You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2013/07/17 02:31:09 UTC

[12/50] [abbrv] git commit: Merge remote-tracking branch 'origin/pr/662'

Merge remote-tracking branch 'origin/pr/662'

Conflicts:
	bin/compute-classpath.sh


Project: http://git-wip-us.apache.org/repos/asf/incubator-spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-spark/commit/cd28d9c1
Tree: http://git-wip-us.apache.org/repos/asf/incubator-spark/tree/cd28d9c1
Diff: http://git-wip-us.apache.org/repos/asf/incubator-spark/diff/cd28d9c1

Branch: refs/heads/master
Commit: cd28d9c14732a91416589bb3dc523533495240e8
Parents: 1889f9f 1107b4d
Author: Matei Zaharia <ma...@eecs.berkeley.edu>
Authored: Sat Jul 13 19:10:00 2013 -0700
Committer: Matei Zaharia <ma...@eecs.berkeley.edu>
Committed: Sat Jul 13 19:10:00 2013 -0700

----------------------------------------------------------------------
 bin/compute-classpath.sh | 111 +++++++++++++++++++++++-------------------
 bin/start-slave.sh       |   3 ++
 make-distribution.sh     |  39 +++++++++++++++
 project/SparkBuild.scala |   2 +-
 run                      |  44 ++++++-----------
 spark-shell              |  67 +++++++++++++++++++++++--
 6 files changed, 185 insertions(+), 81 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/cd28d9c1/bin/compute-classpath.sh
----------------------------------------------------------------------
diff --cc bin/compute-classpath.sh
index 75c58d1,47937a0..bd48b43
--- a/bin/compute-classpath.sh
+++ b/bin/compute-classpath.sh
@@@ -24,46 -23,70 +24,71 @@@ PYSPARK_DIR="$FWDIR/python
  
  # Build up classpath
  CLASSPATH="$SPARK_CLASSPATH"
- CLASSPATH="$CLASSPATH:$FWDIR/conf"
- CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes"
- if [ -n "$SPARK_TESTING" ] ; then
-   CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes"
-   CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes"
- fi
- CLASSPATH="$CLASSPATH:$CORE_DIR/src/main/resources"
- CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes"
- CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
- CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes"
- CLASSPATH="$CLASSPATH:$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar
- if [ -e "$FWDIR/lib_managed" ]; then
-   CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*"
-   CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*"
- fi
- CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*"
- # Add the shaded JAR for Maven builds
- if [ -e $REPL_BIN_DIR/target ]; then
-   for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do
+ 
+ function dev_classpath {
+   CLASSPATH="$CLASSPATH:$FWDIR/conf"
+   CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/classes"
+   if [ -n "$SPARK_TESTING" ] ; then
+     CLASSPATH="$CLASSPATH:$CORE_DIR/target/scala-$SCALA_VERSION/test-classes"
+     CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/test-classes"
+   fi
+   CLASSPATH="$CLASSPATH:$CORE_DIR/src/main/resources"
+   CLASSPATH="$CLASSPATH:$REPL_DIR/target/scala-$SCALA_VERSION/classes"
+   CLASSPATH="$CLASSPATH:$EXAMPLES_DIR/target/scala-$SCALA_VERSION/classes"
+   CLASSPATH="$CLASSPATH:$STREAMING_DIR/target/scala-$SCALA_VERSION/classes"
+   CLASSPATH="$CLASSPATH:$STREAMING_DIR/lib/org/apache/kafka/kafka/0.7.2-spark/*" # <-- our in-project Kafka Jar
+   if [ -e "$FWDIR/lib_managed" ]; then
+     CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/jars/*"
+     CLASSPATH="$CLASSPATH:$FWDIR/lib_managed/bundles/*"
+   fi
+   CLASSPATH="$CLASSPATH:$REPL_DIR/lib/*"
+   # Add the shaded JAR for Maven builds
+   if [ -e $REPL_BIN_DIR/target ]; then
+     for jar in `find "$REPL_BIN_DIR/target" -name 'spark-repl-*-shaded-hadoop*.jar'`; do
+       CLASSPATH="$CLASSPATH:$jar"
+     done
+     # The shaded JAR doesn't contain examples, so include those separately
+     EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+     CLASSPATH+=":$EXAMPLES_JAR"
+   fi
+   CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
++  CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
+   for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
      CLASSPATH="$CLASSPATH:$jar"
    done
-   # The shaded JAR doesn't contain examples, so include those separately
-   EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
-   CLASSPATH+=":$EXAMPLES_JAR"
- fi
- CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
- CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
- for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
-   CLASSPATH="$CLASSPATH:$jar"
- done
  
- # Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
- # to avoid the -sources and -doc packages that are built by publish-local.
- if [ -e "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar ]; then
-   # Use the JAR from the SBT build
-   export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar`
- fi
- if [ -e "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar ]; then
-   # Use the JAR from the Maven build
-   export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+   # Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
+   # to avoid the -sources and -doc packages that are built by publish-local.
+   if [ -e "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar ]; then
+     # Use the JAR from the SBT build
+     export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/scala-$SCALA_VERSION/spark-examples"*[0-9T].jar`
+   fi
+   if [ -e "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar ]; then
+     # Use the JAR from the Maven build
+     export SPARK_EXAMPLES_JAR=`ls "$EXAMPLES_DIR/target/spark-examples"*[0-9T].jar`
+   fi
+ 
+   # Add Scala standard library
+   if [ -z "$SCALA_LIBRARY_PATH" ]; then
+     if [ -z "$SCALA_HOME" ]; then
+       echo "SCALA_HOME is not set" >&2
+       exit 1
+     fi
+     SCALA_LIBRARY_PATH="$SCALA_HOME/lib"
+   fi
+   CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-library.jar"
+   CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/scala-compiler.jar"
+   CLASSPATH="$CLASSPATH:$SCALA_LIBRARY_PATH/jline.jar"
+ }
+ 
+ function release_classpath {
+   CLASSPATH="$CLASSPATH:$FWDIR/jars/*"
+ }
+ 
+ if [ -f "$FWDIR/RELEASE" ]; then
+   release_classpath
+ else
+   dev_classpath
  fi
  
  # Add hadoop conf dir - else FileSystem.*, etc fail !

http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/cd28d9c1/make-distribution.sh
----------------------------------------------------------------------
diff --cc make-distribution.sh
index 0000000,8554758..feb13d5
mode 000000,100755..100755
--- a/make-distribution.sh
+++ b/make-distribution.sh
@@@ -1,0 -1,38 +1,39 @@@
+ #!/bin/bash
+ #
+ # Script to create a binary distribution for easy deploys of Spark.
+ # The distribution directory defaults to dist/ but can be overridden below.
+ # The distribution contains fat (assembly) jars that include the Scala library,
+ # so it is completely self contained.
+ # It does not contain source or *.class files.
+ #
+ # Recommended deploy/testing procedure (standalone mode):
+ # 1) Rsync / deploy the dist/ dir to one host
+ # 2) cd to deploy dir; ./bin/start-master.sh
+ # 3) Verify master is up by visiting web page, ie http://master-ip:8080.  Note the spark:// URL.
+ # 4) ./bin/start-slave.sh 1 <<spark:// URL>>
+ # 5) MASTER="spark://my-master-ip:7077" ./spark-shell
+ 
+ # Figure out where the Spark framework is installed
+ FWDIR="$(cd `dirname $0`; pwd)"
+ DISTDIR="$FWDIR/dist"
+ 
+ # Get version from SBT
++export TERM=dumb   # Prevents color codes in SBT output
+ VERSION=$($FWDIR/sbt/sbt "show version" | tail -1 | cut -f 2)
+ echo "Making distribution for Spark $VERSION in $DISTDIR..."
+ 
+ # Build fat JAR
+ $FWDIR/sbt/sbt "repl/assembly"
+ 
+ # Make directories
+ rm -rf "$DISTDIR"
+ mkdir -p "$DISTDIR/jars"
+ echo "$VERSION" >$DISTDIR/RELEASE
+ 
+ # Copy jars
+ cp $FWDIR/repl/target/*.jar "$DISTDIR/jars/"
+ 
+ # Copy other things
+ cp -r "$FWDIR/bin" "$DISTDIR"
+ cp -r "$FWDIR/conf" "$DISTDIR"
 -cp "$FWDIR/run" "$FWDIR/spark-shell" "$DISTDIR"
++cp "$FWDIR/run" "$FWDIR/spark-shell" "$DISTDIR"

http://git-wip-us.apache.org/repos/asf/incubator-spark/blob/cd28d9c1/project/SparkBuild.scala
----------------------------------------------------------------------
diff --cc project/SparkBuild.scala
index 641d379,6058fb1..bc9214d
--- a/project/SparkBuild.scala
+++ b/project/SparkBuild.scala
@@@ -197,7 -198,7 +197,7 @@@ object SparkBuild extends Build 
    def replSettings = sharedSettings ++ Seq(
      name := "spark-repl",
      libraryDependencies <+= scalaVersion("org.scala-lang" % "scala-compiler" % _)
-   )
 -  ) ++ assemblySettings ++ extraAssemblySettings ++ Twirl.settings
++  ) ++ assemblySettings ++ extraAssemblySettings
  
    def examplesSettings = sharedSettings ++ Seq(
      name := "spark-examples",