Merge remote-tracking branch 'apache-github/master' into network-rece…

…iver-api Conflicts: external/mqtt/src/main/scala/org/apache/spark/streaming/mqtt/MQTTInputDStream.scala streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala streaming/src/main/scala/org/apache/spark/streaming/dstream/NetworkInputDStream.scala streaming/src/main/scala/org/apache/spark/streaming/scheduler/NetworkInputTracker.scala streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala
pdeyhim · Apr 15, 2014 · 9e37a0b · 9e37a0b
2 parents 3223e95 + 037fe4d
commit 9e37a0b
Show file tree

Hide file tree

Showing 681 changed files with 20,125 additions and 6,106 deletions.
diff --git a/.rat-excludes b/.rat-excludes
@@ -39,3 +39,6 @@ work
 .*\.q
 golden
 test.out/*
+.*iml
+python/metastore/service.properties
+python/metastore/db.lck
diff --git a/assembly/pom.xml b/assembly/pom.xml
@@ -163,6 +163,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>
@@ -208,7 +218,7 @@
           <plugin>
             <groupId>org.codehaus.mojo</groupId>
             <artifactId>buildnumber-maven-plugin</artifactId>
-            <version>1.1</version>
+            <version>1.2</version>
             <executions>
               <execution>
                 <phase>validate</phase>

diff --git a/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala b/bagel/src/main/scala/org/apache/spark/bagel/Bagel.scala
@@ -220,27 +220,31 @@ object Bagel extends Logging {
    */
   private def comp[K: Manifest, V <: Vertex, M <: Message[K], C](
     sc: SparkContext,
-    grouped: RDD[(K, (Seq[C], Seq[V]))],
+    grouped: RDD[(K, (Iterable[C], Iterable[V]))],
     compute: (V, Option[C]) => (V, Array[M]),
     storageLevel: StorageLevel
   ): (RDD[(K, (V, Array[M]))], Int, Int) = {
     var numMsgs = sc.accumulator(0)
     var numActiveVerts = sc.accumulator(0)
-    val processed = grouped.flatMapValues {
-      case (_, vs) if vs.size == 0 => None
-      case (c, vs) =>
+    val processed = grouped.mapValues(x => (x._1.iterator, x._2.iterator))
+      .flatMapValues {
+      case (_, vs) if !vs.hasNext => None
+      case (c, vs) => {
         val (newVert, newMsgs) =
-          compute(vs(0), c match {
-            case Seq(comb) => Some(comb)
-            case Seq() => None
-          })
+          compute(vs.next,
+            c.hasNext match {
+              case true => Some(c.next)
+              case false => None
+            }
+          )
 
         numMsgs += newMsgs.size
         if (newVert.active) {
           numActiveVerts += 1
         }
 
         Some((newVert, newMsgs))
+      }
     }.persist(storageLevel)
 
     // Force evaluation of processed RDD for accurate performance measurements

diff --git a/bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala b/bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala
@@ -28,9 +28,9 @@ class TestVertex(val active: Boolean, val age: Int) extends Vertex with Serializ
 class TestMessage(val targetId: String) extends Message[String] with Serializable
 
 class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeouts {
-  
+
   var sc: SparkContext = _
-  
+
   after {
     if (sc != null) {
       sc.stop()

diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
@@ -30,21 +30,7 @@ FWDIR="$(cd `dirname $0`/..; pwd)"
 # Build up classpath
 CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
 
-# Support for interacting with Hive.  Since hive pulls in a lot of dependencies that might break
-# existing Spark applications, it is not included in the standard spark assembly.  Instead, we only
-# include it in the classpath if the user has explicitly requested it by running "sbt hive/assembly"
-# Hopefully we will find a way to avoid uber-jars entirely and deploy only the needed packages in
-# the future.
-if [ -f "$FWDIR"/sql/hive/target/scala-$SCALA_VERSION/spark-hive-assembly-*.jar ]; then
-
-  # Datanucleus jars do not work if only included in the uberjar as plugin.xml metadata is lost.
-  DATANUCLEUSJARS=$(JARS=("$FWDIR/lib_managed/jars"/datanucleus-*.jar); IFS=:; echo "${JARS[*]}")
-  CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
-
-  ASSEMBLY_DIR="$FWDIR/sql/hive/target/scala-$SCALA_VERSION/"
-else
-  ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION/"
-fi
+ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
 
 # First check if we have a dependencies jar. If so, include binary classes with the deps jar
 if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
@@ -59,7 +45,7 @@ if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
 
-  DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*-deps.jar`
+  DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar`
   CLASSPATH="$CLASSPATH:$DEPS_ASSEMBLY_JAR"
 else
   # Else use spark-assembly jar from either RELEASE or assembly directory
@@ -71,6 +57,23 @@ else
   CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
 fi
 
+# When Hive support is needed, Datanucleus jars must be included on the classpath.
+# Datanucleus jars do not work if only included in the  uber jar as plugin.xml metadata is lost.
+# Both sbt and maven will populate "lib_managed/jars/" with the datanucleus jars when Spark is
+# built with Hive, so first check if the datanucleus jars exist, and then ensure the current Spark
+# assembly is built for Hive, before actually populating the CLASSPATH with the jars.
+# Note that this check order is faster (by up to half a second) in the case where Hive is not used.
+num_datanucleus_jars=$(ls "$FWDIR"/lib_managed/jars/ 2>/dev/null | grep "datanucleus-.*\\.jar" | wc -l)
+if [ $num_datanucleus_jars -gt 0 ]; then
+  AN_ASSEMBLY_JAR=${ASSEMBLY_JAR:-$DEPS_ASSEMBLY_JAR}
+  num_hive_files=$(jar tvf "$AN_ASSEMBLY_JAR" org/apache/hadoop/hive/ql/exec 2>/dev/null | wc -l)
+  if [ $num_hive_files -gt 0 ]; then
+    echo "Spark assembly has been built with Hive, including Datanucleus jars on classpath" 1>&2
+    DATANUCLEUSJARS=$(echo "$FWDIR/lib_managed/jars"/datanucleus-*.jar | tr " " :)
+    CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
+  fi
+fi
+
 # Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1
 if [[ $SPARK_TESTING == 1 ]]; then
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/test-classes"

diff --git a/bin/load-spark-env.sh b/bin/load-spark-env.sh
@@ -30,6 +30,9 @@ if [ -z "$SPARK_ENV_LOADED" ]; then
   use_conf_dir=${SPARK_CONF_DIR:-"$parent_dir/conf"}
 
   if [ -f "${use_conf_dir}/spark-env.sh" ]; then
+    # Promote all variable declarations to environment (exported) variables
+    set -a
     . "${use_conf_dir}/spark-env.sh"
+    set +a
   fi
 fi
diff --git a/bin/pyspark b/bin/pyspark
@@ -55,7 +55,8 @@ if [ -n "$IPYTHON_OPTS" ]; then
   IPYTHON=1
 fi
 
-if [[ "$IPYTHON" = "1" ]] ; then
+# Only use ipython if no command line arguments were provided [SPARK-1134]
+if [[ "$IPYTHON" = "1" && $# = 0 ]] ; then
   exec ipython $IPYTHON_OPTS
 else
   exec "$PYSPARK_PYTHON" "$@"

diff --git a/bin/spark-class b/bin/spark-class
@@ -47,9 +47,9 @@ DEFAULT_MEM=${SPARK_MEM:-512m}
 
 SPARK_DAEMON_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS -Dspark.akka.logLifecycleEvents=true"
 
-# Add java opts and memory settings for master, worker, executors, and repl.
+# Add java opts and memory settings for master, worker, history server, executors, and repl.
 case "$1" in
-  # Master and Worker use SPARK_DAEMON_JAVA_OPTS (and specific opts) + SPARK_DAEMON_MEMORY.
+  # Master, Worker, and HistoryServer use SPARK_DAEMON_JAVA_OPTS (and specific opts) + SPARK_DAEMON_MEMORY.
   'org.apache.spark.deploy.master.Master')
     OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS $SPARK_MASTER_OPTS"
     OUR_JAVA_MEM=${SPARK_DAEMON_MEMORY:-$DEFAULT_MEM}
@@ -58,6 +58,10 @@ case "$1" in
     OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS $SPARK_WORKER_OPTS"
     OUR_JAVA_MEM=${SPARK_DAEMON_MEMORY:-$DEFAULT_MEM}
     ;;
+  'org.apache.spark.deploy.history.HistoryServer')
+    OUR_JAVA_OPTS="$SPARK_DAEMON_JAVA_OPTS $SPARK_HISTORY_OPTS"
+    OUR_JAVA_MEM=${SPARK_DAEMON_MEMORY:-$DEFAULT_MEM}
+    ;;
 
   # Executors use SPARK_JAVA_OPTS + SPARK_EXECUTOR_MEMORY.
   'org.apache.spark.executor.CoarseGrainedExecutorBackend')
@@ -154,5 +158,3 @@ if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
 fi
 
 exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
-
-
diff --git a/bin/spark-class2.cmd b/bin/spark-class2.cmd
@@ -45,14 +45,17 @@ if "x%OUR_JAVA_MEM%"=="x" set OUR_JAVA_MEM=512m
 
 set SPARK_DAEMON_JAVA_OPTS=%SPARK_DAEMON_JAVA_OPTS% -Dspark.akka.logLifecycleEvents=true
 
-rem Add java opts and memory settings for master, worker, executors, and repl.
-rem Master and Worker use SPARK_DAEMON_JAVA_OPTS (and specific opts) + SPARK_DAEMON_MEMORY.
+rem Add java opts and memory settings for master, worker, history server, executors, and repl.
+rem Master, Worker and HistoryServer use SPARK_DAEMON_JAVA_OPTS (and specific opts) + SPARK_DAEMON_MEMORY.
 if "%1"=="org.apache.spark.deploy.master.Master" (
   set OUR_JAVA_OPTS=%SPARK_DAEMON_JAVA_OPTS% %SPARK_MASTER_OPTS%
   if not "x%SPARK_DAEMON_MEMORY%"=="x" set OUR_JAVA_MEM=%SPARK_DAEMON_MEMORY%
 ) else if "%1"=="org.apache.spark.deploy.worker.Worker" (
   set OUR_JAVA_OPTS=%SPARK_DAEMON_JAVA_OPTS% %SPARK_WORKER_OPTS%
   if not "x%SPARK_DAEMON_MEMORY%"=="x" set OUR_JAVA_MEM=%SPARK_DAEMON_MEMORY%
+) else if "%1"=="org.apache.spark.deploy.history.HistoryServer" (
+  set OUR_JAVA_OPTS=%SPARK_DAEMON_JAVA_OPTS% %SPARK_HISTORY_OPTS%
+  if not "x%SPARK_DAEMON_MEMORY%"=="x" set OUR_JAVA_MEM=%SPARK_DAEMON_MEMORY%
 
 rem Executors use SPARK_JAVA_OPTS + SPARK_EXECUTOR_MEMORY.
 ) else if "%1"=="org.apache.spark.executor.CoarseGrainedExecutorBackend" (

diff --git a/bin/spark-shell b/bin/spark-shell
@@ -34,7 +34,7 @@ set -o posix
 FWDIR="$(cd `dirname $0`/..; pwd)"
 
 SPARK_REPL_OPTS="${SPARK_REPL_OPTS:-""}"
-DEFAULT_MASTER="local"
+DEFAULT_MASTER="local[*]"
 MASTER=${MASTER:-""}
 
 info_log=0
@@ -64,7 +64,7 @@ ${txtbld}OPTIONS${txtrst}:
                               is followed by m for megabytes or g for gigabytes, e.g. "1g".
     -dm --driver-memory     : The memory used by the Spark Shell, the number is followed 
                               by m for megabytes or g for gigabytes, e.g. "1g".
-    -m  --master            : A full string that describes the Spark Master, defaults to "local"
+    -m  --master            : A full string that describes the Spark Master, defaults to "local[*]"
                               e.g. "spark://localhost:7077".
     --log-conf              : Enables logging of the supplied SparkConf as INFO at start of the
                               Spark Context.
@@ -127,7 +127,7 @@ function set_spark_log_conf(){
 
 function set_spark_master(){
     if ! [[ "$1" =~ $ARG_FLAG_PATTERN ]]; then
-        MASTER="$1"
+        export MASTER="$1"
     else
         out_error "wrong format for $2"
     fi
@@ -145,7 +145,7 @@ function resolve_spark_master(){
     fi
 
     if [ -z "$MASTER" ]; then
-        MASTER="$DEFAULT_MASTER"
+        export MASTER="$DEFAULT_MASTER"
     fi
 
 }

diff --git a/core/pom.xml b/core/pom.xml
@@ -117,12 +117,10 @@
     <dependency>
       <groupId>com.twitter</groupId>
       <artifactId>chill_${scala.binary.version}</artifactId>
-      <version>0.3.1</version>
     </dependency>
     <dependency>
       <groupId>com.twitter</groupId>
       <artifactId>chill-java</artifactId>
-      <version>0.3.1</version>
     </dependency>
     <dependency>
       <groupId>commons-net</groupId>
@@ -150,7 +148,7 @@
       <artifactId>json4s-jackson_${scala.binary.version}</artifactId>
       <version>3.2.6</version>
       <!-- see also exclusion for lift-json; this is necessary since it depends on
-         scala-library and scalap 2.10.0, but we use 2.10.3, and only override
+         scala-library and scalap 2.10.0, but we use 2.10.4, and only override
          scala-library -->
       <exclusions>
         <exclusion>
@@ -159,10 +157,6 @@
         </exclusion>
       </exclusions>
     </dependency>
-    <dependency>
-      <groupId>it.unimi.dsi</groupId>
-      <artifactId>fastutil</artifactId>
-    </dependency>
     <dependency>
       <groupId>colt</groupId>
       <artifactId>colt</artifactId>
@@ -200,6 +194,53 @@
       <artifactId>derby</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.tachyonproject</groupId>
+      <artifactId>tachyon</artifactId>
+      <version>0.4.1-thrift</version>
+      <exclusions>
+        <exclusion>
+          <groupId>org.apache.hadoop</groupId>
+          <artifactId>hadoop-client</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.curator</groupId>
+          <artifactId>curator-recipes</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-jsp</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-webapp</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-server</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.eclipse.jetty</groupId>
+          <artifactId>jetty-servlet</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>junit</groupId>
+          <artifactId>junit</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.powermock</groupId>
+          <artifactId>powermock-module-junit4</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.powermock</groupId>
+          <artifactId>powermock-api-mockito</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.curator</groupId>
+          <artifactId>curator-test</artifactId>
+        </exclusion>
+      </exclusions>
+    </dependency>
     <dependency>
       <groupId>org.scalatest</groupId>
       <artifactId>scalatest_${scala.binary.version}</artifactId>

diff --git a/core/src/main/java/org/apache/spark/api/java/StorageLevels.java b/core/src/main/java/org/apache/spark/api/java/StorageLevels.java
@@ -23,17 +23,18 @@
  * Expose some commonly useful storage level constants.
  */
 public class StorageLevels {
-  public static final StorageLevel NONE = create(false, false, false, 1);
-  public static final StorageLevel DISK_ONLY = create(true, false, false, 1);
-  public static final StorageLevel DISK_ONLY_2 = create(true, false, false, 2);
-  public static final StorageLevel MEMORY_ONLY = create(false, true, true, 1);
-  public static final StorageLevel MEMORY_ONLY_2 = create(false, true, true, 2);
-  public static final StorageLevel MEMORY_ONLY_SER = create(false, true, false, 1);
-  public static final StorageLevel MEMORY_ONLY_SER_2 = create(false, true, false, 2);
-  public static final StorageLevel MEMORY_AND_DISK = create(true, true, true, 1);
-  public static final StorageLevel MEMORY_AND_DISK_2 = create(true, true, true, 2);
-  public static final StorageLevel MEMORY_AND_DISK_SER = create(true, true, false, 1);
-  public static final StorageLevel MEMORY_AND_DISK_SER_2 = create(true, true, false, 2);
+  public static final StorageLevel NONE = create(false, false, false, false, 1);
+  public static final StorageLevel DISK_ONLY = create(true, false, false, false, 1);
+  public static final StorageLevel DISK_ONLY_2 = create(true, false, false, false, 2);
+  public static final StorageLevel MEMORY_ONLY = create(false, true, false, true, 1);
+  public static final StorageLevel MEMORY_ONLY_2 = create(false, true, false, true, 2);
+  public static final StorageLevel MEMORY_ONLY_SER = create(false, true, false, false, 1);
+  public static final StorageLevel MEMORY_ONLY_SER_2 = create(false, true, false, false, 2);
+  public static final StorageLevel MEMORY_AND_DISK = create(true, true, false, true, 1);
+  public static final StorageLevel MEMORY_AND_DISK_2 = create(true, true, false, true, 2);
+  public static final StorageLevel MEMORY_AND_DISK_SER = create(true, true, false, false, 1);
+  public static final StorageLevel MEMORY_AND_DISK_SER_2 = create(true, true, false, false, 2);
+  public static final StorageLevel OFF_HEAP = create(false, false, true, false, 1);
 
   /**
    * Create a new StorageLevel object.
@@ -42,7 +43,26 @@ public class StorageLevels {
    * @param deserialized saved as deserialized objects, if true
    * @param replication replication factor
    */
-  public static StorageLevel create(boolean useDisk, boolean useMemory, boolean deserialized, int replication) {
-    return StorageLevel.apply(useDisk, useMemory, deserialized, replication);
+  @Deprecated
+  public static StorageLevel create(boolean useDisk, boolean useMemory, boolean deserialized,
+      int replication) {
+    return StorageLevel.apply(useDisk, useMemory, false, deserialized, replication);
+  }
+
+  /**
+   * Create a new StorageLevel object.
+   * @param useDisk saved to disk, if true
+   * @param useMemory saved to memory, if true
+   * @param useOffHeap saved to Tachyon, if true
+   * @param deserialized saved as deserialized objects, if true
+   * @param replication replication factor
+   */
+  public static StorageLevel create(
+    boolean useDisk,
+    boolean useMemory,
+    boolean useOffHeap,
+    boolean deserialized,
+    int replication) {
+    return StorageLevel.apply(useDisk, useMemory, useOffHeap, deserialized, replication);
   }
 }
diff --git a/core/src/main/java/org/apache/spark/api/java/function/FlatMapFunction.java b/core/src/main/java/org/apache/spark/api/java/function/FlatMapFunction.java
@@ -24,4 +24,4 @@
  */
 public interface FlatMapFunction<T, R> extends Serializable {
   public Iterable<R> call(T t) throws Exception;
-}
+}