Merge branch 'reorgscripts' into scripts-reorg

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"

pyspark2.cmd → bin/pyspark2.cmd

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.9.3
 
 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

@@ -20,7 +20,7 @@
 SCALA_VERSION=2.9.3
 
 # 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"
@@ -56,7 +56,7 @@ 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"
 
 # Find java binary

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

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.9.3
 
 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%
 

bin/spark

@@ -0,0 +1,92 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+SCALA_VERSION=2.9.3
+
+# Figure out where the Scala framework is installed
+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
+  . $FWDIR/conf/spark-env.sh
+fi
+
+if [ -z "$1" ]; then
+  echo "Usage: spark <class> [<args>]" >&2
+  echo "Usage: export SPARK_CLASSPATH before running the command" >&2
+  exit 1
+fi
+
+
+# Find the java binary
+if [ -n "${JAVA_HOME}" ]; then
+  RUNNER="${JAVA_HOME}/bin/java"
+else
+  if [ `command -v java` ]; then
+    RUNNER="java"
+  else
+    echo "JAVA_HOME is not set" >&2
+    exit 1
+  fi
+fi
+
+# Set SPARK_MEM if it isn't already set
+SPARK_MEM=${SPARK_MEM:-512m}
+export SPARK_MEM
+
+# Set APP_MEM if it isn't already set, we use this for this process as the app driver process may need 
+# as much memory as specified in SPARK_MEM
+APP_MEM=${APP_MEM:-512m}
+
+# Set JAVA_OPTS to be able to load native libraries and to set heap size
+JAVA_OPTS="$OUR_JAVA_OPTS"
+JAVA_OPTS="$JAVA_OPTS -Djava.library.path=$SPARK_LIBRARY_PATH"
+JAVA_OPTS="$JAVA_OPTS -Xms$APP_MEM -Xmx$APP_MEM"
+# Load extra JAVA_OPTS from conf/java-opts, if it exists
+if [ -e $FWDIR/conf/java-opts ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat $FWDIR/conf/java-opts`"
+fi
+export JAVA_OPTS
+# Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in ExecutorRunner.scala!
+
+if [ ! -f "$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 $FWDIR/assembly/target" >&2
+    echo "You need to build Spark with sbt/sbt assembly before running this program" >&2
+    exit 1
+  fi
+fi
+
+# Compute classpath using external script
+CLASSPATH=`$FWDIR/sbin/compute-classpath.sh`
+export CLASSPATH
+
+if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
+  echo -n "Spark Command: "
+  echo "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
+  echo "========================================"
+  echo
+fi
+
+exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"

spark-shell → bin/spark-shell

@@ -28,7 +28,7 @@
 # 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
@@ -79,7 +79,7 @@ if [[ ! $? ]]; then
   saved_stty=""
 fi
 
-$FWDIR/spark-class $OPTIONS org.apache.spark.repl.Main "$@"
+$FWDIR/sbin/spark-class $OPTIONS org.apache.spark.repl.Main "$@"
 
 # record the exit status lest it be overwritten:
 # then reenable echo and propagate the code.

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

@@ -120,7 +120,7 @@ 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

@@ -125,7 +125,7 @@ private[spark] class CoarseMesosSchedulerBackend(
       StandaloneSchedulerBackend.ACTOR_NAME)
     val uri = System.getProperty("spark.executor.uri")
     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.StandaloneExecutorBackend %s %s %s %d".format(
           runScript, driverUrl, offer.getSlaveId.getValue, offer.getHostname, numCores))
@@ -134,7 +134,7 @@ 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.StandaloneExecutorBackend %s %s %s %d".format(
+        "cd %s*; ./sbin/spark-class org.apache.spark.executor.StandaloneExecutorBackend %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

@@ -103,12 +103,12 @@ private[spark] class MesosSchedulerBackend(
       .setEnvironment(environment)
     val uri = System.getProperty("spark.executor.uri")
     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

@@ -35,7 +35,7 @@ private[spark] object UIWorkloadGenerator {
 
   def main(args: Array[String]) {
     if (args.length < 2) {
-      println("usage: ./spark-class spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]")
+      println("usage: ./sbin/spark-class spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]")
       System.exit(1)
     }
     val master = args(0)

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(30 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

@@ -42,7 +42,7 @@ This would be used to connect to the cluster, write to the dfs and submit jobs t
 
 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> \
@@ -62,7 +62,7 @@ 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

@@ -25,7 +25,7 @@ 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).
@@ -67,12 +67,12 @@ 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() {
-    $FWDIR/pyspark $1 2>&1 | tee -a unit-tests.log
+    $FWDIR/bin/pyspark $1 2>&1 | tee -a unit-tests.log
     FAILED=$((PIPESTATUS[0]||$FAILED))
 }
 

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

@@ -20,7 +20,7 @@
 SCALA_VERSION=2.9.3
 
 # 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="$FWDIR"
@@ -104,7 +104,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
 fi
 
 # Compute classpath using external script
-CLASSPATH=`$FWDIR/bin/compute-classpath.sh`
+CLASSPATH=`$FWDIR/sbin/compute-classpath.sh`
 export CLASSPATH
 
 if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then

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

@@ -20,7 +20,7 @@ rem
 set SCALA_VERSION=2.9.3
 
 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%
@@ -67,7 +67,7 @@ if "%FOUND_JAR%"=="0" (
 
 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
 
 rem Figure out where java is.