Merge remote-tracking branch 'upstream/master'

Author: Li Pu

.gitignore

@@ -7,7 +7,7 @@
 sbt/*.jar
 .settings
 .cache
-.mima-excludes
+.generated-mima*
 /build/
 work/
 out/

.rat-excludes

@@ -3,6 +3,9 @@ target
 .project
 .classpath
 .mima-excludes
+.generated-mima-excludes
+.generated-mima-class-excludes
+.generated-mima-member-excludes
 .rat-excludes
 .*md
 derby.log
@@ -19,8 +22,11 @@ slaves
 spark-env.sh
 spark-env.sh.template
 log4j-defaults.properties
+bootstrap-tooltip.js
+jquery-1.11.1.min.js
 sorttable.js
 .*txt
+.*json
 .*data
 .*log
 cloudpickle.py

README.md

@@ -69,29 +69,28 @@ can be run using:
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
 storage systems. Because the protocols have changed in different versions of
 Hadoop, you must build Spark against the same version that your cluster runs.
-You can change the version by setting the `SPARK_HADOOP_VERSION` environment
-when building Spark.
+You can change the version by setting `-Dhadoop.version` when building Spark.
 
 For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
 versions without YARN, use:
 
     # Apache Hadoop 1.2.1
-    $ SPARK_HADOOP_VERSION=1.2.1 sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=1.2.1 assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v1
-    $ SPARK_HADOOP_VERSION=2.0.0-mr1-cdh4.2.0 sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.0-mr1-cdh4.2.0 assembly
 
 For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
 with YARN, also set `SPARK_YARN=true`:
 
     # Apache Hadoop 2.0.5-alpha
-    $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.5-alpha -Pyarn assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v2
-    $ SPARK_HADOOP_VERSION=2.0.0-cdh4.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.0.0-cdh4.2.0 -Pyarn assembly
 
     # Apache Hadoop 2.2.X and newer
-    $ SPARK_HADOOP_VERSION=2.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ sbt/sbt -Dhadoop.version=2.2.0 -Pyarn assembly
 
 When developing a Spark application, specify the Hadoop version by adding the
 "hadoop-client" artifact to your project's dependencies. For example, if you're

assembly/pom.xml

@@ -21,7 +21,7 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.0.0-SNAPSHOT</version>
+    <version>1.1.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
@@ -32,6 +32,7 @@
   <packaging>pom</packaging>
 
   <properties>
+    <sbt.project.name>assembly</sbt.project.name>
     <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
     <spark.jar.basename>spark-assembly-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
     <spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>

bagel/pom.xml

@@ -21,12 +21,15 @@
   <parent>
     <groupId>org.apache.spark</groupId>
     <artifactId>spark-parent</artifactId>
-    <version>1.0.0-SNAPSHOT</version>
+    <version>1.1.0-SNAPSHOT</version>
     <relativePath>../pom.xml</relativePath>
   </parent>
 
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-bagel_2.10</artifactId>
+  <properties>
+     <sbt.project.name>bagel</sbt.project.name>
+  </properties>
   <packaging>jar</packaging>
   <name>Spark Project Bagel</name>
   <url>http://spark.apache.org/</url>

bagel/src/test/scala/org/apache/spark/bagel/BagelSuite.scala

@@ -38,8 +38,6 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
       sc.stop()
       sc = null
     }
-    // To avoid Akka rebinding to the same port, since it doesn't unbind immediately on shutdown
-    System.clearProperty("spark.driver.port")
   }
 
   test("halting by voting") {
@@ -82,7 +80,7 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
   test("large number of iterations") {
     // This tests whether jobs with a large number of iterations finish in a reasonable time,
     // because non-memoized recursion in RDD or DAGScheduler used to cause them to hang
-    failAfter(10 seconds) {
+    failAfter(30 seconds) {
       sc = new SparkContext("local", "test")
       val verts = sc.parallelize((1 to 4).map(id => (id.toString, new TestVertex(true, 0))))
       val msgs = sc.parallelize(Array[(String, TestMessage)]())
@@ -103,7 +101,7 @@ class BagelSuite extends FunSuite with Assertions with BeforeAndAfter with Timeo
       sc = new SparkContext("local", "test")
       val verts = sc.parallelize((1 to 4).map(id => (id.toString, new TestVertex(true, 0))))
       val msgs = sc.parallelize(Array[(String, TestMessage)]())
-      val numSupersteps = 50
+      val numSupersteps = 20
       val result =
         Bagel.run(sc, verts, msgs, sc.defaultParallelism, StorageLevel.DISK_ONLY) {
           (self: TestVertex, msgs: Option[Array[TestMessage]], superstep: Int) =>

bin/compute-classpath.sh

@@ -38,8 +38,10 @@ else
   JAR_CMD="jar"
 fi
 
-# First check if we have a dependencies jar. If so, include binary classes with the deps jar
-if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
+# A developer option to prepend more recently compiled Spark classes
+if [ -n "$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:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
@@ -51,24 +53,38 @@ if [ -f "$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"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
+fi
 
-  ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar 2>/dev/null)
+# Use spark-assembly jar from either RELEASE or assembly directory
+if [ -f "$FWDIR/RELEASE" ]; then
+  assembly_folder="$FWDIR"/lib
 else
-  # Else use spark-assembly jar from either RELEASE or assembly directory
-  if [ -f "$FWDIR/RELEASE" ]; then
-    ASSEMBLY_JAR=$(ls "$FWDIR"/lib/spark-assembly*hadoop*.jar 2>/dev/null)
-  else
-    ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*.jar 2>/dev/null)
-  fi
+  assembly_folder="$ASSEMBLY_DIR"
 fi
 
+num_jars=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*\.jar" | wc -l)
+if [ "$num_jars" -eq "0" ]; then
+  echo "Failed to find Spark assembly in $assembly_folder"
+  echo "You need to build Spark before running this program."
+  exit 1
+fi
+if [ "$num_jars" -gt "1" ]; then
+  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
+  echo "Found multiple Spark assembly jars in $assembly_folder:"
+  echo "$jars_list"
+  echo "Please remove all but one jar."
+  exit 1
+fi
+
+ASSEMBLY_JAR=$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)
+
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then
-  echo "Loading Spark jar with '$JAR_CMD' failed. "
-  echo "This is likely because Spark was compiled with Java 7 and run "
-  echo "with Java 6. (see SPARK-1703). Please use Java 7 to run Spark "
-  echo "or build Spark with Java 6."
+  echo "Loading Spark jar with '$JAR_CMD' failed. " 1>&2
+  echo "This is likely because Spark was compiled with Java 7 and run " 1>&2
+  echo "with Java 6. (see SPARK-1703). Please use Java 7 to run Spark " 1>&2
+  echo "or build Spark with Java 6." 1>&2
   exit 1
 fi
 

bin/pyspark

@@ -26,7 +26,7 @@ export SPARK_HOME="$FWDIR"
 SCALA_VERSION=2.10
 
 if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
-  echo "Usage: ./bin/pyspark [options]"
+  echo "Usage: ./bin/pyspark [options]" 1>&2
   $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
   exit 0
 fi
@@ -36,16 +36,16 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
   # Exit if the user hasn't compiled Spark
   ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar >& /dev/null
   if [[ $? != 0 ]]; then
-    echo "Failed to find Spark assembly in $FWDIR/assembly/target" >&2
-    echo "You need to build Spark before running this program" >&2
+    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
 
 # Figure out which Python executable to use
-if [ -z "$PYSPARK_PYTHON" ] ; then
+if [[ -z "$PYSPARK_PYTHON" ]]; then
   PYSPARK_PYTHON="python"
 fi
 export PYSPARK_PYTHON
@@ -59,7 +59,7 @@ export OLD_PYTHONSTARTUP=$PYTHONSTARTUP
 export PYTHONSTARTUP=$FWDIR/python/pyspark/shell.py
 
 # If IPython options are specified, assume user wants to run IPython
-if [ -n "$IPYTHON_OPTS" ]; then
+if [[ -n "$IPYTHON_OPTS" ]]; then
   IPYTHON=1
 fi
 
@@ -76,6 +76,16 @@ for i in "$@"; do
 done
 export PYSPARK_SUBMIT_ARGS
 
+# For pyspark tests
+if [[ -n "$SPARK_TESTING" ]]; then
+  if [[ -n "$PYSPARK_DOC_TEST" ]]; then
+    exec "$PYSPARK_PYTHON" -m doctest $1
+  else
+    exec "$PYSPARK_PYTHON" $1
+  fi
+  exit
+fi
+
 # 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

bin/run-example

@@ -27,9 +27,9 @@ if [ -n "$1" ]; then
   EXAMPLE_CLASS="$1"
   shift
 else
-  echo "Usage: ./bin/run-example <example-class> [example-args]"
-  echo "  - set MASTER=XX to use a specific master"
-  echo "  - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)"
+  echo "Usage: ./bin/run-example <example-class> [example-args]" 1>&2
+  echo "  - set MASTER=XX to use a specific master" 1>&2
+  echo "  - can use abbreviated example class name (e.g. SparkPi, mllib.LinearRegression)" 1>&2
   exit 1
 fi
 
@@ -40,8 +40,8 @@ elif [ -e "$EXAMPLES_DIR"/target/scala-$SCALA_VERSION/spark-examples-*hadoop*.ja
 fi
 
 if [[ -z $SPARK_EXAMPLES_JAR ]]; then
-  echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" >&2
-  echo "You need to build Spark before running this program" >&2
+  echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
+  echo "You need to build Spark before running this program" 1>&2
   exit 1
 fi
 
@@ -51,7 +51,7 @@ if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then
   EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS"
 fi
 
-./bin/spark-submit \
+"$FWDIR"/bin/spark-submit \
   --master $EXAMPLE_MASTER \
   --class $EXAMPLE_CLASS \
   "$SPARK_EXAMPLES_JAR" \

bin/spark-class

@@ -33,13 +33,13 @@ export SPARK_HOME="$FWDIR"
 . $FWDIR/bin/load-spark-env.sh
 
 if [ -z "$1" ]; then
-  echo "Usage: spark-class <class> [<args>]" >&2
+  echo "Usage: spark-class <class> [<args>]" 1>&2
   exit 1
 fi
 
 if [ -n "$SPARK_MEM" ]; then
-  echo "Warning: SPARK_MEM is deprecated, please use a more specific config option"
-  echo "(e.g., spark.executor.memory or SPARK_DRIVER_MEMORY)."
+  echo -e "Warning: SPARK_MEM is deprecated, please use a more specific config option" 1>&2
+  echo -e "(e.g., spark.executor.memory or SPARK_DRIVER_MEMORY)." 1>&2
 fi
 
 # Use SPARK_MEM or 512m as the default memory, to be overridden by specific options
@@ -108,28 +108,11 @@ fi
 export JAVA_OPTS
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
 
-if [ ! -f "$FWDIR/RELEASE" ]; then
-  # Exit if the user hasn't compiled Spark
-  num_jars=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar" | wc -l)
-  jars_list=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar")
-  if [ "$num_jars" -eq "0" ]; then
-    echo "Failed to find Spark assembly in $FWDIR/assembly/target/scala-$SCALA_VERSION/" >&2
-    echo "You need to build Spark before running this program." >&2
-    exit 1
-  fi
-  if [ "$num_jars" -gt "1" ]; then
-    echo "Found multiple Spark assembly jars in $FWDIR/assembly/target/scala-$SCALA_VERSION:" >&2
-    echo "$jars_list"
-    echo "Please remove all but one jar."
-    exit 1
-  fi
-fi
-
 TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
-if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then
+if [ -e "$TOOLS_DIR"/target/scala-$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/*assembly*[0-9Tg].jar`
+  export SPARK_TOOLS_JAR=`ls "$TOOLS_DIR"/target/scala-$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
@@ -147,6 +130,11 @@ else
 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 "You need to build spark before running $1." 1>&2
+    exit 1
+  fi
   CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"
 fi
 
@@ -159,10 +147,9 @@ fi
 export CLASSPATH
 
 if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
-  echo -n "Spark Command: "
-  echo "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
-  echo "========================================"
-  echo
+  echo -n "Spark Command: " 1>&2
+  echo "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@" 1>&2
+  echo -e "========================================\n" 1>&2
 fi
 
 exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"