252 601:252 602:246 603:197 604:253 605:252 606:252 607:252 608:220 609:133 610:6 624:19 625:99 626:239 627:253 628:252 629:252 630:252 631:252 632:253 633:252 634:245 635:223 636:99 654:63 655:112 656:112 657:221 658:252 659:252 660:253 661:127 662:87 +0 153:12 154:136 155:254 156:255 157:195 158:115 159:3 180:6 181:175 182:253 183:196 184:160 185:252 186:253 187:15 208:130 209:253 210:234 211:4 213:27 214:205 215:232 216:40 235:54 236:246 237:253 238:68 242:24 243:243 244:106 262:3 263:134 264:235 265:99 266:4 271:132 272:247 273:77 290:56 291:253 292:62 299:23 300:233 301:129 318:179 319:183 320:4 328:182 329:220 345:21 346:232 347:59 356:95 357:232 358:21 373:128 374:183 385:228 386:85 401:187 402:124 413:228 414:186 429:187 430:124 441:228 442:104 457:187 458:124 469:169 470:184 485:187 486:124 497:203 498:150 513:187 514:124 524:10 525:220 526:39 541:187 542:155 552:111 553:201 569:129 570:228 571:7 579:12 580:181 581:76 598:234 599:166 600:9 606:24 607:209 608:106 626:139 627:250 628:167 629:11 630:2 631:11 632:11 633:129 634:227 635:90 636:11 655:95 656:247 657:253 658:178 659:253 660:253 661:244 662:86 684:47 685:175 686:253 687:232 688:149 689:40 +1 128:255 129:253 130:57 156:253 157:251 158:225 159:56 183:169 184:254 185:253 186:254 187:84 211:168 212:253 213:251 214:253 215:83 238:85 239:253 240:254 241:253 242:169 266:85 267:251 268:253 269:251 270:56 294:141 295:253 296:254 297:253 322:253 323:251 324:253 325:251 350:254 351:253 352:254 353:253 378:253 379:251 380:253 381:251 406:254 407:253 408:254 409:196 433:114 434:253 435:251 436:253 437:83 461:169 462:254 463:253 464:226 465:56 489:168 490:253 491:251 492:168 516:85 517:253 518:254 519:253 544:85 545:251 546:253 547:251 572:254 573:253 574:254 575:253 600:253 601:251 602:253 603:251 628:254 629:253 630:254 631:253 656:139 657:251 658:253 659:138 +0 151:23 152:167 153:208 154:254 155:255 156:129 157:19 179:151 180:253 181:253 182:253 183:253 184:253 185:209 186:26 207:181 208:253 209:253 210:253 211:227 212:181 213:253 214:207 215:22 235:227 236:253 237:253 238:253 239:92 240:38 241:226 242:253 243:129 244:2 263:193 264:253 265:253 266:248 267:62 269:50 270:253 271:253 272:45 291:170 292:253 293:253 294:135 297:12 298:208 299:253 300:119 318:16 319:232 320:253 321:253 322:21 326:60 327:253 328:185 346:164 347:253 348:253 349:224 350:14 354:14 355:217 356:247 357:62 373:3 374:193 375:253 376:250 377:64 383:199 384:253 385:179 401:67 402:253 403:253 404:205 411:98 412:253 413:188 429:151 430:253 431:245 432:43 439:63 440:250 441:188 457:151 458:253 459:243 468:244 469:222 470:22 485:151 486:253 487:217 496:244 497:253 498:115 512:3 513:195 514:253 515:134 524:156 525:253 526:150 541:140 542:253 543:134 552:239 553:253 554:139 569:44 570:253 571:134 579:53 580:246 581:237 582:32 597:8 598:200 599:229 600:40 606:25 607:225 608:253 609:188 626:120 627:250 628:230 629:58 630:17 632:12 633:42 634:213 635:253 636:238 637:84 655:151 656:253 657:253 658:217 659:179 660:206 661:253 662:253 663:196 664:118 683:18 684:58 685:145 686:152 687:253 688:214 689:145 690:74 691:7 +1 130:24 131:150 132:233 133:38 156:14 157:89 158:253 159:254 160:254 161:71 183:78 184:203 185:254 186:254 187:254 188:232 189:77 190:54 191:8 209:12 210:155 211:240 212:254 213:223 214:76 215:254 216:254 217:254 218:254 219:68 235:3 236:101 237:216 238:254 239:227 240:122 241:26 242:110 243:254 244:254 245:254 246:184 247:100 262:46 263:222 264:254 265:254 266:179 267:48 270:181 271:254 272:254 273:146 274:6 288:2 289:145 290:248 291:254 292:182 293:111 294:4 297:3 298:250 299:254 300:206 301:3 315:6 316:144 317:254 318:254 319:171 325:125 326:254 327:252 328:80 342:6 343:142 344:254 345:179 346:95 347:4 352:61 353:246 354:254 355:150 370:64 371:254 372:177 373:14 380:124 381:254 382:246 383:32 398:108 399:97 400:15 407:24 408:226 409:254 410:116 435:177 436:255 437:254 438:5 463:196 464:254 465:99 466:1 490:3 491:199 492:254 493:79 518:129 519:254 520:254 521:23 546:178 547:254 548:192 549:8 550:3 551:43 573:11 574:198 575:254 576:128 577:66 578:130 579:225 595:137 596:202 597:106 598:84 599:84 600:84 601:112 602:254 603:254 604:254 605:254 606:212 607:151 623:172 624:254 625:254 626:254 627:254 628:254 629:254 630:254 631:254 632:254 633:162 634:75 651:12 652:106 653:177 654:254 655:254 656:254 657:235 658:135 659:100 660:17 661:2 +0 125:120 126:253 127:253 128:63 151:38 152:131 153:246 154:252 155:252 156:203 157:15 179:222 180:252 181:252 182:252 183:252 184:166 185:38 205:4 206:107 207:253 208:252 209:252 210:252 211:252 212:253 213:224 214:137 215:26 233:107 234:252 235:253 236:252 237:220 238:128 239:252 240:253 241:252 242:252 243:239 244:140 261:170 262:253 263:255 264:168 267:79 268:192 269:253 270:253 271:253 272:253 273:255 274:90 288:51 289:243 290:252 291:215 292:33 296:12 297:74 298:233 299:252 300:252 301:253 302:195 303:19 316:166 317:252 318:252 319:31 326:43 327:149 328:195 329:253 330:252 331:177 332:19 343:57 344:234 345:252 346:252 357:237 358:252 359:252 360:180 361:13 371:85 372:252 373:252 374:173 385:50 386:237 387:252 388:252 389:112 399:226 400:253 401:240 402:63 414:163 415:253 416:253 417:112 426:38 427:234 428:252 429:176 442:85 443:252 444:252 445:158 454:113 455:252 456:252 457:84 470:19 471:209 472:252 473:252 482:207 483:252 484:252 485:84 498:10 499:203 500:252 501:236 510:253 511:252 512:252 513:84 526:85 527:252 528:252 529:112 538:114 539:253 540:253 541:146 553:51 554:159 555:253 556:240 557:63 566:75 567:243 568:252 569:249 570:146 579:57 580:85 581:238 582:252 583:252 584:99 595:116 596:252 597:252 598:252 599:198 600:197 601:165 602:57 603:57 604:57 605:182 606:197 607:234 608:252 609:253 610:233 611:164 612:19 623:28 624:84 625:180 626:252 627:253 628:252 629:252 630:252 631:252 632:253 633:252 634:252 635:252 636:252 637:225 638:71 653:13 654:112 655:253 656:252 657:252 658:252 659:252 660:253 661:252 662:252 663:157 664:112 +1 127:155 128:253 129:126 155:253 156:251 157:141 158:4 183:253 184:251 185:251 186:31 211:253 212:251 213:251 214:31 239:253 240:251 241:251 242:31 267:255 268:253 269:253 270:31 293:8 294:131 295:253 296:251 297:235 298:27 321:64 322:251 323:253 324:251 325:126 349:64 350:251 351:253 352:251 353:126 377:64 378:251 379:253 380:251 381:126 405:64 406:253 407:255 408:221 433:182 434:251 435:253 436:200 460:64 461:236 462:251 463:253 464:62 487:8 488:158 489:251 490:251 491:169 492:8 515:32 516:251 517:251 518:251 519:158 543:32 544:253 545:253 546:253 547:159 571:32 572:251 573:251 574:251 575:39 599:32 600:251 601:251 602:251 627:32 628:251 629:251 630:251 631:100 655:32 656:251 657:251 658:251 +0 101:88 102:127 103:5 126:19 127:58 128:20 129:14 130:217 131:19 152:7 153:146 154:247 155:253 156:235 157:27 158:84 159:81 180:126 181:253 182:164 183:19 184:15 187:156 188:9 208:214 209:222 210:34 215:234 216:58 235:59 236:254 237:116 243:235 244:58 263:141 264:251 265:72 271:151 272:140 291:224 292:233 299:136 300:223 319:254 320:218 327:136 328:253 347:254 348:135 355:136 356:253 374:23 375:255 376:114 383:137 384:231 402:98 403:254 404:122 411:136 412:155 430:98 431:254 432:106 439:166 440:155 458:98 459:254 460:128 467:234 468:193 486:98 487:254 488:135 494:61 495:248 496:118 515:255 516:238 517:18 521:13 522:224 523:254 524:58 543:201 544:253 545:128 546:2 548:5 549:150 550:253 551:167 552:9 571:18 572:226 573:253 574:49 575:31 576:156 577:253 578:228 579:13 600:147 601:253 602:243 603:241 604:254 605:227 606:43 628:5 629:126 630:245 631:253 632:231 633:46 +0 127:37 128:141 129:156 130:156 131:194 132:194 133:47 153:11 154:132 155:239 156:253 157:253 158:253 159:253 160:254 161:181 180:25 181:172 182:253 183:235 184:167 185:78 186:93 187:174 188:254 189:247 190:54 207:26 208:210 209:253 210:237 211:90 216:201 217:253 218:78 235:192 236:253 237:237 238:58 244:156 245:253 246:78 262:141 263:254 264:235 265:53 269:19 270:5 272:156 273:254 274:78 289:46 290:254 291:253 292:92 296:17 297:226 298:217 299:49 300:148 301:253 302:78 317:165 318:254 319:239 320:24 324:20 325:253 326:253 327:58 328:18 329:115 330:24 344:37 345:248 346:254 347:91 352:2 353:117 354:250 355:163 356:91 372:77 373:253 374:254 375:39 382:196 383:253 384:173 400:159 401:254 402:218 403:15 410:77 411:254 412:255 413:61 428:234 429:253 430:113 438:21 439:226 440:254 441:135 455:25 456:240 457:253 458:68 467:195 468:254 469:135 483:79 484:253 485:253 495:195 496:254 497:135 511:79 512:253 513:253 514:76 523:195 524:254 525:99 540:212 541:254 542:209 543:9 550:10 551:209 552:196 553:15 568:54 569:253 570:254 571:137 572:36 576:2 577:20 578:168 579:253 580:60 596:28 597:235 598:254 599:253 600:199 601:124 602:79 603:79 604:167 605:253 606:253 607:185 608:30 625:15 626:117 627:217 628:253 629:253 630:253 631:254 632:253 633:240 634:109 635:12 655:27 656:126 657:208 658:253 659:193 660:147 661:40 +0 154:32 155:134 156:218 157:254 158:254 159:254 160:217 161:84 176:44 177:208 178:215 179:156 180:35 181:119 182:236 183:246 184:136 185:91 186:69 187:151 188:249 189:246 190:78 203:44 204:230 205:254 206:254 207:254 208:254 209:254 210:196 211:48 216:60 217:224 218:210 219:24 231:118 232:254 233:202 234:19 235:201 236:254 237:181 238:9 245:35 246:233 247:168 259:193 260:223 261:34 263:59 264:163 265:236 266:15 274:140 275:205 276:8 286:60 287:254 288:176 293:38 302:54 303:237 304:80 314:59 315:254 316:93 331:131 332:200 342:59 343:240 344:24 359:79 360:214 370:59 371:234 387:67 388:248 389:54 398:59 399:234 416:235 417:58 426:60 427:235 443:79 444:255 445:59 454:59 455:251 456:66 471:79 472:250 473:54 482:59 483:254 484:108 499:146 500:214 510:5 511:203 512:187 513:3 526:4 527:188 528:199 539:118 540:254 541:57 554:96 555:254 556:117 567:16 568:237 569:224 570:14 581:14 582:187 583:206 584:8 596:88 597:252 598:186 599:16 608:16 609:187 610:252 611:125 625:100 626:254 627:237 628:94 629:24 635:13 636:214 637:254 638:166 653:3 654:57 655:215 656:248 657:241 658:235 659:197 660:137 661:137 662:137 663:231 664:238 665:155 666:25 684:57 685:155 686:246 687:254 688:254 689:254 690:254 691:147 692:36 +1 124:102 125:252 126:252 127:41 152:102 153:250 154:250 155:202 180:102 181:250 182:250 183:232 184:91 208:102 209:250 210:250 211:212 212:29 236:102 237:252 238:252 239:254 240:150 264:102 265:250 266:250 267:252 268:149 292:102 293:250 294:250 295:252 296:149 320:102 321:250 322:250 323:252 324:231 325:80 349:152 350:252 351:254 352:252 353:100 377:151 378:250 379:252 380:250 381:100 405:151 406:250 407:252 408:250 409:100 433:151 434:250 435:252 436:250 437:100 461:123 462:243 463:254 464:252 465:100 490:202 491:252 492:250 493:100 518:80 519:252 520:250 521:190 522:30 547:252 548:250 549:250 550:49 575:255 576:252 577:252 578:252 579:214 580:31 603:171 604:250 605:250 606:250 607:252 608:190 609:40 631:20 632:160 633:250 634:250 635:252 636:250 637:100 660:20 661:170 662:250 663:212 664:49 665:20 +0 124:20 125:121 126:197 127:253 128:64 151:23 152:200 153:252 154:252 155:252 156:184 157:6 178:25 179:197 180:252 181:252 182:252 183:252 184:253 185:228 186:107 187:15 205:26 206:196 207:252 208:252 209:252 210:252 211:252 212:253 213:252 214:252 215:219 216:178 217:21 233:186 234:252 235:238 236:94 237:67 238:224 239:217 240:53 241:109 242:245 243:252 244:252 245:213 246:63 260:98 261:242 262:252 263:101 266:39 267:31 270:109 271:128 272:241 273:252 274:207 275:97 287:17 288:230 289:252 290:241 291:56 300:109 301:252 302:252 303:229 304:17 314:13 315:192 316:252 317:243 318:96 328:25 329:127 330:252 331:252 332:120 342:121 343:252 344:252 345:165 357:125 358:252 359:252 360:246 361:70 370:190 371:252 372:252 373:39 385:26 386:210 387:252 388:252 389:119 398:255 399:253 400:159 414:22 415:209 416:253 417:183 426:253 427:252 428:103 443:34 444:252 445:252 454:253 455:252 456:26 471:27 472:252 473:252 482:253 483:252 484:168 485:13 499:70 500:252 501:209 510:147 511:252 512:252 513:75 526:68 527:233 528:252 529:119 538:121 539:252 540:252 541:189 542:40 552:15 553:82 554:231 555:252 556:214 557:31 566:38 567:135 568:248 569:252 570:231 571:145 572:41 573:41 574:41 575:41 576:20 577:24 578:37 579:83 580:194 581:252 582:252 583:212 584:33 596:83 597:213 598:252 599:252 600:252 601:252 602:252 603:252 604:204 605:213 606:243 607:252 608:252 609:252 610:212 611:34 625:34 626:140 627:238 628:248 629:252 630:252 631:252 632:253 633:252 634:252 635:241 636:238 637:238 638:75 656:82 657:119 658:119 659:119 660:120 661:119 662:119 663:19 +1 127:20 128:254 129:255 130:37 155:19 156:253 157:253 158:134 183:19 184:253 185:253 186:246 187:125 211:76 212:253 213:253 214:253 215:158 239:207 240:253 241:253 242:253 243:158 267:207 268:253 269:253 270:253 271:158 294:48 295:223 296:253 297:253 298:243 299:106 322:141 323:253 324:253 325:253 326:113 349:65 350:237 351:253 352:253 353:253 354:36 377:76 378:253 379:253 380:253 381:253 382:36 405:76 406:253 407:253 408:253 409:253 410:36 433:76 434:253 435:253 436:253 437:118 438:4 460:4 461:148 462:253 463:253 464:253 465:103 488:10 489:253 490:253 491:253 492:253 493:103 516:10 517:253 518:253 519:253 520:173 521:7 544:10 545:253 546:253 547:253 548:168 572:143 573:253 574:253 575:239 576:49 600:198 601:253 602:253 603:234 615:140 628:198 629:253 630:253 631:234 656:198 657:253 658:253 659:234 +0 235:40 236:37 238:7 239:77 240:137 241:136 242:136 243:136 244:136 245:40 246:6 261:16 262:135 263:254 264:233 266:152 267:215 268:96 269:140 270:155 271:118 272:230 273:254 274:158 275:68 288:19 289:164 290:254 291:114 294:235 295:140 301:99 302:230 303:254 304:186 305:14 315:70 316:226 317:242 318:121 322:104 323:195 324:38 330:33 331:179 332:253 333:140 342:41 343:241 344:198 345:43 359:24 360:209 361:223 370:164 371:250 372:66 388:136 389:253 398:254 399:158 416:136 417:215 426:255 427:76 442:5 443:127 444:246 445:133 454:254 455:122 469:5 470:150 471:247 472:91 473:9 482:254 483:165 495:13 496:79 497:194 498:216 499:84 510:111 511:251 512:87 519:16 520:25 521:40 522:107 523:186 524:213 525:117 526:25 538:14 539:185 540:235 541:142 542:23 546:91 547:157 548:231 549:207 550:126 551:49 569:143 570:195 571:255 572:254 573:254 574:244 575:157 576:76 599:39 600:39 601:39 602:33 +1 128:166 129:255 130:187 131:6 156:165 157:253 158:253 159:13 183:15 184:191 185:253 186:253 187:13 211:49 212:253 213:253 214:253 215:13 239:141 240:253 241:253 242:169 243:4 266:4 267:189 268:253 269:249 270:53 294:69 295:253 296:253 297:246 322:69 323:253 324:253 325:246 350:118 351:253 352:253 353:124 378:206 379:253 380:231 381:21 405:66 406:241 407:253 408:199 433:105 434:253 435:253 436:89 460:3 461:228 462:253 463:252 464:86 488:111 489:253 490:253 491:205 516:166 517:253 518:253 519:75 543:43 544:249 545:253 546:193 547:9 570:4 571:160 572:253 573:253 574:184 598:37 599:253 600:253 601:253 602:88 626:140 627:253 628:253 629:186 630:18 654:14 655:253 656:253 657:27 +1 128:117 129:128 155:2 156:199 157:127 183:81 184:254 185:87 211:116 212:254 213:48 239:175 240:234 241:18 266:5 267:230 268:168 294:80 295:255 296:142 322:80 323:255 324:142 350:80 351:251 352:57 378:129 379:239 406:164 407:209 433:28 434:245 435:159 461:64 462:254 463:144 489:84 490:254 491:80 517:143 518:254 519:30 544:3 545:225 546:200 572:48 573:254 574:174 600:48 601:254 602:174 628:93 629:254 630:129 656:53 657:234 658:41 +1 129:159 130:142 156:11 157:220 158:141 184:78 185:254 186:141 212:111 213:254 214:109 240:196 241:221 242:15 267:26 268:221 269:159 295:63 296:254 297:159 323:178 324:254 325:93 350:7 351:191 352:254 353:97 378:42 379:255 380:254 381:41 406:42 407:254 408:195 409:10 434:141 435:255 436:78 461:11 462:202 463:254 464:59 489:86 490:254 491:254 492:59 517:142 518:254 519:248 520:52 545:142 546:254 547:195 573:142 574:254 575:164 601:142 602:254 603:77 629:142 630:254 631:131 657:77 658:172 659:5 +0 124:66 125:254 126:254 127:58 128:60 129:59 130:59 131:50 151:73 152:233 153:253 154:253 155:148 156:254 157:253 158:253 159:232 160:73 179:156 180:253 181:253 182:253 183:117 184:255 185:253 186:253 187:253 188:223 189:176 190:162 205:37 206:116 207:246 208:253 209:180 210:18 211:4 212:18 213:109 214:241 215:253 216:253 217:253 218:236 219:28 233:235 234:253 235:253 236:245 237:107 242:109 243:170 244:253 245:253 246:253 247:174 261:235 262:253 263:253 264:233 271:15 272:156 273:253 274:253 275:223 276:72 287:10 288:156 289:250 290:253 291:253 292:67 300:99 301:253 302:253 303:253 304:127 305:5 315:118 316:253 317:253 318:253 319:204 320:26 328:68 329:223 330:253 331:253 332:253 333:57 342:32 343:191 344:253 345:253 346:253 347:97 357:156 358:253 359:253 360:253 361:57 370:59 371:253 372:253 373:253 374:253 375:97 385:36 386:224 387:253 388:253 389:57 398:60 399:254 400:255 401:254 402:156 413:37 414:226 415:254 416:254 417:58 426:59 427:253 428:253 429:253 430:154 441:156 442:253 443:253 444:253 445:57 454:59 455:253 456:253 457:253 458:154 469:156 470:253 471:253 472:253 473:57 482:59 483:253 484:253 485:253 486:246 487:90 496:16 497:171 498:253 499:253 500:231 501:49 510:59 511:253 512:253 513:253 514:253 515:156 516:91 524:99 525:253 526:253 527:222 528:71 538:59 539:253 540:253 541:253 542:253 543:253 544:245 545:109 551:145 552:194 553:253 554:253 555:174 566:9 567:38 568:174 569:251 570:253 571:253 572:253 573:241 574:215 575:215 576:217 577:215 578:215 579:250 580:253 581:253 582:221 583:26 597:235 598:253 599:253 600:253 601:253 602:253 603:253 604:254 605:253 606:253 607:253 608:253 609:204 610:26 625:108 626:116 627:200 628:253 629:253 630:253 631:253 632:254 633:253 634:253 635:253 636:199 637:44 655:36 656:57 657:118 658:253 659:253 660:58 661:57 662:57 663:57 664:35 +1 129:101 130:222 131:84 157:225 158:252 159:84 184:89 185:246 186:208 187:19 212:128 213:252 214:195 239:79 240:253 241:252 242:195 267:141 268:255 269:253 270:133 294:26 295:240 296:253 297:252 298:55 322:60 323:252 324:253 325:154 326:12 349:7 350:178 351:252 352:253 353:27 377:57 378:252 379:252 380:253 381:27 405:57 406:253 407:253 408:204 409:15 433:104 434:252 435:252 436:94 460:19 461:209 462:252 463:252 488:101 489:252 490:252 491:157 516:225 517:252 518:252 519:112 544:226 545:253 546:240 547:63 572:225 573:252 574:223 600:225 601:252 602:223 628:225 629:252 630:242 631:75 656:146 657:252 658:236 659:50 +0 124:41 125:254 126:254 127:157 128:34 129:34 130:218 131:255 132:206 133:34 134:18 151:53 152:238 153:252 154:252 155:252 156:252 157:252 158:252 159:252 160:252 161:252 162:162 163:26 178:66 179:220 180:252 181:252 182:252 183:209 184:153 185:223 186:252 187:252 188:252 189:252 190:252 191:98 206:166 207:252 208:252 209:252 210:252 211:141 213:85 214:230 215:252 216:252 217:252 218:252 219:98 234:166 235:252 236:252 237:252 238:252 239:141 242:73 243:102 244:252 245:252 246:252 247:98 262:166 263:252 264:252 265:252 266:191 267:30 271:5 272:97 273:252 274:252 275:220 276:51 289:123 290:245 291:252 292:252 293:202 294:14 300:56 301:252 302:252 303:252 304:65 316:18 317:154 318:252 319:252 320:241 328:56 329:252 330:252 331:252 332:65 343:21 344:146 345:252 346:252 347:252 348:241 356:56 357:252 358:252 359:252 360:65 371:67 372:252 373:252 374:252 375:252 376:241 384:56 385:252 386:252 387:252 388:65 399:67 400:252 401:252 402:252 403:252 404:116 412:56 413:252 414:252 415:252 416:65 427:67 428:252 429:252 430:252 431:252 432:20 440:56 441:252 442:252 443:252 444:65 455:67 456:252 457:252 458:252 459:87 460:4 468:56 469:252 470:252 471:124 472:11 483:67 484:252 485:252 486:252 487:54 494:19 495:236 496:245 497:252 498:252 499:98 511:67 512:252 513:252 514:252 515:97 516:5 521:39 522:219 523:252 524:252 525:252 526:252 527:98 539:67 540:252 541:252 542:252 543:252 544:102 545:89 546:89 547:89 548:89 549:203 550:252 551:252 552:252 553:252 554:209 555:64 567:67 568:252 569:252 570:252 571:252 572:252 573:252 574:252 575:252 576:252 577:252 578:252 579:252 580:226 581:130 582:68 595:67 596:252 597:252 598:252 599:252 600:252 601:252 602:252 603:252 604:252 605:252 606:252 607:239 608:77 623:17 624:65 625:163 626:252 627:252 628:252 629:252 630:252 631:252 632:252 633:252 634:96 635:59 653:17 654:176 655:252 656:252 657:252 658:252 659:155 660:32 661:32 662:6 +0 96:56 97:247 98:121 124:24 125:242 126:245 127:122 153:231 154:253 155:253 156:104 157:12 181:90 182:253 183:253 184:254 185:221 186:120 187:120 188:85 206:67 207:75 208:36 209:11 210:56 211:222 212:254 213:253 214:253 215:253 216:245 217:207 218:36 233:86 234:245 235:249 236:105 239:44 240:224 241:230 242:253 243:253 244:253 245:253 246:214 247:10 260:8 261:191 262:253 263:143 269:29 270:119 271:119 272:158 273:253 274:253 275:94 288:15 289:253 290:226 291:48 300:4 301:183 302:253 303:248 304:56 316:42 317:253 318:178 329:179 330:253 331:184 332:14 344:164 345:253 346:178 357:179 358:253 359:163 371:61 372:254 373:254 374:179 384:76 385:254 386:254 387:164 399:60 400:253 401:253 402:178 411:29 412:206 413:253 414:253 415:40 427:60 428:253 429:253 430:178 439:120 440:253 441:253 442:245 443:13 455:60 456:253 457:253 458:178 467:120 468:253 469:239 470:63 483:60 484:253 485:253 486:178 494:14 495:238 496:253 497:179 511:18 512:190 513:253 514:231 515:70 521:43 522:184 523:253 524:253 525:74 540:86 541:253 542:253 543:239 544:134 545:8 548:56 549:163 550:253 551:253 552:213 553:35 568:16 569:253 570:253 571:253 572:253 573:240 574:239 575:239 576:247 577:253 578:253 579:210 580:27 596:4 597:59 598:204 599:253 600:253 601:253 602:253 603:253 604:254 605:253 606:250 607:110 626:31 627:122 628:253 629:253 630:253 631:253 632:255 633:217 634:98 +0 125:19 126:164 127:253 128:255 129:253 130:118 131:59 132:36 153:78 154:251 155:251 156:253 157:251 158:251 159:251 160:199 161:45 180:14 181:198 182:251 183:251 184:253 185:251 186:251 187:251 188:251 189:204 190:26 208:5 209:117 210:251 211:251 212:243 213:212 214:239 215:251 216:251 217:251 218:218 236:95 237:251 238:251 239:251 240:120 242:175 243:251 244:251 245:251 246:231 263:97 264:237 265:251 266:251 267:251 270:67 271:240 272:251 273:251 274:243 275:108 290:8 291:163 292:251 293:251 294:240 295:81 299:68 300:251 301:251 302:251 303:179 304:9 317:13 318:145 319:251 320:251 321:226 322:80 327:39 328:251 329:251 330:251 331:251 332:115 345:144 346:251 347:251 348:251 349:173 355:18 356:167 357:251 358:251 359:251 360:115 373:233 374:251 375:251 376:251 377:173 384:98 385:251 386:251 387:251 388:115 400:176 401:253 402:253 403:216 404:179 412:99 413:253 414:253 415:253 416:116 427:55 428:210 429:251 430:251 431:96 440:98 441:251 442:251 443:214 444:62 455:117 456:251 457:251 458:251 459:96 467:28 468:204 469:251 470:237 471:53 482:55 483:241 484:251 485:251 486:160 487:7 494:28 495:222 496:251 497:251 498:231 510:59 511:251 512:251 513:251 514:153 520:23 521:98 522:204 523:251 524:251 525:251 526:156 538:59 539:251 540:251 541:251 542:153 546:85 547:155 548:179 549:251 550:251 551:251 552:251 553:154 554:15 566:59 567:251 568:251 569:251 570:236 571:214 572:214 573:214 574:234 575:251 576:253 577:251 578:251 579:248 580:156 581:15 594:41 595:209 596:251 597:251 598:251 599:251 600:251 601:251 602:251 603:251 604:253 605:251 606:196 607:146 623:54 624:115 625:241 626:251 627:251 628:251 629:251 630:251 631:251 632:253 633:187 634:35 653:83 654:251 655:251 656:251 657:251 658:251 659:101 660:57 661:31 +1 129:232 130:255 131:107 156:58 157:244 158:253 159:106 184:95 185:253 186:253 187:106 212:95 213:253 214:253 215:106 240:95 241:253 242:249 243:69 268:144 269:253 270:192 295:97 296:233 297:253 298:66 323:195 324:253 325:253 326:5 350:38 351:232 352:253 353:182 354:2 377:10 378:160 379:253 380:231 381:53 405:42 406:253 407:253 408:158 433:141 434:253 435:253 436:115 460:75 461:245 462:253 463:183 464:4 487:1 488:147 489:253 490:251 491:58 515:20 516:253 517:253 518:180 543:202 544:253 545:226 546:27 571:243 572:253 573:212 598:85 599:251 600:253 601:173 626:209 627:253 628:244 629:57 654:169 655:253 656:174 +1 127:63 128:128 129:2 155:63 156:254 157:123 183:63 184:254 185:179 211:63 212:254 213:179 239:63 240:254 241:179 267:142 268:254 269:179 295:187 296:254 297:158 323:187 324:254 325:55 350:68 351:235 352:254 353:55 378:181 379:254 380:254 381:55 406:181 407:254 408:202 409:14 434:181 435:254 436:186 462:181 463:254 464:146 490:181 491:254 492:62 518:181 519:254 520:62 546:181 547:254 548:62 574:181 575:255 576:62 602:181 603:254 604:241 605:52 630:181 631:254 632:222 633:30 658:181 659:224 660:34 +1 130:131 131:255 132:184 133:15 157:99 158:247 159:253 160:182 161:15 185:124 186:253 187:253 188:253 189:38 212:9 213:171 214:253 215:253 216:140 217:1 240:47 241:253 242:253 243:251 244:117 267:43 268:219 269:253 270:253 271:153 295:78 296:253 297:253 298:253 299:84 323:97 324:253 325:253 326:244 327:74 350:69 351:243 352:253 353:253 354:183 377:10 378:168 379:253 380:253 381:215 382:34 405:31 406:253 407:253 408:253 409:129 433:107 434:253 435:253 436:242 437:67 460:24 461:204 462:253 463:253 464:187 488:95 489:253 490:253 491:201 492:25 516:239 517:253 518:253 519:176 543:119 544:251 545:253 546:253 547:138 570:30 571:212 572:253 573:252 574:165 575:8 598:193 599:253 600:253 601:222 626:193 627:253 628:253 629:189 654:193 655:253 656:201 657:27 +0 125:57 126:255 127:253 128:198 129:85 153:168 154:253 155:251 156:253 157:251 158:169 159:56 180:86 181:253 182:254 183:253 184:254 185:253 186:254 187:253 188:57 208:197 209:251 210:253 211:251 212:253 213:251 214:253 215:251 216:225 217:56 235:169 236:255 237:253 238:226 239:56 241:114 242:254 243:253 244:254 245:84 262:57 263:224 264:253 265:251 266:56 270:139 271:251 272:253 273:83 290:141 291:253 292:255 293:84 298:57 299:225 300:254 301:196 318:253 319:251 320:253 321:83 327:168 328:253 329:83 345:169 346:254 347:253 348:169 355:169 356:254 357:253 358:169 373:168 374:253 375:251 376:56 383:168 384:253 385:251 386:56 401:169 402:254 403:84 412:254 413:253 429:168 430:253 431:83 440:253 441:251 456:29 457:197 458:254 459:84 467:169 468:254 469:196 484:85 485:251 486:253 487:83 494:57 495:224 496:253 497:83 512:57 513:225 514:254 515:139 521:57 522:141 523:253 524:254 525:84 541:168 542:253 543:251 544:169 545:56 547:114 548:169 549:224 550:253 551:251 552:253 553:83 569:169 570:254 571:253 572:254 573:253 574:254 575:253 576:254 577:253 578:254 579:253 580:226 581:56 597:56 598:253 599:251 600:253 601:251 602:253 603:251 604:253 605:251 606:253 607:251 608:56 626:169 627:225 628:254 629:253 630:254 631:253 632:254 633:253 634:226 635:56 655:56 656:253 657:251 658:253 659:251 660:84 661:83 662:56 +0 127:12 128:105 129:224 130:255 131:247 132:22 155:131 156:254 157:254 158:243 159:252 160:76 182:131 183:225 184:254 185:224 186:48 187:136 208:13 209:109 210:252 211:254 212:254 213:254 214:197 215:76 235:9 236:181 237:254 238:254 239:240 240:229 241:237 242:254 243:252 244:152 245:21 262:9 263:143 264:254 265:254 266:226 267:36 269:22 270:138 271:254 272:254 273:188 289:13 290:181 291:254 292:254 293:250 294:64 298:2 299:53 300:236 301:252 302:131 317:102 318:254 319:254 320:254 321:111 328:56 329:243 330:251 331:42 344:30 345:186 346:254 347:254 348:206 349:29 357:199 358:254 359:91 372:92 373:254 374:254 375:237 376:13 385:134 386:254 387:91 400:133 401:254 402:254 403:126 413:134 414:250 415:17 428:187 429:254 430:237 431:23 441:200 442:183 456:187 457:254 458:213 467:2 468:134 469:252 470:101 484:183 485:254 486:133 495:14 496:254 497:234 498:34 512:92 513:254 514:161 522:84 523:204 524:254 525:56 540:92 541:254 542:229 549:85 550:252 551:252 552:188 553:11 568:56 569:252 570:229 575:3 576:53 577:235 578:253 579:166 597:224 598:245 599:130 600:68 601:68 602:134 603:214 604:254 605:254 606:159 625:141 626:254 627:254 628:254 629:254 630:254 631:254 632:233 633:95 634:3 653:14 654:152 655:254 656:254 657:254 658:186 659:157 660:53 +1 130:226 131:247 132:55 157:99 158:248 159:254 160:230 161:30 185:125 186:254 187:254 188:254 189:38 213:125 214:254 215:254 216:212 217:24 240:18 241:223 242:254 243:252 244:118 268:24 269:254 270:254 271:239 295:27 296:195 297:254 298:254 299:93 323:78 324:254 325:254 326:246 327:74 351:158 352:254 353:254 354:185 378:41 379:239 380:254 381:254 382:43 405:22 406:218 407:254 408:254 409:167 410:9 433:32 434:254 435:254 436:254 437:130 460:24 461:187 462:254 463:254 464:234 465:16 488:189 489:254 490:254 491:254 492:128 515:64 516:247 517:254 518:255 519:219 520:42 543:139 544:254 545:254 546:222 547:40 570:30 571:213 572:254 573:235 574:45 598:194 599:254 600:254 601:223 626:194 627:254 628:254 629:190 654:194 655:254 656:202 657:27 +1 130:166 131:253 132:124 133:53 158:140 159:251 160:251 161:180 185:125 186:246 187:251 188:251 189:51 212:32 213:190 214:251 215:251 216:251 217:103 240:21 241:174 242:251 243:251 244:251 268:73 269:176 270:253 271:253 272:201 296:149 297:251 298:251 299:251 300:71 323:27 324:228 325:251 326:251 327:157 328:10 351:180 352:253 353:251 354:251 355:142 377:27 378:180 379:231 380:253 381:251 382:96 383:41 405:89 406:253 407:253 408:255 409:211 410:25 433:217 434:251 435:251 436:253 437:107 460:21 461:221 462:251 463:251 464:242 465:92 487:32 488:190 489:251 490:251 491:251 492:103 515:202 516:251 517:251 518:251 519:122 542:53 543:255 544:253 545:253 546:221 547:51 570:180 571:253 572:251 573:251 574:142 598:180 599:253 600:251 601:251 602:142 626:180 627:253 628:251 629:157 630:82 654:180 655:253 656:147 657:10 +1 129:17 130:206 131:229 132:44 157:2 158:125 159:254 160:123 185:95 186:254 187:254 188:123 212:78 213:240 214:254 215:254 216:123 240:100 241:254 242:254 243:254 244:123 267:2 268:129 269:254 270:254 271:220 272:20 295:9 296:254 297:254 298:254 299:123 322:22 323:179 324:254 325:254 326:254 327:49 350:83 351:254 352:254 353:254 354:183 355:19 378:136 379:254 380:254 381:254 382:139 404:3 405:111 406:252 407:254 408:254 409:232 410:45 432:67 433:254 434:254 435:254 436:216 437:40 459:14 460:192 461:254 462:254 463:254 464:140 486:23 487:192 488:254 489:254 490:254 491:246 514:77 515:254 516:254 517:255 518:241 519:100 541:65 542:235 543:254 544:254 545:254 546:172 568:30 569:238 570:254 571:254 572:254 573:219 574:26 596:34 597:254 598:254 599:254 600:216 601:41 624:34 625:254 626:254 627:254 628:188 652:12 653:170 654:254 655:254 656:82 +1 130:218 131:253 132:124 157:84 158:236 159:251 160:251 184:63 185:236 186:251 187:251 188:122 212:73 213:251 214:251 215:251 216:173 240:202 241:251 242:251 243:251 244:71 267:53 268:255 269:253 270:253 271:253 272:72 295:180 296:253 297:251 298:251 299:188 300:30 323:180 324:253 325:251 326:251 327:142 350:47 351:211 352:253 353:251 354:235 355:82 377:27 378:211 379:251 380:253 381:251 382:215 405:89 406:253 407:253 408:255 409:253 410:164 433:217 434:251 435:251 436:253 437:168 438:15 460:21 461:221 462:251 463:251 464:253 465:107 487:32 488:190 489:251 490:251 491:251 492:221 493:61 515:73 516:251 517:251 518:251 519:251 520:180 543:255 544:253 545:253 546:253 547:201 570:105 571:253 572:251 573:251 574:251 575:71 598:180 599:253 600:251 601:246 602:137 603:10 626:180 627:253 628:251 629:215 654:180 655:253 656:251 657:86 +1 124:102 125:180 126:1 152:140 153:254 154:130 180:140 181:254 182:204 208:140 209:254 210:204 236:72 237:254 238:204 264:25 265:231 266:250 267:135 292:11 293:211 294:254 295:222 321:101 322:254 323:250 324:15 349:96 350:254 351:254 352:95 377:2 378:251 379:254 380:95 405:2 406:251 407:254 408:95 433:96 434:254 435:254 436:95 461:53 462:253 463:254 464:139 490:250 491:254 492:235 493:27 518:201 519:254 520:254 521:128 546:80 547:254 548:254 549:139 574:65 575:254 576:254 577:139 602:150 603:254 604:254 605:139 630:229 631:254 632:254 633:43 658:52 659:196 660:168 661:9 +0 128:87 129:208 130:249 155:27 156:212 157:254 158:195 182:118 183:225 184:254 185:254 186:232 187:147 188:46 209:115 210:248 211:254 212:254 213:254 214:254 215:254 216:230 217:148 218:12 236:18 237:250 238:254 239:245 240:226 241:254 242:254 243:254 244:254 245:254 246:148 263:92 264:205 265:254 266:250 267:101 268:20 269:194 270:254 271:254 272:254 273:254 274:229 275:53 291:152 292:254 293:254 294:94 297:14 298:124 299:187 300:254 301:254 302:254 303:213 318:95 319:252 320:254 321:206 322:15 327:3 328:6 329:51 330:231 331:254 332:94 345:50 346:246 347:254 348:254 349:20 358:200 359:254 360:96 372:21 373:184 374:254 375:254 376:147 377:2 386:200 387:254 388:96 400:177 401:254 402:254 403:218 404:33 413:16 414:211 415:254 416:96 427:11 428:219 429:254 430:251 431:92 441:84 442:254 443:232 444:44 455:101 456:254 457:254 458:141 469:162 470:254 471:231 472:42 483:235 484:254 485:227 486:42 496:51 497:238 498:254 499:213 511:235 512:254 513:199 524:160 525:254 526:229 527:52 539:235 540:254 541:199 549:10 550:84 551:150 552:253 553:254 554:147 567:235 568:254 569:213 570:20 575:17 576:63 577:158 578:254 579:254 580:254 581:155 582:12 595:122 596:248 597:254 598:204 599:98 600:42 601:177 602:180 603:200 604:254 605:254 606:253 607:213 608:82 609:10 624:203 625:254 626:254 627:254 628:254 629:254 630:254 631:254 632:251 633:219 634:94 652:35 653:221 654:254 655:254 656:254 657:254 658:254 659:217 660:95 +1 126:134 127:230 154:133 155:231 156:10 182:133 183:253 184:96 210:133 211:253 212:96 238:133 239:253 240:183 266:133 267:253 268:217 294:133 295:253 296:217 322:133 323:253 324:217 350:133 351:253 352:217 378:133 379:253 380:217 406:134 407:254 408:218 434:133 435:253 436:159 462:133 463:253 464:199 490:156 491:253 492:96 518:254 519:247 520:73 546:254 547:248 548:74 573:99 574:254 575:245 576:64 600:89 601:230 602:254 603:125 627:140 628:251 629:253 630:243 631:10 655:114 656:242 657:195 658:69 +1 125:29 126:85 127:255 128:139 153:197 154:251 155:253 156:251 181:254 182:253 183:254 184:253 209:253 210:251 211:253 212:251 237:254 238:253 239:254 240:253 265:253 266:251 267:253 268:138 293:254 294:253 295:254 296:196 321:253 322:251 323:253 324:196 349:254 350:253 351:254 352:84 377:253 378:251 379:253 380:196 405:254 406:253 407:254 408:253 433:253 434:251 435:253 436:251 461:254 462:253 463:254 464:253 489:253 490:251 491:253 492:251 517:254 518:253 519:254 520:253 545:253 546:251 547:253 548:251 573:254 574:253 575:254 576:253 601:253 602:251 603:253 604:251 629:57 630:225 631:254 632:253 658:56 659:253 660:251 +1 125:149 126:255 127:254 128:58 153:215 154:253 155:183 156:2 180:41 181:232 182:253 183:181 208:92 209:253 210:253 211:181 236:92 237:253 238:253 239:181 264:92 265:253 266:253 267:181 292:92 293:253 294:253 295:181 320:92 321:253 322:253 323:181 348:92 349:253 350:253 351:181 376:92 377:253 378:253 379:181 404:92 405:253 406:253 407:181 432:92 433:253 434:253 435:181 460:92 461:253 462:253 463:181 488:31 489:228 490:253 491:181 517:198 518:253 519:228 520:54 545:33 546:226 547:253 548:195 549:7 574:199 575:253 576:253 577:75 602:34 603:218 604:253 605:228 606:117 607:14 608:12 631:33 632:219 633:253 634:253 635:253 636:211 660:32 661:123 662:149 663:230 664:41 +1 130:79 131:203 132:141 157:51 158:240 159:240 160:140 185:88 186:252 187:252 188:140 213:197 214:252 215:252 216:140 241:197 242:252 243:252 244:140 268:147 269:253 270:253 271:253 295:38 296:234 297:252 298:242 299:89 323:113 324:252 325:252 326:223 350:16 351:207 352:252 353:252 354:129 377:16 378:203 379:253 380:252 381:220 382:37 405:29 406:253 407:255 408:253 409:56 432:19 433:181 434:252 435:253 436:176 437:6 460:166 461:252 462:252 463:228 464:52 487:10 488:203 489:252 490:252 491:126 514:63 515:178 516:252 517:252 518:173 542:114 543:253 544:253 545:225 570:238 571:252 572:252 573:99 596:7 597:135 598:253 599:252 600:176 601:19 624:29 625:252 626:253 627:252 628:55 652:13 653:189 654:253 655:204 656:25 +1 126:94 127:254 128:75 154:166 155:253 156:231 182:208 183:253 184:147 210:208 211:253 212:116 238:208 239:253 240:168 266:146 267:254 268:222 294:166 295:253 296:116 322:208 323:253 324:116 350:166 351:253 352:158 378:145 379:253 380:231 406:209 407:254 408:169 434:187 435:253 436:168 462:93 463:253 464:116 490:93 491:253 492:116 518:93 519:253 520:116 546:94 547:254 548:179 549:11 574:93 575:253 576:246 577:101 602:145 603:253 604:255 605:92 630:93 631:253 632:246 633:59 658:93 659:253 660:74 +0 127:46 128:105 129:254 130:254 131:224 132:59 133:59 134:9 155:196 156:254 157:253 158:253 159:253 160:253 161:253 162:128 182:96 183:235 184:254 185:253 186:253 187:253 188:253 189:253 190:247 191:122 208:4 209:101 210:244 211:253 212:254 213:234 214:241 215:253 216:253 217:253 218:253 219:186 220:18 236:96 237:253 238:253 239:253 240:232 241:83 242:109 243:170 244:253 245:253 246:253 247:253 248:116 264:215 265:253 266:253 267:253 268:196 271:40 272:253 273:253 274:253 275:253 276:116 290:8 291:141 292:247 293:253 294:253 295:237 296:29 299:6 300:38 301:171 302:253 303:253 304:116 317:13 318:146 319:253 320:253 321:253 322:253 323:57 329:156 330:253 331:253 332:116 345:40 346:253 347:253 348:253 349:253 350:178 351:27 357:156 358:253 359:253 360:116 372:136 373:204 374:253 375:253 376:253 377:192 378:27 385:156 386:253 387:253 388:116 399:28 400:195 401:254 402:254 403:254 404:250 405:135 412:99 413:255 414:254 415:254 416:117 427:118 428:253 429:253 430:253 431:253 432:142 439:19 440:170 441:253 442:253 443:216 444:62 454:42 455:212 456:253 457:253 458:253 459:253 460:38 466:124 467:188 468:253 469:253 470:253 471:174 482:59 483:253 484:253 485:253 486:237 487:93 488:3 491:31 492:40 493:130 494:247 495:253 496:253 497:253 498:204 499:13 510:59 511:253 512:253 513:253 514:154 518:54 519:218 520:254 521:253 522:253 523:253 524:253 525:253 526:38 538:59 539:253 540:253 541:253 542:215 543:156 544:156 545:156 546:209 547:253 548:255 549:253 550:253 551:253 552:192 553:97 554:15 566:55 567:242 568:253 569:253 570:253 571:253 572:253 573:253 574:253 575:253 576:254 577:253 578:253 579:204 580:23 595:118 596:253 597:253 598:253 599:253 600:253 601:253 602:253 603:253 604:254 605:216 606:174 607:13 623:54 624:116 625:243 626:253 627:253 628:253 629:253 630:253 631:146 632:117 633:62 653:53 654:132 655:253 656:253 657:192 658:57 659:13 +1 125:42 126:232 127:254 128:58 153:86 154:253 155:253 156:58 181:86 182:253 183:253 184:58 209:206 210:253 211:253 212:58 237:215 238:253 239:253 240:58 265:215 266:253 267:253 268:58 293:215 294:253 295:253 296:58 321:215 322:253 323:253 324:58 349:215 350:253 351:253 352:58 377:215 378:253 379:253 380:58 405:215 406:253 407:253 408:58 433:188 434:253 435:253 436:85 461:86 462:253 463:253 464:200 465:12 489:29 490:223 491:253 492:253 493:151 518:209 519:253 520:253 521:194 546:128 547:253 548:253 549:200 550:8 574:32 575:213 576:253 577:253 578:152 579:6 603:32 604:221 605:253 606:253 607:153 608:5 632:90 633:215 634:253 635:253 636:151 661:59 662:253 663:253 664:84 +1 156:60 157:229 158:38 184:187 185:254 186:78 211:121 212:252 213:254 214:78 239:197 240:254 241:206 242:6 267:197 268:254 269:202 294:27 295:218 296:233 297:62 322:117 323:254 324:195 350:203 351:254 352:195 377:64 378:244 379:254 380:195 405:79 406:254 407:255 408:161 433:79 434:254 435:254 436:65 461:79 462:254 463:241 464:52 489:79 490:254 491:189 517:79 518:254 519:189 545:79 546:254 547:189 573:79 574:254 575:189 601:79 602:254 603:194 604:5 629:35 630:219 631:254 632:72 658:34 659:223 660:195 687:129 688:195 +1 101:11 102:150 103:72 129:37 130:251 131:71 157:63 158:251 159:71 185:217 186:251 187:71 213:217 214:251 215:71 240:145 241:253 242:253 243:72 267:42 268:206 269:251 270:251 271:71 295:99 296:251 297:251 298:251 299:71 323:253 324:251 325:251 326:251 327:71 350:130 351:253 352:251 353:251 354:251 355:71 377:110 378:253 379:255 380:253 381:253 382:253 383:72 405:109 406:251 407:253 408:251 409:251 410:188 411:30 433:109 434:251 435:253 436:251 437:246 438:123 460:16 461:170 462:251 463:253 464:251 465:215 488:37 489:251 490:251 491:253 492:251 493:86 516:218 517:253 518:253 519:255 520:253 521:35 543:84 544:236 545:251 546:251 547:253 548:168 549:15 571:144 572:251 573:251 574:251 575:190 576:15 599:144 600:251 601:251 602:251 603:180 626:53 627:221 628:251 629:251 630:251 631:180 +0 127:45 128:254 129:254 130:254 131:148 132:24 133:9 154:43 155:254 156:252 157:252 158:252 159:252 160:252 161:121 162:13 181:58 182:237 183:254 184:252 185:252 186:252 187:252 188:252 189:252 190:68 208:69 209:224 210:252 211:254 212:252 213:252 214:252 215:252 216:252 217:252 218:135 219:17 235:75 236:216 237:252 238:252 239:254 240:231 241:168 242:252 243:252 244:252 245:252 246:252 247:45 262:77 263:212 264:252 265:252 266:252 267:242 268:93 269:32 270:114 271:177 272:252 273:252 274:252 275:158 276:12 289:75 290:212 291:252 292:252 293:252 294:252 295:231 299:116 300:252 301:252 302:252 303:252 304:21 316:69 317:216 318:252 319:252 320:252 321:252 322:252 323:62 327:116 328:252 329:252 330:252 331:252 332:21 344:93 345:252 346:252 347:252 348:252 349:252 350:62 355:21 356:158 357:252 358:252 359:252 360:21 371:64 372:239 373:252 374:252 375:252 376:252 377:252 378:21 384:139 385:252 386:252 387:252 388:21 398:5 399:87 400:254 401:254 402:254 403:254 404:237 405:41 411:11 412:150 413:254 414:254 415:254 416:22 425:5 426:85 427:252 428:252 429:252 430:252 431:222 432:55 439:116 440:252 441:252 442:252 443:214 444:18 453:24 454:252 455:252 456:252 457:252 458:252 459:91 466:26 467:153 468:252 469:252 470:252 471:45 481:24 482:252 483:252 484:252 485:252 486:252 487:91 492:18 493:93 494:151 495:252 496:252 497:252 498:184 499:28 509:24 510:252 511:252 512:252 513:252 514:252 515:164 516:116 517:116 518:116 519:117 520:141 521:252 522:252 523:252 524:252 525:252 526:68 537:24 538:252 539:252 540:252 541:252 542:252 543:252 544:252 545:252 546:252 547:254 548:252 549:252 550:252 551:252 552:252 553:163 554:31 565:9 566:121 567:252 568:252 569:252 570:252 571:252 572:252 573:252 574:252 575:254 576:252 577:252 578:252 579:178 580:91 581:33 594:13 595:119 596:252 597:252 598:252 599:252 600:252 601:252 602:252 603:254 604:252 605:252 606:184 607:37 623:13 624:121 625:252 626:252 627:252 628:252 629:252 630:252 631:254 632:214 633:45 634:28 652:8 653:21 654:21 655:169 656:252 657:252 658:41 659:22 660:18 +0 125:218 126:253 127:253 128:255 129:149 130:62 151:42 152:144 153:236 154:251 155:251 156:253 157:251 158:236 159:144 160:144 179:99 180:251 181:251 182:251 183:225 184:253 185:251 186:251 187:251 188:251 189:166 190:16 206:79 207:253 208:251 209:251 210:204 211:41 212:143 213:205 214:251 215:251 216:251 217:253 218:169 219:15 233:79 234:231 235:253 236:251 237:225 238:41 241:41 242:226 243:251 244:251 245:253 246:251 247:164 260:37 261:253 262:253 263:255 264:253 265:35 271:79 272:232 273:255 274:253 275:227 276:42 288:140 289:251 290:251 291:253 292:168 293:15 300:77 301:253 302:251 303:251 304:142 315:21 316:221 317:251 318:251 319:164 320:15 329:227 330:251 331:251 332:236 333:61 342:32 343:190 344:251 345:251 346:251 357:73 358:251 359:251 360:251 361:71 370:73 371:251 372:251 373:251 374:251 385:73 386:251 387:251 388:251 389:71 398:73 399:253 400:253 401:253 402:201 413:73 414:253 415:253 416:253 417:72 426:176 427:251 428:251 429:251 430:71 441:73 442:251 443:251 444:251 445:71 454:253 455:251 456:251 457:157 458:10 469:73 470:251 471:251 472:251 473:71 482:253 483:251 484:251 485:142 497:150 498:251 499:251 500:204 501:41 510:124 511:251 512:251 513:220 514:180 524:130 525:253 526:251 527:225 528:41 538:73 539:253 540:253 541:253 542:253 543:73 544:73 545:10 549:42 550:73 551:150 552:253 553:255 554:253 555:216 566:31 567:189 568:251 569:251 570:251 571:253 572:251 573:159 574:144 575:144 576:145 577:206 578:251 579:251 580:251 581:253 582:168 583:92 595:20 596:195 597:251 598:251 599:253 600:251 601:251 602:251 603:251 604:253 605:251 606:251 607:251 608:225 609:164 610:15 624:21 625:142 626:220 627:253 628:251 629:251 630:251 631:251 632:253 633:251 634:251 635:204 636:41 654:51 655:72 656:174 657:251 658:251 659:251 660:253 661:147 662:71 663:41 +0 127:60 128:96 129:96 130:48 153:16 154:171 155:228 156:253 157:251 158:220 159:51 160:32 181:127 182:251 183:251 184:253 185:251 186:251 187:251 188:251 189:80 207:24 208:182 209:236 210:251 211:211 212:189 213:236 214:251 215:251 216:251 217:242 218:193 234:100 235:194 236:251 237:251 238:211 239:35 241:71 242:173 243:251 244:251 245:253 246:240 247:158 248:19 261:64 262:253 263:255 264:253 265:205 266:19 271:40 272:218 273:255 274:253 275:253 276:91 288:16 289:186 290:251 291:253 292:247 293:110 300:39 301:233 302:251 303:251 304:188 315:16 316:189 317:251 318:251 319:205 320:110 329:48 330:220 331:251 332:220 333:48 343:72 344:251 345:251 346:251 347:158 358:51 359:251 360:251 361:232 371:190 372:251 373:251 374:251 375:59 386:32 387:251 388:251 389:251 398:96 399:253 400:253 401:253 402:95 414:32 415:253 416:253 417:193 426:214 427:251 428:251 429:204 430:23 442:52 443:251 444:251 445:94 454:253 455:251 456:251 457:109 469:48 470:221 471:251 472:219 473:47 482:253 483:251 484:251 485:70 497:234 498:251 499:251 500:188 510:253 511:251 512:251 513:188 523:40 524:158 525:253 526:251 527:172 528:70 539:191 540:253 541:253 542:253 543:96 544:24 549:12 550:174 551:253 552:253 553:255 554:221 567:71 568:251 569:251 570:251 571:253 572:205 573:190 574:190 575:190 576:191 577:197 578:251 579:251 580:231 581:221 582:93 595:16 596:126 597:236 598:251 599:253 600:251 601:251 602:251 603:251 604:253 605:251 606:251 607:140 608:47 625:67 626:188 627:189 628:188 629:188 630:188 631:188 632:189 633:188 634:109 635:4 +0 126:32 127:202 128:255 129:253 130:253 131:175 132:21 152:84 153:144 154:190 155:251 156:253 157:251 158:251 159:251 160:174 176:6 177:37 178:166 179:218 180:236 181:251 182:251 183:251 184:253 185:251 186:251 187:251 188:251 189:156 204:115 205:251 206:251 207:253 208:251 209:251 210:251 211:251 212:253 213:251 214:251 215:251 216:251 217:180 231:105 232:241 233:251 234:251 235:253 236:251 237:251 238:251 239:122 240:72 241:71 242:71 243:148 244:251 245:180 258:73 259:253 260:253 261:253 262:253 263:202 264:253 265:253 266:143 286:31 287:189 288:251 289:251 290:251 291:31 292:189 293:251 294:142 314:63 315:236 316:251 317:251 318:96 320:124 321:246 322:142 330:21 331:166 332:21 342:73 343:251 344:251 345:251 346:71 349:217 350:142 357:32 358:190 359:251 360:142 370:73 371:251 372:251 373:251 374:71 377:217 378:142 385:73 386:251 387:251 388:142 398:73 399:253 400:253 401:253 402:72 405:156 406:103 413:73 414:253 415:253 416:253 417:72 426:73 427:251 428:251 429:251 430:174 441:73 442:251 443:251 444:251 445:71 454:73 455:251 456:251 457:251 458:251 469:73 470:251 471:251 472:251 473:71 482:42 483:205 484:251 485:251 486:251 487:79 497:73 498:251 499:251 500:251 501:71 511:41 512:226 513:251 514:251 515:232 516:77 525:73 526:251 527:251 528:251 529:71 540:166 541:253 542:253 543:255 544:253 545:227 546:73 547:21 553:125 554:253 555:253 556:143 568:16 569:169 570:251 571:253 572:251 573:251 574:251 575:174 576:105 579:63 580:144 581:253 582:251 583:251 584:142 597:15 598:35 599:253 600:251 601:251 602:251 603:251 604:243 605:217 606:217 607:231 608:251 609:253 610:251 611:220 612:20 627:143 628:142 629:236 630:251 631:251 632:253 633:251 634:251 635:251 636:251 637:253 638:251 639:137 657:61 658:71 659:200 660:253 661:251 662:251 663:251 664:251 665:201 666:71 667:10 +1 130:218 131:170 132:108 157:32 158:227 159:252 160:232 185:129 186:252 187:252 188:252 212:1 213:253 214:252 215:252 216:168 240:144 241:253 242:252 243:236 244:62 268:144 269:253 270:252 271:215 296:144 297:253 298:252 299:112 323:21 324:206 325:253 326:252 327:71 351:99 352:253 353:255 354:119 378:63 379:242 380:252 381:253 382:35 406:94 407:252 408:252 409:154 410:10 433:145 434:237 435:252 436:252 461:255 462:253 463:253 464:108 487:11 488:155 489:253 490:252 491:179 492:15 514:11 515:150 516:252 517:253 518:200 519:20 542:73 543:252 544:252 545:253 546:97 569:47 570:233 571:253 572:253 596:1 597:149 598:252 599:252 600:252 624:1 625:252 626:252 627:246 628:132 652:1 653:169 654:252 655:132 +1 130:116 131:255 132:123 157:29 158:213 159:253 160:122 185:189 186:253 187:253 188:122 213:189 214:253 215:253 216:122 241:189 242:253 243:253 244:122 267:2 268:114 269:243 270:253 271:186 272:19 295:100 296:253 297:253 298:253 299:48 323:172 324:253 325:253 326:253 327:48 351:172 352:253 353:253 354:182 355:19 378:133 379:251 380:253 381:175 382:4 405:107 406:251 407:253 408:253 409:65 432:26 433:194 434:253 435:253 436:214 437:40 459:105 460:205 461:253 462:253 463:125 464:40 487:139 488:253 489:253 490:253 491:81 514:41 515:231 516:253 517:253 518:159 519:16 541:65 542:155 543:253 544:253 545:172 546:4 569:124 570:253 571:253 572:253 573:98 597:124 598:253 599:253 600:214 601:41 624:22 625:207 626:253 627:253 628:139 653:124 654:253 655:162 656:9 diff --git a/data/mllib/sample_linear_regression_data.txt b/data/mllib/sample_linear_regression_data.txt new file mode 100755 index 0000000000000..9aaaa4297548b --- /dev/null +++ b/data/mllib/sample_linear_regression_data.txt @@ -0,0 +1,501 @@ +-9.490009878824548 1:0.4551273600657362 2:0.36644694351969087 3:-0.38256108933468047 4:-0.4458430198517267 5:0.33109790358914726 6:0.8067445293443565 7:-0.2624341731773887 8:-0.44850386111659524 9:-0.07269284838169332 10:0.5658035575800715 +0.2577820163584905 1:0.8386555657374337 2:-0.1270180511534269 3:0.499812362510895 4:-0.22686625128130267 5:-0.6452430441812433 6:0.18869982177936828 7:-0.5804648622673358 8:0.651931743775642 9:-0.6555641246242951 10:0.17485476357259122 +-4.438869807456516 1:0.5025608135349202 2:0.14208069682973434 3:0.16004976900412138 4:0.505019897181302 5:-0.9371635223468384 6:-0.2841601610457427 7:0.6355938616712786 8:-0.1646249064941625 9:0.9480713629917628 10:0.42681251564645817 +-19.782762789614537 1:-0.0388509668871313 2:-0.4166870051763918 3:0.8997202693189332 4:0.6409836467726933 5:0.273289095712564 6:-0.26175701211620517 7:-0.2794902492677298 8:-0.1306778297187794 9:-0.08536581111046115 10:-0.05462315824828923 +-7.966593841555266 1:-0.06195495876886281 2:0.6546448480299902 3:-0.6979368909424835 4:0.6677324708883314 5:-0.07938725467767771 6:-0.43885601665437957 7:-0.608071585153688 8:-0.6414531182501653 9:0.7313735926547045 10:-0.026818676347611925 +-7.896274316726144 1:-0.15805658673794265 2:0.26573958270655806 3:0.3997172901343442 4:-0.3693430998846541 5:0.14324061105995334 6:-0.25797542063247825 7:0.7436291919296774 8:0.6114618853239959 9:0.2324273700703574 10:-0.25128128782199144 +-8.464803554195287 1:0.39449745853945895 2:0.817229160415142 3:-0.6077058562362969 4:0.6182496334554788 5:0.2558665508269453 6:-0.07320145794330979 7:-0.38884168866510227 8:0.07981886851873865 9:0.27022202891277614 10:-0.7474843534024693 +2.1214592666251364 1:-0.005346215048158909 2:-0.9453716674280683 3:-0.9270309666195007 4:-0.032312290091389695 5:0.31010676221964206 6:-0.20846743965751569 7:0.8803449313707621 8:-0.23077831216541722 9:0.29246395759528565 10:0.5409312755478819 +1.0720117616524107 1:0.7880855916368177 2:0.19767407429003536 3:0.9520689432368168 4:-0.845829774129496 5:0.5502413918543512 6:-0.44235539500246457 7:0.7984106594591154 8:-0.2523277127589152 9:-0.1373808897290778 10:-0.3353514432305029 +-13.772441561702871 1:-0.3697050572653644 2:-0.11452811582755928 3:-0.807098168238352 4:0.4903066124307711 5:-0.6582805242342049 6:0.6107814398427647 7:-0.7204208094262783 8:-0.8141063661170889 9:-0.9459402662357332 10:0.09666938346350307 +-5.082010756207233 1:-0.43560342773870375 2:0.9349906440170221 3:0.8090021580031235 4:-0.3121157071110545 5:-0.9718883630945336 6:0.6191882496201251 7:0.0429886073795116 8:0.670311110015402 9:0.16692329718223786 10:0.37649213869502973 +7.887786536531237 1:0.11276440263810383 2:-0.7684997525607482 3:0.1770172737885798 4:0.7902845707138706 5:0.2529503304079441 6:-0.23483801763662826 7:0.8072501895004851 8:0.6673992021927047 9:-0.4796127376677324 10:0.9244724404994455 +14.323146365332388 1:-0.2049276879687938 2:0.1470694373531216 3:-0.48366999792166787 4:0.643491115907358 5:0.3183669486383729 6:0.22821350958477082 7:-0.023605251086149304 8:-0.2770587742156372 9:0.47596326458377436 10:0.7107229819632654 +-20.057482615789212 1:-0.3205057828114841 2:0.51605972926996 3:0.45215640988181516 4:0.01712446974606241 5:0.5508198371849293 6:-0.2478254241316491 7:0.7256483175955235 8:0.39418662792516 9:-0.6797384914236382 10:0.6001217520150142 +-0.8995693247765151 1:0.4508991072414843 2:0.589749448443134 3:0.6464818311502738 4:0.7005669004769028 5:0.9699584106930381 6:-0.7417466269908464 7:0.22818964839784495 8:0.08574936236270037 9:-0.6945765138377225 10:0.06915201979238828 +-19.16829262296376 1:0.09798746565879424 2:-0.34288007110901964 3:0.440249350802451 4:-0.22440768392359534 5:-0.9695067570891225 6:-0.7942032659310758 7:-0.792286205517398 8:-0.6535487038528798 9:0.7952676470618951 10:-0.1622831617066689 +5.601801561245534 1:0.6949189734965766 2:-0.32697929564739403 3:-0.15359663581829275 4:-0.8951865090520432 5:0.2057889391931318 6:-0.6676656789571533 7:-0.03553655732400762 8:0.14550349954571096 9:0.034600542078191854 10:0.4223352065067103 +-3.2256352187273354 1:0.35278245969741096 2:0.7022211035026023 3:0.5686638754605697 4:-0.4202155290448111 5:-0.26102723928249216 6:0.010688215941416779 7:-0.4311544807877927 8:0.9500151672991208 9:0.14380635780710693 10:-0.7549354840975826 +1.5299675726687754 1:-0.13079299081883855 2:0.0983382230287082 3:0.15347083875928424 4:0.45507300685816965 5:0.1921083467305864 6:0.6361110540492223 7:0.7675261182370992 8:-0.2543488202081907 9:0.2927051050236915 10:0.680182444769418 +-0.250102447941961 1:-0.8062832278617296 2:0.8266289890474885 3:0.22684501241708888 4:0.1726291966578266 5:-0.6778773666126594 6:0.9993906921393696 7:0.1789490173139363 8:0.5584053824232391 9:0.03495894704368174 10:-0.8505720014852347 +12.792267926563595 1:-0.008461200645088818 2:-0.648273596036564 3:-0.005334477339629995 4:0.3781469006858833 5:0.30565234666790686 6:-0.2822867492866177 7:0.10175120738413801 8:0.5342432888482425 9:0.05146513075475534 10:-0.6459729964194652 +6.082192787194888 1:0.42519013450094767 2:0.09441503345243984 3:-0.07898439043103522 4:-0.32207498048636474 5:-0.9180071861219266 6:0.5951317320731633 7:0.41000814588717693 8:-0.3926260640533046 9:0.2789036768568971 10:0.13163692286014528 +-7.481405271455238 1:0.03324842612749346 2:0.07055844751995122 3:-0.47199515597021113 4:-0.682690342465275 5:0.3983414713797069 6:-0.2136729393256811 7:-0.09066563475481249 8:-0.4640338194317184 9:-0.03513782089224482 10:-0.1711809802758364 +6.739533816100517 1:0.1774546460228057 2:-0.6783644553523549 3:-0.47871398278230504 4:0.02272121490463097 5:-0.5047649289302389 6:0.26479596144873896 7:-0.32045436544054096 8:0.3113047940487379 9:0.6269418147567556 10:0.9710114516962312 +3.780807062175497 1:0.01715676997104909 2:0.8975962429865936 3:-0.46594560920034134 4:0.2873623499953055 5:0.8894362304584083 6:0.17973981232418468 7:0.49105791400707743 8:-0.7359842740294882 9:0.38941133808001127 10:-0.7151884777228046 +4.564039393483412 1:0.07478785545033317 2:-0.8672651994084235 3:0.450599300176334 4:0.35104802298560056 5:0.6797318185095045 6:-0.03891997518827006 7:-0.33208695871398675 8:0.6166574577055226 9:0.5730212324012205 10:-0.4194925751047054 +-0.3195679646035633 1:0.054527683864544096 2:-0.15591931640565093 3:0.9266742559542833 4:0.888522581905147 5:0.6576203900699167 6:0.6417770212400336 7:0.7509788029052338 8:-0.3104974571382815 9:0.7234744267051683 10:-0.15869049651427103 +11.290452658023497 1:0.20173310976772196 2:0.8657502566551409 3:0.9325160601080682 4:0.24570884032596263 5:-0.6546108813337841 6:-0.14020032028377583 7:-0.8825687891702743 8:-0.21420166926412865 9:-0.8600275184792756 10:-0.7990574622230739 +-4.003499192090455 1:0.8325875503351796 2:-0.5956350140619129 3:0.12598048009007923 4:0.12340188733473134 5:-0.839435659309717 6:-0.16623481818728414 7:0.12028795301041662 8:-0.7994713170657952 9:0.2216721974907896 10:0.8407561415075087 +-19.872991038068406 1:-0.9325810772922609 2:-0.6411471147334535 3:0.9949216290375054 4:0.483048267470493 5:-0.8736297429070232 6:-0.36222771685582544 7:0.26397860162786957 8:0.45527588775737704 9:-0.9424989711186325 10:0.6251162293059616 +10.502762149373098 1:-0.2307778924009991 2:0.6977871128979924 3:0.022830408261390822 4:0.6257738824362347 5:0.9770979848265122 6:0.09985730624684575 7:-0.9755858424230182 8:-0.689969833240031 9:-0.7294587311376761 10:0.3496326193951331 +-14.328978509075442 1:0.37929821892417404 2:0.8402056881660709 3:-0.1806835799958202 4:0.766314307210441 5:0.865876513623024 6:-0.7113501219432434 7:-0.0932956557986735 8:-0.7042025810921411 9:0.47530696925672267 10:-0.4629102077669889 +-16.26143027545273 1:-0.9309578475799722 2:0.7591795880911123 3:0.06296957473213705 4:0.786790093290086 5:-0.9527998391625465 6:-0.08573982501921895 7:-0.3812232026687308 8:-0.6890669703685022 9:0.25415911467755015 10:-0.07664746267502509 +11.772544195529013 1:0.3614756404325046 2:0.14508027508253818 3:0.23042774014795753 4:0.4164348685332022 5:0.4109091750657461 6:0.03853098236933272 7:0.38911994885223145 8:-0.5031309357181766 9:-0.596467768575587 10:0.17884522225228028 +14.697703557439503 1:0.24508864174863 2:0.7576193329655578 3:0.09030511120334461 4:0.9537528991778741 5:-0.7224092160621338 6:-0.34089385162121943 7:0.6924170720838818 8:0.32912306214891784 9:-0.4064624712125904 10:-0.5344662061201593 +-13.976130931152703 1:0.5891192531479754 2:0.29862103742464274 3:-0.36153976712796343 4:-0.6552669564323226 5:-0.22672513691161766 6:0.3001336202535376 7:0.34490251346382617 8:0.2072633053920192 9:-0.5659371284058774 10:0.49599636156628835 +-14.762758252931127 1:0.31302496164254223 2:-0.6062773982342133 3:-0.9874007658402217 4:-0.6214904627601421 5:-0.11421073677207683 6:-0.5850843421161205 7:0.1250679146774638 8:-0.7108170726393621 9:-0.6888351241194393 10:0.6077343683084389 +-3.300641320608255 1:-0.1407178879203672 2:0.12960233233004925 3:-0.4236196478321872 4:0.7903078296084356 5:-0.8755754953628643 6:-0.2062360260394529 7:-0.045680124889026175 8:0.783182093429277 9:-0.02995737262668463 10:-0.33382351650328435 +-15.72351561304857 1:-0.1802575775708093 2:-0.991006951265341 3:-0.9107951763247621 4:0.9069820084047908 5:-0.12691921206803047 6:-0.7087012119383593 7:-0.9179510577925369 8:0.18480349982718325 9:-0.4478459144114004 10:-0.5560585660624608 +-22.949825936196074 1:0.4797855980916854 2:0.01997502546020402 3:-0.8827928315487465 4:0.2755107907750989 5:0.015544482147298977 6:0.9652687138748801 7:0.6622667860970648 8:-0.7708138539912186 9:0.17728148663006627 10:0.47818190728952925 +12.092431628826905 1:0.1358843437335564 2:0.03643446587894239 3:-0.31070823939673287 4:0.5283033206569152 5:0.3469111543845367 6:-0.5162518174930761 7:0.24270234207184016 8:0.7352292800096338 9:0.8860322286740037 10:0.6748068653962045 +-23.51088409032297 1:-0.4683538422180036 2:0.1469540185936138 3:0.9113612952591796 4:-0.9838482669789823 5:0.4506466371133697 6:0.6456121712599778 7:0.8264783725578371 8:0.562664168655115 9:-0.8299281852090683 10:0.40690300256653256 +5.998186124881712 1:-0.9781302074883151 2:0.32984303335155785 3:0.7303430847899663 4:0.841481297188956 5:0.05580773881989276 6:0.7130788298702062 7:-0.218087116119847 8:-0.9889494995220598 9:0.9182854134226501 10:-0.7501751701020942 +9.852316338642547 1:0.146854160091757 2:-0.3611508707370965 3:0.3517016971654914 4:0.6187697988029395 5:-0.010768583697787548 6:0.5236725885871243 7:0.5945666964145524 8:-0.009180562740628506 9:-0.44474762415618274 10:0.41852743519493685 +-5.313930756588526 1:-0.6304209277071555 2:-0.37010359785263813 3:-0.3194739026510125 4:-0.750533359080716 5:0.45500303301733114 6:-0.012727544364283805 7:-0.43941651856862274 8:0.927108876532093 9:-0.24164903158058149 10:0.44134972919002124 +-4.2775224863223915 1:-0.35785764991284363 2:0.942797043714243 3:0.4539569191274251 4:-0.6944903010994341 5:-0.08357221983075225 6:0.4433049548665855 7:-0.5488972050023557 8:-0.24014623658145773 9:-0.6178118485382511 10:-0.4575463952834564 +-10.57769830424322 1:0.22693864400257335 2:-0.041639691095668674 3:0.9948726461115123 4:-0.7450471554938383 5:-0.1114847126717804 6:-0.27881184842402673 7:0.029766812446276214 8:-0.3727649352432578 9:-0.7791732805568077 10:0.9425576681069683 +-0.8430338600258201 1:0.4607090007225536 2:-0.6079961642969514 3:-0.5671626932935381 4:0.12784576080614185 5:-0.30766031989910236 6:-0.21232963505711555 7:0.3310463755850872 8:-0.6807682731528943 9:0.7826634145951483 10:0.0608057623636995 +13.450586257053727 1:-0.2697769964284986 2:0.07743737732312428 3:-0.8459687499864881 4:0.6091901514177853 5:-0.9464815428211699 6:0.15780407422581533 7:-0.28552052619478996 8:-0.27500859181806403 9:-0.7207541548282903 10:0.05215593729084533 +20.358241877831016 1:0.29768927445620164 2:-0.5379390525163252 3:0.6591913001003027 4:0.6635992348010928 5:0.3786594651413009 6:-0.7217135278882543 7:0.9634013908615768 8:0.03961253903778861 9:0.1335121312144949 10:0.7933944303463509 +9.800993960518852 1:0.39896823489212285 2:0.30948413101894023 3:0.08568060094378493 4:-0.7454513450113371 5:0.8054125831421357 6:-0.24464240413169347 7:-0.18294406588625112 8:-0.883455504399858 9:0.2468431033653562 10:-0.708151566382103 +-21.432387764165806 1:-0.4785033857256795 2:0.520350718059089 3:-0.2988515012130126 4:-0.46260150057299754 5:0.5394344995663083 6:0.39320468081626836 7:0.1890560923345248 8:0.13123799325264507 9:0.43613839380760355 10:0.39541998419731494 +-4.090570760187878 1:0.3909705814857716 2:0.9830271975811611 3:0.672523651785939 4:0.0035177223850744177 5:0.567082732451311 6:-0.2620454326881394 7:0.46622578556708105 8:0.646246879249865 9:0.4263175536668733 10:0.8982696975276223 +3.7459201216906926 1:-0.9480167656870653 2:-4.888270196095057E-4 3:0.48226844071577646 4:-0.23706663537631645 5:0.22420266627462127 6:0.2981747607694978 7:0.3893425967975348 8:0.6302701381298614 9:-0.21909113816064196 10:0.8371697958140494 +9.767952084958061 1:-0.2300790371078303 2:-0.4457883630748676 3:0.28710853302295325 4:0.7112839743052013 5:-0.8765858382640623 6:-0.6470779468607217 7:0.4369262584371727 8:-0.7175412028407337 9:0.5506733477278882 10:0.5393007189573547 +6.9802839308913365 1:0.21769855012808215 2:0.8653818331675485 3:0.2322943113578111 4:0.3760591265797468 5:0.06554014167292377 6:0.6866096712933549 7:0.866929973115441 8:-0.6462263417217329 9:0.2507247465275353 10:-0.7005877782050307 +16.014720800069103 1:0.6058055248984549 2:0.048517868234337014 3:-0.15744912875924877 4:0.32598079708869365 5:-0.587791997223768 6:-0.4636187312118474 7:0.7771908559246068 8:-0.349403853888719 9:0.229800030145503 10:-0.674614818934488 +8.417571532985823 1:-0.21164946152466801 2:-0.9981936663594053 3:0.8611869575187896 4:0.11100891297254312 5:-0.7406067304729631 6:-0.7613837395522254 7:-0.9617573325708704 8:0.5697426971647488 9:-0.5830879716990833 10:0.5951448538064159 +-12.491442077546413 1:-0.19172117564625735 2:-0.12421304883392126 3:0.7095605786791346 4:0.6401582292398038 5:-0.9347790209840108 6:0.6592209285686903 7:0.702282297844389 8:-0.22765902007749528 9:-0.17746922342943816 10:0.7196663432778121 +-8.605713514762092 1:0.36490454976480846 2:0.6991204480538957 3:0.6546945560337121 4:-0.032324845758738174 5:0.2453935969836043 6:0.5363119225093116 7:0.6266741350524205 8:-0.2132266305382322 9:-0.308105870487996 10:-0.08219413867616465 +-10.35591860037468 1:-0.014204168485027147 2:-0.7077035677144325 3:0.024004217785642767 4:0.818971992516166 5:0.9081305263471056 6:0.808854493237229 7:-0.6474336785461867 8:-0.32559288177031465 9:-0.32850453072496055 10:-0.7035310416695784 +3.605002621628445 1:0.6085817977516599 2:0.8101072412357928 3:0.7697891508923966 4:-0.5738750389864677 5:-0.734314989863889 6:-0.7879014492215499 7:0.6884442838920775 8:-0.46131231930402383 9:-0.7730585954271005 10:-0.7819874019145132 +12.30435312415091 1:0.3283668768730639 2:-0.18316686990068187 3:0.3955614099142126 4:0.8450470350842108 5:0.3958042901611589 6:0.6578475571960676 7:-0.4395488558075096 8:0.15720430113495376 9:-0.5318362828977672 10:0.45585285255232044 +9.020048819638827 1:-0.5986521145193395 2:0.3266542215286443 3:-0.09911773729611917 4:-0.21478254478908676 5:0.6546175049764293 6:-0.1414796368932345 7:0.25802631337510085 8:-0.6773828562539816 9:-0.22038193899258718 10:-0.17465737306657902 +14.854262978981406 1:0.5293763924477841 2:-0.24658868331583683 3:0.8268631648872109 4:0.8969207203400265 5:0.03933229861213983 6:-0.6212951181360529 7:-0.36695460282178205 8:-0.5468014636386027 9:-0.3419492829414976 10:-0.8273314086998671 +5.658665647926016 1:0.9543096383762801 2:0.13230023957687176 3:-0.3071929861496465 4:-0.3646067841449696 5:0.6979929890816723 6:-0.20721664168809228 7:0.6676482547655365 8:0.944757051233543 9:0.024377296173674567 10:-0.9413728609667691 +-6.930603551528371 1:0.09198647857985232 2:-0.3685113649452161 3:-0.2361728930325453 4:0.3674268130607439 5:0.27385598384498344 6:-0.7151900241735676 7:0.3310154476154119 8:-0.24328111897361682 9:0.2511378679668912 10:-0.35825141175578934 +13.361196783041926 1:0.11676665169094824 2:-0.49968608916548307 3:0.9941342810313298 4:-0.17858967215374988 5:0.1993744673440312 6:0.14596837574280297 7:-0.8245495433125194 8:-0.5637934691545672 9:-0.8589185806222286 10:-0.4923216901915597 +-3.280508467210429 1:-0.9917770074538397 2:-0.1547651813493751 3:0.621733177563484 4:0.7303326279246298 5:-0.0786900332560696 6:0.9107127797641994 7:0.7104513024299466 8:-0.32858522942354407 9:0.17013652749847386 10:0.27656984316288824 +11.13509519160867 1:0.6874932143640391 2:-0.46610293161038907 3:0.8744681017967024 4:0.40900365224695956 5:-0.49770054448432055 6:-0.0635770754462921 7:-0.5705387648707747 8:-0.577988250149829 9:-0.8099463063934682 10:0.42132700180827354 +-11.857350365429426 1:-0.24607974991258308 2:-0.943388538022258 3:0.8679112109377674 4:0.7779951176637694 5:-0.5802336023276593 6:-0.9093352471884992 7:0.29337797938742316 8:0.498519874589175 9:0.3493034812120912 10:-0.07307210651399076 +11.421632138263703 1:0.3911519359353859 2:-0.8154393787235621 3:0.47194271125243237 4:0.14014792298759593 5:-0.3589345913619957 6:0.7887695409762479 7:0.49962792312858895 8:-0.6402670146359797 9:-0.2314041601683119 10:-0.798901341175887 +5.194792012146463 1:0.810279303469398 2:-0.9772756877199589 3:-0.20925958437085557 4:0.8797562461102444 5:0.3211532423260066 6:0.25250279470783754 7:0.14387831263435813 8:-0.021466789385169882 9:0.18909293657271564 10:-0.5981349964027893 +12.242677118499806 1:0.3565715672082048 2:0.7366743237221687 3:0.1922233582434527 4:-0.3551925780624561 5:0.5290849503909634 6:0.7744214641246749 7:0.7277215028580597 8:-0.590440215391044 9:0.7427328184290733 10:-0.6231904162251609 +3.496172341296411 1:0.5028717258135624 2:-0.5838871888624848 3:-0.5540116561110324 4:0.8502487679795261 5:-0.7983061034328727 6:-0.3853123296389005 7:-0.1493800684643869 8:0.6008798629354264 9:-0.32299062155495406 10:-0.5827019502242026 +-15.437384793431217 1:0.41994681418237345 2:0.7106426870657483 3:-0.45211033467567696 4:-0.7272406549392239 5:-0.35736594496490737 6:0.4764507578985955 7:-0.5249912641281373 8:0.8562010912051132 9:0.45927621623833637 10:-0.3701817429794385 +5.490036861541498 1:0.8414999442459015 2:0.9273442862476728 3:-0.054654787893199774 4:-0.23126134156257327 5:-0.9155048245317694 6:0.25750538376376975 7:-0.8470916763665326 8:0.9105674676753848 9:0.5026028522378054 10:-0.06650501561108468 +-1.074065343287859 1:0.37484830603001607 2:-0.9858854245832975 3:0.007159356555897611 4:0.8172796295244154 5:0.519147377529164 6:0.8211049991970722 7:0.9901658817979146 8:-0.026519560032641998 9:-0.2328762488733862 10:0.43161994187258035 +2.0482082496444622 1:0.24940246021565793 2:0.47248358864259177 3:0.23833814894291105 4:-0.3449172512379757 5:0.7412869866239866 6:0.1351422898741914 7:-0.003784141556894216 8:-0.6321917152754075 9:0.8246267827865776 10:0.5057520480449009 +16.709794859608397 1:-0.5977424405191092 2:-0.13991362149785713 3:0.613487896720806 4:-0.37681525320218157 5:-0.4369592282569783 6:0.4702242879506955 7:0.07498463532645339 8:-0.9942304127133292 9:0.41304209196175257 10:0.6799250665519481 +4.598881854940949 1:-0.41212838137243835 2:0.6737124633791323 3:0.8376369191216593 4:0.2848328781926128 5:-0.17960265353296 6:0.0035488712665472377 7:-0.8355355482928055 8:-0.7439716673142398 9:-0.009043467128117433 10:0.7423272515054122 +9.566038608555402 1:-0.662329643040616 2:0.4727113884417973 3:-0.15734218732411365 4:-0.3950754785173889 5:0.13837083076070011 6:0.633261314089351 7:0.9929998062307679 8:-0.4639028424346423 9:-0.073992579817449 10:0.3413166410117088 +1.629198477883475 1:-0.2875719791707101 2:0.9395753700232541 3:-0.45090801750966314 4:-0.384528069378699 5:-0.35937736478702753 6:0.9597102694501136 7:-0.6898325123180971 8:-0.11436012866371303 9:-0.5330550575952768 10:0.24688769932037258 +-7.374620970147229 1:0.16864051681940984 2:-0.08391828256018252 3:-0.8184503043836224 4:0.5461252511055263 5:0.7264676659099087 6:-0.9654384426822686 7:-0.8537533138667612 8:0.9189716013058653 9:-0.03449322582531389 10:0.5490329745887035 +-0.5741704240890674 1:0.9392753294760656 2:-0.5579682000156501 3:-0.8083270703362093 4:-0.7022804026958895 5:-0.30426803430649896 6:0.8211432527140852 7:-0.8101343265051797 8:-0.0945946325760949 9:0.49546915718101814 10:0.5184327698839013 +12.583032451116004 1:0.20496323995364651 2:0.5082017540304999 3:0.2428646053751764 4:0.7101854338863274 5:-0.9619925264660094 6:0.4610134502825909 7:-0.5620669052678122 8:0.6766614078376236 9:-0.7169693435782278 10:-0.14362322382035164 +-10.489157123372898 1:-0.7441633083637054 2:0.07069898351187809 3:-0.47119552972566336 4:-0.43970155900871344 5:0.43192289605353973 6:-0.0798550143899397 7:0.2111188135787776 8:0.9101748615761336 9:-0.4079984876629721 10:-0.8101424982394589 +-3.811365493249739 1:0.7250263461647963 2:0.22182621035333838 3:-0.12735342714215725 4:0.26222861719040624 5:0.3928174057935714 6:0.817131411734006 7:-0.056109765698795 8:0.7908779197353637 9:-0.06768319505245768 10:0.4107045608924882 +-7.604636483513961 1:0.876751634787073 2:0.04037085575852295 3:0.18142385658771398 4:0.38350565074271903 5:-0.30937664332011905 6:-0.9544807672006823 7:0.008643477632712449 8:-0.27676843472226276 9:-0.12938540988602476 10:-0.2929762262661819 +-1.9889499615051784 1:-0.4243149295090465 2:0.22578711943818686 3:0.662530786460152 4:0.28592235843136105 5:0.4170345231441832 6:0.9290881132120887 7:0.5332443368002588 8:-0.33248958421809927 9:0.16273139830495942 10:0.6899022585936985 +-1.99891354174786 1:-0.1732078452611825 2:0.2361029542296429 3:-0.8455867017505336 4:0.31638672033240867 5:-0.648387667144986 6:-0.7647886103837449 7:0.6910155501192978 8:-0.2665663102538198 9:-0.5980899570876459 10:-0.9165896495676276 +9.74348630903265 1:0.18934450539532244 2:-0.715110505416745 3:-0.453777527810155 4:0.2743741252197758 5:-0.8439310405443103 6:-0.533835190276116 7:-0.5911710854054728 8:0.21026462628920695 9:-0.45849607678093585 10:0.1327074179200407 +20.221961806051706 1:0.624731930687735 2:-0.39914395421723015 3:0.781887900750925 4:0.5442619051596436 5:0.16651193067479153 6:0.9064846121246533 7:-0.3643159594276202 8:-0.5182065337246469 9:-0.6785628247191553 10:0.7111152852903913 +20.456947955410897 1:-0.21923785332346513 2:0.11340668617783778 3:0.7397883986253251 4:-0.11748081084695605 5:0.06314872700777197 6:-0.7124574845946587 7:0.18043581960897104 8:-0.09023925260092103 9:-0.7256417560118238 10:-0.5038088673851804 +12.241006086129564 1:-0.15271598143132215 2:0.9038942665552285 3:-0.6168514099878155 4:-0.12219038322317011 5:0.5402785935596728 6:0.4059744401803913 7:0.258870596734184 8:0.3190881033039108 9:0.2372469007313076 10:0.367188299614863 +3.980473021620311 1:-0.9025895351376971 2:-0.03333947011476446 3:-0.8220776066161464 4:0.449117985679933 5:0.9970519437779266 6:0.27430911004640457 7:0.039081352882204046 8:-0.8621514950929796 9:-0.569587565933642 10:-0.9118346349929578 +-13.420594775890757 1:0.3697979495309094 2:0.07383664120111888 3:0.7199366131785143 4:0.2118625428869032 5:-0.9015976323216077 6:-0.5298395275757712 7:-0.9517419542156635 8:0.39554920787574743 9:-0.3721957439110324 10:-0.4750272836396878 +-1.052659359353786 1:0.02106845330888185 2:0.7571245678782959 3:0.8034228830223251 4:0.32968340513846917 5:-0.6510386482911554 6:0.2710115488605187 7:-0.1319580272290235 8:0.932600992666184 9:0.8260461527035414 10:-0.8507648952138052 +9.813440129324034 1:0.41048687946340134 2:0.9384639988086239 3:0.4569555844323441 4:-0.3084729082645552 5:-0.7299010284877061 6:-0.6925012997779212 7:-0.6798013915257548 8:-0.504368104320321 9:-0.6234398059664716 10:0.8633407902005543 +-2.8942782378157714 1:0.5546381825677706 2:0.7959405841824887 3:0.584699836289184 4:-0.5726371777829862 5:-0.2827976152663936 6:0.138034013875719 7:-0.2935080791661324 8:-0.5323479091625714 9:0.6837641044797451 10:0.5986680812032501 +8.562937733537664 1:0.14753220510180776 2:-0.31591341855048327 3:-0.748545617199091 4:0.3251888821665734 5:0.8228589483149358 6:0.046659706976506676 7:-0.35049927996132624 8:0.2953170004605874 9:-0.6429374177050204 10:0.4624083116836044 +13.413187970975178 1:-0.7229883396779724 2:0.8876940454894067 3:-0.033794226589695775 4:0.46700071356381523 5:0.1599557295166274 6:-0.8944619785248653 7:-0.1258464584151997 8:-0.8797551785991506 9:-0.14408879184669354 10:0.11020655997336015 +-5.491389764900794 1:-0.366507395597937 2:0.630480481240723 3:-0.16600801981741609 4:0.09842042773854076 5:0.30129535029579047 6:0.14102166298628882 7:-0.28131788612036623 8:0.49635295715686234 9:0.0625636989631968 10:-0.41748132718912 +-10.29566593602992 1:-0.7898597726154271 2:-0.05425577320946573 3:0.5992645759265662 4:-0.4716868549309716 5:-0.020137302700854676 6:0.6216515277233232 7:-0.7295510954484412 8:-0.41443875567123967 9:-0.610576632050404 10:-0.9515988311377204 +7.084732852050431 1:0.9990215581592679 2:-0.9868954542412269 3:0.49133473382040704 4:0.7697599878561228 5:-0.34668939907967267 6:0.9777705993519483 7:0.4449043102759509 8:0.9812971199646168 9:0.6666598587737487 10:0.14398842572598514 +0.23715467505851734 1:0.21628799185444336 2:-0.4526390568867018 3:0.6558486691929235 4:0.13730688681492142 5:0.23076986155942736 6:0.7020484017619715 7:-0.12077999528458938 8:0.8306084972447003 9:-0.49337323198621563 10:-0.8270028152572872 +1.1552619549601455 1:-0.48202394020369277 2:-0.6274878708695264 3:-0.27623674153600697 4:-0.5312153415813432 5:-0.030820182786174044 6:-0.5893370965577813 7:0.6666315120904487 8:-0.36482991729570036 9:0.6065771813692735 10:0.05831057330788525 +-0.20433879835596253 1:-0.4702220250018212 2:0.9123705796362889 3:-0.2045657170490376 4:-0.18922063450309534 5:-0.31431213362503163 6:0.4150130060120387 7:0.34016193625941127 8:0.8391374136299805 9:0.6884250315764333 10:-0.7916408854251566 +-9.751622607785082 1:-0.0014232315621649505 2:-0.1284246813729939 3:0.5228953023175369 4:0.9688522449007109 5:-0.7857721219549156 6:-0.7812922263391038 7:-0.5916136652814756 8:0.793988610184206 9:0.7982949061274296 10:-0.592785473963741 +-22.837460416919342 1:-0.17363144173810174 2:-0.3340314573781735 3:0.9351424971322297 4:-0.6430601902397572 5:-0.13363305808148818 6:-0.42446359566938585 7:-0.4093070316761178 8:-0.9302259781839204 9:0.47004365892170585 10:-0.6231289889808045 +-3.6318714209289436 1:-0.8296410705737971 2:-0.6056572341069668 3:-0.2975417404042737 4:0.07134138175064741 5:-0.8966463747179154 6:-0.4112675899658855 7:0.7908013478009401 8:0.407396254566472 9:0.9227769302156879 10:0.12418427404473764 +-3.8909712376010583 1:-0.6552751548581366 2:-0.5641921108932855 3:-0.6340486345063014 4:-0.5441069121131075 5:0.908720622198947 6:-0.026054643814348077 7:0.03706191653058433 8:-0.6672524338819317 9:0.7958274915288801 10:-0.19029619970124023 +-10.600130341909033 1:-0.7457695999520562 2:-0.3739453132549577 3:0.01327423342620393 4:-0.08482897201178563 5:0.84573456086082 6:0.6279927575103963 7:0.014494803555804125 8:0.9420647557771027 9:-0.13484113287285893 10:0.3037405853352888 +-12.094351278535258 1:0.9982796018306028 2:0.8354271779265348 3:0.46284321795736116 4:0.07693347919601745 5:-0.4753440408996932 6:-0.47098252868073787 7:0.4810729184846003 8:-0.6136990339205741 9:-0.6715833036640317 10:-0.6247058955319091 +9.936399360181602 1:0.7330323083522969 2:0.47204204993669197 3:0.3850471475752122 4:0.21483460195167958 5:0.3806220122265147 6:0.6336993433402796 7:-0.47987416364572 8:-0.195509010865196 9:-0.6561820282562041 10:-0.45300480439842894 +-4.706701061062994 1:-0.847895844561626 2:-0.29946646506145114 3:0.25432868082106497 4:0.1352958872054535 5:-0.8803017974303002 6:-0.3675110562764785 7:0.10888496324899721 8:0.9620737605396772 9:-0.031046632561323895 10:-0.09466883461500908 +5.101614991255809 1:-0.5174248135588373 2:0.14394061894828014 3:0.5613709266711013 4:-0.5678634944326011 5:0.930216209978763 6:-0.6204727890080077 7:0.4133141749872311 8:0.6262685035917408 9:0.03382924477926896 10:-0.15231139191832854 +-8.772667465932606 1:-0.2117605577769197 2:-0.4283897136887762 3:0.44686767473401035 4:-0.5507826261358746 5:0.237124956028401 6:0.6413157520982717 7:0.2409214827604571 8:-0.8505503638033114 9:-0.9811997368468401 10:-0.9499963936664035 +-11.615775265015627 1:0.8782018665273386 2:-0.9751473570197167 3:0.6307050068521085 4:0.7012721336851997 5:0.21318736263512283 6:0.024885128053773853 7:-0.4580644243558505 8:0.1318650007251434 9:-0.9306090092992167 10:-0.5688746770986652 +19.64829023536192 1:0.14426537998360645 2:0.3557716894181753 3:-0.8577143134654568 4:0.5288643233801469 5:0.9231529738221469 6:0.975999712077738 7:0.24700404691888678 8:0.10206517527052283 9:-0.10041951294847062 10:-0.9412918491876225 +2.7409415438025486 1:-0.7404936009304737 2:-0.9792071376296605 3:-0.49510748520932113 4:0.9538460112904268 5:-0.5075114153141447 6:-0.5890791308058669 7:-0.775366087491284 8:0.4983912525892249 9:-0.2976197956132913 10:0.6791258030468514 +-4.394658158733604 1:-0.41628618754613345 2:-0.1472602552309057 3:0.44136102233464025 4:0.011882653940414434 5:-0.6559502840386595 6:-0.4022529016339016 7:0.048402312931387526 8:0.8753776623326166 9:-0.8528247288266961 10:0.6593783978826002 +1.1915739133607073 1:-0.7840827624854878 2:-0.4860418508208426 3:-0.7418773161179972 4:0.129874781837924 5:-0.22631682294184796 6:0.47794208013755024 7:0.5532183426143056 8:0.11879859459306741 9:0.09927630694484524 10:-0.19268618891399636 +2.156192215438919 1:0.44325986644475646 2:-0.6057278708888592 3:0.3943381582091723 4:0.6560336238050575 5:-0.9651308100517204 6:-0.2358219003943678 7:-0.04143043460232465 8:0.8623951169233035 9:-0.4933545255502605 10:0.8990427200454263 +-1.1009750789589774 1:-0.4515707618788496 2:-0.745936099912899 3:0.41307003181926794 4:0.6127760492402428 5:0.9250878169732681 6:-0.6778628527469126 7:0.42794190420905753 8:0.4943969797578971 9:0.7762709104958854 10:-0.6932349268610041 +10.04434496594037 1:-0.0995467494040092 2:-0.7766769414838959 3:-0.6608009972582911 4:0.7075788021090594 5:0.5208396359138381 6:-0.09724033794207299 7:-0.743087245352148 8:0.765372791789753 9:0.3788699859744704 10:-0.6898257995055466 +8.038039859115667 1:-0.5321510657026671 2:0.5571925538006008 3:0.747268102801854 4:0.09079641165917596 5:0.25861122989509266 6:-0.9948187479498878 7:-0.9665136866462685 8:-0.3904629432867681 9:-0.9975425877998279 10:0.32024289816988416 +5.14371929922303 1:-0.4829199170694627 2:-0.5713285263827719 3:-0.43889652467111184 4:0.18478247261988967 5:-0.27374063120041225 6:-0.8069125377696931 7:-0.15497746743367058 8:0.32448521325998714 9:-0.39397735035206227 10:0.08184957956614292 +-1.6848276484379352 1:-0.39250489761445895 2:0.02730338852529557 3:0.9916055514435305 4:-0.07571433435055064 5:0.19024527726403728 6:0.6385182319185971 7:0.32480605537471297 8:0.5807543325220577 9:-0.35642510103381153 10:-0.9060482769392468 +-11.640549677888826 1:0.03707410390488852 2:0.2527049166981137 3:0.4114872952854447 4:-0.8508977901757795 5:-0.42791544663481895 6:-0.9864047295390463 7:0.6023685964407528 8:0.12018443688097036 9:-0.36816249877130414 10:-0.9583147535652901 +11.672104494601319 1:-0.2416258355340175 2:0.6737553249072334 3:0.9041602191361382 4:-0.2123232797997281 5:-0.008255188002961988 6:-0.5151894064136904 7:-0.7341877977528246 8:0.624625272218277 9:-0.6261434804192929 10:-0.5710586715741532 +-2.2960192492344627 1:-0.7457768645184579 2:-0.5954998103421847 3:0.5428846769211537 4:-0.6176587961491775 5:0.46222150678166574 6:0.7852238239427731 7:-0.3614580530629148 8:-0.325840253127059 9:-0.5660596710348922 10:-0.8060263366626401 +5.428302298615722 1:0.8774286357993033 2:-0.23110126319781088 3:0.6264134914476072 4:-0.143015582616014 5:0.350109539755298 6:-0.147747167834422 7:0.05020570422182824 8:-0.5469605849960337 9:0.951112567977048 10:-0.34800121380288185 +-17.32672073267595 1:0.31374599099683476 2:-0.36270498808879115 3:0.7456203273799138 4:0.046239858938568856 5:-0.030136501929084014 6:-0.06596637210739509 7:-0.46829487815816484 8:-0.2054839116368734 9:-0.7006480295111763 10:-0.6886047709544985 +7.314490512652487 1:0.8745354279105222 2:-0.9270067504840309 3:0.965218170323435 4:0.12808957052353698 5:-0.5309399625085234 6:-0.5968520990090951 7:-0.667403236513185 8:0.08154410986660832 9:0.33025488397543934 10:0.03406708067839537 +4.687373993408297 1:0.6731426721418288 2:-0.7111023070261273 3:-0.9849054116048603 4:-0.12831346258317322 5:-0.04095946352836921 6:0.6967001556166801 7:0.8479895229743999 8:-0.35600791972899404 9:0.5005979045264868 10:0.6421341979636503 +-6.82923852156868 1:-0.04849233571020073 2:-0.8505855619911602 3:0.2927180954190314 4:0.5780268040086791 5:-0.22322207765417268 6:-0.8436513934568071 7:-0.3906240514635124 8:0.7258714963093444 9:-0.21695043530813085 10:0.8049335285918169 +-8.24622879369294 1:0.12154833675098842 2:-0.26446415445316673 3:-0.06653791221669247 4:-0.7920694887292259 5:0.6128791496627621 6:-0.6927179137980173 7:-0.24584418172709932 8:0.3557416365779935 9:0.22868636757755234 10:-0.8288196322549064 +-5.090863544403131 1:-0.1535668648046895 2:-0.59868738365189 3:-0.8822518703008675 4:-0.1790505106198006 5:0.9467581256591948 6:-0.0661313762905984 7:0.31263046332923694 8:-0.03628894224569357 9:0.8969599435828515 10:-0.05386674051170348 +-15.780685032623301 1:-0.2568492063716883 2:0.7740976197426315 3:-0.7829158104387535 4:0.8578846037465748 5:-0.6111039318672586 6:-0.26939268282639306 7:0.3659136640533909 8:-0.8205938562638555 9:-0.24945505706767923 10:-0.935948184861368 +-3.9916779937384743 1:0.22925954469403154 2:0.18159238246979537 3:0.05607027262862396 4:-0.3376037702047998 5:-0.10630000583678934 6:-0.7148277241201622 7:-0.08327294541727137 8:0.6532439360618307 9:0.34352364313237294 10:-0.21028242388807916 +8.798748248458631 1:0.509058184822212 2:-0.17532831457577935 3:-0.6387880909085213 4:-0.966194650702529 5:0.7829797328120436 6:0.5470735549914605 7:-0.38312745239682333 8:-0.8890923931840893 9:0.6823342859396513 10:0.9231260597729121 +14.341273640964873 1:0.6996156678090684 2:0.8612833977834464 3:0.9131301694042417 4:0.5199385192744859 5:-0.32605907950755086 6:-0.9816465962348846 7:-0.5939885763232406 8:-0.7730924566676425 9:0.6367821449954114 10:0.10873812383881054 +9.75855501262469 1:0.2933324921347933 2:-0.4652534314332506 3:-0.2940640558090537 4:0.9883453215038367 5:-0.042460731786114314 6:-0.15438550895912062 7:-0.11182397625560592 8:0.7425954283250873 9:0.5063859049644963 10:0.3012211854180429 +7.695200921242407 1:0.3554353390157281 2:0.08707592690448718 3:-0.10815435665633877 4:0.05524046679762784 5:0.8000157491787581 6:0.3756193347272323 7:-0.18659830666742527 8:-0.08168623764933125 9:-0.2551379303720174 10:0.8560030587463281 +26.903524792043335 1:-0.4672678144441864 2:0.868381965588082 3:-0.04748335609643428 4:-0.0908285508827269 5:-0.22436865911994275 6:-0.953965287326564 7:0.40644848732968164 8:-0.33391575325981115 9:0.008337907338700212 10:-0.45597904754961416 +9.87318781117539 1:0.7310287890171705 2:-0.38300115058116324 3:0.5492682498036086 4:0.552016070316655 5:0.3715022458396897 6:-0.3888040017277252 7:0.21348231125683648 8:0.23219558685722874 9:-0.6271161253492459 10:-0.009137052604519136 +7.6930514050666625 1:0.48603550488592284 2:-0.9218820771919889 3:0.17678612698428053 4:0.5110501870908806 5:0.5817010201164554 6:0.4488707800038747 7:0.4977618637956498 8:0.1683214570038094 9:0.17237242672259323 10:-0.5276084644007359 +3.155413914311745 1:0.04582517188512947 2:-0.9060800653779759 3:0.049786270132956556 4:-0.4236784487542993 5:0.6293910028372613 6:-0.7370237043436467 7:-0.4599678991281728 8:0.5317111095323057 9:0.0029525239228334055 10:0.9294876800738165 +-10.18815737519111 1:-0.9023553189306839 2:0.08434165073970856 3:0.7163931103395633 4:0.41749986495957914 5:-0.8190972970472759 6:-0.9996126872234177 7:0.1779075727741255 8:0.18212754689351862 9:0.24628508239298963 10:0.667589863190412 +18.585731475373457 1:-0.8399129036462931 2:-0.10024819268489127 3:-0.5011350892733817 4:-0.7299256348863585 5:-0.9412022985072928 6:-0.245064895931544 7:-0.1032512650854267 8:0.9943863256441088 9:-0.6429371028855466 10:0.062299742931960056 +8.998359297106072 1:-0.16850226855111905 2:0.7262839202089402 3:-0.04876255055071854 4:0.8948164957242868 5:-0.10720585418953132 6:0.2622719447841948 7:0.26433837506661373 8:-0.5143449147399106 9:0.17444585508955002 10:-0.813182163328944 +13.032424230011074 1:0.4014766166181287 2:-0.1710502754125871 3:-0.309850483152607 4:0.255642456909988 5:0.9949117714165621 6:0.12553772251510864 7:0.6412602805648968 8:-0.6225679446416825 9:-0.15867011477056936 10:-0.4970695349036196 +-6.931030745953174 1:0.5151452174260762 2:0.10077064818539072 3:0.9515221270405545 4:-0.21551878535257907 5:0.29152528087481366 6:-0.10995497026133605 7:-0.7872786530801681 8:0.9909149980139627 9:-0.6044617953251021 10:0.4135285912642448 +15.538062451207367 1:-0.493569696351595 2:0.7280914440594639 3:-0.5399160539735497 4:0.5688018985826291 5:0.8296550361854862 6:-0.3519274619833537 7:-0.5536583684230114 8:-0.9648774930921231 9:-0.2649670832738824 10:-0.2337289004188019 +9.499729032920945 1:0.22017490770298553 2:0.7693082799289328 3:-0.7645745307823122 4:-0.4243400515554365 5:-0.7065281515163817 6:-0.9488470141298047 7:-0.7888781431404843 8:-0.38027758953310964 9:0.11329243985448345 10:-0.5636550498916204 +-0.6039115764951412 1:0.3128791250125589 2:0.4690308315665288 3:-0.9819748103687955 4:0.28931283693913223 5:-0.6283983933456656 6:-0.10795935596621975 7:0.7785831799196448 8:0.4453768248295542 9:0.4055410615499917 10:-0.581108383985806 +9.682301463907875 1:0.5039970331368235 2:-0.008965105921562966 3:-0.5415225380115054 4:0.4677111860370293 5:-0.3854089758945243 6:-0.8468317339287676 7:-0.29258253017713587 8:0.7361173598968789 9:0.5722561668394952 10:0.8524030171340933 +-2.8752191903928064 1:-0.45407356732165205 2:0.6563221064539377 3:-0.8938366926767671 4:0.6028173420234533 5:0.6792881349943096 6:-0.6295604812779405 7:-0.21641416912497213 8:-0.8703620515028858 9:-0.3397362922228042 10:-0.0966947467107604 +-28.046018037776633 1:0.9493308195854675 2:0.3285214661535252 3:0.749300278016316 4:-0.006681618268088219 5:0.2936055273341429 6:0.0044706790416966236 7:0.5006172205470896 8:0.38751814960349473 9:0.6069735922707928 10:-0.794612882855285 +2.8752582614589373 1:-0.9443232811926943 2:0.3153126492983107 3:0.6423843271417344 4:-0.09528333043829118 5:-0.2318773828230698 6:0.32597909562645766 7:0.42808555740416065 8:0.2895959316734451 9:-0.5106491076955746 10:-0.2917418155655722 +-2.203945173593806 1:-0.13844025039418084 2:-0.024638102806725293 3:0.6114514176076162 4:-0.6939316676972749 5:-0.036549673716341324 6:0.0942395290460385 7:0.7943411369475493 8:0.7025693796408046 9:-0.21822635487138853 10:-0.6045250179827362 +-5.070655299509993 1:-0.8035156105848074 2:-0.5344928236067734 3:0.6105404604447127 4:-0.7538635525543969 5:0.9836765037886612 6:-0.5700253195942724 7:0.9232380985458313 8:-0.26374377078100464 9:0.9079431466301682 10:0.8404281771949533 +-2.540181413836895 1:0.220453181647285 2:-0.03105792440486077 3:-0.17131282366411926 4:-0.41800060634660485 5:-0.1477564564540963 6:0.055537469469941536 7:-0.8092076926316594 8:-0.29815112444525727 9:-0.20030580647762464 10:0.337865838755971 +19.341342586351033 1:-0.32052868280788616 2:0.954507993011956 3:0.38642226954792824 4:0.9240442034609888 5:-0.46077559741256824 6:-0.7991393493824104 7:0.9396232321156679 8:-0.2486930151964184 9:-0.6256485833035617 10:0.14861843824730103 +0.31398559122529757 1:-0.4684215762946897 2:0.07873308388585198 3:-0.3589594894052015 4:0.14284662079329458 5:-0.8936272055527841 6:0.5647217242826741 7:0.49613233215723507 8:-0.501698787526992 9:-0.46710107378968724 10:0.898517179577361 +12.243117462926584 1:-0.8147610562690222 2:0.21104006948075482 3:0.42405323019132957 4:-0.667965573810795 5:-0.267026607469405 6:0.7949752815579358 7:-0.07664414977654532 8:-0.6023087644686556 9:-0.659375887511856 10:0.459735946423397 +-4.623091296763939 1:0.08405646515942733 2:-0.40009448092691446 3:-0.39831245310544094 4:0.8794137836499942 5:-0.04788565812369017 6:-0.06763019434549333 7:0.41324877265674065 8:0.39746868847324146 9:-0.986729367280818 10:0.7001677710291752 +-5.782162271139417 1:0.29127970805530157 2:0.6712715787317827 3:0.27575757044478477 4:0.31525054647682804 5:0.6905016168465983 6:-0.5195319089267731 7:-0.06598129860341295 8:-0.5142554034519407 9:-0.11546331150946942 10:-0.2934524891698944 +-9.892155927826222 1:-0.7048583334456604 2:-0.46598491327111247 3:-0.02034722477413209 4:-0.663294196316965 5:0.4485329128582778 6:0.4553619594861118 7:0.7154814909138205 8:0.7532937661147989 9:0.020693077287389894 10:-0.23131986644633207 +0.5422764698408844 1:-0.1513298744027669 2:-0.4591544337339648 3:-0.7192219559850723 4:0.21236658135317632 5:0.12050445497328166 6:-0.42411528242712127 7:-0.15103925528861595 8:0.9032115729799512 9:-0.9228817525021624 10:0.2604090001033641 +4.187800872274017 1:0.3084355607627949 2:0.7029638272178733 3:0.34098344122299573 4:-0.5818421369891376 5:0.1332356708082485 6:0.22671316744441716 7:-0.6750469752494854 8:-0.4065302428716193 9:-0.48213803977370073 10:0.17918596677210186 +4.487701812297124 1:0.8352061350259052 2:0.2757393215770836 3:0.9310504392364667 4:0.519503546762708 5:0.5270245209143005 6:-0.08181154800488488 7:0.5148324302455536 8:-0.6680946101511949 9:0.7574060703813035 10:-0.4721334895419935 +-5.150140984417682 1:0.8113709439821006 2:0.21939305063309278 3:0.02109986546311826 4:0.07450107676582762 5:0.723883853128624 6:0.5392035186380486 7:-0.1382740221237464 8:0.9990201540159807 9:0.10429329766137108 10:-0.1365266408862309 +-6.544633229269576 1:-0.08278037549320039 2:0.6982730989138761 3:0.9090685953368327 4:0.6754092061339365 5:0.5889199822482736 6:0.020678619551471433 7:0.47605785660672084 8:-0.49926771127869873 9:-0.28380077002944093 10:0.5282319276258469 +7.216836352055753 1:-0.8510680074642156 2:0.42611818262128476 3:0.593607821624947 4:0.5635067468583634 5:0.2121930523769171 6:0.2708063180622071 7:-0.31491113345871735 8:0.005990053407278095 9:0.8985259402559085 10:-0.44549339042232794 +20.874246167942125 1:-0.53010692413621 2:-0.9897084749945524 3:-0.9083978261828305 4:-0.15581655583739495 5:0.9974035542095165 6:0.9894717992956665 7:-0.7287287537245402 8:0.06425127137526943 9:-0.06684164745938337 10:-0.3600621883071937 +-6.556192430758147 1:-0.7655958349167471 2:-0.08083170734199419 3:-0.8540636958251198 4:-0.09994429443696973 5:0.1734809016500265 6:-0.29563180244063325 7:0.2158497607364409 8:-0.6071644305523003 9:0.8063426715403785 10:0.47092299197899345 +7.252748885335252 1:-0.36403312429467216 2:0.1237451136826817 3:-0.5756427605741237 4:0.7612833636750866 5:0.9350628314096134 6:-0.012087843264624754 7:-0.03742573515965031 8:-0.05210460803183037 9:-0.5333214800203341 10:-0.013320030179712505 +-9.2679651250406 1:-0.5057250557539077 2:-0.41655319851679495 3:0.1897431234740683 4:-0.038318717640150046 5:0.9136495575471062 6:-0.8890525036858237 7:0.40859501498633377 8:-0.8746985847539293 9:-0.005836984002720369 10:0.7838036026237987 +-15.732088272239245 1:-0.8546867577633044 2:-0.3003980324850013 3:0.49649883896876834 4:0.710496747220617 5:0.5848510480601048 6:0.5714826756665468 7:0.5487975165953451 8:0.5654333402837335 9:0.863539315599626 10:-0.9699410102494574 +-0.20412431312519014 1:0.13323548063028934 2:-0.3030177580658542 3:-0.6358920925969869 4:0.3729380701923921 5:-0.8131818118430312 6:0.11567152703716288 7:-0.3645508535812394 8:-0.5487213252460876 9:0.5605886387366952 10:-0.8400308993051686 +10.445759684895373 1:-0.92707280355555 2:-0.9307772570299944 3:-0.11971873660640964 4:0.5140245291069254 5:0.5751145648836897 6:-0.43850910073502347 7:-0.7872208869913662 8:-0.3087975452145404 9:-0.4645849758749403 10:-0.1563641826381328 +3.349708377102383 1:-0.6334394121009499 2:-0.9008086683014112 3:-0.2678892493467009 4:0.7626514243443427 5:0.6406493676995701 6:0.3669245573649391 7:-0.052050629941784665 8:0.6713394117904852 9:-0.11458974566378233 10:-0.25949626043219576 +-23.487440120936512 1:-0.5195354431261132 2:0.8080357948412571 3:0.8498613208566037 4:0.044766977500795946 5:-0.9031972948753286 6:0.284006053218262 7:0.9640004956647206 8:-0.04090127960289358 9:0.44190479952918427 10:-0.7359820144913463 +-11.827072996392571 1:0.9409739656166973 2:0.17053032210347996 3:-0.5735271206214345 4:0.2713064952443933 5:-0.11725988807909005 6:0.34413389399753047 7:-0.2987734110474076 8:-0.5436538528015331 9:-0.06578668798680076 10:0.7901644743575837 +-3.650649176738987 1:0.9665344025238449 2:0.1395514751689353 3:0.954697162791015 4:0.2093601878355722 5:-0.42841737775246336 6:-0.02877209657213764 7:-0.8382526163632971 8:-0.03773878779258388 9:-0.3751775119106411 10:0.6477987464528951 +0.21915863046310957 1:0.25143109618049353 2:-0.06463696557011112 3:-0.3324862332340037 4:-0.7184623449423757 5:-0.8897217937178385 6:-0.7336278194091297 7:0.8547631637534296 8:-0.7582613025929346 9:0.9080481791309838 10:0.9427850135311773 +4.813247597584681 1:-0.4564689661727537 2:-0.4315414033069003 3:0.09676404446694242 4:0.6024645727173434 5:0.20466090997530606 6:-0.09432916868838737 7:0.6402934161890248 8:0.741842551426011 9:-0.343937669190693 10:0.308871619426873 +-3.0700825038127206 1:0.660084046469162 2:-0.02317305725931229 3:0.7567569356692221 4:0.2528834502236612 5:-0.3935091635208898 6:-0.9965507922509653 7:0.9065754202428946 8:0.6988037588300844 9:0.05145737657924321 10:0.4697377584426863 +9.762542323725354 1:-0.036129448543738896 2:-0.8252508992030534 3:-0.752854859129851 4:-0.9027424488033049 5:-0.4763092428375775 6:0.4832492121777574 7:-0.2935697977919014 8:-0.9197908986231211 9:0.8914359296658816 10:0.8688484670974876 +6.690913813146277 1:-0.7649833946109403 2:0.0419327356721928 3:0.5420954694310764 4:-0.7373259510045522 5:-0.9187577877864708 6:0.6431180783847401 7:-0.6272529754533058 8:-0.43356486537110106 9:0.16848266440424364 10:0.3129700315745716 +21.325049167466855 1:-0.36392795201361383 2:0.846518905511275 3:-0.26361421923150097 4:0.5140384860444887 5:-0.9147771624497878 6:-0.22044646197773576 7:0.14099760779666948 8:-0.546631395802236 9:-0.4345465263406878 10:-0.2759894364167672 +0.41237529640734055 1:0.05016964684797287 2:0.21708512805176072 3:-0.9444942733586354 4:-0.6118772896807114 5:-0.18053631846913665 6:-0.06752556529755416 7:-0.0081819952134361 8:-0.7774039956687315 9:-0.5548994336153177 10:0.7510833121912588 +-15.056482974542433 1:0.6012054064354875 2:-0.6127014811673221 3:-0.8356741843949218 4:0.19830469052767397 5:-0.07726493085289698 6:-0.5756891943805014 7:-0.49010583357941884 8:0.7493759119974515 9:-0.7828994218436376 10:0.6154265137741459 +-2.109441044710089 1:-0.5757976103755722 2:0.3686657403505862 3:0.5418762444017706 4:-0.5896052565388463 5:-0.1000712585735879 6:-0.8114188394866342 7:-0.5863884932327266 8:0.28289838755838015 9:0.5378646921099333 10:0.5063780890366179 +-5.249715067336168 1:0.6828022788286754 2:0.9044668986252975 3:-0.6010464361571437 4:0.8416122052398811 5:-0.9846446498408039 6:-0.3777762313579811 7:0.5763775880953983 8:-0.07608009385213488 9:-0.29576023599575474 10:0.8845728751981716 +6.907770824878343 1:-0.9751352215365647 2:-0.8297271715190588 3:-0.07240311280415779 4:0.4796310183582191 5:0.358213469979769 6:0.4628020211207058 7:-0.9753405605972942 8:-0.765583403709019 9:0.5623611232648877 10:-0.14725965272406616 +-9.299021854126096 1:0.8784076266914045 2:-0.8314918563417382 3:0.8701529449600536 4:-0.8070129727442199 5:0.07396877198841345 6:0.0040889707225901795 7:0.40529205456687145 8:0.6412485325027342 9:0.1443450351498905 10:0.404997568726581 +10.95643670126225 1:-0.37321642594676097 2:0.47766490569544473 3:0.9201313123144423 4:-0.649393433578801 5:-0.9084894063674787 6:-0.2547160991750408 7:0.7674649994523459 8:0.646056370118979 9:0.6014100713287893 10:-0.15130291862509182 +-2.6397202393123336 1:0.3285252466844373 2:-0.2714281159811125 3:-0.5869561846815805 4:-0.5643935541712441 5:-0.7285201267315389 6:0.6502951074428092 7:0.8611880383193904 8:0.6380425291162128 9:0.5118538704085516 10:0.4012684110865874 +12.521131042032012 1:0.4843931319727355 2:0.06440853455169626 3:-0.6151259240105509 4:-0.4180928328467284 5:-0.4607061773323424 6:0.8104775289268906 7:0.3284199695768064 8:0.8425028998495565 9:-0.34822319854822825 10:0.1969239149176112 +-16.151349351277112 1:0.7787909191620395 2:-0.5219981442072688 3:-0.7230569918898555 4:-0.05707801168212101 5:-0.8134225824740247 6:0.09950684183685454 7:0.6261274830059296 8:-0.9502006765164366 9:-0.6724983095526844 10:-0.600347212281825 +-5.039628433467326 1:0.7680701397575322 2:0.7956844224408437 3:0.4131717201035916 4:-0.3127895385265915 5:0.7226571953995224 6:-0.06845863083031967 7:-0.1007291660029832 8:-0.9130249132342207 9:-0.4605180615474036 10:0.42093879298156 +9.007596502870785 1:-0.6562175566238462 2:0.08420074013217049 3:0.589801949672486 4:-0.11964901133703987 5:-0.8145711913860048 6:0.43854302140351065 7:0.5992967124729605 8:0.253745043289755 9:-0.10742030998120033 10:-0.5993228348160153 +-12.41094640284016 1:0.31035917086763765 2:-0.8053417167237813 3:0.5754655536186164 4:-0.3645388095106201 5:-0.9135176753316416 6:-0.8690739610562535 7:-0.14039224825138197 8:-0.7112835675593987 9:0.25762942117230825 10:-0.9483300117501923 +-12.130353212287929 1:-0.41404309625298485 2:-0.7695984204591535 3:-0.44569447239245275 4:-0.3168863099965644 5:-0.26669244730409036 6:-0.33484042698895755 7:-0.41062396946367685 8:-0.09075804785640385 9:0.8511367190902208 10:0.021918606255194595 +-15.375857723312297 1:-0.9794952880997945 2:-0.9547237660069134 3:0.2460912345929791 4:0.3174335823329406 5:-0.23758562926743054 6:-0.113610303129287 7:0.18292675847568063 8:-0.9656446754474337 9:-0.58300134324846 10:-0.6689602908128025 +-6.397510534969392 1:0.440780662587545 2:-0.03737991637410243 3:0.9506435891605849 4:0.8177486462589998 5:-0.2917628929963241 6:0.42365289098031034 7:-0.4280555544979745 8:-0.18388426864865903 9:0.5057230088452542 10:-0.1699163749308643 +-9.789294452221961 1:-0.25066699970459694 2:0.1772977344415987 3:0.5913498268900952 4:0.6293756431864681 5:-0.6430441015863757 6:-0.7238519180293621 7:0.13639541626580498 8:-0.6620281401715837 9:-0.9515237061912034 10:-0.4333426289849791 +-13.15333560636553 1:0.3491978525665129 2:-0.4067353159374012 3:-0.8677040612253524 4:-0.5757086910974862 5:-0.3186886816681207 6:-0.06609938943414573 7:-0.5419747642754873 8:0.9632759660044383 9:0.2673520823110991 10:0.36463236596724546 +2.2307697392937795 1:0.12285527276472785 2:0.8938323722714365 3:-0.16995870341610209 4:-0.3298643049714254 5:0.16781582791954253 6:0.42381594687105895 7:0.9245288214717629 8:-0.08709025093361689 9:-0.14227085487682722 10:-0.2888302862659746 +5.892885365508635 1:0.10116053019915738 2:-0.41641547074900154 3:-0.3750004290914961 4:-0.5619470211369917 5:0.33343039544460384 6:0.46766042657994733 7:-0.6937940929321615 8:0.7044604392055189 9:0.8879353764416567 10:-0.5490902425042639 +-16.692207021311106 1:0.9117919458569854 2:0.628599902089868 3:-0.29426892743208954 4:-0.7936280881977256 5:0.8429787263741186 6:0.7932494418330283 7:0.31956207523432667 8:0.9890773145202636 9:-0.7936494627564858 10:0.9917688731048739 +10.454641756541454 1:0.3490213088098768 2:0.6103387992494194 3:0.6753935651135747 4:-0.39560763769937934 5:-0.3042308221531884 6:-0.9283481899557042 7:-0.7904038212853011 8:0.37488335848537346 9:-0.296477977723397 10:0.30894819444660304 +0.08978797103855778 1:-0.13445409764877803 2:-0.6404150831493631 3:-0.24740260669490133 4:0.031151119464385646 5:0.9207882173498612 6:-0.6146471129497393 7:-0.9736175690408087 8:-0.2673180325645341 9:0.5800384183301572 10:0.479811220263183 +1.7362099941626894 1:0.5171681395917551 2:0.6177735922313075 3:0.6446678302226738 4:-0.5731769722311459 5:-0.2686270617709168 6:-0.6048534221658814 7:0.7002124303669326 8:-0.1479765297345712 9:0.009254061109394307 10:-0.31519081920853287 +-1.0349488340235453 1:0.612980711993536 2:0.05771318707554962 3:-0.10821368362160744 4:-0.8755559420458141 5:0.42566546089913326 6:-0.7966341558699277 7:-0.45253617234374466 8:-0.8289517557653971 9:-0.8968075137250837 10:-0.6325457096866376 +0.10157453780074743 1:0.9143592240573388 2:0.06419631741815457 3:-0.9961326744227916 4:-0.47174548800139715 5:-0.0821464027819967 6:-0.5495006555498168 7:-0.5627911401420294 8:-0.43426056724099005 9:0.892026786364895 10:-0.23546485121284055 +-12.92222310337042 1:0.218687524173371 2:0.013626751799176162 3:-0.8372219908323961 4:0.6197296846266354 5:0.7429130827811232 6:0.48009972886541896 7:-0.35667717521227904 8:0.18337067878780533 9:-0.22935396092245197 10:0.4076715024284059 +22.923352376063196 1:-0.7522075505725567 2:-0.20686029838909326 3:-0.1386664769095396 4:0.157117595808127 5:0.9462377653889174 6:0.9182504509330662 7:0.18170057747293833 8:0.27735387813088863 9:-0.6355799944714868 10:0.9764849106195284 +-6.132450015997121 1:0.2822534275343054 2:0.2625905791399692 3:-0.02565260641304068 4:0.4891221076432757 5:-0.6426178913585772 6:-0.8999539149461033 7:0.12659507663825287 8:0.5889572439755832 9:0.49107548332672857 10:0.47595749470452 +-9.173693798406978 1:0.4430245286298278 2:0.9923116639471541 3:-0.5609082824097824 4:-0.36542266258313916 5:-0.5814039716882617 6:0.20413852042674874 7:0.6097541611931963 8:0.5743002479324253 9:0.4735459963431561 10:-0.053969823043886755 +-5.814408490931223 1:-0.9206287328000513 2:-0.48298486023273157 3:-0.8477202041890262 4:0.5801385102362351 5:0.7146074564553095 6:-0.5987672678579339 7:0.6829077928212723 8:-0.3522788540815065 9:0.7729595638821951 10:0.5264904880591215 +6.474329501040298 1:0.6914309300550991 2:-0.4507700505202725 3:0.713821440501512 4:0.41599059910235847 5:0.507160951750409 6:0.8635615811574222 7:-0.6235518270244333 8:-0.5336201820384283 9:-0.7989630679361768 10:0.837293162455248 +6.984517471584806 1:0.16745919469723392 2:0.018033079961716103 3:-0.7339201095541323 4:0.17042828693740697 5:0.4493471632580528 6:-0.8938445962323078 7:-0.3206968104792325 8:-0.616617071238893 9:0.9327878222034172 10:-0.6575294247048245 +-12.479280211451497 1:0.9769767754725367 2:0.7706430863248943 3:-0.4506244622476816 4:0.12921761745628713 5:-0.0697804449658812 6:-0.7702703569987461 7:0.017734558413919688 8:0.7216294158911261 9:0.42547357862241886 10:-0.9001915116155741 +2.8363866587728186 1:0.11478724114928918 2:-0.4679790550082039 3:0.2344912687736711 4:0.5524878060045462 5:0.5252859884051309 6:0.5080674087215156 7:0.5010449021825665 8:0.048046765816400105 9:0.06654581719548891 10:-0.5801934713347348 +4.186809777233374 1:-0.02335342201396018 2:0.9035437912091193 3:-0.9283585631882163 4:0.454351316397237 5:-0.6948564428085262 6:0.11495485234890368 7:-0.23683956078769963 8:0.6442534752881419 9:-0.013866407845647188 10:0.23369602940650736 +2.8235031660626415 1:0.5609344938188046 2:0.3449103464885612 3:0.03972169049525687 4:0.31858762565827137 5:0.4409953589124853 6:0.22836189275697016 7:-0.1497811991899889 8:-0.23248048920679265 9:-0.30066618281100177 10:-0.9247232456911632 +6.96223432848425 1:-0.8160398553437558 2:-0.8212180893749699 3:0.7728655115832999 4:0.02387973088796369 5:-0.043499804905828166 6:-0.6997726250046865 7:-0.8686633773265577 8:-0.12597318402253976 9:0.967018116368416 10:0.5951339624149812 +4.669684795838683 1:-0.32226903644852833 2:0.5465858078942492 3:0.5228467793266189 4:-0.013157722224545143 5:0.5810668818928995 6:-0.1372653090293532 7:0.6446157527288279 8:-0.06005754873230629 9:0.014302180040152379 10:0.43474245441042636 +16.112744845653285 1:0.37257742858083365 2:0.19398954512844124 3:-0.11860882189887478 4:0.6492510749703395 5:-0.41273736981203313 6:0.18643017041815835 7:0.29136917186214384 8:0.47602883023389 9:0.7126916980867937 10:0.48462508659691483 +-9.196003366226202 1:-0.7263358951920722 2:-0.8503799288093836 3:-0.3120563620589105 4:0.3925562655164563 5:0.027666662972283484 6:-0.35173134138805406 7:-0.32703527910354757 8:0.3060102722285065 9:0.8609161725740202 10:0.33394557004432923 +1.242972458167591 1:-0.9029238804456814 2:-0.6392681059531908 3:0.8940879647942577 4:-0.8807357173896475 5:-0.13628130467470512 6:-0.5487534785116224 7:-0.40270307148061346 8:0.09152108686997096 9:-0.20745066734844642 10:-0.20624830574384978 +3.453659210660726 1:0.2710596844435682 2:0.6510497900145247 3:-0.2899158136103117 4:-0.13531811694554707 5:0.6965847786422426 6:0.9105343028780231 7:-0.007340232468413754 8:0.7672537187738411 9:0.3538906829188173 10:0.35387524540947646 +-0.48115211266405217 1:-0.17943755364759517 2:-0.1384979591151625 3:0.8425773648797268 4:-0.43234064993405097 5:0.919754442523921 6:0.8390197802990036 7:0.43890653121452683 8:-0.7647648217789051 9:0.14770258954363835 10:-0.6681813635676657 +6.965069440749298 1:-0.9158261471030473 2:0.5228494114644282 3:-0.07760531122743153 4:0.6154296244963067 5:0.5231830145381096 6:0.4892535590799165 7:0.1987053183082137 8:0.9995670294711712 9:-0.2020375688074112 10:-0.7853579334836087 +-1.6896486293598596 1:0.4638529147853421 2:0.0953805943546191 3:0.8506904243225251 4:-0.028262644692445438 5:-0.9462342015500664 6:-0.6934738957112123 7:0.601125018257533 8:-0.04871041957758315 9:-0.015245062056267411 10:0.6119856200040805 +-1.763729644326212 1:0.5376618752928528 2:0.8062119856717131 3:0.44996834959923593 4:0.9917728248530817 5:0.5974717482179492 6:-0.406972851600659 7:-0.8523198502065281 8:-0.3076377139692321 9:0.9099974915864462 10:-0.43374966692373484 +9.012829566937228 1:0.6885456531832366 2:-0.0631164354373237 3:0.8394182300770314 4:0.7207913383891218 5:0.4715324450375691 6:-0.34417503908167757 7:-0.31448279255342126 8:-0.020591617987411936 9:-0.37668573574418107 10:-0.6528048324896532 +-15.951512565794573 1:-0.6112828771933607 2:0.4867007149846869 3:0.863494046941478 4:-0.7292072742454481 5:0.6338749652624007 6:0.5980798993978542 7:-0.5119002889878654 8:0.8394383182101366 9:-0.1412423080445726 10:-0.15838730884968655 +-0.29622788243318465 1:-0.9436253326661384 2:0.2907259958032098 3:-0.1530538226933904 4:-0.6174176535420375 5:0.8209632215649141 6:0.5060548803172731 7:0.8212448453211292 8:0.33506684706740386 9:-0.5408309869188785 10:-0.8105966349150977 +-7.683213587039055 1:0.2525015766703558 2:0.6417869320191234 3:-0.7569571597336913 4:0.5265130776924394 5:-0.03992944660560949 6:0.18292946303778823 7:0.4286344960738724 8:0.9158523573288766 9:0.5039796366711773 10:0.27660486075533797 +3.9061298856792797 1:-0.6501789225392032 2:-0.6040685518173872 3:-0.6448094322678659 4:-0.2019498832769746 5:-0.5302977370883424 6:-0.010754341856880067 7:0.8791702222974846 8:-0.2283571791337704 9:0.4726320486679656 10:0.3413255179758332 +12.928385148211825 1:0.7793178379505685 2:-0.5207562047491976 3:0.37253320760898934 4:0.7540757518052998 5:-0.679378421540417 6:-0.11966022036636881 7:-0.4317798870297489 8:-0.004211291952602059 9:0.39024653887361693 10:0.45391057946097146 +5.787566514603203 1:-0.20596730554338039 2:-0.8840796727164746 3:-0.749416279057892 4:-0.5511023306046077 5:0.9941631901218697 6:-0.09907966722992234 7:0.701617914811792 8:0.9696055014561289 9:-0.7083648075748707 10:0.5781111533720358 +5.701262468657861 1:-0.7066995012593675 2:-0.6756815056791965 3:-0.5720277255842998 4:-0.09218662060241067 5:0.21494136076896653 6:-0.37012884573008153 7:-0.6828277646796448 8:-0.10038134655965236 9:-0.46253754509583356 10:-0.20813933595648115 +0.9473494330088033 1:0.6876806675510589 2:-0.9530860102792402 3:-0.4043172626863887 4:0.6696455505098386 5:0.17863581804857254 6:0.1944646561635497 7:-0.5283662172535679 8:0.4872263841818012 9:-0.2882651789318431 10:-0.06293411605141874 +-2.6834375589185675 1:-0.22376759986120187 2:0.36555755546798885 3:-0.5223502955721961 4:-0.20702347869224624 5:-0.7745351063999764 6:0.22879328233099971 7:-0.5440007473902635 8:-0.6959483071829207 9:-0.131433881760733 10:0.2764225554693165 +-3.2766108642276146 1:0.0304613976530983 2:-0.3148062986719251 3:0.24950420590071953 4:0.7152023826801459 5:0.9656885739650887 6:-0.3210562623763835 7:-0.7305896664502614 8:-0.49074917893875836 9:0.7802670253347352 10:0.8667409958355992 +-1.1838791995691869 1:0.06642047806096318 2:0.5336148776806793 3:-0.6199614859883396 4:-0.15342280723497237 5:0.8407250402808968 6:0.7060811811107444 7:-0.2913182140909305 8:-0.5925203360011633 9:0.22644925021629692 10:0.42395071889002467 +-1.5856680515554806 1:-0.8724712788102853 2:0.11445744032031424 3:0.5483166457680566 4:0.9469521544884028 5:0.2541682828467746 6:-0.436750733871873 7:-0.9001249399695319 8:-0.7555793441458385 9:0.06946992897983018 10:0.9724148045760346 +-13.039928064104615 1:-0.558607026518148 2:-0.7356765018678253 3:-0.7547644426290201 4:-0.24898664843938745 5:-0.3606374046883567 6:0.5836652368902306 7:0.8497678666873467 8:0.21331875915717635 9:0.3558733809635668 10:0.9642603628738968 +-17.428674570939506 1:0.8562209225926345 2:0.7077202100653552 3:0.7449487615498371 4:0.4648122665228682 5:0.20867633509077188 6:0.08516406450475422 7:0.22426604902631664 8:-0.5503074163123833 9:-0.40653248591627533 10:-0.34680731694527833 +13.886853032969585 1:-0.6354915752033683 2:-0.9132338112681755 3:-0.4816479770266455 4:0.5448417181244594 5:-0.6250746297187781 6:0.7410618768880199 7:-0.18029029550083675 8:0.777358236920447 9:0.9625064189449102 10:0.048040935468046 +15.61684729251139 1:0.2980237970192188 2:-0.8160931971814265 3:-0.29649852157138445 4:0.3896688599904572 5:-0.17552110506337826 6:0.8721328328445139 7:0.48984799668438916 8:0.9984496052876473 9:0.9665885195526289 10:0.8966559812150274 +10.33625540376971 1:0.09939495068155724 2:0.9790332181038015 3:0.9483428886275702 4:-0.5717299810793317 5:0.4876405069057712 6:0.163962913892302 7:-0.4095537988924203 8:0.8608269751255508 9:0.010028680058212114 10:0.9095786494455713 +9.706032970113723 1:0.7687898546315146 2:-0.9825109379412285 3:-0.5423211794439926 4:-0.3099509487314134 5:-0.11561305536236333 6:0.9012327035409926 7:0.5257495475790148 8:-0.33804422025989433 9:-0.144428735681567 10:0.28019332199039604 +6.189043888072968 1:0.13246655756059478 2:-0.751192382628302 3:0.2233421456265161 4:-0.1933575076984373 5:0.8681727702736863 6:-0.7656847407654899 7:0.1033145549916572 8:0.33909210370257403 9:-0.22241363302770267 10:-0.14479004187830435 +-8.680225911784335 1:-0.07718769939880432 2:0.6702228057326558 3:0.6647810334933819 4:-0.05115658747070784 5:-0.850780588302118 6:-0.040961453376221924 7:-0.8407690297644956 8:0.33775829053563156 9:-0.45421556034898547 10:0.8238500771967823 +-9.42898793151394 1:0.8925906426831107 2:-0.6771269725125597 3:-0.11635105688280678 4:-0.7266044201050157 5:-0.6902918845825077 6:-0.5911234800910024 7:0.49395074569300657 8:0.43660804414878274 9:0.8736983081269782 10:-0.8001177058312081 +8.486245765579415 1:0.5614295382716652 2:0.3972427851719582 3:-0.276268504977494 4:0.7803448249454739 5:-0.358957923558495 6:0.3477822689529795 7:-0.7944805581842691 8:0.8356932134547437 9:-0.4783293647580624 10:-0.2522633417723845 +-1.8722161156986976 1:0.11831037290857482 2:-0.7309091607574014 3:-0.7339122716951587 4:0.2046641765436359 5:-0.9914679283125301 6:0.13518339528098555 7:-0.9760821540963867 8:-0.6080636193563043 9:0.3890502262427238 10:0.33864957953815145 +0.5122357093733743 1:-0.9555852441641726 2:0.4754771858792488 3:0.3743376249200432 4:-0.2651772997462427 5:-0.7915484529586028 6:-0.7575915279708862 7:-0.10432268807273859 8:0.021604934223709238 9:-0.6458011732912265 10:0.40773716196391674 +-18.845922472898582 1:-0.6031480148285926 2:-0.8736524730197766 3:-0.311456616524979 4:0.420921703897325 5:-0.2904011177124777 6:0.6683252350591937 7:-0.3436202976676894 8:0.5023604359385605 9:-0.33056149241985633 10:0.5168854058825227 +6.492106438811399 1:0.7824832256885428 2:0.6105456307389117 3:-0.0436873997963223 4:0.46730493583332855 5:0.2057529813440686 6:0.5738310686722767 7:0.6307964411259019 8:0.6208424783086652 9:0.8931894299284251 10:0.7164648197763028 +-1.6472226859532182 1:0.8854767145642171 2:-0.8175744681485637 3:-0.14894858038610903 4:0.9667400540136402 5:-0.3575837217508149 6:-0.9211342680517054 7:-0.956785876301889 8:0.6558217028031554 9:0.8014538160668165 10:-0.9475520920917395 +0.185861229793925 1:-0.8181719548530746 2:0.9990094335332504 3:-0.8195848911987829 4:0.6991933015233858 5:0.07295718417836583 6:0.5968996100546737 7:0.4871410306452193 8:0.2980483098540927 9:0.779953293728507 10:-0.7978867112395516 +-5.973450525185694 1:-0.975435413991927 2:-0.7832951303253313 3:0.5098999023442101 4:0.46795978867990007 5:0.2538986807863044 6:-0.8182887550010198 7:0.8335391734637112 8:0.4286082996234335 9:-0.1726765956719154 10:0.7649845978453362 +-12.773226999251197 1:-0.383327656965585 2:-0.9439560491389036 3:0.25039001869622446 4:-0.9342091044843222 5:0.8711023711291135 6:-0.6027135241543655 7:0.9456874780319795 8:-0.243290468946338 9:0.625765915285031 10:0.5160550067618355 +24.290551295953957 1:-0.8368553572749229 2:-0.5859456648150321 3:0.873779532007048 4:0.7462623178738954 5:-0.08133011570245352 6:0.36767541461776676 7:-0.33129619282275047 8:0.6104289727615573 9:0.9416581563055089 10:0.18201841676606856 +14.490247980976621 1:-0.4765937762114507 2:0.16430711839945555 3:-0.526776940706293 4:-0.6802269991653915 5:0.40748236413299344 6:-0.500290139207977 7:-0.31915972151663885 8:-0.4586068416002418 9:-0.15572660263944127 10:-0.32925702602833073 +8.377230871265601 1:0.44141613060964846 2:0.1582267687752743 3:0.8760950367284166 4:0.40434058393690364 5:-0.7063758409891474 6:-0.616055773516162 7:0.996372393127579 8:0.6142084876085476 9:-0.528320587432094 10:-0.2815909691094802 +-3.2987560995836653 1:-0.4600479783378091 2:-0.04201794336103326 3:-0.8934505203905587 4:-0.44991326751905536 5:-0.5220579476363783 6:0.46060949186328703 7:0.9169289030735643 8:-0.022458426893944283 9:0.08100795210565637 10:0.5726732415540354 +0.3422568955736137 1:-0.9888686059817204 2:0.22752298580182706 3:-0.5048696915520232 4:-0.059433420464226616 5:0.7823831512651716 6:0.9865977573980389 7:0.9164100011124972 8:-0.3638554550863984 9:0.3038282907667611 10:0.4652367033461571 +-8.24116881862084 1:0.7565819250331731 2:-0.3733277500524168 3:-0.8841150081071696 4:-0.922282989989148 5:-0.041520813551309876 6:0.8615967014876558 7:0.8474207144091339 8:-0.7518437864641427 9:0.45076605239968837 10:-0.48912984167595375 +-4.367083147104942 1:-0.276459380002813 2:-0.957555271384241 3:-0.3761632810202544 4:-0.3897414804149022 5:-0.3133861519856074 6:0.0777990809172171 7:0.6638552243422928 8:-0.3477312155364247 9:0.5934885465182675 10:-0.5238903641193555 +1.9280240152322783 1:-0.40051093785549696 2:0.5070348672240661 3:0.7506759969575532 4:0.5042104954516786 5:0.9959688260926507 6:0.4657024999761399 7:0.910611131925299 8:0.9836517468598804 9:-0.6263172749113686 10:0.16955852322929155 +8.918138317441574 1:-0.22407391224687023 2:0.5545084933214972 3:0.6335932367683528 4:-0.2786481116648991 5:-0.9549992830441785 6:-0.5577873948545062 7:-0.960657200286197 8:0.3709573488946196 9:-0.9191180485753339 10:0.5033478020271929 +-5.657796797481157 1:0.6359910361030725 2:-0.1742637774815281 3:0.39699327107265137 4:-0.9841991491194473 5:-0.622093571871533 6:-0.5433497301426455 7:-0.6731178481686009 8:0.930615153085582 9:-0.3065877908950827 10:-0.5456093749639228 +8.697079562319692 1:0.4815820396629933 2:0.1173457441514223 3:0.7313645402039386 4:0.3354835387237334 5:-0.10300554535074702 6:0.5116687640761355 7:-0.8850803659104614 8:0.10654026377571157 9:-0.864976708975602 10:0.01345035085413615 +0.033954684723234596 1:0.6703241653088159 2:-0.13447915740201166 3:0.026022550037831937 4:-0.5145659862194116 5:-0.6963587636078901 6:0.652083884947352 7:0.22644722530715278 8:0.2671580129293405 9:0.9659035105360283 10:0.9547989197693989 +7.359108382166921 1:-0.6855762478384229 2:-0.7543318537260015 3:0.4772611975128618 4:-0.5588002332845741 5:-0.24271386844336496 6:-0.28595644325868896 7:0.8732728098501104 8:-0.8026384804471058 9:0.7589508830210041 10:-0.9992933613402135 +4.953597303754355 1:0.8915633023548608 2:0.04688596266450751 3:-0.26866754730613374 4:0.16694236975718102 5:0.23465297255622608 6:0.36488427850844407 7:-0.06717041145276781 8:0.9470029805221898 9:0.32483835237272674 10:-0.7892521260150298 +0.683536559775105 1:-0.32176084249781556 2:0.5446298870866526 3:0.4095848716057642 4:-0.42579711490120187 5:0.4482850543749355 6:-0.0982243826242506 7:-0.9190317048427039 8:0.06234509402976718 9:0.21327512416175054 10:-0.38023673796734525 +-28.571478869743427 1:-0.4597184465402242 2:-0.5489429386926741 3:0.33422914572951634 4:-0.15992695377395516 5:-0.7310003311728188 6:0.18241063863467488 7:-0.48385214010599453 8:0.08139879039334552 9:-0.8401239538877046 10:-0.8896372220209929 +-19.884560774273424 1:0.4619217451285318 2:0.28157115824800005 3:-0.3829811521605375 4:0.5802544015450464 5:0.1117061271473403 6:-0.8926034502584623 7:-0.34862293810401956 8:0.2733254857260612 9:0.6514176550598809 10:-0.02758604919357066 +-17.494200356883344 1:-0.4218585945316018 2:0.15566399304488754 3:-0.164665303422032 4:-0.8579743106885072 5:0.5651453461779163 6:-0.6582935645654426 7:-0.40838717556437576 8:-0.19258926475033356 9:0.9864284520934183 10:0.7156150246487265 +-15.86200932757056 1:-0.6341453831788726 2:-0.9259180639727085 3:0.302702923864538 4:0.749555004323947 5:-0.7932989575334761 6:-0.5620972938631934 7:0.020542041027870717 8:0.11610338700447698 9:-0.7912600154897766 10:0.5108307672038874 +9.027804254487519 1:0.1746878011084212 2:-0.5872807344913673 3:0.6018547246457264 4:0.5106104933121229 5:0.7329523371170135 6:-0.40058771577765895 7:-0.48753463550174025 8:0.34308791976318 9:0.3407668956765344 10:0.5964472848798394 +15.949172086880687 1:-0.7790584545657173 2:-0.017224094786103317 3:-0.0974907790179953 4:-0.10287391996036166 5:0.6007953354774878 6:-0.7032497754397848 7:-0.36068070856329437 8:0.021391994204512432 9:-0.6509100388083549 10:-0.5410899936281377 +-6.151586699415245 1:-0.5318094974022525 2:-0.830796057445983 3:0.603828597318087 4:0.6660892552257192 5:-0.18529748408390523 6:-0.47166833767648986 7:0.592915541856605 8:0.9944601563352204 9:-0.6981606574244703 10:0.34942553665003584 +2.010398523297265 1:-0.9293899922307269 2:-0.07588009904844029 3:-0.8500855420709359 4:0.12191867923536615 5:-0.528778681165414 6:0.3117086447237414 7:-0.4222963938187163 8:-0.03247894950300623 9:-0.05387792412717962 10:0.4053568741659812 +-6.749023248121471 1:-0.9875370165216966 2:0.7137693455001415 3:-0.2510160963160164 4:0.8732150877079123 5:0.49658934612905314 6:-0.9817012857861731 7:-0.2045309437850289 8:0.7562713668333418 9:-0.6787434327188155 10:-0.6147932888026117 +4.452639829999693 1:-0.35256148944834176 2:0.7581152951164591 3:-0.37755890552299265 4:0.9480813371197343 5:-0.3419340388717347 6:0.3487602851799074 7:-0.5576726724270562 8:0.4899696188087421 9:0.563074979676983 10:0.7865891460062227 +-4.938733988900586 1:-0.4108386466193119 2:0.3287655432069885 3:-0.5853553038038923 4:-0.6480591422742821 5:-0.4787998161299789 6:-0.5828003484675421 7:0.42835744317623003 8:0.8378098987706633 9:-0.5645180498703375 10:0.28981512694646705 +-3.373242544176224 1:0.04989033652617936 2:0.6575826440927308 3:-0.24028051935833128 4:-0.6649808138961095 5:-0.6530198970442704 6:-0.19331254127919362 7:-0.6743004878881749 8:-0.7214986105015062 9:-0.30648035516261385 10:-0.6455097687924254 +-3.2843694575334834 1:-0.3548536057581908 2:0.7350125943559394 3:-0.3635282827378974 4:-0.8552820154885781 5:0.9140879208466111 6:0.21870365067770892 7:-0.17738543429561382 8:-0.052851966578491005 9:-0.36066059517759097 10:-0.9020765799355679 +-3.277146077677404 1:0.910961221014513 2:0.4302525202590246 3:0.11079959840001119 4:-0.3614188274820125 5:0.5080231397310961 6:0.013940825892631237 7:0.33583012240022403 8:0.5008797094229163 9:-0.663083147090173 10:-0.0865028013627418 +-0.202246147968096 1:-0.4929308143227653 2:0.8374300027105082 3:0.08763999085193186 4:-0.499738438136623 5:0.5926071511295365 6:-0.5135396038023627 7:0.6946715869746543 8:-0.5184428793490325 9:0.21753085495829239 10:-0.33796308746585235 +-7.1237150573506955 1:-0.8506203499039495 2:-0.6581804183622855 3:0.6484205342724825 4:0.013914696389758285 5:-0.6214530117645831 6:-0.011163110491807293 7:-0.6025372583334574 8:-0.0371573886520411 9:-0.7933455929226487 10:-0.38653838674273455 +6.298226129171093 1:0.7304191211928768 2:0.8128475475660479 3:-0.03161148630216015 4:-0.6018899317958344 5:0.19277055729934367 6:0.3002272616310928 7:0.949169758830406 8:-0.1011823256970481 9:0.16093341376629966 10:0.9596833606094763 +14.906594657519511 1:0.5053240355803015 2:0.6775698974866082 3:-0.6194771000646291 4:-0.02876927004033525 5:-0.5481504206112477 6:-0.9239150546263386 7:0.471216755072994 8:-0.0027794620943384363 9:-0.8954411386878227 10:0.8991742143686698 +2.1710965297686267 1:0.4578509053930304 2:0.9270194505165124 3:0.22470373699901236 4:0.21526179917432753 5:0.5299563895862103 6:-0.5824108997775908 7:0.03801922095671095 8:-0.5164033454609385 9:0.4370246809487237 10:0.6514133050988229 +15.05806598279517 1:0.48645077410559057 2:0.7821442063987365 3:0.1943681666933883 4:0.8289246958621577 5:-0.08034311437806041 6:0.03709694472527203 7:-0.895481297246602 8:-0.42921579749551664 9:0.5447075872378688 10:0.844397849728866 +-0.4683784136986876 1:-0.5083135683360327 2:0.626070365769088 3:-0.8737725909401557 4:0.725622293853621 5:0.0018794384199978253 6:-0.9343604622552886 7:0.6655593328822609 8:0.47501755618845753 9:0.8388618477210947 10:-0.5143806767304449 +5.823027255871114 1:0.08635467091841886 2:0.6314532702073175 3:0.8862069437865836 4:0.6542025864928516 5:-0.6846784290231471 6:0.048487096050569445 7:0.30828004933669395 8:-0.49438881988995687 9:0.5706936923061823 10:0.037705651885639346 +7.03779380408974 1:-0.07193682621291098 2:-0.5816975957307158 3:-0.8426927090342973 4:-0.37504851992255306 5:0.4473129018316815 6:0.3101938194888525 7:0.6160050428837607 8:-0.913998555949695 9:0.40461966540531313 10:-0.7581141330823786 +-9.770500546345563 1:-0.31358873581579894 2:0.11771478839130278 3:-0.3404842110585631 4:-0.0604362797252429 5:0.2159524972176814 6:-0.24737863017398087 7:-0.8541428610709716 8:-0.06753562283135062 9:-0.11567537916769255 10:-0.5606246203677223 +20.000154367451547 1:-0.344717847914646 2:0.8454969480099985 3:-0.58856299370874 4:0.5884510299634649 5:0.49162879631128553 6:0.7958075013181658 7:0.7781911267315837 8:-0.6780885011989877 9:0.9797694629597928 10:-0.1872163682079866 +-6.239848349456753 1:0.9132793720646253 2:0.1680340663118458 3:0.01740115925682284 4:-0.26580395408599133 5:0.28551914590761074 6:-0.9939706142381568 7:-0.8740927279520219 8:-0.8731218126652498 9:-0.10993630739903892 10:-0.3069565039708746 +-4.173072569004537 1:0.7864835254860851 2:-0.5614522227484218 3:-0.7718396381376464 4:0.49508673889127985 5:0.24030155936964714 6:0.8080778221819038 7:0.05395496402881128 8:-0.3045148076729973 9:-0.6134406357458853 10:0.7447268183581948 +-11.328415936777782 1:-0.10183127796258096 2:0.5689039487721601 3:-0.07015335898840225 4:0.23254189629731292 5:-0.3226974656715038 6:0.2859450214054784 7:-0.4916677058012495 8:-0.27564895614732055 9:-0.9416483232894219 10:-0.7472248333434015 +8.719164753818454 1:-0.8231424386390782 2:-0.03953537069863633 3:-0.3271580541537027 4:0.892192314973022 5:-0.6759017192358232 6:-0.419591686354591 7:-0.23967385135363606 8:0.936992531568956 9:-0.12946409158671512 10:-0.9082863469271643 +22.31738046492344 1:0.37030851555335365 2:-0.06654751559177563 3:-0.5759425437665169 4:0.9179952251152963 5:0.8628921839116359 6:0.8421952184405965 7:0.9625804174561126 8:-0.03075332253237728 9:0.12227386374957994 10:-0.6243390357793757 +-1.189108450798179 1:0.5681776913545951 2:0.46049028271139436 3:-0.366463711956754 4:0.025856437432560275 5:0.7547565372954261 6:0.5506193192167212 7:-0.6279807084274867 8:-0.38698884324386107 9:-0.9885778854008227 10:0.7814740172261654 +2.8767042393531965 1:-0.6841229745503388 2:0.6252203895646273 3:-0.6737644654353572 4:-0.7321040107741059 5:0.3162570540986238 6:0.6211089085315002 7:-0.33984617437403464 8:0.1227089818682312 9:0.04586594421613177 10:-0.4679977358965799 +2.783332151730615 1:-0.39148258540779013 2:-0.3037233649803406 3:0.7955133548911926 4:-0.1729544208044842 5:-0.18247049275020033 6:-0.1315085429729259 7:-4.447133918370483E-4 8:-0.805837119503338 9:0.11574866650006688 10:0.8517519041042676 +-8.99205564094827 1:-0.45501536967706535 2:-0.35829694693457914 3:0.775695048377375 4:-0.25331195582275745 5:0.15524612858817055 6:0.7400717904631442 7:0.8382485596668376 8:-0.5619009369436814 9:0.4386801597659249 10:0.09960232210246622 +-9.808386702564658 1:-0.987404834666963 2:-0.6732308850750186 3:0.5528285725528492 4:-0.8796302275267409 5:0.30705569958232193 6:0.8635312232105203 7:-0.14033675947074187 8:0.5516086773506235 9:-0.7487899106678442 10:0.8851518933134919 +4.948281656077033 1:0.4331269064492329 2:0.4628446087354616 3:0.33730748244242537 4:0.3473124014683382 5:-0.1707966473106064 6:0.8558057784524846 7:0.1390312032172829 8:-0.7918343112673001 9:-0.85993782695915 10:0.33563174747577107 +10.791261476321019 1:-0.5417345768902055 2:-0.06334901799780424 3:0.027652223245870466 4:-0.9881487640651161 5:-0.19441123027957707 6:0.40295156581142355 7:-0.8315553696517317 8:0.11405283165483926 9:0.5377980570161418 10:-0.24581620554740824 +-0.7287230169119936 1:0.33985587202063283 2:0.6841261099887705 3:-0.9441564997438197 4:0.28660913255058906 5:-0.7597915572726905 6:-0.8535957517473378 7:0.609134673753593 8:0.29636368731717977 9:0.05791523580926916 10:0.5589907965230858 +-26.805483428483072 1:0.4572552704218824 2:-0.576096954000229 3:-0.20809839485012915 4:0.9140086345619809 5:-0.5922981637492224 6:-0.8969369345510854 7:0.3741080343476908 8:-0.01854004246308416 9:0.07834089512221243 10:0.3838413057880994 +-16.71909683360509 1:-0.24375714099465773 2:-0.11915875769929496 3:-0.3741442802364221 4:-0.3812947578178094 5:-0.7032156297055756 6:-0.18339122712542388 7:-0.8634662520461855 8:-0.714561692659166 9:0.020558676493369177 10:0.22804428969949986 +-8.822357870425154 1:0.39332200105884363 2:0.5652370435795515 3:0.6220479966351453 4:-0.018976695481651484 5:-0.6868425195058918 6:0.2029750380170401 7:-0.5550873767310935 8:0.16864133648532342 9:-0.008843355054633628 10:0.6472547984399621 +0.36392761004065594 1:-0.9059630492963144 2:-0.41039282402227384 3:-0.006673269562094131 4:-0.4989314017618798 5:-0.17726034513032318 6:0.037764439388023874 7:0.30703957185016595 8:-0.09040426404909185 9:0.38661451965066274 10:0.1630571642147851 +7.415902871490132 1:0.188586850708651 2:-0.33013604761672566 3:0.6667976416858177 4:0.8537064956198137 5:0.03971370422819254 6:-0.43229195778759966 7:-0.9607154505216515 8:0.8413204878098277 9:0.40010565279599897 10:0.7306602852367441 +-4.129456164370826 1:-0.7967510984807558 2:0.545111159425699 3:0.16038228447433012 4:0.6311115528116698 5:-0.01985759480036542 6:-0.9516543115476572 7:0.18022912194075458 8:-0.2177157123823752 9:-0.5433158910016767 10:-0.4603867691069983 +-9.211066571082247 1:-0.3611235296125135 2:0.1402619601475985 3:-0.23132525512647795 4:0.5534401725834837 5:-0.34978585787763206 6:-0.24147682088922773 7:0.8089009287617064 8:-0.09075864922490862 9:-0.05759391404550773 10:0.3371306765964468 +6.52392916461972 1:0.19122050285976044 2:-0.625453376800498 3:-0.26804961781489856 4:0.9669297468261109 5:0.9142504122291741 6:0.7678963028488108 7:-0.6852943621882759 8:0.5898129788981794 9:-0.6580947533327339 10:0.46875109532259396 +-12.46765638103286 1:0.35148385951742633 2:-0.5206883134357769 3:0.35436280451876345 4:-0.8837833467474128 5:0.3433887284719144 6:0.3914771858025621 7:-0.17813796710416252 8:0.6553344538056296 9:0.3721548243590813 10:0.9442185832979726 +-4.937258492902948 1:0.9150659354384785 2:-0.17085510578573548 3:0.8233227233543232 4:0.2539669132090434 5:0.18955049451212935 6:-0.2833188558310358 7:-0.48483747414616496 8:0.8917378487725669 9:-0.13169122011498646 10:0.9815059855284158 +-0.5233425797210233 1:0.4238363705720569 2:-0.18363058784066522 3:0.2949874786744968 4:0.12235592695567354 5:-0.9746310186182559 6:-0.8990867637441311 7:-0.8580982328464586 8:-0.7930887027205957 9:0.16757307988090275 10:0.988861929608575 +-11.904986902675114 1:-0.3692990475534952 2:0.32166293883244323 3:0.3401547722249436 4:0.10009747375878408 5:0.7598877208920192 6:0.2853003389082669 7:0.22880221701675074 8:0.4521491122351502 9:0.33222018268933895 10:-0.9500018867461919 +8.324969054805921 1:-0.48086111720736513 2:0.3705524122401185 3:0.43635448766342133 4:0.6544321903349255 5:0.059000747296945155 6:0.3328036763371236 7:0.9609146376298034 8:0.5943082361322021 9:-0.3074246170581105 10:-0.6763916655761453 +0.21701641918233017 1:-0.29449708766806304 2:0.040640346437143426 3:-0.6524819533513639 4:0.37482287233702394 5:-0.29800608396043216 6:-0.537030944860492 7:0.2862394027536084 8:-0.3783043133672048 9:-0.5292179323972728 10:-0.09583783955916791 +-6.84977373580439 1:0.825136109631339 2:-0.5722868691442817 3:0.11048134523744757 4:-0.5946054293068455 5:0.28061485657354823 6:0.9135611623885838 7:0.35590421873954603 8:0.8943562249941011 9:0.4183378981109729 10:0.5714160298247304 +-11.039347808253828 1:-0.9620263418414967 2:0.22669065740934724 3:-0.7378036492234086 4:-0.4460191511609126 5:-0.2594476006347024 6:-0.989879976130936 7:0.762096015449097 8:0.6983868222083149 9:0.8729993459982626 10:0.3426647417451305 +-5.882860061103163 1:0.5247178959769465 2:-0.6217169944869176 3:-0.13640714414758315 4:0.6608201052790283 5:0.5789945243704264 6:-0.12686057623612612 7:0.7277882307863026 8:-0.47949544949858236 9:0.9781208432412936 10:-0.8980068284379361 +23.52945433069272 1:-0.12339549394875426 2:-0.6769524283089239 3:0.9324962870874394 4:0.28956947294105206 5:-0.2957355479338608 6:0.7504385350771912 7:-0.8769262306643106 8:0.41591311300668155 9:-0.7694611231426498 10:0.9885110924181837 +19.043184423383824 1:-0.13783178628851878 2:-0.853631844645959 3:-0.12792415583066052 4:0.6936898387576049 5:0.8488563282318959 6:-0.6530521292304581 7:0.27832187660440666 8:0.09838048719062442 9:-0.5913230087557231 10:0.260839433107553 +6.83105883806984 1:-0.9085282656519695 2:0.65203708247844 3:-0.687580071985604 4:-0.045008726377529173 5:0.4762107922777967 6:0.15939259525248506 7:-0.46363191848939334 8:-0.25856682230410266 9:0.313842004143269 10:0.5042938214484851 +-9.409197719620593 1:-0.34356198962701945 2:-0.06381545064099514 3:-0.9332814619122063 4:-0.2629675367181199 5:-0.03876014002851913 6:-0.4606936151803749 7:0.49272969757318563 8:0.5550196351479111 9:-0.1758425343811718 10:0.20285868144226837 +-1.3101852978323116 1:-0.3740821549570985 2:-0.9788976137554464 3:-0.6078739734947245 4:-0.8007745980271539 5:0.7381298546055934 6:0.7407750458109124 7:-0.7711351008178868 8:-0.9895256155202141 9:0.35793767138197174 10:0.6589909255086295 +0.5180809608973377 1:0.19289850282287446 2:0.6301214514538145 3:-0.15311307199521518 4:-0.8607670552113709 5:-0.46422067276745316 6:-0.29812862604449464 7:0.519464836430044 8:-0.9480450997338103 9:0.973503038633444 10:-0.7843880226794626 +1.9947872601406775 1:-0.15799682110486057 2:0.22645891561571352 3:0.3141842574216682 4:-0.36086019480721676 5:-0.1429373936064291 6:0.8097261636650581 7:0.11764088861630029 8:-0.9151998265501957 9:0.6536711690904891 10:-0.17232697113157425 +12.352290000973428 1:0.8176113135335772 2:0.39342616792621987 3:0.44011948797971234 4:-0.4412435869837865 5:-0.24509203724837314 6:0.8636655043434542 7:-0.4251583124505798 8:0.2068056615503988 9:-0.3501114760443049 10:-0.23701353324739483 +-2.891643319177732 1:0.7722403010820704 2:0.7994121584045861 3:0.18520464815273208 4:0.7273575609391227 5:-0.3758589216283552 6:-0.7598404862373955 7:0.5748649410179301 8:0.6897988099260968 9:0.5638920860629713 10:-0.992567809902162 +4.803737144054077 1:-0.7367711178556622 2:0.07370548192399351 3:-0.5510509754264419 4:0.11949095653894504 5:-0.7723751845800411 6:0.6450480728551136 7:-0.9508825019800493 8:-0.3250395411575804 9:-0.24913562167143777 10:-0.3617439870343031 +5.051689886526102 1:-0.09854955786627007 2:0.5298224514703289 3:-0.014996634675966236 4:-0.4462048687049027 5:0.22912790083984547 6:-0.513533454471272 7:0.1452771069237353 8:0.371152210841464 9:0.9204732090987018 10:0.7472990716905279 +3.8591142298280476 1:0.7532169023970261 2:0.8291433156934658 3:0.9255891263525324 4:0.3248663809949248 5:0.9905320652281553 6:-0.10383453745167626 7:0.8519246838852608 8:0.6024015353989258 9:-0.06958036249881938 10:0.5862142389541998 +11.30005914221598 1:0.026411858067972194 2:-0.6968445330429607 3:-0.8194566946165238 4:-0.12780659247925996 5:0.8406393783194903 6:-0.24617182945415128 7:0.30199973460219853 8:0.6062457235841974 9:-0.19314055910416927 10:-0.48313233883372964 +-10.288657252388708 1:-0.7388306404020344 2:0.07753617971873439 3:-0.5735498713988352 4:0.2183581175474576 5:-0.873572721679176 6:-0.8788755575751708 7:0.7087858362905568 8:0.7126712562404713 9:-0.7607334319316799 10:-0.4627367552114916 +4.895250842405817 1:0.9772954128558484 2:0.6020087399988574 3:0.16946626176056134 4:-0.011334492807484997 5:-0.5391845039589362 6:-0.4315843612118535 7:0.9065130011032458 8:-0.4860160207844919 9:0.0921755607946162 10:-0.022200673265013515 +1.0479421939727227 1:-0.055436367433274514 2:-0.6710483362647659 3:0.9222786043047919 4:-0.22005981623386184 5:-0.8141845044113469 6:-0.31766631447334226 7:0.6067696845798944 8:-0.1445661385071555 9:0.9172271611227454 10:-0.8079554780561127 +-9.754451457291598 1:0.533713237587885 2:0.6499588942067549 3:-0.49188790503368285 4:-0.6925119436487435 5:0.3345265979579788 6:-0.8117849521672496 7:0.9312055115656304 8:0.3273803451149724 9:0.7567478475677727 10:-0.6256676928549367 +5.869027126482974 1:0.7273823383600513 2:-0.2519813990388706 3:-0.8239584025397881 4:-0.13749750031735974 5:0.6142824732416132 6:0.6251630800232315 7:-0.6138240706157267 8:0.7210396245391326 9:-0.41832155201953714 10:-0.8965988320689853 +9.14234252751227 1:0.7295320896113133 2:0.6150271212503227 3:-0.9785024737101733 4:0.30006672036705506 5:0.11703528191771406 6:0.2971639460196238 7:-0.7920108995168815 8:0.32649036066184567 9:0.03522428067355543 10:-0.1766251898148803 +-5.643698771141404 1:0.27360638280623983 2:-0.6124401810442446 3:0.24950528730210886 4:0.09920211684887548 5:0.7187490549286091 6:0.6212724115415782 7:0.5864634211269566 8:0.114951165007104 9:0.44859258949094283 10:-0.3768352371578665 +12.781643819428492 1:0.9144335582094396 2:-0.4579872615218674 3:-0.6521934534632468 4:0.4462086111316512 5:0.240360283350179 6:0.23974046479581124 7:0.4840439971437822 8:-0.7250363120037027 9:-0.29769496257362094 10:-0.3382859512018359 +8.393556738722923 1:-0.8263387132502396 2:0.9434824094966923 3:0.1607861709872136 4:0.15217100448798782 5:-0.6517945935711484 6:-3.354731073326178E-4 7:0.07846631386981562 8:0.687844846942889 9:0.9277854407325892 10:-0.8855380268588307 +-15.348871155379253 1:-0.5734707274250155 2:-0.2526008551945753 3:0.23752094195309925 4:-0.7074613963298721 5:0.4674168537545218 6:-0.3198997855552628 7:-0.10415974108745596 8:0.5616912699671224 9:0.43742425558560694 10:0.19732530755184596 +13.138260063721448 1:-0.9415220143797984 2:0.6015431361268124 3:0.38898046240229545 4:-0.5750448371021175 5:-0.5803995196333898 6:0.11772198725731342 7:0.7512685244060366 8:-0.6683465740662857 9:0.9515652825318053 10:-0.32405935964523547 +-26.736207182601724 1:-0.47083104147202404 2:0.28748860067800597 3:0.007399318769021113 4:-0.8189013750589702 5:-0.5156633937248272 6:-0.9906928746525896 7:-0.8848419810272337 8:0.2197280161306785 9:0.12855082514870197 10:-0.7862803985146845 +-20.212077258958672 1:0.5609065808412279 2:-0.9201904391147984 3:0.908305865183735 4:0.9255146658282842 5:0.6871419344095282 6:0.4201876217923466 7:-0.42906289792612684 8:0.5787691868233418 9:0.7260522064761288 10:0.28251641556690554 +-0.44652227528840105 1:0.37640618494870504 2:-0.20012451052963542 3:0.9420894309510319 4:0.4218728633972739 5:0.5551974480349577 6:0.07615991810462619 7:-0.12409220462011294 8:-0.22212591926375946 9:0.21160498862483723 10:-0.6092792830633924 +-1.9481059746438067 1:-0.43820030250217457 2:-0.6836588417639442 3:0.733018205278934 4:-0.6564348753121718 5:0.7333385435136448 6:-0.5577457688360317 7:-0.31035811050608975 8:-0.7189201447768139 9:-0.7629842028723994 10:0.7179459779331092 +1.1951162998609508 1:0.19541555859727744 2:-0.4796785506546435 3:0.14123852670749248 4:0.7161847585887089 5:-0.2502765085719578 6:0.8815667909545981 7:-0.6418691905513725 8:0.49600147195728783 9:-0.3091837674381053 10:0.4320162841463153 +-8.99125390483227 1:-0.01183888602092864 2:-0.5901829024081027 3:-0.4343074406380647 4:-0.40450313056290166 5:0.05269590196351448 6:0.733631212862198 7:0.9575176715505025 8:0.5974628692830348 9:-0.20284241796038271 10:0.9577348510907686 +-7.955533026930219 1:0.6104830760481679 2:0.5915483572646505 3:0.3275427350991458 4:0.48361434056132424 5:-0.9466590639056058 6:-0.24662428438925743 7:0.9856361456534972 8:0.9434155212648045 9:0.3466736921968707 10:0.12927980558284102 +-12.500773785355054 1:0.5733321361720694 2:0.39154119830075085 3:-0.9347116355607772 4:0.0920586614926524 5:-0.6959457183810456 6:0.2136579936466858 7:0.17595268059814395 8:0.8828168055200465 9:0.18934277314853398 10:0.7565908584660754 +-11.43180236554046 1:0.082018621904135 2:0.9074181204118958 3:0.46125595008850273 4:0.40328845936169966 5:0.7803064691948824 6:0.20802011482729377 7:-0.41368899649077284 8:-0.8997565495498339 9:-0.1880483213318005 10:-0.15538597634233264 +-5.055293333055445 1:0.4442675297698402 2:0.19045719972922193 3:0.4877438951288897 4:0.7984474402420494 5:0.3251350777349489 6:-0.18676050499673869 7:-0.2701840041572374 8:0.4486609996458524 9:0.5403637876036615 10:-0.8971614841211264 +1.0276485382241776 1:0.7953696703382547 2:-0.3245779681908927 3:-0.3507435626548021 4:0.9510986059491036 5:-0.8655491074076527 6:0.20729233888498677 7:-0.43078300089533594 8:0.19504657032168216 9:-0.3173814102187291 10:-0.042479969052890754 +9.690201571311908 1:0.16852987139559206 2:-0.2514893273405625 3:-0.9993240281686275 4:-0.2166013247997891 5:0.33294165754921234 6:-0.5824203831560628 7:-0.15253642946648616 8:0.3547892367555441 9:-0.047604356104869794 10:0.9229112136183077 +2.2591036039970347 1:-0.9919593184325572 2:0.6323551392201245 3:-0.20815293136790447 4:-0.002395046469600759 5:-0.5015903362190326 6:-0.16698803749234048 7:0.7901657583805675 8:0.33755402936964973 9:-0.3707337678548108 10:0.6995480653730146 +1.5130881908855742 1:0.973710432688613 2:0.6518972988019702 3:-0.16491318496856833 4:-0.6066757853095415 5:0.8762371591845273 6:-0.9056066630820714 7:-0.3388079327070965 8:0.3934146060660142 9:-0.8756168865642253 10:0.9522427911640303 +4.023618949132531 1:-0.14974626191548301 2:-0.5874962377709136 3:0.6780439909311404 4:-0.37291203746764356 5:0.08104034602232169 6:-0.4706923395029945 7:-0.8924577368048239 8:-0.3363784341297067 9:-0.4139746050396018 10:-0.5107600309932907 +-2.8674162893420965 1:-0.7554383289076523 2:-0.1355597928418868 3:-0.3891904246986413 4:0.43949832438341785 5:-0.43859957095446833 6:0.37548094528561093 7:-0.5228633291549518 8:0.24169710795100352 9:0.7131753590746546 10:0.03458176767001042 +4.661164232198611 1:-0.12738868751385546 2:0.9446285809821182 3:-0.17981416859193433 4:-0.7535879975625193 5:-0.08594548726529161 6:-0.9983154486609989 7:-0.7272748852665216 8:-0.8197811039616518 9:0.5177610923333253 10:-0.6180731281817853 +-0.12347625601866746 1:0.10820547757674692 2:0.1825421454873002 3:-0.3412486258429426 4:-0.14925445930975534 5:-0.6594599831395103 6:0.9552502376248448 7:-0.7875626067291472 8:0.3854984181307912 9:0.014303876202374832 10:-0.7300443667550689 +14.546296184422973 1:0.2459523985646046 2:0.9434777073825811 3:0.2112745925235362 4:0.7730688005214974 5:-0.13727994893203732 6:0.6140037510172511 7:0.7545298281668846 8:0.7814551909982614 9:0.0026683642139069264 10:0.5633973602849358 +-19.66731861537172 1:0.9353590082406811 2:0.8768609458072838 3:0.9618210554140587 4:0.12103715737151921 5:-0.7691766106953688 6:-0.4220229608873225 7:-0.18117247651928658 8:-0.14333978019692784 9:-0.31512358142857066 10:0.4022153556528465 +18.84119697288412 1:0.4423204637505467 2:-0.4364821709544735 3:0.3935363893778452 4:-0.7750286735195999 5:-0.6981814766625978 6:0.6889512553826111 7:0.3646791168217727 8:0.0023536025493677837 9:-0.08378048150085249 10:-0.05659381771155503 +17.40329212914592 1:0.9155980216177384 2:-0.35593866074295355 3:0.44775710780914824 4:-0.42914421567532357 5:-0.2734430718503955 6:-0.8937042912745483 7:-0.3143761936611371 8:0.07805814979426184 9:-0.31386151509289784 10:0.6202932236456253 +-19.402336030214553 1:0.462288625222409 2:-0.902975525942725 3:0.7442695642729447 4:0.3802724233363486 5:0.4068685903786069 6:-0.5054707879424198 7:-0.8686166000900748 8:-0.014710838968344575 9:-0.1362606460134499 10:0.8444452252816472 +-3.855123203007599 1:0.5072557393175969 2:0.4626973233672753 3:-0.20910077161652119 4:0.9431415515135266 5:-0.1293690767585638 6:-0.2033835058111637 7:0.501429131658198 8:0.175133281735671 9:-0.6091682952201736 10:0.543010689352589 +1.493768355655548 1:-0.7772812666041105 2:-0.7743738591348672 3:-0.2848754060915175 4:0.3336846848765145 5:0.6219572132443736 6:-0.11144657683793624 7:0.7606913325884337 8:0.8547085151723017 9:-0.31728444617771134 10:-0.4668474022688931 +-17.803626188664516 1:0.5176340000264179 2:0.23048377874011128 3:0.6162746928601832 4:0.16908590014785418 5:0.9695207469685181 6:-0.34713218673384705 7:0.8526833760069625 8:0.9895592279649763 9:0.8805561957342884 10:-0.43452438291417894 +1.4060200157931342 1:-0.41964471941333525 2:0.7738486114171979 3:-0.0964606192284374 4:-0.25351781452566025 5:-0.21065389913054244 6:-0.40490416354122916 7:-0.7696501777959646 8:-0.7710488116813146 9:-0.6777228721053572 10:-0.09381158095961428 +-17.026492264209548 1:0.8367805314799452 2:0.1559190443625338 3:0.048200110551483544 4:-0.7340083467235765 5:0.2661150265782781 6:0.3881661781792165 7:0.9485287302765621 8:0.7201540574376382 9:0.8509234862656003 10:0.9658114866648093 +8.729450606651499 1:0.6404862166906327 2:0.16516090922657822 3:0.29013117743588057 4:0.37056732180613317 5:-0.3376494575302882 6:0.9012625630650577 7:-0.42150978319487 8:-0.05630249989686087 9:0.706104255632954 10:0.01935884085365225 +-5.516822117602276 1:-0.5718348423045241 2:-0.2145777722920088 3:-0.09307467998835195 4:-0.7311274103678378 5:0.5272184003067053 6:-0.00528176138162495 7:0.2852826178935919 8:0.6180999884045897 9:-0.7526372151008776 10:0.20416472532830543 +13.001541259752251 1:-0.5137703877272299 2:-0.15452359837207896 3:-0.25657600903152744 4:-0.9773110735601165 5:0.0718147980090178 6:0.18965211809311744 7:0.7795354990363292 8:0.21976898743223638 9:-0.20364089221752524 10:0.33822332985943304 +18.443388694564348 1:-0.9278344397401963 2:0.2678538727090136 3:-0.46932389854374734 4:0.8494176173177825 5:0.45765527018197694 6:0.20546395745879287 7:-0.199860294349123 8:0.47798730134403256 9:-0.2279771893187592 10:-0.30836118564314274 +8.952089112152663 1:-0.7371671220953286 2:0.8160149639986789 3:-0.026630089188139028 4:0.5931015267817183 5:-0.12216243475451294 6:0.161290795125286 7:0.7423016751095652 8:-0.5212872902985852 9:5.606147011660845E-5 10:-0.409626733921443 +-3.7062463981908027 1:0.5633514321449928 2:0.9914900963311462 3:0.1867799930236702 4:-0.15960235736142847 5:0.1204791067384241 6:-0.7733281422620872 7:-0.887447048141158 8:0.7931515335800692 9:0.732289882696125 10:-0.034992898370363124 +-10.58331129986813 1:0.6627003739767989 2:0.10688718810947728 3:-0.49230090744757216 4:0.8936580036513948 5:0.012227929286241057 6:-0.1442038886014838 7:0.9203452040795139 8:-0.20719832624131262 9:0.29561869366253335 10:-0.08597725084864649 +9.818996211259908 1:0.580133516885796 2:0.07422424429848573 3:0.33438634998226924 4:0.26054797992533696 5:-0.8771304726537796 6:-0.9710990591964794 7:-0.1869287393875041 8:-0.6167738073093247 9:0.34401921428837245 10:0.6737600514607418 +-11.87816749996684 1:-0.7193071334885193 2:0.5247127705364141 3:-0.02978727198197606 4:0.18353223007701058 5:0.40350110058596944 6:-0.36002841871228686 7:-0.20781535546501528 8:0.5517883176456557 9:-0.9938027872744732 10:0.6245061418135955 +-12.198096564661412 1:0.27542314155961156 2:0.3459734388741733 3:-0.38737776987446937 4:0.6244101669171684 5:-0.7801218302490938 6:0.20444733666197523 7:-0.5667599464182904 8:-0.9462131580071358 9:0.5576565405741785 10:-0.9307557040059242 +-3.6610413123521357 1:0.045569951437504086 2:0.32203961277046145 3:-0.04228927426053675 4:-0.9435304938416831 5:0.3750509710699601 6:0.21298970117620142 7:0.5491054691791977 8:0.33695088608872203 9:-0.9923500858828505 10:-0.6402707119893463 +3.782742149409224 1:0.7795250611996376 2:0.43296979846218275 3:-0.6481485005937841 4:0.3235717281667645 5:-0.8067382770768907 6:-0.06740397503468509 7:-0.2835017205434338 8:-0.5875853498478532 9:-0.25699561837680585 10:0.7813561594373908 +-17.065399625876015 1:-0.01772446594568744 2:0.563282914714494 3:0.14232420381013955 4:0.031667902604941345 5:-0.7815348482900619 6:0.3657733497576803 7:0.7208326162626688 8:-0.7863253120180662 9:0.3329194167867533 10:0.6175752945608013 +16.23248797654815 1:0.2615647748812251 2:-0.6631801348538622 3:0.6420349382574477 4:-0.31980528388089846 5:0.38021930887251365 6:-0.060298437830818896 7:-0.8911652782989568 8:0.3424617259589986 9:-0.8515350749364614 10:-0.42354709676980207 +-5.015963911416578 1:-0.07890564237014686 2:-0.09864377281008885 3:-0.13139943914680408 4:0.6610949669857866 5:0.06777579108221987 6:-0.26586245727222835 7:0.17443498956808612 8:-0.3129854922817781 9:-0.37913757211269505 10:0.7627186373372121 +22.647750304177556 1:-0.03666997412165163 2:0.49691867674483814 3:-0.45898559472166967 4:-0.09932248891016404 5:0.05692910907689508 6:-0.5006743461081364 7:0.9992936758550379 8:0.8252525466172065 9:0.9431711015127009 10:-0.4891497061921315 +-3.731112242951253 1:0.44353490207818513 2:0.23112032838224117 3:0.4697682541445527 4:-0.7507514828346664 5:-0.06323257550543837 6:0.0997091431243109 7:0.9394036761509628 8:0.4103869738859962 9:0.6564209227640914 10:-0.5427466755921158 +0.6761872737225261 1:-0.30051626190360503 2:-0.26699232020158803 3:0.8668758741279379 4:-0.40325291744583347 5:-0.9756425738484267 6:-0.5116398654634617 7:0.16424789009043073 8:0.8034099442414044 9:0.8554935001446193 10:0.42747702930667497 +8.449247195197387 1:-0.6588765973399024 2:0.2502285196526799 3:-0.20481547024283087 4:0.3770725284683252 5:-0.169707887761277 6:-0.0804075502584003 7:-0.3580757176408007 8:-0.6042549664471129 9:0.360349278976142 10:0.15899650901110962 +27.111027963108548 1:0.7106841652047162 2:0.6853699382312817 3:-0.8076297545289823 4:0.7932321056591545 5:-0.8011085095234463 6:-0.7017292726737878 7:0.10568649778064154 8:-0.40755358264969255 9:-0.061008981132773865 10:0.08895972651409556 +27.78383192005107 1:-0.8378790218922778 2:-0.6651002504721837 3:0.021049638665430415 4:0.32994334871293196 5:-0.7981304887988308 6:-0.2947962117284566 7:0.9739408711845776 8:0.9442893181893954 9:0.010541491359981059 10:0.8332791453382604 +15.700710963871254 1:-0.538773982400854 2:-0.5966426806845984 3:0.14570292467314627 4:-0.5937791901212952 5:0.7779251136963325 6:0.9962962075803357 7:-0.4774083823748394 8:-0.02528476957876369 9:-0.17305036341254398 10:-0.6013841506503688 +-12.558575788856189 1:0.03250364930617211 2:-0.6723950859659307 3:0.7090474884514901 4:0.25034305882632735 5:0.7036774024093582 6:0.622650236684523 7:0.5776881238206741 8:0.7999754726258337 9:0.21332972563833508 10:0.33849062947231645 +6.2776776518215955 1:-0.009605588630256623 2:0.5786496865369053 3:0.9208276908400748 4:-0.9477397424337148 5:0.6306053656362194 6:0.5396434662389846 7:-0.9841930450269964 8:0.5492682920407823 9:-0.020767248025529206 10:-0.8684655435686472 +6.424586997399564 1:0.861374923392324 2:0.8356037964367176 3:-0.7173479824827564 4:-0.6309584820438245 5:0.16136758138471285 6:-0.7485184163431866 7:-0.006053583829132236 8:-0.8762221084691306 9:0.19195377669247726 10:0.07259634302552964 +-9.64772485466405 1:0.7568015336230662 2:-0.4221524485756756 3:0.011711847664269248 4:0.7387065048724242 5:-0.04347512566745104 6:0.06642100869974654 7:-0.6993705848315939 8:0.16312217088045422 9:-0.11975577990989916 10:-0.6188717473788392 +3.8183706502283647 1:-0.7226937936463145 2:-0.5462756960199258 3:-0.39158419906610664 4:0.014310440945434433 5:-0.9950315917350652 6:-0.1844037449550875 7:0.9023517651879036 8:0.7948752060508435 9:-0.6792702010973877 10:0.40730074403235617 +1.1585019476700562 1:0.5575546848694 2:0.8997032130006739 3:0.6088643323129037 4:0.4872893656051758 5:-0.03977520372748922 6:0.3202565433572042 7:-0.31231768645537206 8:-0.6861153669592381 9:-0.08561643820383291 10:0.522243657731251 +-8.18651039877047 1:-0.809069379967462 2:-0.04827229852445103 3:0.19963602092982624 4:0.2568971171641006 5:-0.0015346733366310428 6:-0.6104625526166494 7:0.7746715041233412 8:-0.7343750018341593 9:-0.49272635466510106 10:-0.8115191199688623 +-3.377690136019927 1:-0.9408187510685164 2:0.9654993263332854 3:-0.16725010447984268 4:0.2574069587853294 5:-0.6930506968932861 6:0.11124762075550176 7:0.39145805505914866 8:0.2906495128462767 9:-0.27454907309824916 10:0.9001175309434777 +12.692571815413245 1:0.7404426710258791 2:0.9060576634778448 3:0.7023712021897308 4:-0.9808126157768493 5:0.03447666475715194 6:-0.4146339211599541 7:-0.7329651749553896 8:-0.2696019807317358 9:-0.9885367164723897 10:-0.8540304023043486 +2.5111054050889354 1:0.7448154454968356 2:-0.7532143233138027 3:-0.9724617436335079 4:0.662620399592766 5:0.45517204589358307 6:0.37409736074838684 7:0.337245076577648 8:0.50951903847353 9:0.2590369923587328 10:-0.3248257475117191 +-8.300340493749207 1:0.5504850435404609 2:0.5077232940244447 3:0.778859307357816 4:0.2601916883813373 5:-0.0032275666062382413 6:0.039752927221862855 7:0.19468432568826755 8:-0.2859531554546477 9:-0.4113477962970582 10:0.43272011953041667 +5.904938653193952 1:0.6622293273002955 2:0.6428891633785236 3:0.6999663090423285 4:0.9132698742913088 5:-0.3960072336866507 6:-0.14500922264286054 7:-0.4390171033743564 8:0.002067106212897185 9:-0.6079874251539117 10:-0.7131416109696531 +5.004048239623824 1:0.7212309895357449 2:0.3425199843383353 3:-0.7290323633040705 4:-0.5563097960397918 5:-0.7577898297822001 6:0.647883070472203 7:-0.23710559062843073 8:0.34398507133293954 9:-0.5440251617348038 10:-0.2971638032112218 +6.21255598077158 1:0.2498685983586959 2:-0.2586857335205359 3:-0.6380810501916263 4:0.17008841621855852 5:0.9485802018202867 6:-0.2580306792121272 7:0.032916516140567786 8:0.32950951532163675 9:-0.9291915084526683 10:0.8454021164786922 +-3.741044592262687 1:0.763300390779396 2:-0.1832552896771813 3:-0.39361907876758573 4:0.9050768615040607 5:-0.8850093869496836 6:0.9302208653737598 7:-0.12972094056755412 8:-0.459442486378308 9:0.5044112394875107 10:0.1399067554681861 +7.378402183384303 1:-0.27686808475610114 2:0.12735524561214606 3:0.5216635958678004 4:-0.9418584785460469 5:0.20441570818728771 6:-0.35073421178920583 7:0.7847501694079704 8:0.3222999552829353 9:0.21025696511089764 10:-0.5813710201294744 +-7.1500991588127265 1:-0.1945259148773102 2:-0.4089845159829022 3:-0.1971859124232922 4:0.9531447983295496 5:0.07996455700202221 6:0.17013529724757648 7:-0.2442095218739362 8:-0.8564146371721229 9:-0.5843910532907555 10:-0.33846471424918767 +-4.288417758202577 1:0.020710986120182184 2:-0.7450564238727908 3:0.3674992023059285 4:0.46737461414601555 5:0.9411702705113052 6:-0.7257365059912877 7:0.5813280037560231 8:-0.01567531846894843 9:0.24734195293533467 10:0.6516001002566887 +5.916426037500391 1:0.8260000862135342 2:-0.11324162495165968 3:0.13061304369435334 4:0.5762591624576425 5:0.548049763999644 6:-0.9751599851764361 7:0.02828821483057764 8:-0.4113286027346803 9:0.8912856976307486 10:-0.8470910204808244 +2.431004294471012 1:0.14088576701299083 2:-0.45104190898994734 3:0.29891134031619115 4:0.955503074037666 5:0.15962522624750242 6:0.7664481093046553 7:0.051697815479792686 8:-0.3471787155014081 9:-0.8007151537631465 10:-0.5598899500902301 +-16.08565904102149 1:0.3946137229565083 2:0.8443779319638349 3:0.5116855547320893 4:-0.5319339991982652 5:0.26564506849312797 6:0.18905397829944448 7:0.1976357098053687 8:0.15505612242632538 9:-0.935633748308776 10:-0.9782957013204887 +18.058440348477184 1:0.8402487524597533 2:-0.6200725197687718 3:-0.6158487677192792 4:0.0709328308135515 5:0.7501256905495493 6:0.38092209802839583 7:-0.8192579128383128 8:-0.9304002828581583 9:-0.6570300818845025 10:-0.5252554781538985 +-1.0026720160736349 1:0.46122079684901474 2:-0.7609201036934166 3:-0.9372178059537293 4:-0.25391036498391006 5:-0.7487429157699828 6:0.38024314675291637 7:0.21886059803198576 8:0.027516853267765207 9:0.33483464322377765 10:0.618580130027746 +-2.6688695419207162 1:-0.8775911623423445 2:-0.6647410420697879 3:0.05948516302547313 4:0.7278526664475804 5:-0.011366224409705028 6:0.33475665968289436 7:-0.6386120399761575 8:0.39609772177595115 9:-0.7872076290319412 10:-0.6195857302948329 +-13.867087895158768 1:-0.9114780602695882 2:0.7997695296649912 3:0.8337252417804881 4:-0.7927267913881113 5:0.6863829853181673 6:0.4162562153517635 7:0.2659922421074139 8:-0.551994669040742 9:-0.6403900338772157 10:-0.8680387717518072 +7.826011095515239 1:-0.2881951904396949 2:-0.19317071325391022 3:-0.06581062483451183 4:-0.6074074436315555 5:-0.9434740067975405 6:0.9426572655575483 7:-0.1812629432036228 8:0.39425575292939863 9:0.5065890539615039 10:0.8969825696966649 +1.4213836206303339 1:0.6996840540120932 2:0.1283999569152492 3:-0.2537375462472613 4:0.24772110606788456 5:0.9040210381745799 6:0.47062010977660207 7:0.9697678931927365 8:-0.9215764371674713 9:-0.27541598110075793 10:0.44277003247067803 +-0.973650798730175 1:-0.2121645467631068 2:-0.6770222508071349 3:-0.5733067523949165 4:0.27979529516037105 5:0.7128588235545461 6:-0.9208763636184307 7:0.14128337151047532 8:-0.002851660400375433 9:0.6943908711123281 10:-0.9201922993121072 +-0.17500848560451965 1:-0.6015070903427717 2:0.7815998200409671 3:-0.9932006200204946 4:-0.3303953411379028 5:-0.3329917860768894 6:-0.2822852019877604 7:0.6834785385197197 8:-0.6458607648553825 9:-0.06171476054995373 10:0.11421513352405444 +-15.310980589416289 1:-0.35290763483001486 2:-0.7263565311032778 3:-0.8688987069582226 4:-0.991098319894185 5:0.7029028082332363 6:-0.20251284356518684 7:-0.10928416773360117 8:0.307764663956116 9:0.6423143148384418 10:-0.15527637175127107 +3.260298266762908 1:-0.7817510582064782 2:0.45336200757318257 3:-0.15365670773321338 4:0.5063951567230205 5:-0.7102867196895872 6:-0.48050036620725955 7:0.9838016675169072 8:0.07854601230194436 9:-0.18953694857147863 10:0.19370072527454107 +3.846123583197846 1:0.6665586449040093 2:-0.2894063530813835 3:0.29965348483445386 4:0.23590344101670313 5:-0.7456743720187828 6:-0.4680876353446175 7:0.8106301610699425 8:0.691280702194663 9:-0.6060141408622055 10:0.34018639920235194 +-10.945919657782932 1:0.7669971723591666 2:0.38702771863552776 3:-0.6664311930513411 4:-0.2817072090916286 5:-0.16955916900934387 6:-0.9425831315444453 7:0.5685476711649924 8:-0.20782258743798265 9:0.015213591474494637 10:0.8183723865760859 +9.820049725467145 1:0.9582163993327679 2:0.7503905881505508 3:0.6255110430336392 4:0.6522701954798096 5:0.09248037700932144 6:-0.2833482854986902 7:-0.9841968940607242 8:-0.9343780716625845 9:-0.605526104070818 10:0.6000165028195326 +11.398715935456183 1:0.6605086903456443 2:0.14675454515266395 3:-0.7880053589830274 4:-0.8570785944515658 5:-0.4317693974151271 6:-0.12244918233307645 7:0.9808241653220866 8:0.5455853515046201 9:0.6870972425676756 10:0.7427686762232875 +-7.846310147695936 1:0.4355817642106965 2:0.7659504362110916 3:-0.3784171977305315 4:-0.5675896574776877 5:-0.20116390539973938 6:0.8775467546326667 7:-0.2824903364469842 8:0.7470660314619617 9:0.8967783051712528 10:0.7133700339519966 +-1.3847391232663768 1:0.3707613476850027 2:0.6931092598460797 3:-0.7701621508103305 4:-0.5679366502518555 5:-0.7234356749703683 6:-0.8059255104944509 7:-0.8307993875388229 8:0.6133975694770035 9:-0.7399749904168824 10:-0.1534990394513953 +16.93981662267873 1:0.6552665678625891 2:0.023248457840923775 3:-0.6850641408327465 4:0.7129790774369389 5:0.04166304042825364 6:-0.7160289667702797 7:-0.4733073680976494 8:0.2720897719417634 9:0.05850741911975099 10:0.34427554125371174 +2.8497179990245116 1:0.6664937514484015 2:0.3343796939204209 3:0.2611910348746209 4:-0.13658810351647 5:-0.5821801257591224 6:0.9854683468621908 7:-0.21396555404689188 8:-0.5923272173716836 9:-0.5674796199927252 10:-0.5681633547764235 +4.981807952389501 1:0.7517426071091595 2:0.7029291090701855 3:0.7126619831046563 4:-0.9982007415355478 5:-0.7743343367502893 6:-0.9048858749551119 7:-0.8243783842398396 8:0.4936163270697016 9:-0.6835495591484724 10:0.8412758607464845 +8.508637575729951 1:0.6837354268578517 2:-0.435346907350056 3:0.6597448795477736 4:0.8870204157376871 5:-0.6938576101541436 6:0.9199495715292882 7:0.33119640706964293 8:-0.6181273221979411 9:0.12929034268333317 10:0.6855150395247027 +14.369378079132883 1:-0.9489372180887643 2:-0.6577177233364067 3:0.543899463531252 4:0.5411152154119976 5:0.43733244485250733 6:0.5927084968109424 7:0.6100068837998656 8:0.9392735722529637 9:-0.9806701698603073 10:0.3984176141500082 +-6.456944198081549 1:0.8380442392342373 2:0.05166133486184443 3:-0.25864153418691704 4:-0.9506672344106888 5:0.5227275493542325 6:-0.03899736644563956 7:0.7660133053649136 8:-0.9375236703284806 9:-0.37213210747743175 10:0.0560768367274771 +-10.041353112580456 1:0.5293717914660876 2:-0.35874932480194044 3:0.14403824250820763 4:-0.4106496629336782 5:-0.794648717231762 6:-0.4369956159772408 7:0.8273613210141495 8:0.9212255384858874 9:0.00409867676727993 10:-0.23796544184855795 +-6.606325361718908 1:0.2765102732490652 2:0.10184669160432525 3:-0.9406443798496789 4:-0.46661976112717896 5:-0.5836573778289609 6:0.1308554421925976 7:0.05232199712543473 8:-0.4965370542771641 9:-0.3695836654343949 10:0.4874427445939513 +-15.359544879832677 1:-0.8253830145927283 2:0.29683545543963885 3:-0.9790356574071053 4:0.33749594518426473 5:-0.449483349548623 6:0.1740013774913005 7:0.5737323257916764 8:0.20159372721320645 9:-0.1812760896634873 10:-0.17652712339895738 +2.1801769966756845 1:0.3664130766917151 2:-0.1929450967547921 3:-0.7834945448457515 4:-0.03806442314852432 5:-0.6167622313628849 6:0.34919852301325394 7:-0.785891329691004 8:-0.5704062599527768 9:0.9846140894872721 10:-0.548571249100203 +-2.7006646885251415 1:-0.48505178676353067 2:0.06347121974094883 3:-0.3704723119141229 4:0.7407080276548548 5:0.06713252857406937 6:-0.2103524488773294 7:-0.9402467715192988 8:-0.8555624501612784 9:0.6244760190429901 10:-0.9038885681517279 +0.2105613019270259 1:-0.17125223509187282 2:-0.23328463772140529 3:-0.6497773470047024 4:0.33111604806115524 5:0.7944287248398398 6:0.5163977380074081 7:-0.025715995643062595 8:0.11762566041047462 9:0.9938658554834845 10:0.5363394203614278 +-0.6433952980357234 1:-0.905126800719938 2:0.5826442985002787 3:-0.8207546276288018 4:-0.0773547002692121 5:-0.6420058913410687 6:-0.9290787206193325 7:0.21829202840889095 8:-0.7752845890678082 9:0.4533233304372326 10:0.5457315861825041 +5.622874731146287 1:0.5486636398086722 2:-0.21867854114956642 3:0.13260110994566032 4:-0.024868470628895967 5:0.9246597814546305 6:0.07490395250443149 7:-0.21327567620097132 8:-0.33970581204395867 9:-0.19408398882121713 10:0.9757334811378136 +-18.27521356600463 1:-0.489685764918109 2:0.6832314342743568 3:0.9115808714640257 4:-4.680515344936964E-4 5:0.03760860984717218 6:0.4344127744883004 7:-0.30019645809377127 8:-0.48339658188341783 9:-0.5488933834939806 10:-0.4735052851773165 +5.518650144654079 1:-0.16881374315243192 2:0.22747702179774354 3:-0.8555270909193926 4:-0.6914231522703247 5:0.03618437407657238 6:-0.8404831131806643 7:0.16378525699004887 8:-0.333895928854854 9:0.23026574917978326 10:0.9409087845740918 +2.5599738684677646 1:-0.24371170373626905 2:-0.1752613047793694 3:-0.7930324885557696 4:0.17288443448968627 5:0.7233942014077801 6:0.47222694561171963 7:0.7878187692414558 8:-0.6520011755878357 9:-0.9952507460157223 10:-0.32951026378415094 +-8.508663400554862 1:0.9194236423060742 2:0.9517284917259223 3:-0.18723709334016392 4:-0.24913001260985546 5:0.8818286401027424 6:0.13661210218384512 7:-0.40792517201812983 8:-0.33132907984544957 9:-0.49137388288628703 10:-0.3273925353006979 +-10.233439586953153 1:0.0960128812383454 2:-0.8611756848964027 3:0.11807312551418647 4:-0.24570750746947145 5:-0.047826307143366886 6:-0.717269426008625 7:-0.2841658181308486 8:-0.31500935950449516 9:0.23183474949267713 10:-0.512986169560546 +-6.3459370724834265 1:0.9537835418930307 2:0.4598546399405288 3:-0.257013655072986 4:-0.29185820894937575 5:-0.6843688281544562 6:0.8343952028925479 7:-0.9656517094615942 8:-0.447440560943553 9:-0.9510349521362857 10:0.5918946980259567 +1.114406550703455 1:-0.5721838436595965 2:0.1201917297381252 3:-0.5253701290141362 4:-0.5874011312890843 5:0.7893580092022578 6:-0.18012813622584134 7:0.4781905737504004 8:-4.6732390143988667E-4 9:-0.7965374182885014 10:-0.8515444146742359 +8.688243146888663 1:0.2245581140502393 2:-0.0697600364101425 3:-0.7661833153629154 4:-0.2289151515902894 5:-0.5643191391300282 6:0.08069861795512168 7:-0.9670317635091523 8:0.14826752863715287 9:0.9325364047311011 10:0.4071178661803092 +14.896035572185347 1:0.20630949870309911 2:-0.5738578325975092 3:0.5664829389128903 4:0.3732752326637825 5:0.04079303403038881 6:-0.6604984910400766 7:0.15136076091734352 8:-0.6244939282579305 9:-0.5236288549540624 10:0.47284992666739023 +4.396558596072123 1:0.5565602414172521 2:0.1444095747909111 3:0.028227502879770272 4:0.38297378287943773 5:-0.26739745457451725 6:-0.708209627997985 7:0.7604483272526881 8:0.8072075261139096 9:0.11460574885028274 10:-0.07669406807610635 +1.7457141275341528 1:0.3668576517164046 2:-0.5352200081463954 3:0.5853385976871426 4:-0.4482551060006992 5:-0.5676795208498786 6:0.8043295590331514 7:-0.02160829797068753 8:0.42281303847010454 9:0.027894531623162466 10:-0.541120112980032 +-15.334767479922341 1:-0.036676500783341615 2:0.804758241454594 3:-0.0642091078911513 4:0.1402705435750966 5:-0.9215322030628859 6:0.7951173116514345 7:-0.994819896842561 8:0.2382406912119326 9:0.6634166177958731 10:0.7623222578718651 +5.017247792012723 1:-0.5925393497160352 2:0.48506599831456443 3:-0.5079795649118319 4:0.6668553329827696 5:-0.1103174867779837 6:0.7048535526809607 7:-0.9819230894106692 8:0.19609620625274982 9:0.5173985272313828 10:-0.11269849619148875 +6.201510810634532 1:-0.6802942101330738 2:0.898957584078176 3:0.853293387559251 4:0.6089336185656065 5:-0.9352626288322801 6:0.3208583332890447 7:-0.964481544931127 8:-0.8294773786068643 9:-0.8817311989413614 10:0.5165364663580934 +19.174935630244647 1:-0.20026105252200788 2:0.7276178994821614 3:0.7748716685190951 4:-0.7423420145576229 5:0.13147770471985032 6:-0.8382015712894606 7:0.021760992104270294 8:-0.24586987823702944 9:-0.05958177281299326 10:0.47347236224860834 +-14.822152909751189 1:0.7255660700197897 2:-0.22751988933383926 3:-0.08409197084114317 4:0.072750455428638 5:0.1841692073989072 6:-0.33838406658716513 7:-0.44701963574290526 8:0.5031210959133143 9:0.09640858549693743 10:0.9857351194637847 +-6.310082095945472 1:-0.7692076133438608 2:0.8533601511731044 3:0.676268298275629 4:-0.783895030001512 5:-0.8195462819549715 6:0.3963101354895673 7:-0.6254922461977397 8:-0.7521135990258581 9:-0.8032003997516024 10:0.8388672800826487 +8.853802632714807 1:0.46950948246522195 2:-0.6148693581037883 3:0.028739220735170656 4:-0.024281643566285815 5:-0.3495458137792231 6:-0.12347196435522867 7:0.5253894065203333 8:0.5100713458262918 9:0.63975795701667 10:0.08644353314625053 +-10.293714040655924 1:-0.17971950768550893 2:-0.6621720204354751 3:0.888036885802737 4:-0.04977483590350751 5:-0.8964991391283221 6:0.6873490822438724 7:0.42369087852118836 8:0.48972554317650663 9:0.8617233178519317 10:-0.8348331836605276 +0.23985611568891863 1:0.050526696983213215 2:0.8544297176525815 3:0.8586358519997579 4:-0.021299752441110487 5:0.2606696929560939 6:-0.39446486150105997 7:-0.4166234435381613 8:-0.6097643266459343 9:0.46633996256010146 10:-0.22521646199731027 +21.57719950299147 1:-0.5878491135126271 2:0.802134056970349 3:-0.5471017580843434 4:0.6067966843473331 5:-0.691712219323007 6:0.7814323754276735 7:0.31689445927290016 8:-0.1668780061940922 9:0.5285692389527452 10:0.8027091025203246 +-0.7836538830323514 1:0.5766794801558166 2:0.8281463568384935 3:0.5087453132796032 4:0.5212853344036532 5:0.6294700781054074 6:-0.9385097739886943 7:-0.13127371407538302 8:0.9845390503404141 9:-0.7224166213906742 10:-0.11155327354295896 +6.710413649604831 1:-0.6919803228062729 2:-0.6526904017578161 3:-0.34211291948607014 4:0.9094842803341618 5:-0.9454398661995895 6:0.3780766512494227 7:0.5823385348738088 8:0.8817830051841733 9:-0.514843382774189 10:0.32579701113259296 +5.384747201245483 1:-0.9661857672086316 2:-0.519769534339731 3:-0.4466396856529564 4:-0.4370113024678448 5:-0.6397400687811474 6:0.08225309277403725 7:-0.25936524603970756 8:-0.1711463274766858 9:-0.42848099098115755 10:-0.8096854737357237 +7.688509532916731 1:0.3892872094452817 2:-0.13306620868059982 3:-0.932974891205117 4:-0.8921357494146682 5:0.4806996560679244 6:-0.21500288444218696 7:-0.8911268070046585 8:-0.9510264953215406 9:0.1899740993687098 10:-0.43944320580463536 +2.2546997585565296 1:-0.5963883101717473 2:-0.01115153603404151 3:0.8781871380140298 4:0.7736250964135891 5:-0.7325745711528668 6:0.2518631794989008 7:0.5760249284318746 8:0.8690107952725199 9:0.02320853138646095 10:0.08570951531344417 +5.597710012706039 1:-0.5323512235815979 2:0.03366944321271936 3:0.5143537675853551 4:0.28471250955283445 5:0.4012202634439719 6:0.12032039285431151 7:-0.08108716844967812 8:0.30231384371011294 9:0.03259115565303028 10:0.9567467516929173 +-12.977848725392104 1:-0.5908891529017144 2:-0.7678208242918028 3:0.8512434510178621 4:-0.14910196410347298 5:0.6250260229199651 6:0.5393378705290228 7:-0.9573580597625002 8:-0.864881502860934 9:0.4175735160503429 10:0.4872169215922426 +10.35887243981476 1:-0.09126023790482862 2:0.18852634121926526 3:-0.13523918100503107 4:0.8333842692409983 5:-0.6015442103644761 6:0.5347736461652235 7:-0.823489760471118 8:0.5562688292037381 9:-0.807478561291906 10:-0.666881464988351 +0.4250502150408626 1:0.7771717566171905 2:-0.8729202752916785 3:-0.25782888805127024 4:-0.13605474993771205 5:0.5911781118120025 6:-0.8444023967853633 7:0.6787302541469229 8:-0.5444299313083194 9:0.356121883138657 10:-0.8845333845080687 +-0.8743487925900991 1:-0.9087681208947878 2:-0.292625136739453 3:-0.35113758823291774 4:-0.705933223571676 5:-0.6882289471031144 6:0.8350131255297044 7:-0.7659016065609232 8:0.11400114955653207 9:-0.9466143658505732 10:-0.5033643125229932 +-5.615143641864686 1:-0.6688289820084299 2:-0.4623159855015393 3:0.012827807007503855 4:-0.44521264878006117 5:-0.5563111031201406 6:-0.6065295981983794 7:0.3806712426786838 8:-0.11317152118817408 9:0.507896127467435 10:-0.8487801189674464 +-0.1829397047693725 1:0.09377558075225512 2:0.5774384503027374 3:-0.7104684187448009 4:-0.07285914169135976 5:-0.8797920488335114 6:0.6099615504974201 7:-0.8047440624324915 8:-0.6877856114263066 9:0.5843004021777447 10:0.5190581455348131 +18.479680552020344 1:0.9635517137863321 2:0.9954507816218203 3:0.11959899129360774 4:0.3753283274192787 5:-0.9386713095183621 6:0.0926833703812433 7:0.48003949462701323 8:0.9432769781973132 9:-0.9637036991931129 10:-0.4064407447273508 +1.3850645873427236 1:0.14476184437006356 2:-0.11280617018445871 3:-0.4385084538142101 4:-0.5961619435136434 5:0.419554626795412 6:-0.5047767472761191 7:0.457180284958592 8:-0.9129360314541999 9:-0.6320022059786656 10:-0.44989608519659363 diff --git a/data/mllib/sample_movielens_data.txt b/data/mllib/sample_movielens_data.txt new file mode 100644 index 0000000000000..f0eee19875f76 --- /dev/null +++ b/data/mllib/sample_movielens_data.txt @@ -0,0 +1,1501 @@ +0::2::3 +0::3::1 +0::5::2 +0::9::4 +0::11::1 +0::12::2 +0::15::1 +0::17::1 +0::19::1 +0::21::1 +0::23::1 +0::26::3 +0::27::1 +0::28::1 +0::29::1 +0::30::1 +0::31::1 +0::34::1 +0::37::1 +0::41::2 +0::44::1 +0::45::2 +0::46::1 +0::47::1 +0::48::1 +0::50::1 +0::51::1 +0::54::1 +0::55::1 +0::59::2 +0::61::2 +0::64::1 +0::67::1 +0::68::1 +0::69::1 +0::71::1 +0::72::1 +0::77::2 +0::79::1 +0::83::1 +0::87::1 +0::89::2 +0::91::3 +0::92::4 +0::94::1 +0::95::2 +0::96::1 +0::98::1 +0::99::1 +1::2::2 +1::3::1 +1::4::2 +1::6::1 +1::9::3 +1::12::1 +1::13::1 +1::14::1 +1::16::1 +1::19::1 +1::21::3 +1::27::1 +1::28::3 +1::33::1 +1::36::2 +1::37::1 +1::40::1 +1::41::2 +1::43::1 +1::44::1 +1::47::1 +1::50::1 +1::54::1 +1::56::2 +1::57::1 +1::58::1 +1::60::1 +1::62::4 +1::63::1 +1::67::1 +1::68::4 +1::70::2 +1::72::1 +1::73::1 +1::74::2 +1::76::1 +1::77::3 +1::78::1 +1::81::1 +1::82::1 +1::85::3 +1::86::2 +1::88::2 +1::91::1 +1::92::2 +1::93::1 +1::94::2 +1::96::1 +1::97::1 +2::4::3 +2::6::1 +2::8::5 +2::9::1 +2::10::1 +2::12::3 +2::13::1 +2::15::2 +2::18::2 +2::19::4 +2::22::1 +2::26::1 +2::28::1 +2::34::4 +2::35::1 +2::37::5 +2::38::1 +2::39::5 +2::40::4 +2::47::1 +2::50::1 +2::52::2 +2::54::1 +2::55::1 +2::57::2 +2::58::2 +2::59::1 +2::61::1 +2::62::1 +2::64::1 +2::65::1 +2::66::3 +2::68::1 +2::71::3 +2::76::1 +2::77::1 +2::78::1 +2::80::1 +2::83::5 +2::85::1 +2::87::2 +2::88::1 +2::89::4 +2::90::1 +2::92::4 +2::93::5 +3::0::1 +3::1::1 +3::2::1 +3::7::3 +3::8::3 +3::9::1 +3::14::1 +3::15::1 +3::16::1 +3::18::4 +3::19::1 +3::24::3 +3::26::1 +3::29::3 +3::33::1 +3::34::3 +3::35::1 +3::36::3 +3::37::1 +3::38::2 +3::43::1 +3::44::1 +3::46::1 +3::47::1 +3::51::5 +3::52::3 +3::56::1 +3::58::1 +3::60::3 +3::62::1 +3::65::2 +3::66::1 +3::67::1 +3::68::2 +3::70::1 +3::72::2 +3::76::3 +3::79::3 +3::80::4 +3::81::1 +3::83::1 +3::84::1 +3::86::1 +3::87::2 +3::88::4 +3::89::1 +3::91::1 +3::94::3 +4::1::1 +4::6::1 +4::8::1 +4::9::1 +4::10::1 +4::11::1 +4::12::1 +4::13::1 +4::14::2 +4::15::1 +4::17::1 +4::20::1 +4::22::1 +4::23::1 +4::24::1 +4::29::4 +4::30::1 +4::31::1 +4::34::1 +4::35::1 +4::36::1 +4::39::2 +4::40::3 +4::41::4 +4::43::2 +4::44::1 +4::45::1 +4::46::1 +4::47::1 +4::49::2 +4::50::1 +4::51::1 +4::52::4 +4::54::1 +4::55::1 +4::60::3 +4::61::1 +4::62::4 +4::63::3 +4::65::1 +4::67::2 +4::69::1 +4::70::4 +4::71::1 +4::73::1 +4::78::1 +4::84::1 +4::85::1 +4::87::3 +4::88::3 +4::89::2 +4::96::1 +4::97::1 +4::98::1 +4::99::1 +5::0::1 +5::1::1 +5::4::1 +5::5::1 +5::8::1 +5::9::3 +5::10::2 +5::13::3 +5::15::1 +5::19::1 +5::20::3 +5::21::2 +5::23::3 +5::27::1 +5::28::1 +5::29::1 +5::31::1 +5::36::3 +5::38::2 +5::39::1 +5::42::1 +5::48::3 +5::49::4 +5::50::3 +5::51::1 +5::52::1 +5::54::1 +5::55::5 +5::56::3 +5::58::1 +5::60::1 +5::61::1 +5::64::3 +5::65::2 +5::68::4 +5::70::1 +5::71::1 +5::72::1 +5::74::1 +5::79::1 +5::81::2 +5::84::1 +5::85::1 +5::86::1 +5::88::1 +5::90::4 +5::91::2 +5::95::2 +5::99::1 +6::0::1 +6::1::1 +6::2::3 +6::5::1 +6::6::1 +6::9::1 +6::10::1 +6::15::2 +6::16::2 +6::17::1 +6::18::1 +6::20::1 +6::21::1 +6::22::1 +6::24::1 +6::25::5 +6::26::1 +6::28::1 +6::30::1 +6::33::1 +6::38::1 +6::39::1 +6::43::4 +6::44::1 +6::45::1 +6::48::1 +6::49::1 +6::50::1 +6::53::1 +6::54::1 +6::55::1 +6::56::1 +6::58::4 +6::59::1 +6::60::1 +6::61::3 +6::63::3 +6::66::1 +6::67::3 +6::68::1 +6::69::1 +6::71::2 +6::73::1 +6::75::1 +6::77::1 +6::79::1 +6::81::1 +6::84::1 +6::85::3 +6::86::1 +6::87::1 +6::88::1 +6::89::1 +6::91::2 +6::94::1 +6::95::2 +6::96::1 +7::1::1 +7::2::2 +7::3::1 +7::4::1 +7::7::1 +7::10::1 +7::11::2 +7::14::2 +7::15::1 +7::16::1 +7::18::1 +7::21::1 +7::22::1 +7::23::1 +7::25::5 +7::26::1 +7::29::4 +7::30::1 +7::31::3 +7::32::1 +7::33::1 +7::35::1 +7::37::2 +7::39::3 +7::40::2 +7::42::2 +7::44::1 +7::45::2 +7::47::4 +7::48::1 +7::49::1 +7::53::1 +7::54::1 +7::55::1 +7::56::1 +7::59::1 +7::61::2 +7::62::3 +7::63::2 +7::66::1 +7::67::3 +7::74::1 +7::75::1 +7::76::3 +7::77::1 +7::81::1 +7::82::1 +7::84::2 +7::85::4 +7::86::1 +7::92::2 +7::96::1 +7::97::1 +7::98::1 +8::0::1 +8::2::4 +8::3::2 +8::4::2 +8::5::1 +8::7::1 +8::9::1 +8::11::1 +8::15::1 +8::18::1 +8::19::1 +8::21::1 +8::29::5 +8::31::3 +8::33::1 +8::35::1 +8::36::1 +8::40::2 +8::44::1 +8::45::1 +8::50::1 +8::51::1 +8::52::5 +8::53::5 +8::54::1 +8::55::1 +8::56::1 +8::58::4 +8::60::3 +8::62::4 +8::64::1 +8::67::3 +8::69::1 +8::71::1 +8::72::3 +8::77::3 +8::78::1 +8::79::1 +8::83::1 +8::85::5 +8::86::1 +8::88::1 +8::90::1 +8::92::2 +8::95::4 +8::96::3 +8::97::1 +8::98::1 +8::99::1 +9::2::3 +9::3::1 +9::4::1 +9::5::1 +9::6::1 +9::7::5 +9::9::1 +9::12::1 +9::14::3 +9::15::1 +9::19::1 +9::21::1 +9::22::1 +9::24::1 +9::25::1 +9::26::1 +9::30::3 +9::32::4 +9::35::2 +9::36::2 +9::37::2 +9::38::1 +9::39::1 +9::43::3 +9::49::5 +9::50::3 +9::53::1 +9::54::1 +9::58::1 +9::59::1 +9::60::1 +9::61::1 +9::63::3 +9::64::3 +9::68::1 +9::69::1 +9::70::3 +9::71::1 +9::73::2 +9::75::1 +9::77::2 +9::81::2 +9::82::1 +9::83::1 +9::84::1 +9::86::1 +9::87::4 +9::88::1 +9::90::3 +9::94::2 +9::95::3 +9::97::2 +9::98::1 +10::0::3 +10::2::4 +10::4::3 +10::7::1 +10::8::1 +10::10::1 +10::13::2 +10::14::1 +10::16::2 +10::17::1 +10::18::1 +10::21::1 +10::22::1 +10::24::1 +10::25::3 +10::28::1 +10::35::1 +10::36::1 +10::37::1 +10::38::1 +10::39::1 +10::40::4 +10::41::2 +10::42::3 +10::43::1 +10::49::3 +10::50::1 +10::51::1 +10::52::1 +10::55::2 +10::56::1 +10::58::1 +10::63::1 +10::66::1 +10::67::2 +10::68::1 +10::75::1 +10::77::1 +10::79::1 +10::86::1 +10::89::3 +10::90::1 +10::97::1 +10::98::1 +11::0::1 +11::6::2 +11::9::1 +11::10::1 +11::11::1 +11::12::1 +11::13::4 +11::16::1 +11::18::5 +11::19::4 +11::20::1 +11::21::1 +11::22::1 +11::23::5 +11::25::1 +11::27::5 +11::30::5 +11::32::5 +11::35::3 +11::36::2 +11::37::2 +11::38::4 +11::39::1 +11::40::1 +11::41::1 +11::43::2 +11::45::1 +11::47::1 +11::48::5 +11::50::4 +11::51::3 +11::59::1 +11::61::1 +11::62::1 +11::64::1 +11::66::4 +11::67::1 +11::69::5 +11::70::1 +11::71::3 +11::72::3 +11::75::3 +11::76::1 +11::77::1 +11::78::1 +11::79::5 +11::80::3 +11::81::4 +11::82::1 +11::86::1 +11::88::1 +11::89::1 +11::90::4 +11::94::2 +11::97::3 +11::99::1 +12::2::1 +12::4::1 +12::6::1 +12::7::3 +12::8::1 +12::14::1 +12::15::2 +12::16::4 +12::17::5 +12::18::2 +12::21::1 +12::22::2 +12::23::3 +12::24::1 +12::25::1 +12::27::5 +12::30::2 +12::31::4 +12::35::5 +12::38::1 +12::41::1 +12::44::2 +12::45::1 +12::50::4 +12::51::1 +12::52::1 +12::53::1 +12::54::1 +12::56::2 +12::57::1 +12::60::1 +12::63::1 +12::64::5 +12::66::3 +12::67::1 +12::70::1 +12::72::1 +12::74::1 +12::75::1 +12::77::1 +12::78::1 +12::79::3 +12::82::2 +12::83::1 +12::84::1 +12::85::1 +12::86::1 +12::87::1 +12::88::1 +12::91::3 +12::92::1 +12::94::4 +12::95::2 +12::96::1 +12::98::2 +13::0::1 +13::3::1 +13::4::2 +13::5::1 +13::6::1 +13::12::1 +13::14::2 +13::15::1 +13::17::1 +13::18::3 +13::20::1 +13::21::1 +13::22::1 +13::26::1 +13::27::1 +13::29::3 +13::31::1 +13::33::1 +13::40::2 +13::43::2 +13::44::1 +13::45::1 +13::49::1 +13::51::1 +13::52::2 +13::53::3 +13::54::1 +13::62::1 +13::63::2 +13::64::1 +13::68::1 +13::71::1 +13::72::3 +13::73::1 +13::74::3 +13::77::2 +13::78::1 +13::79::2 +13::83::3 +13::85::1 +13::86::1 +13::87::2 +13::88::2 +13::90::1 +13::93::4 +13::94::1 +13::98::1 +13::99::1 +14::1::1 +14::3::3 +14::4::1 +14::5::1 +14::6::1 +14::7::1 +14::9::1 +14::10::1 +14::11::1 +14::12::1 +14::13::1 +14::14::3 +14::15::1 +14::16::1 +14::17::1 +14::20::1 +14::21::1 +14::24::1 +14::25::2 +14::27::1 +14::28::1 +14::29::5 +14::31::3 +14::34::1 +14::36::1 +14::37::2 +14::39::2 +14::40::1 +14::44::1 +14::45::1 +14::47::3 +14::48::1 +14::49::1 +14::51::1 +14::52::5 +14::53::3 +14::54::1 +14::55::1 +14::56::1 +14::62::4 +14::63::5 +14::67::3 +14::68::1 +14::69::3 +14::71::1 +14::72::4 +14::73::1 +14::76::5 +14::79::1 +14::82::1 +14::83::1 +14::88::1 +14::93::3 +14::94::1 +14::95::2 +14::96::4 +14::98::1 +15::0::1 +15::1::4 +15::2::1 +15::5::2 +15::6::1 +15::7::1 +15::13::1 +15::14::1 +15::15::1 +15::17::2 +15::19::2 +15::22::2 +15::23::2 +15::25::1 +15::26::3 +15::27::1 +15::28::2 +15::29::1 +15::32::1 +15::33::2 +15::34::1 +15::35::2 +15::36::1 +15::37::1 +15::39::1 +15::42::1 +15::46::5 +15::48::2 +15::50::2 +15::51::1 +15::52::1 +15::58::1 +15::62::1 +15::64::3 +15::65::2 +15::72::1 +15::73::1 +15::74::1 +15::79::1 +15::80::1 +15::81::1 +15::82::2 +15::85::1 +15::87::1 +15::91::2 +15::96::1 +15::97::1 +15::98::3 +16::2::1 +16::5::3 +16::6::2 +16::7::1 +16::9::1 +16::12::1 +16::14::1 +16::15::1 +16::19::1 +16::21::2 +16::29::4 +16::30::2 +16::32::1 +16::34::1 +16::36::1 +16::38::1 +16::46::1 +16::47::3 +16::48::1 +16::49::1 +16::50::1 +16::51::5 +16::54::5 +16::55::1 +16::56::2 +16::57::1 +16::60::1 +16::63::2 +16::65::1 +16::67::1 +16::72::1 +16::74::1 +16::80::1 +16::81::1 +16::82::1 +16::85::5 +16::86::1 +16::90::5 +16::91::1 +16::93::1 +16::94::3 +16::95::2 +16::96::3 +16::98::3 +16::99::1 +17::2::1 +17::3::1 +17::6::1 +17::10::4 +17::11::1 +17::13::2 +17::17::5 +17::19::1 +17::20::5 +17::22::4 +17::28::1 +17::29::1 +17::33::1 +17::34::1 +17::35::2 +17::37::1 +17::38::1 +17::45::1 +17::46::5 +17::47::1 +17::49::3 +17::51::1 +17::55::5 +17::56::3 +17::57::1 +17::58::1 +17::59::1 +17::60::1 +17::63::1 +17::66::1 +17::68::4 +17::69::1 +17::70::1 +17::72::1 +17::73::3 +17::78::1 +17::79::1 +17::82::2 +17::84::1 +17::90::5 +17::91::3 +17::92::1 +17::93::1 +17::94::4 +17::95::2 +17::97::1 +18::1::1 +18::4::3 +18::5::2 +18::6::1 +18::7::1 +18::10::1 +18::11::4 +18::12::2 +18::13::1 +18::15::1 +18::18::1 +18::20::1 +18::21::2 +18::22::1 +18::23::2 +18::25::1 +18::26::1 +18::27::1 +18::28::5 +18::29::1 +18::31::1 +18::32::1 +18::36::1 +18::38::5 +18::39::5 +18::40::1 +18::42::1 +18::43::1 +18::44::4 +18::46::1 +18::47::1 +18::48::1 +18::51::2 +18::55::1 +18::56::1 +18::57::1 +18::62::1 +18::63::1 +18::66::3 +18::67::1 +18::70::1 +18::75::1 +18::76::3 +18::77::1 +18::80::3 +18::81::3 +18::82::1 +18::83::5 +18::84::1 +18::97::1 +18::98::1 +18::99::2 +19::0::1 +19::1::1 +19::2::1 +19::4::1 +19::6::2 +19::11::1 +19::12::1 +19::14::1 +19::23::1 +19::26::1 +19::31::1 +19::32::4 +19::33::1 +19::34::1 +19::37::1 +19::38::1 +19::41::1 +19::43::1 +19::45::1 +19::48::1 +19::49::1 +19::50::2 +19::53::2 +19::54::3 +19::55::1 +19::56::2 +19::58::1 +19::61::1 +19::62::1 +19::63::1 +19::64::1 +19::65::1 +19::69::2 +19::72::1 +19::74::3 +19::76::1 +19::78::1 +19::79::1 +19::81::1 +19::82::1 +19::84::1 +19::86::1 +19::87::2 +19::90::4 +19::93::1 +19::94::4 +19::95::2 +19::96::1 +19::98::4 +20::0::1 +20::1::1 +20::2::2 +20::4::2 +20::6::1 +20::8::1 +20::12::1 +20::21::2 +20::22::5 +20::24::2 +20::25::1 +20::26::1 +20::29::2 +20::30::2 +20::32::2 +20::39::1 +20::40::1 +20::41::2 +20::45::2 +20::48::1 +20::50::1 +20::51::3 +20::53::3 +20::55::1 +20::57::2 +20::60::1 +20::61::1 +20::64::1 +20::66::1 +20::70::2 +20::72::1 +20::73::2 +20::75::4 +20::76::1 +20::77::4 +20::78::1 +20::79::1 +20::84::2 +20::85::2 +20::88::3 +20::89::1 +20::90::3 +20::91::1 +20::92::2 +20::93::1 +20::94::4 +20::97::1 +21::0::1 +21::2::4 +21::3::1 +21::7::2 +21::11::1 +21::12::1 +21::13::1 +21::14::3 +21::17::1 +21::19::1 +21::20::1 +21::21::1 +21::22::1 +21::23::1 +21::24::1 +21::27::1 +21::29::5 +21::30::2 +21::38::1 +21::40::2 +21::43::3 +21::44::1 +21::45::1 +21::46::1 +21::48::1 +21::51::1 +21::53::5 +21::54::1 +21::55::1 +21::56::1 +21::58::3 +21::59::3 +21::64::1 +21::66::1 +21::68::1 +21::71::1 +21::73::1 +21::74::4 +21::80::1 +21::81::1 +21::83::1 +21::84::1 +21::85::3 +21::87::4 +21::89::2 +21::92::2 +21::96::3 +21::99::1 +22::0::1 +22::3::2 +22::5::2 +22::6::2 +22::9::1 +22::10::1 +22::11::1 +22::13::1 +22::14::1 +22::16::1 +22::18::3 +22::19::1 +22::22::5 +22::25::1 +22::26::1 +22::29::3 +22::30::5 +22::32::4 +22::33::1 +22::35::1 +22::36::3 +22::37::1 +22::40::1 +22::41::3 +22::44::1 +22::45::2 +22::48::1 +22::51::5 +22::55::1 +22::56::2 +22::60::3 +22::61::1 +22::62::4 +22::63::1 +22::65::1 +22::66::1 +22::68::4 +22::69::4 +22::70::3 +22::71::1 +22::74::5 +22::75::5 +22::78::1 +22::80::3 +22::81::1 +22::82::1 +22::84::1 +22::86::1 +22::87::3 +22::88::5 +22::90::2 +22::92::3 +22::95::2 +22::96::2 +22::98::4 +22::99::1 +23::0::1 +23::2::1 +23::4::1 +23::6::2 +23::10::4 +23::12::1 +23::13::4 +23::14::1 +23::15::1 +23::18::4 +23::22::2 +23::23::4 +23::24::1 +23::25::1 +23::26::1 +23::27::5 +23::28::1 +23::29::1 +23::30::4 +23::32::5 +23::33::2 +23::36::3 +23::37::1 +23::38::1 +23::39::1 +23::43::1 +23::48::5 +23::49::5 +23::50::4 +23::53::1 +23::55::5 +23::57::1 +23::59::1 +23::60::1 +23::61::1 +23::64::4 +23::65::5 +23::66::2 +23::67::1 +23::68::3 +23::69::1 +23::72::1 +23::73::3 +23::77::1 +23::82::2 +23::83::1 +23::84::1 +23::85::1 +23::87::3 +23::88::1 +23::95::2 +23::97::1 +24::4::1 +24::6::3 +24::7::1 +24::10::2 +24::12::1 +24::15::1 +24::19::1 +24::24::1 +24::27::3 +24::30::5 +24::31::1 +24::32::3 +24::33::1 +24::37::1 +24::39::1 +24::40::1 +24::42::1 +24::43::3 +24::45::2 +24::46::1 +24::47::1 +24::48::1 +24::49::1 +24::50::1 +24::52::5 +24::57::1 +24::59::4 +24::63::4 +24::65::1 +24::66::1 +24::67::1 +24::68::3 +24::69::5 +24::71::1 +24::72::4 +24::77::4 +24::78::1 +24::80::1 +24::82::1 +24::84::1 +24::86::1 +24::87::1 +24::88::2 +24::89::1 +24::90::5 +24::91::1 +24::92::1 +24::94::2 +24::95::1 +24::96::5 +24::98::1 +24::99::1 +25::1::3 +25::2::1 +25::7::1 +25::9::1 +25::12::3 +25::16::3 +25::17::1 +25::18::1 +25::20::1 +25::22::1 +25::23::1 +25::26::2 +25::29::1 +25::30::1 +25::31::2 +25::33::4 +25::34::3 +25::35::2 +25::36::1 +25::37::1 +25::40::1 +25::41::1 +25::43::1 +25::47::4 +25::50::1 +25::51::1 +25::53::1 +25::56::1 +25::58::2 +25::64::2 +25::67::2 +25::68::1 +25::70::1 +25::71::4 +25::73::1 +25::74::1 +25::76::1 +25::79::1 +25::82::1 +25::84::2 +25::85::1 +25::91::3 +25::92::1 +25::94::1 +25::95::1 +25::97::2 +26::0::1 +26::1::1 +26::2::1 +26::3::1 +26::4::4 +26::5::2 +26::6::3 +26::7::5 +26::13::3 +26::14::1 +26::16::1 +26::18::3 +26::20::1 +26::21::3 +26::22::5 +26::23::5 +26::24::5 +26::27::1 +26::31::1 +26::35::1 +26::36::4 +26::40::1 +26::44::1 +26::45::2 +26::47::1 +26::48::1 +26::49::3 +26::50::2 +26::52::1 +26::54::4 +26::55::1 +26::57::3 +26::58::1 +26::61::1 +26::62::2 +26::66::1 +26::68::4 +26::71::1 +26::73::4 +26::76::1 +26::81::3 +26::85::1 +26::86::3 +26::88::5 +26::91::1 +26::94::5 +26::95::1 +26::96::1 +26::97::1 +27::0::1 +27::9::1 +27::10::1 +27::18::4 +27::19::3 +27::20::1 +27::22::2 +27::24::2 +27::25::1 +27::27::3 +27::28::1 +27::29::1 +27::31::1 +27::33::3 +27::40::1 +27::42::1 +27::43::1 +27::44::3 +27::45::1 +27::51::3 +27::52::1 +27::55::3 +27::57::1 +27::59::1 +27::60::1 +27::61::1 +27::64::1 +27::66::3 +27::68::1 +27::70::1 +27::71::2 +27::72::1 +27::75::3 +27::78::1 +27::80::3 +27::82::1 +27::83::3 +27::86::1 +27::87::2 +27::90::1 +27::91::1 +27::92::1 +27::93::1 +27::94::2 +27::95::1 +27::98::1 +28::0::3 +28::1::1 +28::2::4 +28::3::1 +28::6::1 +28::7::1 +28::12::5 +28::13::2 +28::14::1 +28::15::1 +28::17::1 +28::19::3 +28::20::1 +28::23::3 +28::24::3 +28::27::1 +28::29::1 +28::33::1 +28::34::1 +28::36::1 +28::38::2 +28::39::2 +28::44::1 +28::45::1 +28::49::4 +28::50::1 +28::52::1 +28::54::1 +28::56::1 +28::57::3 +28::58::1 +28::59::1 +28::60::1 +28::62::3 +28::63::1 +28::65::1 +28::75::1 +28::78::1 +28::81::5 +28::82::4 +28::83::1 +28::85::1 +28::88::2 +28::89::4 +28::90::1 +28::92::5 +28::94::1 +28::95::2 +28::98::1 +28::99::1 +29::3::1 +29::4::1 +29::5::1 +29::7::2 +29::9::1 +29::10::3 +29::11::1 +29::13::3 +29::14::1 +29::15::1 +29::17::3 +29::19::3 +29::22::3 +29::23::4 +29::25::1 +29::29::1 +29::31::1 +29::32::4 +29::33::2 +29::36::2 +29::38::3 +29::39::1 +29::42::1 +29::46::5 +29::49::3 +29::51::2 +29::59::1 +29::61::1 +29::62::1 +29::67::1 +29::68::3 +29::69::1 +29::70::1 +29::74::1 +29::75::1 +29::79::2 +29::80::1 +29::81::2 +29::83::1 +29::85::1 +29::86::1 +29::90::4 +29::93::1 +29::94::4 +29::97::1 +29::99::1 diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala index 4001908c98015..56b02b65d8724 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala @@ -29,8 +29,9 @@ import org.apache.spark.mllib.optimization.{SquaredL2Updater, L1Updater} /** * An example app for binary classification. Run with * {{{ - * ./bin/run-example org.apache.spark.examples.mllib.BinaryClassification + * bin/run-example org.apache.spark.examples.mllib.BinaryClassification * }}} + * A synthetic dataset is located at `data/mllib/sample_binary_classification_data.txt`. * If you use it as a template to create your own app, please use `spark-submit` to submit your app. */ object BinaryClassification { @@ -81,6 +82,15 @@ object BinaryClassification { .required() .text("input paths to labeled examples in LIBSVM format") .action((x, c) => c.copy(input = x)) + note( + """ + |For example, the following command runs this app on a synthetic dataset: + | + | bin/spark-submit --class org.apache.spark.examples.mllib.BinaryClassification \ + | examples/target/scala-*/spark-examples-*.jar \ + | --algorithm LR --regType L2 --regParam 1.0 \ + | data/mllib/sample_binary_classification_data.txt + """.stripMargin) } parser.parse(args, defaultParams).map { params => diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala index 658d370f8656e..4811bb70e4b28 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala @@ -28,8 +28,9 @@ import org.apache.spark.mllib.optimization.{SimpleUpdater, SquaredL2Updater, L1U /** * An example app for linear regression. Run with * {{{ - * ./bin/run-example org.apache.spark.examples.mllib.LinearRegression + * bin/run-example org.apache.spark.examples.mllib.LinearRegression * }}} + * A synthetic dataset can be found at `data/mllib/sample_linear_regression_data.txt`. * If you use it as a template to create your own app, please use `spark-submit` to submit your app. */ object LinearRegression extends App { @@ -68,6 +69,14 @@ object LinearRegression extends App { .required() .text("input paths to labeled examples in LIBSVM format") .action((x, c) => c.copy(input = x)) + note( + """ + |For example, the following command runs this app on a synthetic dataset: + | + | bin/spark-submit --class org.apache.spark.examples.mllib.LinearRegression \ + | examples/target/scala-*/spark-examples-*.jar \ + | data/mllib/sample_linear_regression_data.txt + """.stripMargin) } parser.parse(args, defaultParams).map { params => diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala index 0e4447e0de24f..6eb41e7ba36fb 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala @@ -29,6 +29,12 @@ import org.apache.spark.serializer.{KryoSerializer, KryoRegistrator} /** * An example app for ALS on MovieLens data (http://grouplens.org/datasets/movielens/). + * Run with + * {{{ + * bin/run-example org.apache.spark.examples.mllib.MovieLensALS + * }}} + * A synthetic dataset in MovieLens format can be found at `data/mllib/sample_movielens_data.txt`. + * If you use it as a template to create your own app, please use `spark-submit` to submit your app. */ object MovieLensALS { @@ -70,6 +76,15 @@ object MovieLensALS { .required() .text("input paths to a MovieLens dataset of ratings") .action((x, c) => c.copy(input = x)) + note( + """ + |For example, the following command runs this app on a synthetic dataset: + | + | bin/spark-submit --class org.apache.spark.examples.mllib.MovieLensALS \ + | examples/target/scala-*/spark-examples-*.jar \ + | --rank 5 --numIterations 20 --lambda 1.0 --kryo \ + | data/mllib/sample_movielens_data.txt + """.stripMargin) } parser.parse(args, defaultParams).map { params => From 52eb54d02403a3c37d84b9da7cc1cdb261048cf8 Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Mon, 19 May 2014 22:36:24 -0700 Subject: [PATCH 85/99] [Spark 1877] ClassNotFoundException when loading RDD with serialized objects Updated version of #821 Author: Tathagata Das Author: Ghidireac Closes #835 from tdas/SPARK-1877 and squashes the following commits: f346f71 [Tathagata Das] Addressed Patrick's comments. fee0c5d [Ghidireac] SPARK-1877: ClassNotFoundException when loading RDD with serialized objects --- core/src/main/scala/org/apache/spark/SparkContext.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 634c10c33fc86..49737fa4be56b 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -718,7 +718,7 @@ class SparkContext(config: SparkConf) extends Logging { minPartitions: Int = defaultMinPartitions ): RDD[T] = { sequenceFile(path, classOf[NullWritable], classOf[BytesWritable], minPartitions) - .flatMap(x => Utils.deserialize[Array[T]](x._2.getBytes)) + .flatMap(x => Utils.deserialize[Array[T]](x._2.getBytes, Utils.getContextOrSparkClassLoader)) } protected[spark] def checkpointFile[T: ClassTag]( From 7f0cfe47f4709843d70ceccc25dee7551206ce0d Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Tue, 20 May 2014 10:27:12 -0700 Subject: [PATCH 86/99] [Hotfix] Blacklisted flaky HiveCompatibility test `lateral_view_outer` query sometimes returns a different set of 10 rows. Author: Tathagata Das Closes #838 from tdas/hive-test-fix2 and squashes the following commits: 9128a0d [Tathagata Das] Blacklisted flaky HiveCompatibility test. --- .../spark/sql/hive/execution/HiveCompatibilitySuite.scala | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala index d83732b51e9c2..9031abf733cd4 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala @@ -169,7 +169,10 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter { "archive_corrupt", // No support for case sensitivity is resolution using hive properties atm. - "case_sensitivity" + "case_sensitivity", + + // Flaky test, Hive sometimes returns different set of 10 rows. + "lateral_view_outer" ) /** @@ -476,7 +479,6 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter { "join_view", "lateral_view", "lateral_view_cp", - "lateral_view_outer", "lateral_view_ppd", "lineage1", "literal_double", From 6e337380fc47071fc7fb28d744e8209c729fe1e9 Mon Sep 17 00:00:00 2001 From: Sumedh Mungee Date: Wed, 21 May 2014 01:22:25 -0700 Subject: [PATCH 87/99] [SPARK-1250] Fixed misleading comments in bin/pyspark, bin/spark-class Fixed a couple of misleading comments in bin/pyspark and bin/spark-class. The comments make it seem like the script is looking for the Scala installation when in fact it is looking for Spark. Author: Sumedh Mungee Closes #843 from smungee/spark-1250-fix-comments and squashes the following commits: 26870f3 [Sumedh Mungee] [SPARK-1250] Fixed misleading comments in bin/pyspark and bin/spark-class --- bin/pyspark | 2 +- bin/spark-class | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/bin/pyspark b/bin/pyspark index 3908ffe79939b..d0fa56f31913f 100755 --- a/bin/pyspark +++ b/bin/pyspark @@ -17,7 +17,7 @@ # limitations under the License. # -# Figure out where the Scala framework is installed +# Figure out where Spark is installed FWDIR="$(cd `dirname $0`/..; pwd)" # Export this as SPARK_HOME diff --git a/bin/spark-class b/bin/spark-class index 2e57295fd0234..e884511010c6c 100755 --- a/bin/spark-class +++ b/bin/spark-class @@ -24,7 +24,7 @@ esac SCALA_VERSION=2.10 -# Figure out where the Scala framework is installed +# Figure out where Spark is installed FWDIR="$(cd `dirname $0`/..; pwd)" # Export this as SPARK_HOME From 1014668f2727863fe46f9c75201ee459d093bf0c Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Wed, 21 May 2014 01:23:34 -0700 Subject: [PATCH 88/99] [Docs] Correct example of creating a new SparkConf The example code on the configuration page currently does not compile. Author: Andrew Or Closes #842 from andrewor14/conf-docs and squashes the following commits: aabff57 [Andrew Or] Correct example of creating a new SparkConf --- docs/configuration.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/configuration.md b/docs/configuration.md index f89040d714773..462a9d9013d98 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -23,7 +23,7 @@ cluster (e.g. master URL and application name), as well as arbitrary key-value p `set()` method. For example, we could initialize an application as follows: {% highlight scala %} -val conf = new SparkConf +val conf = new SparkConf() .setMaster("local") .setAppName("CountingSheep") .set("spark.executor.memory", "1g") From 7c79ef7d43de258ad9a5de15c590132bd78ce8dd Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Wed, 21 May 2014 01:25:10 -0700 Subject: [PATCH 89/99] [Minor] Move JdbcRDDSuite to the correct package It was in the wrong package Author: Andrew Or Closes #839 from andrewor14/jdbc-suite and squashes the following commits: f948c5a [Andrew Or] cache -> cache() b215279 [Andrew Or] Move JdbcRDDSuite to the correct package --- .../scala/org/apache/spark/rdd/JdbcRDDSuite.scala | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala index 7c7f69b261a0a..76e317d754ba3 100644 --- a/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala +++ b/core/src/test/scala/org/apache/spark/rdd/JdbcRDDSuite.scala @@ -15,13 +15,13 @@ * limitations under the License. */ -package org.apache.spark +package org.apache.spark.rdd import java.sql._ import org.scalatest.{BeforeAndAfter, FunSuite} -import org.apache.spark.rdd.JdbcRDD +import org.apache.spark.{LocalSparkContext, SparkContext} class JdbcRDDSuite extends FunSuite with BeforeAndAfter with LocalSparkContext { @@ -35,18 +35,18 @@ class JdbcRDDSuite extends FunSuite with BeforeAndAfter with LocalSparkContext { ID INTEGER NOT NULL GENERATED ALWAYS AS IDENTITY (START WITH 1, INCREMENT BY 1), DATA INTEGER )""") - create.close + create.close() val insert = conn.prepareStatement("INSERT INTO FOO(DATA) VALUES(?)") (1 to 100).foreach { i => insert.setInt(1, i * 2) insert.executeUpdate } - insert.close + insert.close() } catch { case e: SQLException if e.getSQLState == "X0Y32" => // table exists } finally { - conn.close + conn.close() } } @@ -57,7 +57,7 @@ class JdbcRDDSuite extends FunSuite with BeforeAndAfter with LocalSparkContext { () => { DriverManager.getConnection("jdbc:derby:target/JdbcRDDSuiteDb") }, "SELECT DATA FROM FOO WHERE ? <= ID AND ID <= ?", 1, 100, 3, - (r: ResultSet) => { r.getInt(1) } ).cache + (r: ResultSet) => { r.getInt(1) } ).cache() assert(rdd.count === 100) assert(rdd.reduce(_+_) === 10100) From ba5d4a99425a2083fea2a9759050c5e770197e23 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Wed, 21 May 2014 11:59:05 -0700 Subject: [PATCH 90/99] [Typo] Stoped -> Stopped Author: Andrew Or Closes #847 from andrewor14/yarn-typo and squashes the following commits: c1906af [Andrew Or] Stoped -> Stopped --- .../spark/scheduler/cluster/YarnClientSchedulerBackend.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala index 2924189077b7d..0ac162538fc4b 100644 --- a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala @@ -113,7 +113,7 @@ private[spark] class YarnClientSchedulerBackend( override def stop() { super.stop() client.stop() - logInfo("Stoped") + logInfo("Stopped") } } From f18fd05b513b136363c94adb3e5b841f8bf48134 Mon Sep 17 00:00:00 2001 From: Kan Zhang Date: Wed, 21 May 2014 13:26:53 -0700 Subject: [PATCH 91/99] [SPARK-1519] Support minPartitions param of wholeTextFiles() in PySpark Author: Kan Zhang Closes #697 from kanzhang/SPARK-1519 and squashes the following commits: 4f8d1ed [Kan Zhang] [SPARK-1519] Support minPartitions param of wholeTextFiles() in PySpark --- python/pyspark/context.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/python/pyspark/context.py b/python/pyspark/context.py index cac133d0fcf6c..c9ff82d23b3cf 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -211,6 +211,13 @@ def defaultParallelism(self): """ return self._jsc.sc().defaultParallelism() + @property + def defaultMinPartitions(self): + """ + Default min number of partitions for Hadoop RDDs when not given by user + """ + return self._jsc.sc().defaultMinPartitions() + def __del__(self): self.stop() @@ -264,7 +271,7 @@ def textFile(self, name, minPartitions=None): return RDD(self._jsc.textFile(name, minPartitions), self, UTF8Deserializer()) - def wholeTextFiles(self, path): + def wholeTextFiles(self, path, minPartitions=None): """ Read a directory of text files from HDFS, a local file system (available on all nodes), or any Hadoop-supported file system @@ -300,7 +307,8 @@ def wholeTextFiles(self, path): >>> sorted(textFiles.collect()) [(u'.../1.txt', u'1'), (u'.../2.txt', u'2')] """ - return RDD(self._jsc.wholeTextFiles(path), self, + minPartitions = minPartitions or self.defaultMinPartitions + return RDD(self._jsc.wholeTextFiles(path, minPartitions), self, PairDeserializer(UTF8Deserializer(), UTF8Deserializer())) def _checkpointFile(self, name, input_deserializer): From bb88875ad52e8209c25e8350af1fe4b7159086ae Mon Sep 17 00:00:00 2001 From: Takuya UESHIN Date: Wed, 21 May 2014 15:37:47 -0700 Subject: [PATCH 92/99] [SPARK-1889] [SQL] Apply splitConjunctivePredicates to join condition while finding join ke... ...ys. When tables are equi-joined by multiple-keys `HashJoin` should be used, but `CartesianProduct` and then `Filter` are used. The join keys are paired by `And` expression so we need to apply `splitConjunctivePredicates` to join condition while finding join keys. Author: Takuya UESHIN Closes #836 from ueshin/issues/SPARK-1889 and squashes the following commits: fe1c387 [Takuya UESHIN] Apply splitConjunctivePredicates to join condition while finding join keys. --- .../sql/catalyst/planning/patterns.scala | 11 ++++++----- .../spark/sql/execution/PlannerSuite.scala | 19 ++++++++++++++++++- 2 files changed, 24 insertions(+), 6 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala index 0e3a8a6bd30a8..4544b32958c7e 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala @@ -129,11 +129,12 @@ object HashFilteredJoin extends Logging with PredicateHelper { // as join keys. def splitPredicates(allPredicates: Seq[Expression], join: Join): Option[ReturnType] = { val Join(left, right, joinType, _) = join - val (joinPredicates, otherPredicates) = allPredicates.partition { - case Equals(l, r) if (canEvaluate(l, left) && canEvaluate(r, right)) || - (canEvaluate(l, right) && canEvaluate(r, left)) => true - case _ => false - } + val (joinPredicates, otherPredicates) = + allPredicates.flatMap(splitConjunctivePredicates).partition { + case Equals(l, r) if (canEvaluate(l, left) && canEvaluate(r, right)) || + (canEvaluate(l, right) && canEvaluate(r, left)) => true + case _ => false + } val joinKeys = joinPredicates.map { case Equals(l, r) if canEvaluate(l, left) && canEvaluate(r, right) => (l, r) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala index e24c74a7a5572..c563d63627544 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala @@ -21,7 +21,7 @@ import org.scalatest.FunSuite import org.apache.spark.sql.TestData._ import org.apache.spark.sql.catalyst.expressions._ -import org.apache.spark.sql.catalyst.plans.logical +import org.apache.spark.sql.catalyst.plans._ import org.apache.spark.sql.execution import org.apache.spark.sql.test.TestSQLContext._ import org.apache.spark.sql.test.TestSQLContext.planner._ @@ -57,4 +57,21 @@ class PlannerSuite extends FunSuite { val planned = PartialAggregation(query) assert(planned.isEmpty) } + + test("equi-join is hash-join") { + val x = testData2.as('x) + val y = testData2.as('y) + val join = x.join(y, Inner, Some("x.a".attr === "y.a".attr)).queryExecution.analyzed + val planned = planner.HashJoin(join) + assert(planned.size === 1) + } + + test("multiple-key equi-join is hash-join") { + val x = testData2.as('x) + val y = testData2.as('y) + val join = x.join(y, Inner, + Some("x.a".attr === "y.a".attr && "x.b".attr === "y.b".attr)).queryExecution.analyzed + val planned = planner.HashJoin(join) + assert(planned.size === 1) + } } From 2a948e7e1a345ae4e3d89ea24123410819d799d1 Mon Sep 17 00:00:00 2001 From: Reynold Xin Date: Wed, 21 May 2014 18:49:12 -0700 Subject: [PATCH 93/99] Configuration documentation updates 1. Add < code > to configuration options 2. List env variables in tabular format to be consistent with other pages. 3. Moved Viewing Spark Properties section up. This is against branch-1.0, but should be cherry picked into master as well. Author: Reynold Xin Closes #851 from rxin/doc-config and squashes the following commits: 28ac0d3 [Reynold Xin] Add to configuration options, and list env variables in a table. (cherry picked from commit 75af8bd3336d09e8c691e54ae9d2358fe1bf3723) Signed-off-by: Reynold Xin --- docs/configuration.md | 194 +++++++++++++++++++++++------------------- 1 file changed, 105 insertions(+), 89 deletions(-) diff --git a/docs/configuration.md b/docs/configuration.md index 462a9d9013d98..4d41c36e38e26 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -47,6 +47,13 @@ Any values specified in the file will be passed on to the application, and merge specified through SparkConf. If the same configuration property exists in both `spark-defaults.conf` and SparkConf, then the latter will take precedence as it is the most application-specific. +## Viewing Spark Properties + +The application web UI at `http://:4040` lists Spark properties in the "Environment" tab. +This is a useful place to check to make sure that your properties have been set correctly. Note +that only values explicitly specified through either `spark-defaults.conf` or SparkConf will +appear. For all other configuration properties, you can assume the default value is used. + ## All Configuration Properties Most of the properties that control internal settings have reasonable default values. However, @@ -55,14 +62,14 @@ there are at least five properties that you will commonly want to control: - + - + - + - + - +
Property NameDefaultMeaning
spark.executor.memoryspark.executor.memory 512m Amount of memory to use per executor process, in the same format as JVM memory strings (e.g. 512m, 2g).
spark.serializerspark.serializer org.apache.spark.serializer.
JavaSerializer		 Class to use for serializing objects that will be sent over the network or need to be cached @@ -73,7 +80,7 @@ there are at least five properties that you will commonly want to control:
spark.kryo.registratorspark.kryo.registrator (none) If you use Kryo serialization, set this class to register your custom classes with Kryo. @@ -83,7 +90,7 @@ there are at least five properties that you will commonly want to control:
spark.local.dirspark.local.dir /tmp Directory to use for "scratch" space in Spark, including map output files and RDDs that get stored @@ -95,7 +102,7 @@ there are at least five properties that you will commonly want to control:
spark.cores.maxspark.cores.max (not set) When running on a standalone deploy cluster or a @@ -114,7 +121,7 @@ Apart from these, the following properties are also available, and may be useful - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - +
Property NameDefaultMeaning
spark.default.parallelismspark.default.parallelism
  • Local mode: number of cores on the local machine
    • @@ -128,7 +135,7 @@ Apart from these, the following properties are also available, and may be useful
spark.storage.memoryFractionspark.storage.memoryFraction 0.6 Fraction of Java heap to use for Spark's memory cache. This should not be larger than the "old" @@ -137,7 +144,7 @@ Apart from these, the following properties are also available, and may be useful
spark.shuffle.memoryFractionspark.shuffle.memoryFraction 0.3 Fraction of Java heap to use for aggregation and cogroups during shuffles, if @@ -148,7 +155,7 @@ Apart from these, the following properties are also available, and may be useful
spark.storage.memoryMapThresholdspark.storage.memoryMapThreshold 8192 Size of a block, in bytes, above which Spark memory maps when reading a block from disk. @@ -157,7 +164,7 @@ Apart from these, the following properties are also available, and may be useful
spark.tachyonStore.baseDirspark.tachyonStore.baseDir System.getProperty("java.io.tmpdir") Directories of the Tachyon File System that store RDDs. The Tachyon file system's URL is set by spark.tachyonStore.url. @@ -165,14 +172,14 @@ Apart from these, the following properties are also available, and may be useful
spark.tachyonStore.urlspark.tachyonStore.url tachyon://localhost:19998 The URL of the underlying Tachyon file system in the TachyonStore.
spark.mesos.coarsespark.mesos.coarse false If set to "true", runs over Mesos clusters in @@ -183,21 +190,21 @@ Apart from these, the following properties are also available, and may be useful
spark.ui.portspark.ui.port 4040 Port for your application's dashboard, which shows memory and workload data
spark.ui.retainedStagesspark.ui.retainedStages 1000 How many stages the Spark UI remembers before garbage collecting.
spark.ui.filtersspark.ui.filters None Comma separated list of filter class names to apply to the Spark web ui. The filter should be a @@ -207,7 +214,7 @@ Apart from these, the following properties are also available, and may be useful
spark.ui.acls.enablespark.ui.acls.enable false Whether spark web ui acls should are enabled. If enabled, this checks to see if the user has @@ -217,7 +224,7 @@ Apart from these, the following properties are also available, and may be useful
spark.ui.view.aclsspark.ui.view.acls Empty Comma separated list of users that have view access to the spark web ui. By default only the @@ -225,35 +232,35 @@ Apart from these, the following properties are also available, and may be useful
spark.ui.killEnabledspark.ui.killEnabled true Allows stages and corresponding jobs to be killed from the web ui.
spark.shuffle.compressspark.shuffle.compress true Whether to compress map output files. Generally a good idea.
spark.shuffle.spill.compressspark.shuffle.spill.compress true Whether to compress data spilled during shuffles.
spark.broadcast.compressspark.broadcast.compress true Whether to compress broadcast variables before sending them. Generally a good idea.
spark.rdd.compressspark.rdd.compress false Whether to compress serialized RDD partitions (e.g. for StorageLevel.MEMORY_ONLY_SER). @@ -261,7 +268,7 @@ Apart from these, the following properties are also available, and may be useful
spark.io.compression.codecspark.io.compression.codec org.apache.spark.io.
LZFCompressionCodec		 The codec used to compress internal data such as RDD partitions and shuffle outputs. By default, Spark provides two @@ -269,14 +276,14 @@ Apart from these, the following properties are also available, and may be useful
spark.io.compression.snappy.block.sizespark.io.compression.snappy.block.size 32768 Block size (in bytes) used in Snappy compression, in the case when Snappy compression codec is used.
spark.scheduler.modespark.scheduler.mode FIFO The scheduling mode between @@ -286,14 +293,14 @@ Apart from these, the following properties are also available, and may be useful
spark.scheduler.revive.intervalspark.scheduler.revive.interval 1000 The interval length for the scheduler to revive the worker resource offers to run tasks. (in milliseconds)
spark.reducer.maxMbInFlightspark.reducer.maxMbInFlight 48 Maximum size (in megabytes) of map outputs to fetch simultaneously from each reduce task. Since @@ -302,14 +309,14 @@ Apart from these, the following properties are also available, and may be useful
spark.closure.serializerspark.closure.serializer org.apache.spark.serializer.
JavaSerializer		 Serializer class to use for closures. Currently only the Java serializer is supported.
spark.kryo.referenceTrackingspark.kryo.referenceTracking true Whether to track references to the same object when serializing data with Kryo, which is @@ -319,7 +326,7 @@ Apart from these, the following properties are also available, and may be useful
spark.kryoserializer.buffer.mbspark.kryoserializer.buffer.mb 2 Maximum object size to allow within Kryo (the library needs to create a buffer at least as @@ -328,7 +335,7 @@ Apart from these, the following properties are also available, and may be useful
spark.serializer.objectStreamResetspark.serializer.objectStreamReset 10000 When serializing using org.apache.spark.serializer.JavaSerializer, the serializer caches @@ -339,14 +346,14 @@ Apart from these, the following properties are also available, and may be useful
spark.broadcast.factoryspark.broadcast.factory org.apache.spark.broadcast.
HttpBroadcastFactory		 Which broadcast implementation to use.
spark.locality.waitspark.locality.wait 3000 Number of milliseconds to wait to launch a data-local task before giving up and launching it @@ -358,7 +365,7 @@ Apart from these, the following properties are also available, and may be useful
spark.locality.wait.processspark.locality.wait.process spark.locality.wait Customize the locality wait for process locality. This affects tasks that attempt to access @@ -366,7 +373,7 @@ Apart from these, the following properties are also available, and may be useful
spark.locality.wait.nodespark.locality.wait.node spark.locality.wait Customize the locality wait for node locality. For example, you can set this to 0 to skip @@ -374,14 +381,14 @@ Apart from these, the following properties are also available, and may be useful
spark.locality.wait.rackspark.locality.wait.rack spark.locality.wait Customize the locality wait for rack locality.
spark.worker.timeoutspark.worker.timeout 60 Number of seconds after which the standalone deploy master considers a worker lost if it @@ -389,7 +396,7 @@ Apart from these, the following properties are also available, and may be useful
spark.worker.cleanup.enabledspark.worker.cleanup.enabled false Enable periodic cleanup of worker / application directories. Note that this only affects standalone @@ -398,7 +405,7 @@ Apart from these, the following properties are also available, and may be useful
spark.worker.cleanup.intervalspark.worker.cleanup.interval 1800 (30 minutes) Controls the interval, in seconds, at which the worker cleans up old application work dirs @@ -406,7 +413,7 @@ Apart from these, the following properties are also available, and may be useful
spark.worker.cleanup.appDataTtlspark.worker.cleanup.appDataTtl 7 * 24 * 3600 (7 days) The number of seconds to retain application work directories on each worker. This is a Time To Live @@ -416,7 +423,7 @@ Apart from these, the following properties are also available, and may be useful
spark.akka.frameSizespark.akka.frameSize 10 Maximum message size to allow in "control plane" communication (for serialized tasks and task @@ -425,7 +432,7 @@ Apart from these, the following properties are also available, and may be useful
spark.akka.threadsspark.akka.threads 4 Number of actor threads to use for communication. Can be useful to increase on large clusters @@ -433,49 +440,49 @@ Apart from these, the following properties are also available, and may be useful
spark.akka.timeoutspark.akka.timeout 100 Communication timeout between Spark nodes, in seconds.
spark.akka.heartbeat.pausesspark.akka.heartbeat.pauses 600 This is set to a larger value to disable failure detector that comes inbuilt akka. It can be enabled again, if you plan to use this feature (Not recommended). Acceptable heart beat pause in seconds for akka. This can be used to control sensitivity to gc pauses. Tune this in combination of `spark.akka.heartbeat.interval` and `spark.akka.failure-detector.threshold` if you need to.
spark.akka.failure-detector.thresholdspark.akka.failure-detector.threshold 300.0 This is set to a larger value to disable failure detector that comes inbuilt akka. It can be enabled again, if you plan to use this feature (Not recommended). This maps to akka's `akka.remote.transport-failure-detector.threshold`. Tune this in combination of `spark.akka.heartbeat.pauses` and `spark.akka.heartbeat.interval` if you need to.
spark.akka.heartbeat.intervalspark.akka.heartbeat.interval 1000 This is set to a larger value to disable failure detector that comes inbuilt akka. It can be enabled again, if you plan to use this feature (Not recommended). A larger interval value in seconds reduces network overhead and a smaller value ( ~ 1 s) might be more informative for akka's failure detector. Tune this in combination of `spark.akka.heartbeat.pauses` and `spark.akka.failure-detector.threshold` if you need to. Only positive use case for using failure detector can be, a sensistive failure detector can help evict rogue executors really quick. However this is usually not the case as gc pauses and network lags are expected in a real spark cluster. Apart from that enabling this leads to a lot of exchanges of heart beats between nodes leading to flooding the network with those.
spark.driver.hostspark.driver.host (local hostname) Hostname or IP address for the driver to listen on.
spark.driver.portspark.driver.port (random) Port for the driver to listen on.
spark.cleaner.ttlspark.cleaner.ttl (infinite) Duration (seconds) of how long Spark will remember any metadata (stages generated, tasks generated, etc.). @@ -485,7 +492,7 @@ Apart from these, the following properties are also available, and may be useful
spark.streaming.blockIntervalspark.streaming.blockInterval 200 Interval (milliseconds) at which data received by Spark Streaming receivers is coalesced @@ -493,7 +500,7 @@ Apart from these, the following properties are also available, and may be useful
spark.streaming.unpersistspark.streaming.unpersist true Force RDDs generated and persisted by Spark Streaming to be automatically unpersisted from @@ -504,7 +511,7 @@ Apart from these, the following properties are also available, and may be useful
spark.task.maxFailuresspark.task.maxFailures 4 Number of individual task failures before giving up on the job. @@ -512,7 +519,7 @@ Apart from these, the following properties are also available, and may be useful
spark.broadcast.blockSizespark.broadcast.blockSize 4096 Size of each piece of a block in kilobytes for TorrentBroadcastFactory. @@ -521,14 +528,14 @@ Apart from these, the following properties are also available, and may be useful
spark.shuffle.consolidateFilesspark.shuffle.consolidateFiles false If set to "true", consolidates intermediate files created during a shuffle. Creating fewer files can improve filesystem performance for shuffles with large numbers of reduce tasks. It is recommended to set this to "true" when using ext4 or xfs filesystems. On ext3, this option might degrade performance on machines with many (>8) cores due to filesystem limitations.
spark.shuffle.file.buffer.kbspark.shuffle.file.buffer.kb 100 Size of the in-memory buffer for each shuffle file output stream, in kilobytes. These buffers @@ -536,7 +543,7 @@ Apart from these, the following properties are also available, and may be useful
spark.shuffle.spillspark.shuffle.spill true If set to "true", limits the amount of memory used during reduces by spilling data out to disk. This spilling @@ -544,56 +551,56 @@ Apart from these, the following properties are also available, and may be useful
spark.speculationspark.speculation false If set to "true", performs speculative execution of tasks. This means if one or more tasks are running slowly in a stage, they will be re-launched.
spark.speculation.intervalspark.speculation.interval 100 How often Spark will check for tasks to speculate, in milliseconds.
spark.speculation.quantilespark.speculation.quantile 0.75 Percentage of tasks which must be complete before speculation is enabled for a particular stage.
spark.speculation.multiplierspark.speculation.multiplier 1.5 How many times slower a task is than the median to be considered for speculation.
spark.logConfspark.logConf false Whether to log the supplied SparkConf as INFO at start of spark context.
spark.eventLog.enabledspark.eventLog.enabled false Whether to log spark events, useful for reconstructing the Web UI after the application has finished.
spark.eventLog.compressspark.eventLog.compress false Whether to compress logged events, if spark.eventLog.enabled is true.
spark.eventLog.dirspark.eventLog.dir file:///tmp/spark-events Base directory in which spark events are logged, if spark.eventLog.enabled is true. @@ -602,7 +609,7 @@ Apart from these, the following properties are also available, and may be useful
spark.deploy.spreadOutspark.deploy.spreadOut true Whether the standalone cluster manager should spread applications out across nodes or try @@ -613,7 +620,7 @@ Apart from these, the following properties are also available, and may be useful
spark.deploy.defaultCoresspark.deploy.defaultCores (infinite) Default number of cores to give to applications in Spark's standalone mode if they don't @@ -626,14 +633,14 @@ Apart from these, the following properties are also available, and may be useful
spark.files.overwritespark.files.overwrite false Whether to overwrite files added through SparkContext.addFile() when the target file exists and its contents do not match those of the source.
spark.files.fetchTimeoutspark.files.fetchTimeout false Communication timeout to use when fetching files added through SparkContext.addFile() from @@ -641,7 +648,7 @@ Apart from these, the following properties are also available, and may be useful
spark.files.userClassPathFirstspark.files.userClassPathFirst false (Experimental) Whether to give user-added jars precedence over Spark's own jars when @@ -650,7 +657,7 @@ Apart from these, the following properties are also available, and may be useful
spark.authenticatespark.authenticate false Whether spark authenticates its internal connections. See spark.authenticate.secret if not @@ -658,7 +665,7 @@ Apart from these, the following properties are also available, and may be useful
spark.authenticate.secretspark.authenticate.secret None Set the secret key used for Spark to authenticate between components. This needs to be set if @@ -666,7 +673,7 @@ Apart from these, the following properties are also available, and may be useful
spark.core.connection.auth.wait.timeoutspark.core.connection.auth.wait.timeout 30 Number of seconds for the connection to wait for authentication to occur before timing @@ -674,14 +681,14 @@ Apart from these, the following properties are also available, and may be useful
spark.task.cpusspark.task.cpus 1 Number of cores to allocate for each task.
spark.executor.extraJavaOptionsspark.executor.extraJavaOptions (none) A string of extra JVM options to pass to executors. For instance, GC settings or other @@ -692,7 +699,7 @@ Apart from these, the following properties are also available, and may be useful
spark.executor.extraClassPathspark.executor.extraClassPath (none) Extra classpath entries to append to the classpath of executors. This exists primarily @@ -701,7 +708,7 @@ Apart from these, the following properties are also available, and may be useful
spark.executor.extraLibraryPathspark.executor.extraLibraryPath (none) Set a special library path to use when launching executor JVM's. @@ -710,13 +717,6 @@ Apart from these, the following properties are also available, and may be useful
-## Viewing Spark Properties - -The application web UI at `http://:4040` lists Spark properties in the "Environment" tab. -This is a useful place to check to make sure that your properties have been set correctly. Note -that only values explicitly specified through either `spark-defaults.conf` or SparkConf will -appear. For all other configuration properties, you can assume the default value is used. - # Environment Variables Certain Spark settings can be configured through environment variables, which are read from the `conf/spark-env.sh` @@ -729,12 +729,28 @@ Note that `conf/spark-env.sh` does not exist by default when Spark is installed. The following variables can be set in `spark-env.sh`: -* `JAVA_HOME`, the location where Java is installed (if it's not on your default `PATH`) -* `PYSPARK_PYTHON`, the Python binary to use for PySpark -* `SPARK_LOCAL_IP`, to configure which IP address of the machine to bind to. -* `SPARK_PUBLIC_DNS`, the hostname your Spark program will advertise to other machines. -* Options for the Spark [standalone cluster scripts](spark-standalone.html#cluster-launch-scripts), - such as number of cores to use on each machine and maximum memory. + + + + + + + + + + + + + + + + + + + +
Environment VariableMeaning
JAVA_HOMELocation where Java is installed (if it's not on your default `PATH`).
PYSPARK_PYTHONPython binary executable to use for PySpark.
SPARK_LOCAL_IPIP address of the machine to bind to.
SPARK_PUBLIC_DNSHostname your Spark program will advertise to other machines.
+ +In addition to the above, there are also options for setting up the Spark [standalone cluster scripts](spark-standalone.html#cluster-launch-scripts), such as number of cores to use on each machine and maximum memory. Since `spark-env.sh` is a shell script, some of these can be set programmatically -- for example, you might compute `SPARK_LOCAL_IP` by looking up the IP of a specific network interface. From dba314029b4c9d72d7e48a2093b39edd01931f57 Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Thu, 22 May 2014 01:52:50 -0700 Subject: [PATCH 94/99] [SPARK-1870] Make spark-submit --jars work in yarn-cluster mode. Sent secondary jars to distributed cache of all containers and add the cached jars to classpath before executors start. Tested on a YARN cluster (CDH-5.0). `spark-submit --jars` also works in standalone server and `yarn-client`. Thanks for @andrewor14 for testing! I removed "Doesn't work for drivers in standalone mode with "cluster" deploy mode." from `spark-submit`'s help message, though we haven't tested mesos yet. CC: @dbtsai @sryza Author: Xiangrui Meng Closes #848 from mengxr/yarn-classpath and squashes the following commits: 23e7df4 [Xiangrui Meng] rename spark.jar to __spark__.jar and app.jar to __app__.jar to avoid confliction apped $CWD/ and $CWD/* to the classpath remove unused methods a40f6ed [Xiangrui Meng] standalone -> cluster 65e04ad [Xiangrui Meng] update spark-submit help message and add a comment for yarn-client 11e5354 [Xiangrui Meng] minor changes 3e7e1c4 [Xiangrui Meng] use sparkConf instead of hadoop conf dc3c825 [Xiangrui Meng] add secondary jars to classpath in yarn --- .../spark/deploy/SparkSubmitArguments.scala | 3 +- .../apache/spark/deploy/yarn/ClientBase.scala | 69 +++++-------------- .../cluster/YarnClientSchedulerBackend.scala | 2 +- 3 files changed, 19 insertions(+), 55 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala index 264d4544cd31c..0cc05fb95aef0 100644 --- a/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala +++ b/core/src/main/scala/org/apache/spark/deploy/SparkSubmitArguments.scala @@ -326,8 +326,7 @@ private[spark] class SparkSubmitArguments(args: Seq[String]) { | --class CLASS_NAME Your application's main class (for Java / Scala apps). | --name NAME A name of your application. | --jars JARS Comma-separated list of local jars to include on the driver - | and executor classpaths. Doesn't work for drivers in - | standalone mode with "cluster" deploy mode. + | and executor classpaths. | --py-files PY_FILES Comma-separated list of .zip or .egg files to place on the | PYTHONPATH for Python apps. | --files FILES Comma-separated list of files to be placed in the working diff --git a/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala index 27a518ccda459..aeb3f0062df3b 100644 --- a/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala +++ b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala @@ -44,7 +44,7 @@ import org.apache.spark.{Logging, SparkConf, SparkContext} * Client submits an application to the YARN ResourceManager. * * Depending on the deployment mode this will launch one of two application master classes: - * 1. In standalone mode, it will launch an [[org.apache.spark.deploy.yarn.ApplicationMaster]] + * 1. In cluster mode, it will launch an [[org.apache.spark.deploy.yarn.ApplicationMaster]] * which launches a driver program inside of the cluster. * 2. In client mode, it will launch an [[org.apache.spark.deploy.yarn.ExecutorLauncher]] to * request executors on behalf of a driver running outside of the cluster. @@ -220,10 +220,11 @@ trait ClientBase extends Logging { } } + var cachedSecondaryJarLinks = ListBuffer.empty[String] val fileLists = List( (args.addJars, LocalResourceType.FILE, true), (args.files, LocalResourceType.FILE, false), (args.archives, LocalResourceType.ARCHIVE, false) ) - fileLists.foreach { case (flist, resType, appMasterOnly) => + fileLists.foreach { case (flist, resType, addToClasspath) => if (flist != null && !flist.isEmpty()) { flist.split(',').foreach { case file: String => val localURI = new URI(file.trim()) @@ -232,11 +233,15 @@ trait ClientBase extends Logging { val linkname = Option(localURI.getFragment()).getOrElse(localPath.getName()) val destPath = copyRemoteFile(dst, localPath, replication) distCacheMgr.addResource(fs, conf, destPath, localResources, resType, - linkname, statCache, appMasterOnly) + linkname, statCache) + if (addToClasspath) { + cachedSecondaryJarLinks += linkname + } } } } } + sparkConf.set(ClientBase.CONF_SPARK_YARN_SECONDARY_JARS, cachedSecondaryJarLinks.mkString(",")) UserGroupInformation.getCurrentUser().addCredentials(credentials) localResources @@ -374,11 +379,12 @@ trait ClientBase extends Logging { } object ClientBase { - val SPARK_JAR: String = "spark.jar" - val APP_JAR: String = "app.jar" + val SPARK_JAR: String = "__spark__.jar" + val APP_JAR: String = "__app__.jar" val LOG4J_PROP: String = "log4j.properties" val LOG4J_CONF_ENV_KEY: String = "SPARK_LOG4J_CONF" val LOCAL_SCHEME = "local" + val CONF_SPARK_YARN_SECONDARY_JARS = "spark.yarn.secondary.jars" def getSparkJar = sys.env.get("SPARK_JAR").getOrElse(SparkContext.jarOfClass(this.getClass).head) @@ -479,66 +485,25 @@ object ClientBase { extraClassPath.foreach(addClasspathEntry) - addClasspathEntry(Environment.PWD.$()) + val cachedSecondaryJarLinks = + sparkConf.getOption(CONF_SPARK_YARN_SECONDARY_JARS).getOrElse("").split(",") // Normally the users app.jar is last in case conflicts with spark jars if (sparkConf.get("spark.yarn.user.classpath.first", "false").toBoolean) { addPwdClasspathEntry(APP_JAR) + cachedSecondaryJarLinks.foreach(addPwdClasspathEntry) addPwdClasspathEntry(SPARK_JAR) ClientBase.populateHadoopClasspath(conf, env) } else { addPwdClasspathEntry(SPARK_JAR) ClientBase.populateHadoopClasspath(conf, env) addPwdClasspathEntry(APP_JAR) + cachedSecondaryJarLinks.foreach(addPwdClasspathEntry) } + // Append all class files and jar files under the working directory to the classpath. + addClasspathEntry(Environment.PWD.$()) addPwdClasspathEntry("*") } - /** - * Adds the user jars which have local: URIs (or alternate names, such as APP_JAR) explicitly - * to the classpath. - */ - private def addUserClasspath(args: ClientArguments, env: HashMap[String, String]) = { - if (args != null) { - addClasspathEntry(args.userJar, APP_JAR, env) - } - - if (args != null && args.addJars != null) { - args.addJars.split(",").foreach { case file: String => - addClasspathEntry(file, null, env) - } - } - } - - /** - * Adds the given path to the classpath, handling "local:" URIs correctly. - * - * If an alternate name for the file is given, and it's not a "local:" file, the alternate - * name will be added to the classpath (relative to the job's work directory). - * - * If not a "local:" file and no alternate name, the environment is not modified. - * - * @param path Path to add to classpath (optional). - * @param fileName Alternate name for the file (optional). - * @param env Map holding the environment variables. - */ - private def addClasspathEntry(path: String, fileName: String, - env: HashMap[String, String]) : Unit = { - if (path != null) { - scala.util.control.Exception.ignoring(classOf[URISyntaxException]) { - val localPath = getLocalPath(path) - if (localPath != null) { - YarnSparkHadoopUtil.addToEnvironment(env, Environment.CLASSPATH.name, localPath, - File.pathSeparator) - return - } - } - } - if (fileName != null) { - YarnSparkHadoopUtil.addToEnvironment(env, Environment.CLASSPATH.name, - Environment.PWD.$() + Path.SEPARATOR + fileName, File.pathSeparator); - } - } - /** * Returns the local path if the URI is a "local:" URI, or null otherwise. */ diff --git a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala index 0ac162538fc4b..e01ed5a57d697 100644 --- a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala @@ -52,7 +52,7 @@ private[spark] class YarnClientSchedulerBackend( val argsArrayBuf = new ArrayBuffer[String]() argsArrayBuf += ( "--class", "notused", - "--jar", null, + "--jar", null, // The primary jar will be added dynamically in SparkContext. "--args", hostport, "--am-class", classOf[ExecutorLauncher].getName ) From f9f5fd5f4e81828a3e0c391892e0f28751568843 Mon Sep 17 00:00:00 2001 From: Aaron Davidson Date: Thu, 22 May 2014 15:11:05 -0700 Subject: [PATCH 95/99] Fix UISuite unit test that fails under Jenkins contention Due to perhaps zombie processes on Jenkins, it seems that at least 10 Spark ports are in use. It also doesn't matter that the port increases when used, it could in fact go down -- the only part that matters is that it selects a different port rather than failing to bind. Changed test to match this. Thanks to @andrewor14 for helping diagnose this. Author: Aaron Davidson Closes #857 from aarondav/tiny and squashes the following commits: c199ec8 [Aaron Davidson] Fix UISuite unit test that fails under Jenkins contention --- core/src/test/scala/org/apache/spark/ui/UISuite.scala | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/core/src/test/scala/org/apache/spark/ui/UISuite.scala b/core/src/test/scala/org/apache/spark/ui/UISuite.scala index fff8020ade6d1..038746d2eda4b 100644 --- a/core/src/test/scala/org/apache/spark/ui/UISuite.scala +++ b/core/src/test/scala/org/apache/spark/ui/UISuite.scala @@ -94,7 +94,7 @@ class UISuite extends FunSuite { } } - test("jetty port increases under contention") { + test("jetty selects different port under contention") { val startPort = 4040 val server = new Server(startPort) @@ -110,8 +110,9 @@ class UISuite extends FunSuite { // Allow some wiggle room in case ports on the machine are under contention val boundPort1 = serverInfo1.boundPort val boundPort2 = serverInfo2.boundPort - assert(boundPort1 > startPort && boundPort1 < startPort + 10) - assert(boundPort2 > boundPort1 && boundPort2 < boundPort1 + 10) + assert(boundPort1 != startPort) + assert(boundPort2 != startPort) + assert(boundPort1 != boundPort2) } test("jetty binds to port 0 correctly") { From 8edbee7d1b4afc192d97ba192a5526affc464205 Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Thu, 22 May 2014 20:25:41 -0700 Subject: [PATCH 96/99] [SPARK-1897] Respect spark.jars (and --jars) in spark-shell Spark shell currently overwrites `spark.jars` with `ADD_JARS`. In all modes except yarn-cluster, this means the `--jar` flag passed to `bin/spark-shell` is also discarded. However, in the [docs](http://people.apache.org/~pwendell/spark-1.0.0-rc7-docs/scala-programming-guide.html#initializing-spark), we explicitly tell the users to add the jars this way. Author: Andrew Or Closes #849 from andrewor14/shell-jars and squashes the following commits: 928a7e6 [Andrew Or] ',' -> "," (minor) afc357c [Andrew Or] Handle spark.jars == "" in SparkILoop, not SparkSubmit c6da113 [Andrew Or] Do not set spark.jars to "" d8549f7 [Andrew Or] Respect spark.jars and --jars in spark-shell --- .../src/main/scala/org/apache/spark/repl/SparkILoop.scala | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala index 296da740687ec..55684e94bd614 100644 --- a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala +++ b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala @@ -993,7 +993,13 @@ object SparkILoop { implicit def loopToInterpreter(repl: SparkILoop): SparkIMain = repl.intp private def echo(msg: String) = Console println msg - def getAddedJars: Array[String] = Option(System.getenv("ADD_JARS")).map(_.split(',')).getOrElse(new Array[String](0)) + def getAddedJars: Array[String] = { + val envJars = sys.env.get("ADD_JARS") + val propJars = sys.props.get("spark.jars").flatMap { p => + if (p == "") None else Some(p) + } + propJars.orElse(envJars).map(_.split(",")).getOrElse(Array.empty) + } // Designed primarily for use by test code: take a String with a // bunch of code, and prints out a transcript of what it would look From cce77457e00aa5f1f4db3d50454cf257efb156ed Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Thu, 22 May 2014 20:32:27 -0700 Subject: [PATCH 97/99] [SPARK-1896] Respect spark.master (and --master) before MASTER in spark-shell The hierarchy for configuring the Spark master in the shell is as follows: ``` MASTER > --master > spark.master (spark-defaults.conf) ``` This is inconsistent with the way we run normal applications, which is: ``` --master > spark.master (spark-defaults.conf) > MASTER ``` I was trying to run a shell locally on a standalone cluster launched through the ec2 scripts, which automatically set `MASTER` in spark-env.sh. It was surprising to me that `--master` didn't take effect, considering that this is the way we tell users to set their masters [here](http://people.apache.org/~pwendell/spark-1.0.0-rc7-docs/scala-programming-guide.html#initializing-spark). Author: Andrew Or Closes #846 from andrewor14/shell-master and squashes the following commits: 2cb81c9 [Andrew Or] Respect spark.master before MASTER in REPL --- repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala index 55684e94bd614..5f34362ccd973 100644 --- a/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala +++ b/repl/src/main/scala/org/apache/spark/repl/SparkILoop.scala @@ -962,11 +962,10 @@ class SparkILoop(in0: Option[BufferedReader], protected val out: JPrintWriter, private def getMaster(): String = { val master = this.master match { case Some(m) => m - case None => { + case None => val envMaster = sys.env.get("MASTER") val propMaster = sys.props.get("spark.master") - envMaster.orElse(propMaster).getOrElse("local[*]") - } + propMaster.orElse(envMaster).getOrElse("local[*]") } master } From b2bdd0e505f1ae3d39c46139f17bd43779ece635 Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Thu, 22 May 2014 20:48:55 -0700 Subject: [PATCH 98/99] Updated scripts for auditing releases - Added script to automatically generate change list CHANGES.txt - Added test for verifying linking against maven distributions of `spark-sql` and `spark-hive` - Added SBT projects for testing functionality of `spark-sql` and `spark-hive` - Fixed issues in existing tests that might have come up because of changes in Spark 1.0 Author: Tathagata Das Closes #844 from tdas/update-dev-scripts and squashes the following commits: 25090ba [Tathagata Das] Added missing license e2e20b3 [Tathagata Das] Updated tests for auditing releases. --- dev/audit-release/audit_release.py | 11 +- .../src/main/java/SimpleApp.java | 1 + .../src/main/scala/SparkApp.scala | 2 +- dev/audit-release/sbt_app_hive/build.sbt | 29 +++ dev/audit-release/sbt_app_hive/data.txt | 9 + .../src/main/resources/hive-site.xml | 213 ++++++++++++++++++ .../sbt_app_hive/src/main/scala/HiveApp.scala | 57 +++++ dev/audit-release/sbt_app_sql/build.sbt | 29 +++ .../sbt_app_sql/src/main/scala/SqlApp.scala | 57 +++++ .../src/main/scala/StreamingApp.scala | 1 - dev/create-release/generate-changelist.py | 144 ++++++++++++ 11 files changed, 547 insertions(+), 6 deletions(-) create mode 100644 dev/audit-release/sbt_app_hive/build.sbt create mode 100644 dev/audit-release/sbt_app_hive/data.txt create mode 100644 dev/audit-release/sbt_app_hive/src/main/resources/hive-site.xml create mode 100644 dev/audit-release/sbt_app_hive/src/main/scala/HiveApp.scala create mode 100644 dev/audit-release/sbt_app_sql/build.sbt create mode 100644 dev/audit-release/sbt_app_sql/src/main/scala/SqlApp.scala create mode 100755 dev/create-release/generate-changelist.py diff --git a/dev/audit-release/audit_release.py b/dev/audit-release/audit_release.py index 4a816d4101e57..8c7573b91f688 100755 --- a/dev/audit-release/audit_release.py +++ b/dev/audit-release/audit_release.py @@ -93,9 +93,12 @@ def get_url(url): # For each of these modules, we'll test an 'empty' application in sbt and # maven that links against them. This will catch issues with messed up # dependencies within those projects. -modules = ["spark-core", "spark-bagel", "spark-mllib", "spark-streaming", "spark-repl", - "spark-graphx", "spark-streaming-flume", "spark-streaming-kafka", - "spark-streaming-mqtt", "spark-streaming-twitter", "spark-streaming-zeromq"] +modules = [ + "spark-core", "spark-bagel", "spark-mllib", "spark-streaming", "spark-repl", + "spark-graphx", "spark-streaming-flume", "spark-streaming-kafka", + "spark-streaming-mqtt", "spark-streaming-twitter", "spark-streaming-zeromq", + "spark-catalyst", "spark-sql", "spark-hive" +] modules = map(lambda m: "%s_%s" % (m, SCALA_BINARY_VERSION), modules) # Check for directories that might interfere with tests @@ -122,7 +125,7 @@ def ensure_path_not_present(x): os.chdir(original_dir) # SBT application tests -for app in ["sbt_app_core", "sbt_app_graphx", "sbt_app_streaming"]: +for app in ["sbt_app_core", "sbt_app_graphx", "sbt_app_streaming", "sbt_app_sql", "sbt_app_hive"]: os.chdir(app) ret = run_cmd("sbt clean run", exit_on_failure=False) test(ret == 0, "sbt application (%s)" % app) diff --git a/dev/audit-release/maven_app_core/src/main/java/SimpleApp.java b/dev/audit-release/maven_app_core/src/main/java/SimpleApp.java index 6b65dda39b1a2..5217689e7c092 100644 --- a/dev/audit-release/maven_app_core/src/main/java/SimpleApp.java +++ b/dev/audit-release/maven_app_core/src/main/java/SimpleApp.java @@ -37,5 +37,6 @@ public static void main(String[] args) { System.exit(-1); } System.out.println("Test succeeded"); + sc.stop(); } } diff --git a/dev/audit-release/sbt_app_core/src/main/scala/SparkApp.scala b/dev/audit-release/sbt_app_core/src/main/scala/SparkApp.scala index a89b0d7d38bf1..77bbd167b199a 100644 --- a/dev/audit-release/sbt_app_core/src/main/scala/SparkApp.scala +++ b/dev/audit-release/sbt_app_core/src/main/scala/SparkApp.scala @@ -19,6 +19,7 @@ package main.scala import scala.util.Try +import org.apache.spark.SparkConf import org.apache.spark.SparkContext import org.apache.spark.SparkContext._ @@ -30,7 +31,6 @@ object SimpleApp { } val logFile = "input.txt" val sc = new SparkContext(conf) - SparkContext.jarOfClass(this.getClass).foreach(sc.addJar) val logData = sc.textFile(logFile, 2).cache() val numAs = logData.filter(line => line.contains("a")).count() val numBs = logData.filter(line => line.contains("b")).count() diff --git a/dev/audit-release/sbt_app_hive/build.sbt b/dev/audit-release/sbt_app_hive/build.sbt new file mode 100644 index 0000000000000..7ac1be729c561 --- /dev/null +++ b/dev/audit-release/sbt_app_hive/build.sbt @@ -0,0 +1,29 @@ +// +// Licensed to the Apache Software Foundation (ASF) under one or more +// contributor license agreements. See the NOTICE file distributed with +// this work for additional information regarding copyright ownership. +// The ASF licenses this file to You under the Apache License, Version 2.0 +// (the "License"); you may not use this file except in compliance with +// the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. +// + +name := "Simple Project" + +version := "1.0" + +scalaVersion := System.getenv.get("SCALA_VERSION") + +libraryDependencies += "org.apache.spark" %% "spark-hive" % System.getenv.get("SPARK_VERSION") + +resolvers ++= Seq( + "Spark Release Repository" at System.getenv.get("SPARK_RELEASE_REPOSITORY"), + "Akka Repository" at "http://repo.akka.io/releases/", + "Spray Repository" at "http://repo.spray.cc/") diff --git a/dev/audit-release/sbt_app_hive/data.txt b/dev/audit-release/sbt_app_hive/data.txt new file mode 100644 index 0000000000000..0229e67f51e01 --- /dev/null +++ b/dev/audit-release/sbt_app_hive/data.txt @@ -0,0 +1,9 @@ +0val_0 +1val_1 +2val_2 +3val_3 +4val_4 +5val_5 +6val_6 +7val_7 +9val_9 diff --git a/dev/audit-release/sbt_app_hive/src/main/resources/hive-site.xml b/dev/audit-release/sbt_app_hive/src/main/resources/hive-site.xml new file mode 100644 index 0000000000000..93b835813d535 --- /dev/null +++ b/dev/audit-release/sbt_app_hive/src/main/resources/hive-site.xml @@ -0,0 +1,213 @@ + + + + + + + + + + + + + + + + + + build.dir + ${user.dir}/build + + + + build.dir.hive + ${build.dir}/hive + + + + hadoop.tmp.dir + ${build.dir.hive}/test/hadoop-${user.name} + A base for other temporary directories. + + + + + + hive.exec.scratchdir + ${build.dir}/scratchdir + Scratch space for Hive jobs + + + + hive.exec.local.scratchdir + ${build.dir}/localscratchdir/ + Local scratch space for Hive jobs + + + + javax.jdo.option.ConnectionURL + + jdbc:derby:;databaseName=../build/test/junit_metastore_db;create=true + + + + javax.jdo.option.ConnectionDriverName + org.apache.derby.jdbc.EmbeddedDriver + + + + javax.jdo.option.ConnectionUserName + APP + + + + javax.jdo.option.ConnectionPassword + mine + + + + + hive.metastore.warehouse.dir + ${test.warehouse.dir} + + + + + hive.metastore.metadb.dir + ${build.dir}/test/data/metadb/ + + Required by metastore server or if the uris argument below is not supplied + + + + + test.log.dir + ${build.dir}/test/logs + + + + + test.src.dir + ${build.dir}/src/test + + + + + + + hive.jar.path + ${build.dir.hive}/ql/hive-exec-${version}.jar + + + + + hive.metastore.rawstore.impl + org.apache.hadoop.hive.metastore.ObjectStore + Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. This class is used to store and retrieval of raw metadata objects such as table, database + + + + hive.querylog.location + ${build.dir}/tmp + Location of the structured hive logs + + + + + + hive.task.progress + false + Track progress of a task + + + + hive.support.concurrency + false + Whether hive supports concurrency or not. A zookeeper instance must be up and running for the default hive lock manager to support read-write locks. + + + + fs.pfile.impl + org.apache.hadoop.fs.ProxyLocalFileSystem + A proxy for local file system used for cross file system testing + + + + hive.exec.mode.local.auto + false + + Let hive determine whether to run in local mode automatically + Disabling this for tests so that minimr is not affected + + + + + hive.auto.convert.join + false + Whether Hive enable the optimization about converting common join into mapjoin based on the input file size + + + + hive.ignore.mapjoin.hint + false + Whether Hive ignores the mapjoin hint + + + + hive.input.format + org.apache.hadoop.hive.ql.io.CombineHiveInputFormat + The default input format, if it is not specified, the system assigns it. It is set to HiveInputFormat for hadoop versions 17, 18 and 19, whereas it is set to CombineHiveInputFormat for hadoop 20. The user can always overwrite it - if there is a bug in CombineHiveInputFormat, it can always be manually set to HiveInputFormat. + + + + hive.default.rcfile.serde + org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + The default SerDe hive will use for the rcfile format + + + diff --git a/dev/audit-release/sbt_app_hive/src/main/scala/HiveApp.scala b/dev/audit-release/sbt_app_hive/src/main/scala/HiveApp.scala new file mode 100644 index 0000000000000..7257d17d10116 --- /dev/null +++ b/dev/audit-release/sbt_app_hive/src/main/scala/HiveApp.scala @@ -0,0 +1,57 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package main.scala + +import scala.collection.mutable.{ListBuffer, Queue} + +import org.apache.spark.SparkConf +import org.apache.spark.SparkContext +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.hive.LocalHiveContext + +case class Person(name: String, age: Int) + +object SparkSqlExample { + + def main(args: Array[String]) { + val conf = sys.env.get("SPARK_AUDIT_MASTER") match { + case Some(master) => new SparkConf().setAppName("Simple Sql App").setMaster(master) + case None => new SparkConf().setAppName("Simple Sql App") + } + val sc = new SparkContext(conf) + val hiveContext = new LocalHiveContext(sc) + + import hiveContext._ + hql("DROP TABLE IF EXISTS src") + hql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)") + hql("LOAD DATA LOCAL INPATH 'data.txt' INTO TABLE src") + val results = hql("FROM src SELECT key, value WHERE key >= 0 AND KEY < 5").collect() + results.foreach(println) + + def test(f: => Boolean, failureMsg: String) = { + if (!f) { + println(failureMsg) + System.exit(-1) + } + } + + test(results.size == 5, "Unexpected number of selected elements: " + results) + println("Test succeeded") + sc.stop() + } +} diff --git a/dev/audit-release/sbt_app_sql/build.sbt b/dev/audit-release/sbt_app_sql/build.sbt new file mode 100644 index 0000000000000..6e0ad3b4b2960 --- /dev/null +++ b/dev/audit-release/sbt_app_sql/build.sbt @@ -0,0 +1,29 @@ +// +// Licensed to the Apache Software Foundation (ASF) under one or more +// contributor license agreements. See the NOTICE file distributed with +// this work for additional information regarding copyright ownership. +// The ASF licenses this file to You under the Apache License, Version 2.0 +// (the "License"); you may not use this file except in compliance with +// the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. +// + +name := "Simple Project" + +version := "1.0" + +scalaVersion := System.getenv.get("SCALA_VERSION") + +libraryDependencies += "org.apache.spark" %% "spark-sql" % System.getenv.get("SPARK_VERSION") + +resolvers ++= Seq( + "Spark Release Repository" at System.getenv.get("SPARK_RELEASE_REPOSITORY"), + "Akka Repository" at "http://repo.akka.io/releases/", + "Spray Repository" at "http://repo.spray.cc/") diff --git a/dev/audit-release/sbt_app_sql/src/main/scala/SqlApp.scala b/dev/audit-release/sbt_app_sql/src/main/scala/SqlApp.scala new file mode 100644 index 0000000000000..50af90c213b5a --- /dev/null +++ b/dev/audit-release/sbt_app_sql/src/main/scala/SqlApp.scala @@ -0,0 +1,57 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package main.scala + +import scala.collection.mutable.{ListBuffer, Queue} + +import org.apache.spark.SparkConf +import org.apache.spark.SparkContext +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.SQLContext + +case class Person(name: String, age: Int) + +object SparkSqlExample { + + def main(args: Array[String]) { + val conf = sys.env.get("SPARK_AUDIT_MASTER") match { + case Some(master) => new SparkConf().setAppName("Simple Sql App").setMaster(master) + case None => new SparkConf().setAppName("Simple Sql App") + } + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + + import sqlContext._ + val people = sc.makeRDD(1 to 100, 10).map(x => Person(s"Name$x", x)) + people.registerAsTable("people") + val teenagers = sql("SELECT name FROM people WHERE age >= 13 AND age <= 19") + val teenagerNames = teenagers.map(t => "Name: " + t(0)).collect() + teenagerNames.foreach(println) + + def test(f: => Boolean, failureMsg: String) = { + if (!f) { + println(failureMsg) + System.exit(-1) + } + } + + test(teenagerNames.size == 7, "Unexpected number of selected elements: " + teenagerNames) + println("Test succeeded") + sc.stop() + } +} diff --git a/dev/audit-release/sbt_app_streaming/src/main/scala/StreamingApp.scala b/dev/audit-release/sbt_app_streaming/src/main/scala/StreamingApp.scala index a1d8971abe9a4..58a662bd9b2e8 100644 --- a/dev/audit-release/sbt_app_streaming/src/main/scala/StreamingApp.scala +++ b/dev/audit-release/sbt_app_streaming/src/main/scala/StreamingApp.scala @@ -32,7 +32,6 @@ object SparkStreamingExample { case None => new SparkConf().setAppName("Simple Streaming App") } val ssc = new StreamingContext(conf, Seconds(1)) - SparkContext.jarOfClass(this.getClass).foreach(ssc.sparkContext.addJar) val seen = ListBuffer[RDD[Int]]() val rdd1 = ssc.sparkContext.makeRDD(1 to 100, 10) diff --git a/dev/create-release/generate-changelist.py b/dev/create-release/generate-changelist.py new file mode 100755 index 0000000000000..13b744ec1b37e --- /dev/null +++ b/dev/create-release/generate-changelist.py @@ -0,0 +1,144 @@ +#!/usr/bin/python + +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +# Creates CHANGES.txt from git history. +# +# Usage: +# First set the new release version and old CHANGES.txt version in this file. +# Make sure you have SPARK_HOME set. +# $ python generate-changelist.py + + +import os +import sys +import subprocess +import time +import traceback + +SPARK_HOME = os.environ["SPARK_HOME"] +NEW_RELEASE_VERSION = "1.0.0" +PREV_RELEASE_GIT_TAG = "v0.9.1" + +CHANGELIST = "CHANGES.txt" +OLD_CHANGELIST = "%s.old" % (CHANGELIST) +NEW_CHANGELIST = "%s.new" % (CHANGELIST) +TMP_CHANGELIST = "%s.tmp" % (CHANGELIST) + +# date before first PR in TLP Spark repo +SPARK_REPO_CHANGE_DATE1 = time.strptime("2014-02-26", "%Y-%m-%d") +# date after last PR in incubator Spark repo +SPARK_REPO_CHANGE_DATE2 = time.strptime("2014-03-01", "%Y-%m-%d") +# Threshold PR number that differentiates PRs to TLP +# and incubator repos +SPARK_REPO_PR_NUM_THRESH = 200 + +LOG_FILE_NAME = "changes_%s" % time.strftime("%h_%m_%Y_%I_%M_%S") +LOG_FILE = open(LOG_FILE_NAME, 'w') + +def run_cmd(cmd): + try: + print >> LOG_FILE, "Running command: %s" % cmd + output = subprocess.check_output(cmd, shell=True, stderr=LOG_FILE) + print >> LOG_FILE, "Output: %s" % output + return output + except: + traceback.print_exc() + cleanup() + sys.exit(1) + +def append_to_changelist(string): + with open(TMP_CHANGELIST, "a") as f: + print >> f, string + +def cleanup(ask = True): + if ask == True: + print "OK to delete temporary and log files? (y/N): " + response = raw_input() + if ask == False or (ask == True and response == "y"): + if os.path.isfile(TMP_CHANGELIST): + os.remove(TMP_CHANGELIST) + if os.path.isfile(OLD_CHANGELIST): + os.remove(OLD_CHANGELIST) + LOG_FILE.close() + os.remove(LOG_FILE_NAME) + +print "Generating new %s for Spark release %s" % (CHANGELIST, NEW_RELEASE_VERSION) +os.chdir(SPARK_HOME) +if os.path.isfile(TMP_CHANGELIST): + os.remove(TMP_CHANGELIST) +if os.path.isfile(OLD_CHANGELIST): + os.remove(OLD_CHANGELIST) + +append_to_changelist("Spark Change Log") +append_to_changelist("----------------") +append_to_changelist("") +append_to_changelist("Release %s" % NEW_RELEASE_VERSION) +append_to_changelist("") + +print "Getting commits between tag %s and HEAD" % PREV_RELEASE_GIT_TAG +hashes = run_cmd("git log %s..HEAD --pretty='%%h'" % PREV_RELEASE_GIT_TAG).split() + +print "Getting details of %s commits" % len(hashes) +for h in hashes: + date = run_cmd("git log %s -1 --pretty='%%ad' --date=iso | head -1" % h).strip() + subject = run_cmd("git log %s -1 --pretty='%%s' | head -1" % h).strip() + body = run_cmd("git log %s -1 --pretty='%%b'" % h) + committer = run_cmd("git log %s -1 --pretty='%%cn <%%ce>' | head -1" % h).strip() + body_lines = body.split("\n") + + if "Merge pull" in subject: + ## Parse old format commit message + append_to_changelist(" %s %s" % (h, date)) + append_to_changelist(" %s" % subject) + append_to_changelist(" [%s]" % body_lines[0]) + append_to_changelist("") + + elif "maven-release" not in subject: + ## Parse new format commit message + # Get authors from commit message, committer otherwise + authors = [committer] + if "Author:" in body: + authors = [line.split(":")[1].strip() for line in body_lines if "Author:" in line] + + # Generate GitHub PR URL for easy access if possible + github_url = "" + if "Closes #" in body: + pr_num = [line.split()[1].lstrip("#") for line in body_lines if "Closes #" in line][0] + github_url = "github.com/apache/spark/pull/%s" % pr_num + day = time.strptime(date.split()[0], "%Y-%m-%d") + if day < SPARK_REPO_CHANGE_DATE1 or (day < SPARK_REPO_CHANGE_DATE2 and pr_num < SPARK_REPO_PR_NUM_THRESH): + github_url = "github.com/apache/incubator-spark/pull/%s" % pr_num + + append_to_changelist(" %s" % subject) + append_to_changelist(" %s" % ', '.join(authors)) + # for author in authors: + # append_to_changelist(" %s" % author) + append_to_changelist(" %s" % date) + if len(github_url) > 0: + append_to_changelist(" Commit: %s, %s" % (h, github_url)) + else: + append_to_changelist(" Commit: %s" % h) + append_to_changelist("") + +# Append old change list +print "Appending changelist from tag %s" % PREV_RELEASE_GIT_TAG +run_cmd("git show %s:%s | tail -n +3 >> %s" % (PREV_RELEASE_GIT_TAG, CHANGELIST, TMP_CHANGELIST)) +run_cmd("cp %s %s" % (TMP_CHANGELIST, NEW_CHANGELIST)) +print "New change list generated as %s" % NEW_CHANGELIST +cleanup(False) + From a08262d8769808dd3a8ee1b1e80fbf6ac13a557c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?baishuo=28=E7=99=BD=E7=A1=95=29?= Date: Fri, 23 May 2014 13:02:40 -0700 Subject: [PATCH 99/99] Update LBFGSSuite.scala MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit the same reason as https://github.com/apache/spark/pull/588 Author: baishuo(白硕) Closes #815 from baishuo/master and squashes the following commits: 6876c1e [baishuo(白硕)] Update LBFGSSuite.scala --- .../org/apache/spark/mllib/optimization/LBFGSSuite.scala | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mllib/src/test/scala/org/apache/spark/mllib/optimization/LBFGSSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/optimization/LBFGSSuite.scala index 6af1b502eb4dd..820eca9b1bf65 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/optimization/LBFGSSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/optimization/LBFGSSuite.scala @@ -43,7 +43,7 @@ class LBFGSSuite extends FunSuite with LocalSparkContext with ShouldMatchers { // Add an extra variable consisting of all 1.0's for the intercept. val testData = GradientDescentSuite.generateGDInput(A, B, nPoints, 42) val data = testData.map { case LabeledPoint(label, features) => - label -> Vectors.dense(1.0, features.toArray: _*) + label -> Vectors.dense(1.0 +: features.toArray) } lazy val dataRDD = sc.parallelize(data, 2).cache() @@ -55,7 +55,7 @@ class LBFGSSuite extends FunSuite with LocalSparkContext with ShouldMatchers { test("LBFGS loss should be decreasing and match the result of Gradient Descent.") { val regParam = 0 - val initialWeightsWithIntercept = Vectors.dense(1.0, initialWeights: _*) + val initialWeightsWithIntercept = Vectors.dense(1.0 +: initialWeights.toArray) val convergenceTol = 1e-12 val maxNumIterations = 10