Merge branch 'scripts-reorg' of github.com:shane-huang/incubator-spar…

…k into spark-915-segregate-scripts

Conflicts:
	bin/spark-shell
	core/pom.xml
	core/src/main/scala/org/apache/spark/SparkContext.scala
	core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala
	core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
	core/src/test/scala/org/apache/spark/DriverSuite.scala
	python/run-tests
	sbin/compute-classpath.sh
	sbin/spark-class
	sbin/stop-slaves.sh

assembly/src/main/assembly/assembly.xml

@@ -39,23 +39,20 @@
     </fileSet>
     <fileSet>
       <directory>
-        ${project.parent.basedir}/bin/
+        ${project.parent.basedir}/sbin/
       </directory>
-      <outputDirectory>/bin</outputDirectory>
+      <outputDirectory>/sbin</outputDirectory>
       <includes>
         <include>**/*</include>
       </includes>
     </fileSet>
     <fileSet>
       <directory>
-        ${project.parent.basedir}
+        ${project.parent.basedir}/bin/
       </directory>
       <outputDirectory>/bin</outputDirectory>
       <includes>
-        <include>run-example*</include>
-        <include>spark-class*</include>
-        <include>spark-shell*</include>
-        <include>spark-executor*</include>
+        <include>**/*</include>
       </includes>
     </fileSet>
   </fileSets>

pyspark → bin/pyspark

@@ -18,7 +18,7 @@
 #
 
 # Figure out where the Scala framework is installed
-FWDIR="$(cd `dirname $0`; pwd)"
+FWDIR="$(cd `dirname $0`/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
@@ -37,7 +37,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
 fi
 
 # Load environment variables from conf/spark-env.sh, if it exists
-if [ -e $FWDIR/conf/spark-env.sh ] ; then
+if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 

pyspark2.cmd → bin/pyspark2.cmd

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.10
 
 rem Figure out where the Spark framework is installed
-set FWDIR=%~dp0
+set FWDIR=%~dp0..\
 
 rem Export this as SPARK_HOME
 set SPARK_HOME=%FWDIR%

run-example → bin/run-example

@@ -25,13 +25,13 @@ esac
 SCALA_VERSION=2.10
 
 # Figure out where the Scala framework is installed
-FWDIR="$(cd `dirname $0`; pwd)"
+FWDIR="$(cd `dirname $0`/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
 # Load environment variables from conf/spark-env.sh, if it exists
-if [ -e $FWDIR/conf/spark-env.sh ] ; then
+if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 
@@ -61,7 +61,7 @@ fi
 
 # Since the examples JAR ideally shouldn't include spark-core (that dependency should be
 # "provided"), also add our standard Spark classpath, built using compute-classpath.sh.
-CLASSPATH=`$FWDIR/bin/compute-classpath.sh`
+CLASSPATH=`$FWDIR/sbin/compute-classpath.sh`
 CLASSPATH="$SPARK_EXAMPLES_JAR:$CLASSPATH"
 
 if $cygwin; then

run-example2.cmd → bin/run-example2.cmd

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.10
 
 rem Figure out where the Spark framework is installed
-set FWDIR=%~dp0
+set FWDIR=%~dp0..\
 
 rem Export this as SPARK_HOME
 set SPARK_HOME=%FWDIR%
@@ -49,7 +49,7 @@ if "x%SPARK_EXAMPLES_JAR%"=="x" (
 
 rem Compute Spark classpath using external script
 set DONT_PRINT_CLASSPATH=1
-call "%FWDIR%bin\compute-classpath.cmd"
+call "%FWDIR%sbin\compute-classpath.cmd"
 set DONT_PRINT_CLASSPATH=0
 set CLASSPATH=%SPARK_EXAMPLES_JAR%;%CLASSPATH%
 

spark-shell → bin/spark-shell

@@ -32,7 +32,7 @@ esac
 # Enter posix mode for bash
 set -o posix
 
-FWDIR="`dirname $0`"
+FWDIR="$(cd `dirname $0`/..; pwd)"
 
 for o in "$@"; do
   if [ "$1" = "-c" -o "$1" = "--cores" ]; then
@@ -90,10 +90,10 @@ if $cygwin; then
     # "Backspace sends ^H" setting in "Keys" section of the Mintty options
     # (see https://github.com/sbt/sbt/issues/562).
     stty -icanon min 1 -echo > /dev/null 2>&1
-    $FWDIR/spark-class -Djline.terminal=unix $OPTIONS org.apache.spark.repl.Main "$@"
+    $FWDIR/sbin/spark-class -Djline.terminal=unix $OPTIONS org.apache.spark.repl.Main "$@"
     stty icanon echo > /dev/null 2>&1
 else
-    $FWDIR/spark-class $OPTIONS org.apache.spark.repl.Main "$@"
+    $FWDIR/sbin/spark-class $OPTIONS org.apache.spark.repl.Main "$@"
 fi
 
 # record the exit status lest it be overwritten:

spark-shell.cmd → bin/spark-shell.cmd

@@ -17,6 +17,7 @@ rem See the License for the specific language governing permissions and
 rem limitations under the License.
 rem
 
-set FWDIR=%~dp0
+rem Find the path of sbin
+set SBIN=%~dp0..\sbin\
 
-cmd /V /E /C %FWDIR%spark-class2.cmd org.apache.spark.repl.Main %*
+cmd /V /E /C %SBIN%spark-class2.cmd org.apache.spark.repl.Main %*

core/src/main/scala/org/apache/spark/deploy/worker/ExecutorRunner.scala

@@ -122,7 +122,7 @@ private[spark] class ExecutorRunner(
     // 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(
-        Seq(sparkHome + "/bin/compute-classpath" + ext),
+        Seq(sparkHome + "/sbin/compute-classpath" + ext),
         extraEnvironment=appDesc.command.environment)
 
     Seq("-cp", classPath) ++ libraryOpts ++ workerLocalOpts ++ userOpts ++ memoryOpts

core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala

@@ -127,7 +127,7 @@ private[spark] class CoarseMesosSchedulerBackend(
       CoarseGrainedSchedulerBackend.ACTOR_NAME)
     val uri = conf.get("spark.executor.uri", null)
     if (uri == null) {
-      val runScript = new File(sparkHome, "spark-class").getCanonicalPath
+      val runScript = new File(sparkHome, "./sbin/spark-class").getCanonicalPath
       command.setValue(
         "\"%s\" org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d".format(
           runScript, driverUrl, offer.getSlaveId.getValue, offer.getHostname, numCores))
@@ -136,7 +136,7 @@ private[spark] class CoarseMesosSchedulerBackend(
       // glob the directory "correctly".
       val basename = uri.split('/').last.split('.').head
       command.setValue(
-        "cd %s*; ./spark-class org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d"
+        "cd %s*; ./sbin/spark-class org.apache.spark.executor.CoarseGrainedExecutorBackend %s %s %s %d"
           .format(basename, driverUrl, offer.getSlaveId.getValue, offer.getHostname, numCores))
       command.addUris(CommandInfo.URI.newBuilder().setValue(uri))
     }

core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala

@@ -102,12 +102,12 @@ private[spark] class MesosSchedulerBackend(
       .setEnvironment(environment)
     val uri = sc.conf.get("spark.executor.uri", null)
     if (uri == null) {
-      command.setValue(new File(sparkHome, "spark-executor").getCanonicalPath)
+      command.setValue(new File(sparkHome, "/sbin/spark-executor").getCanonicalPath)
     } else {
       // Grab everything to the first '.'. We'll use that and '*' to
       // glob the directory "correctly".
       val basename = uri.split('/').last.split('.').head
-      command.setValue("cd %s*; ./spark-executor".format(basename))
+      command.setValue("cd %s*; ./sbin/spark-executor".format(basename))
       command.addUris(CommandInfo.URI.newBuilder().setValue(uri))
     }
     val memory = Resource.newBuilder()

core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala

@@ -36,7 +36,7 @@ private[spark] object UIWorkloadGenerator {
 
   def main(args: Array[String]) {
     if (args.length < 2) {
-      println("usage: ./spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]")
+      println("usage: ./sbin/spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]")
       System.exit(1)
     }
 

core/src/test/scala/org/apache/spark/DriverSuite.scala

@@ -35,7 +35,7 @@ class DriverSuite extends FunSuite with Timeouts {
     val masters = Table(("master"), ("local"), ("local-cluster[2,1,512]"))
     forAll(masters) { (master: String) =>
       failAfter(60 seconds) {
-        Utils.execute(Seq("./spark-class", "org.apache.spark.DriverWithoutCleanup", master),
+        Utils.execute(Seq("./sbin/spark-class", "org.apache.spark.DriverWithoutCleanup", master),
           new File(System.getenv("SPARK_HOME")))
       }
     }

docs/running-on-yarn.md

@@ -54,7 +54,7 @@ There are two scheduler mode that can be used to launch spark application on YAR
 
 The command to launch the YARN Client is as follows:
 
-    SPARK_JAR=<SPARK_ASSEMBLY_JAR_FILE> ./spark-class org.apache.spark.deploy.yarn.Client \
+    SPARK_JAR=<SPARK_ASSEMBLY_JAR_FILE> ./sbin/spark-class org.apache.spark.deploy.yarn.Client \
       --jar <YOUR_APP_JAR_FILE> \
       --class <APP_MAIN_CLASS> \
       --args <APP_MAIN_ARGUMENTS> \
@@ -79,7 +79,7 @@ For example:
 
     # Submit Spark's ApplicationMaster to YARN's ResourceManager, and instruct Spark to run the SparkPi example
     $ SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \
-        ./spark-class org.apache.spark.deploy.yarn.Client \
+        ./sbin/spark-class org.apache.spark.deploy.yarn.Client \
           --jar examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \
           --class org.apache.spark.examples.SparkPi \
           --args yarn-standalone \

docs/spark-standalone.md

@@ -28,7 +28,7 @@ the master's web UI, which is [http://localhost:8080](http://localhost:8080) by
 
 Similarly, you can start one or more workers and connect them to the master via:
 
-    ./spark-class org.apache.spark.deploy.worker.Worker spark://IP:PORT
+    ./sbin/spark-class org.apache.spark.deploy.worker.Worker spark://IP:PORT
 
 Once you have started a worker, look at the master's web UI ([http://localhost:8080](http://localhost:8080) by default).
 You should see the new node listed there, along with its number of CPUs and memory (minus one gigabyte left for the OS).
@@ -70,12 +70,12 @@ To launch a Spark standalone cluster with the launch scripts, you need to create
 
 Once you've set up this file, you can launch or stop your cluster with the following shell scripts, based on Hadoop's deploy scripts, and available in `SPARK_HOME/bin`:
 
-- `bin/start-master.sh` - Starts a master instance on the machine the script is executed on.
-- `bin/start-slaves.sh` - Starts a slave instance on each machine specified in the `conf/slaves` file.
-- `bin/start-all.sh` - Starts both a master and a number of slaves as described above.
-- `bin/stop-master.sh` - Stops the master that was started via the `bin/start-master.sh` script.
-- `bin/stop-slaves.sh` - Stops the slave instances that were started via `bin/start-slaves.sh`.
-- `bin/stop-all.sh` - Stops both the master and the slaves as described above.
+- `sbin/start-master.sh` - Starts a master instance on the machine the script is executed on.
+- `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-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.
 

make-distribution.sh

@@ -98,10 +98,7 @@ mkdir "$DISTDIR"/conf
 cp "$FWDIR"/conf/*.template "$DISTDIR"/conf
 cp -r "$FWDIR/bin" "$DISTDIR"
 cp -r "$FWDIR/python" "$DISTDIR"
-cp "$FWDIR/spark-class" "$DISTDIR"
-cp "$FWDIR/spark-shell" "$DISTDIR"
-cp "$FWDIR/spark-executor" "$DISTDIR"
-cp "$FWDIR/pyspark" "$DISTDIR"
+cp -r "$FWDIR/sbin" "$DISTDIR"
 
 
 if [ "$MAKE_TGZ" == "true" ]; then

python/pyspark/java_gateway.py

@@ -31,7 +31,7 @@ def launch_gateway():
     # Launch the Py4j gateway using Spark's run command so that we pick up the
     # proper classpath and SPARK_MEM settings from spark-env.sh
     on_windows = platform.system() == "Windows"
-    script = "spark-class.cmd" if on_windows else "spark-class"
+    script = "./sbin/spark-class.cmd" if on_windows else "./sbin/spark-class"
     command = [os.path.join(SPARK_HOME, script), "py4j.GatewayServer",
                "--die-on-broken-pipe", "0"]
     if not on_windows:

python/run-tests

@@ -29,7 +29,7 @@ FAILED=0
 rm -f unit-tests.log
 
 function run_test() {
-    SPARK_TESTING=0 $FWDIR/pyspark $1 2>&1 | tee -a unit-tests.log
+    SPARK_TESTING=0 $FWDIR/bin/pyspark $1 2>&1 | tee -a unit-tests.log
     FAILED=$((PIPESTATUS[0]||$FAILED))
 }
 

repl-bin/src/deb/bin/run

@@ -48,8 +48,7 @@ fi
 export JAVA_OPTS
 
 # Build up classpath
-CLASSPATH="$SPARK_CLASSPATH"
-CLASSPATH+=":$FWDIR/conf"
+CLASSPATH=":$FWDIR/conf"
 for jar in `find $FWDIR -name '*jar'`; do
   CLASSPATH+=":$jar"
 done

repl/pom.xml

@@ -127,7 +127,6 @@
           <environmentVariables>
             <SPARK_HOME>${basedir}/..</SPARK_HOME>
             <SPARK_TESTING>1</SPARK_TESTING>
-            <SPARK_CLASSPATH>${spark.classpath}</SPARK_CLASSPATH>
           </environmentVariables>
         </configuration>
       </plugin>

bin/compute-classpath.cmd → sbin/compute-classpath.cmd

@@ -29,7 +29,7 @@ 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 Build up classpath
-set CLASSPATH=%SPARK_CLASSPATH%;%FWDIR%conf
+set CLASSPATH=%FWDIR%conf
 if exist "%FWDIR%RELEASE" (
   for %%d in ("%FWDIR%jars\spark-assembly*.jar") do (
     set ASSEMBLY_JAR=%%d

bin/compute-classpath.sh → sbin/compute-classpath.sh

@@ -26,7 +26,7 @@ SCALA_VERSION=2.10
 FWDIR="$(cd `dirname $0`/..; pwd)"
 
 # Load environment variables from conf/spark-env.sh, if it exists
-if [ -e $FWDIR/conf/spark-env.sh ] ; then
+if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 

bin/slaves.sh → sbin/slaves.sh

@@ -36,10 +36,10 @@ if [ $# -le 0 ]; then
   exit 1
 fi
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 # If the slaves file is specified in the command line,
 # then it takes precedence over the definition in

spark-class → sbin/spark-class

@@ -25,13 +25,13 @@ esac
 SCALA_VERSION=2.10
 
 # Figure out where the Scala framework is installed
-FWDIR="$(cd `dirname $0`; pwd)"
+FWDIR="$(cd `dirname $0`/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
 
 # Load environment variables from conf/spark-env.sh, if it exists
-if [ -e $FWDIR/conf/spark-env.sh ] ; then
+if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
   . $FWDIR/conf/spark-env.sh
 fi
 
@@ -92,7 +92,7 @@ JAVA_OPTS="$OUR_JAVA_OPTS"
 JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH"
 JAVA_OPTS="$JAVA_OPTS -Xms$SPARK_MEM -Xmx$SPARK_MEM"
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
-if [ -e $FWDIR/conf/java-opts ] ; then
+if [ -e "$FWDIR/conf/java-opts" ] ; then
   JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`"
 fi
 export JAVA_OPTS
@@ -128,7 +128,7 @@ if [ -e "$TOOLS_DIR"/target/spark-tools*[0-9Tg].jar ]; then
 fi
 
 # Compute classpath using external script
-CLASSPATH=`$FWDIR/bin/compute-classpath.sh`
+CLASSPATH=`$FWDIR/sbin/compute-classpath.sh`
 
 if [ "$1" == "org.apache.spark.tools.JavaAPICompletenessChecker" ]; then
   CLASSPATH="$CLASSPATH:$SPARK_TOOLS_JAR"

spark-class2.cmd → sbin/spark-class2.cmd

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.10
 
 rem Figure out where the Spark framework is installed
-set FWDIR=%~dp0
+set FWDIR=%~dp0..\
 
 rem Export this as SPARK_HOME
 set SPARK_HOME=%FWDIR%
@@ -73,7 +73,7 @@ for %%d in ("%TOOLS_DIR%\target\scala-%SCALA_VERSION%\spark-tools*assembly*.jar"
 
 rem Compute classpath using external script
 set DONT_PRINT_CLASSPATH=1
-call "%FWDIR%bin\compute-classpath.cmd"
+call "%FWDIR%sbin\compute-classpath.cmd"
 set DONT_PRINT_CLASSPATH=0
 set CLASSPATH=%CLASSPATH%;%SPARK_TOOLS_JAR%
 

bin/spark-daemon.sh → sbin/spark-daemon.sh

@@ -37,10 +37,10 @@ if [ $# -le 1 ]; then
   exit 1
 fi
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 # get arguments
 
@@ -147,7 +147,7 @@ case $startStop in
     spark_rotate_log "$log"
     echo starting $command, logging to $log
     cd "$SPARK_PREFIX"
-    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
+    nohup nice -n $SPARK_NICENESS "$SPARK_PREFIX"/sbin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
     newpid=$!
     echo $newpid > $pid
     sleep 2