Update

.gitignore

@@ -49,7 +49,7 @@ dependency-reduced-pom.xml
 checkpoint
 derby.log
 dist/
-spark-*-bin.tar.gz
+spark-*-bin-*.tgz
 unit-tests.log
 /lib/
 rat-results.txt

.rat-excludes

@@ -44,6 +44,7 @@ SparkImports.scala
 SparkJLineCompletion.scala
 SparkJLineReader.scala
 SparkMemberHandlers.scala
+SparkReplReporter.scala
 sbt
 sbt-launch-lib.bash
 plugins.sbt

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.3.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -66,22 +66,22 @@
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-repl_${scala.binary.version}</artifactId>
+      <artifactId>spark-streaming_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-streaming_${scala.binary.version}</artifactId>
+      <artifactId>spark-graphx_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-graphx_${scala.binary.version}</artifactId>
+      <artifactId>spark-sql_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
-      <artifactId>spark-sql_${scala.binary.version}</artifactId>
+      <artifactId>spark-repl_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
   </dependencies>
@@ -197,6 +197,11 @@
           <artifactId>spark-hive_${scala.binary.version}</artifactId>
           <version>${project.version}</version>
         </dependency>
+      </dependencies>
+    </profile>
+    <profile>
+      <id>hive-thriftserver</id>
+      <dependencies>
         <dependency>
           <groupId>org.apache.spark</groupId>
           <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>

bagel/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.3.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 

bin/compute-classpath.sh

@@ -20,8 +20,6 @@
 # This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
 # script and the ExecutorRunner in standalone cluster mode.
 
-SCALA_VERSION=2.10
-
 # Figure out where Spark is installed
 FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
@@ -36,7 +34,7 @@ else
   CLASSPATH="$CLASSPATH:$FWDIR/conf"
 fi
 
-ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION"
+ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SPARK_SCALA_VERSION"
 
 if [ -n "$JAVA_HOME" ]; then
   JAR_CMD="$JAVA_HOME/bin/jar"
@@ -48,19 +46,19 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
-  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/tools/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/tools/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory
@@ -123,15 +121,15 @@ 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"
-  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/test-classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SPARK_SCALA_VERSION/test-classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/test-classes"
 fi
 
 # Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !

bin/load-spark-env.sh

@@ -36,3 +36,23 @@ if [ -z "$SPARK_ENV_LOADED" ]; then
     set +a
   fi
 fi
+
+# Setting SPARK_SCALA_VERSION if not already set.
+
+if [ -z "$SPARK_SCALA_VERSION" ]; then
+
+    ASSEMBLY_DIR2="$FWDIR/assembly/target/scala-2.11"
+    ASSEMBLY_DIR1="$FWDIR/assembly/target/scala-2.10"
+
+    if [[ -d "$ASSEMBLY_DIR2" && -d "$ASSEMBLY_DIR1" ]]; then
+        echo -e "Presence of build for both scala versions(SCALA 2.10 and SCALA 2.11) detected." 1>&2
+        echo -e 'Either clean one of them or, export SPARK_SCALA_VERSION=2.11 in spark-env.sh.' 1>&2
+        exit 1
+    fi
+
+    if [ -d "$ASSEMBLY_DIR2" ]; then
+        export SPARK_SCALA_VERSION="2.11"
+    else
+        export SPARK_SCALA_VERSION="2.10"
+    fi        
+fi

bin/pyspark

@@ -25,7 +25,7 @@ export SPARK_HOME="$FWDIR"
 
 source "$FWDIR/bin/utils.sh"
 
-SCALA_VERSION=2.10
+source "$FWDIR"/bin/load-spark-env.sh
 
 function usage() {
   echo "Usage: ./bin/pyspark [options]" 1>&2
@@ -40,16 +40,14 @@ fi
 # Exit if the user hasn't compiled Spark
 if [ ! -f "$FWDIR/RELEASE" ]; then
   # Exit if the user hasn't compiled Spark
-  ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null
+  ls "$FWDIR"/assembly/target/scala-$SPARK_SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null
   if [[ $? != 0 ]]; then
     echo "Failed to find Spark assembly in $FWDIR/assembly/target" 1>&2
     echo "You need to build Spark before running this program" 1>&2
     exit 1
   fi
 fi
 
-. "$FWDIR"/bin/load-spark-env.sh
-
 # In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython`
 # executable, while the worker would still be launched using PYSPARK_PYTHON.
 #
@@ -134,7 +132,5 @@ if [[ "$1" =~ \.py$ ]]; then
   gatherSparkSubmitOpts "$@"
   exec "$FWDIR"/bin/spark-submit "${SUBMISSION_OPTS[@]}" "$primary" "${APPLICATION_OPTS[@]}"
 else
-  # PySpark shell requires special handling downstream
-  export PYSPARK_SHELL=1
   exec "$PYSPARK_DRIVER_PYTHON" $PYSPARK_DRIVER_PYTHON_OPTS
 fi

bin/pyspark2.cmd

@@ -59,7 +59,6 @@ for /f %%i in ('echo %1^| findstr /R "\.py"') do (
 )
 
 if [%PYTHON_FILE%] == [] (
-  set PYSPARK_SHELL=1
   if [%IPYTHON%] == [1] (
 	ipython %IPYTHON_OPTS%
   ) else (

bin/run-example

@@ -17,12 +17,12 @@
 # limitations under the License.
 #
 
-SCALA_VERSION=2.10
-
 FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 export SPARK_HOME="$FWDIR"
 EXAMPLES_DIR="$FWDIR"/examples
 
+. "$FWDIR"/bin/load-spark-env.sh
+
 if [ -n "$1" ]; then
   EXAMPLE_CLASS="$1"
   shift
@@ -36,8 +36,8 @@ 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
-  export SPARK_EXAMPLES_JAR="`ls "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.jar`"
+elif [ -e "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar ]; then
+  export SPARK_EXAMPLES_JAR="`ls "$EXAMPLES_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-examples-*hadoop*.jar`"
 fi
 
 if [[ -z "$SPARK_EXAMPLES_JAR" ]]; then

bin/spark-class

@@ -24,8 +24,6 @@ case "`uname`" in
     CYGWIN*) cygwin=true;;
 esac
 
-SCALA_VERSION=2.10
-
 # Figure out where Spark is installed
 FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
@@ -128,9 +126,9 @@ fi
 
 TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
-if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar ]; then
+if [ -e "$TOOLS_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the SBT build
-  export SPARK_TOOLS_JAR="`ls "$TOOLS_DIR"/target/scala-$SCALA_VERSION/spark-tools*[0-9Tg].jar`"
+  export SPARK_TOOLS_JAR="`ls "$TOOLS_DIR"/target/scala-$SPARK_SCALA_VERSION/spark-tools*[0-9Tg].jar`"
 fi
 if [ -e "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar ]; then
   # Use the JAR from the Maven build
@@ -149,7 +147,7 @@ fi
 
 if [[ "$1" =~ org.apache.spark.tools.* ]]; then
   if test -z "$SPARK_TOOLS_JAR"; then
-    echo "Failed to find Spark Tools Jar in $FWDIR/tools/target/scala-$SCALA_VERSION/" 1>&2
+    echo "Failed to find Spark Tools Jar in $FWDIR/tools/target/scala-$SPARK_SCALA_VERSION/" 1>&2
     echo "You need to build Spark before running $1." 1>&2
     exit 1
   fi

bin/spark-sql

@@ -23,6 +23,8 @@
 # Enter posix mode for bash
 set -o posix
 
+# NOTE: This exact class name is matched downstream by SparkSubmit.
+# Any changes need to be reflected there.
 CLASS="org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
 
 # Figure out where Spark is installed

bin/spark-submit

@@ -22,6 +22,9 @@
 export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
 ORIG_ARGS=("$@")
 
+# Set COLUMNS for progress bar
+export COLUMNS=`tput cols`
+
 while (($#)); do
   if [ "$1" = "--deploy-mode" ]; then
     SPARK_SUBMIT_DEPLOY_MODE=$2

conf/spark-env.sh.template

@@ -28,7 +28,7 @@
 # - SPARK_YARN_DIST_FILES, Comma separated list of files to be distributed with the job.
 # - SPARK_YARN_DIST_ARCHIVES, Comma separated list of archives to be distributed with the job.
 
-# Options for the daemons used in the standalone deploy mode:
+# 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 for the master
 # - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y")
@@ -41,3 +41,10 @@
 # - SPARK_HISTORY_OPTS, to set config properties only for the history server (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
+
+# Generic options for the daemons used in the standalone deploy mode
+# - SPARK_CONF_DIR      Alternate conf dir. (Default: ${SPARK_HOME}/conf)
+# - SPARK_LOG_DIR       Where log files are stored.  (Default: ${SPARK_HOME}/logs)
+# - SPARK_PID_DIR       Where the pid file is stored. (Default: /tmp)
+# - SPARK_IDENT_STRING  A string representing this instance of spark. (Default: $USER)
+# - SPARK_NICENESS      The scheduling priority for daemons. (Default: 0)