Merge pull request #317 from ScrapCodes/spark-915-segregate-scripts

Spark-915 segregate scripts

62 files changed, 155 insertions, 161 deletions

diff --git a/README.md b/README.md
index 1550a8b551..f7ad26de5b 100644
--- a/README.md
+++ b/README.md
@@ -19,14 +19,14 @@ which is packaged with it. To build Spark and its example programs, run:
 
 Once you've built Spark, the easiest way to start using it is the shell:
 
-    ./spark-shell
+    ./bin/spark-shell
 
-Or, for the Python API, the Python shell (`./pyspark`).
+Or, for the Python API, the Python shell (`./bin/pyspark`).
 
 Spark also comes with several sample programs in the `examples` directory.
-To run one of them, use `./run-example <class> <params>`. For example:
+To run one of them, use `./bin/run-example <class> <params>`. For example:
 
-    ./run-example org.apache.spark.examples.SparkLR local[2]
+    ./bin/run-example org.apache.spark.examples.SparkLR local[2]
 
 will run the Logistic Regression example locally on 2 CPUs.
 
diff --git a/assembly/src/main/assembly/assembly.xml b/assembly/src/main/assembly/assembly.xml
index 47d3fa93d0..6af383db65 100644
--- a/assembly/src/main/assembly/assembly.xml
+++ b/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>
diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd
index 9e3e10ecaa..4f60bff19c 100644
--- a/bin/compute-classpath.cmd
+++ b/bin/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
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
index 40555089fc..0c82310421 100755
--- a/bin/compute-classpath.sh
+++ b/bin/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
 
diff --git a/pyspark b/bin/pyspark
index 12cc926dda..d6810f4686 100755
--- a/pyspark
+++ b/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
 
diff --git a/pyspark.cmd b/bin/pyspark.cmd
index 7c26fbbac2..7c26fbbac2 100644
--- a/pyspark.cmd
+++ b/bin/pyspark.cmd
diff --git a/pyspark2.cmd b/bin/pyspark2.cmd
index 21f9a34388..95791095ec 100644
--- a/pyspark2.cmd
+++ b/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%
diff --git a/run-example b/bin/run-example
index a78192d31d..6c5d4a6a8f 100755
--- a/run-example
+++ b/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
 
diff --git a/run-example.cmd b/bin/run-example.cmd
index 5b2d048d6e..5b2d048d6e 100644
--- a/run-example.cmd
+++ b/bin/run-example.cmd
diff --git a/run-example2.cmd b/bin/run-example2.cmd
index d4ad98d6e7..6861334cb0 100644
--- a/run-example2.cmd
+++ b/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%
 
diff --git a/spark-class b/bin/spark-class
index 1858ea6247..c4225a392d 100755
--- a/spark-class
+++ b/bin/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
diff --git a/spark-class.cmd b/bin/spark-class.cmd
index 19850db9e1..19850db9e1 100644
--- a/spark-class.cmd
+++ b/bin/spark-class.cmd
diff --git a/spark-class2.cmd b/bin/spark-class2.cmd
index dc9dadf356..460e661476 100644
--- a/spark-class2.cmd
+++ b/bin/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%
 
diff --git a/spark-shell b/bin/spark-shell
index d20af0fb39..e6885b51ef 100755
--- a/spark-shell
+++ b/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/bin/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/bin/spark-class $OPTIONS org.apache.spark.repl.Main "$@"
 fi
 
 # record the exit status lest it be overwritten:
diff --git a/spark-shell.cmd b/bin/spark-shell.cmd
index 3e52bf835e..23973e3e3d 100644
--- a/spark-shell.cmd
+++ b/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 %*
diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala
index 08811520cf..d46fceba89 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/CoarseMesosSchedulerBackend.scala
+++ b/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, "./bin/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*; ./bin/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))
     }
diff --git a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala b/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala
index bb278fb155..ae8d527352 100644
--- a/core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala
+++ b/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()
diff --git a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
index 58d47a201d..6ba15187d9 100644
--- a/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
+++ b/core/src/main/scala/org/apache/spark/ui/UIWorkloadGenerator.scala
@@ -27,7 +27,7 @@ import org.apache.spark.scheduler.SchedulingMode
 /**
  * Continuously generates jobs that expose various features of the WebUI (internal testing tool).
  *
- * Usage: ./run spark.ui.UIWorkloadGenerator [master]
+ * Usage: ./bin/spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]
  */
 private[spark] object UIWorkloadGenerator {
 
@@ -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: ./bin/spark-class org.apache.spark.ui.UIWorkloadGenerator [master] [FIFO|FAIR]")
       System.exit(1)
     }
 
diff --git a/core/src/test/scala/org/apache/spark/DriverSuite.scala b/core/src/test/scala/org/apache/spark/DriverSuite.scala
index 6d1695eae7..605588f7f6 100644
--- a/core/src/test/scala/org/apache/spark/DriverSuite.scala
+++ b/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("./bin/spark-class", "org.apache.spark.DriverWithoutCleanup", master),
           new File(System.getenv("SPARK_HOME")))
       }
     }
diff --git a/kmeans_data.txt b/data/kmeans_data.txt
index 338664f78d..338664f78d 100644
--- a/kmeans_data.txt
+++ b/data/kmeans_data.txt
diff --git a/lr_data.txt b/data/lr_data.txt
index d4df0634e0..d4df0634e0 100644
--- a/lr_data.txt
+++ b/data/lr_data.txt
diff --git a/pagerank_data.txt b/data/pagerank_data.txt
index 95755ab8f5..95755ab8f5 100644
--- a/pagerank_data.txt
+++ b/data/pagerank_data.txt
diff --git a/docs/bagel-programming-guide.md b/docs/bagel-programming-guide.md
index de001e6c52..c4f1f6d6ad 100644
--- a/docs/bagel-programming-guide.md
+++ b/docs/bagel-programming-guide.md
@@ -157,8 +157,8 @@ trait Message[K] {
 
 # Where to Go from Here
 
-Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `run-example` script included in Spark; e.g.:
+Two example jobs, PageRank and shortest path, are included in `examples/src/main/scala/org/apache/spark/examples/bagel`. You can run them by passing the class name to the `bin/run-example` script included in Spark; e.g.:
 
-    ./run-example org.apache.spark.examples.bagel.WikipediaPageRank
+    ./bin/run-example org.apache.spark.examples.bagel.WikipediaPageRank
 
 Each example program prints usage help when run without any arguments.
diff --git a/docs/index.md b/docs/index.md
index d3ac696d1e..86d574daaa 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -24,9 +24,9 @@ For its Scala API, Spark {{site.SPARK_VERSION}} depends on Scala {{site.SCALA_VE
 # Running the Examples and Shell
 
 Spark comes with several sample programs in the `examples` directory.
-To run one of the samples, use `./run-example <class> <params>` in the top-level Spark directory
-(the `run-example` script sets up the appropriate paths and launches that program).
-For example, try `./run-example org.apache.spark.examples.SparkPi local`.
+To run one of the samples, use `./bin/run-example <class> <params>` in the top-level Spark directory
+(the `bin/run-example` script sets up the appropriate paths and launches that program).
+For example, try `./bin/run-example org.apache.spark.examples.SparkPi local`.
 Each example prints usage help when run with no parameters.
 
 Note that all of the sample programs take a `<master>` parameter specifying the cluster URL
@@ -34,8 +34,8 @@ to connect to. This can be a [URL for a distributed cluster](scala-programming-g
 or `local` to run locally with one thread, or `local[N]` to run locally with N threads. You should start by using
 `local` for testing.
 
-Finally, you can run Spark interactively through modified versions of the Scala shell (`./spark-shell`) or
-Python interpreter (`./pyspark`). These are a great way to learn the framework.
+Finally, you can run Spark interactively through modified versions of the Scala shell (`./bin/spark-shell`) or
+Python interpreter (`./bin/pyspark`). These are a great way to learn the framework.
 
 # Launching on a Cluster
 
diff --git a/docs/java-programming-guide.md b/docs/java-programming-guide.md
index 53085cc671..07732fa122 100644
--- a/docs/java-programming-guide.md
+++ b/docs/java-programming-guide.md
@@ -190,9 +190,9 @@ We hope to generate documentation with Java-style syntax in the future.
 
 Spark includes several sample programs using the Java API in
 [`examples/src/main/java`](https://github.com/apache/incubator-spark/tree/master/examples/src/main/java/org/apache/spark/examples).  You can run them by passing the class name to the
-`run-example` script included in Spark; for example:
+`bin/run-example` script included in Spark; for example:
 
-    ./run-example org.apache.spark.examples.JavaWordCount
+    ./bin/run-example org.apache.spark.examples.JavaWordCount
 
 Each example program prints usage help when run
 without any arguments.
diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md
index c1ff9c417c..95537ef185 100644
--- a/docs/mllib-guide.md
+++ b/docs/mllib-guide.md
@@ -87,7 +87,7 @@ svmAlg.optimizer.setNumIterations(200)
 val modelL1 = svmAlg.run(parsedData)
 {% endhighlight %}
 
-Both of the code snippets above can be executed in `spark-shell` to generate a
+Both of the code snippets above can be executed in `bin/spark-shell` to generate a
 classifier for the provided dataset.
 
 Available algorithms for binary classification:
diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md
index 96f93e24fe..dc187b3efe 100644
--- a/docs/python-programming-guide.md
+++ b/docs/python-programming-guide.md
@@ -47,7 +47,7 @@ PySpark will automatically ship these functions to workers, along with any objec
 Instances of classes will be serialized and shipped to workers by PySpark, but classes themselves cannot be automatically distributed to workers.
 The [Standalone Use](#standalone-use) section describes how to ship code dependencies to workers.
 
-In addition, PySpark fully supports interactive use---simply run `./pyspark` to launch an interactive shell.
+In addition, PySpark fully supports interactive use---simply run `./bin/pyspark` to launch an interactive shell.
 
 
 # Installing and Configuring PySpark
@@ -60,17 +60,17 @@ By default, PySpark requires `python` to be available on the system `PATH` and u
 
 All of PySpark's library dependencies, including [Py4J](http://py4j.sourceforge.net/), are bundled with PySpark and automatically imported.
 
-Standalone PySpark applications should be run using the `pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`.
-The script automatically adds the `pyspark` package to the `PYTHONPATH`.
+Standalone PySpark applications should be run using the `bin/pyspark` script, which automatically configures the Java and Python environment using the settings in `conf/spark-env.sh` or `.cmd`.
+The script automatically adds the `bin/pyspark` package to the `PYTHONPATH`.
 
 
 # Interactive Use
 
-The `pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options:
+The `bin/pyspark` script launches a Python interpreter that is configured to run PySpark applications. To use `pyspark` interactively, first build Spark, then launch it directly from the command line without any options:
 
 {% highlight bash %}
 $ sbt/sbt assembly
-$ ./pyspark
+$ ./bin/pyspark
 {% endhighlight %}
 
 The Python shell can be used explore data interactively and is a simple way to learn the API:
@@ -82,35 +82,35 @@ The Python shell can be used explore data interactively and is a simple way to l
 >>> help(pyspark) # Show all pyspark functions
 {% endhighlight %}
 
-By default, the `pyspark` shell creates SparkContext that runs applications locally on a single core.
+By default, the `bin/pyspark` shell creates SparkContext that runs applications locally on a single core.
 To connect to a non-local cluster, or use multiple cores, set the `MASTER` environment variable.
-For example, to use the `pyspark` shell with a [standalone Spark cluster](spark-standalone.html):
+For example, to use the `bin/pyspark` shell with a [standalone Spark cluster](spark-standalone.html):
 
 {% highlight bash %}
-$ MASTER=spark://IP:PORT ./pyspark
+$ MASTER=spark://IP:PORT ./bin/pyspark
 {% endhighlight %}
 
 Or, to use four cores on the local machine:
 
 {% highlight bash %}
-$ MASTER=local[4] ./pyspark
+$ MASTER=local[4] ./bin/pyspark
 {% endhighlight %}
 
 
 ## IPython
 
 It is also possible to launch PySpark in [IPython](http://ipython.org), the enhanced Python interpreter.
-To do this, set the `IPYTHON` variable to `1` when running `pyspark`:
+To do this, set the `IPYTHON` variable to `1` when running `bin/pyspark`:
 
 {% highlight bash %}
-$ IPYTHON=1 ./pyspark
+$ IPYTHON=1 ./bin/pyspark
 {% endhighlight %}
 
 Alternatively, you can customize the `ipython` command by setting `IPYTHON_OPTS`. For example, to launch
 the [IPython Notebook](http://ipython.org/notebook.html) with PyLab graphing support:
 
 {% highlight bash %}
-$ IPYTHON_OPTS="notebook --pylab inline" ./pyspark
+$ IPYTHON_OPTS="notebook --pylab inline" ./bin/pyspark
 {% endhighlight %}
 
 IPython also works on a cluster or on multiple cores if you set the `MASTER` environment variable.
@@ -118,7 +118,7 @@ IPython also works on a cluster or on multiple cores if you set the `MASTER` env
 
 # Standalone Programs
 
-PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `pyspark`.
+PySpark can also be used from standalone Python scripts by creating a SparkContext in your script and running the script using `bin/pyspark`.
 The Quick Start guide includes a [complete example](quick-start.html#a-standalone-app-in-python) of a standalone Python application.
 
 Code dependencies can be deployed by listing them in the `pyFiles` option in the SparkContext constructor:
@@ -153,6 +153,6 @@ Many of the methods also contain [doctests](http://docs.python.org/2/library/doc
 PySpark also includes several sample programs in the [`python/examples` folder](https://github.com/apache/incubator-spark/tree/master/python/examples).
 You can run them by passing the files to `pyspark`; e.g.:
 
-    ./pyspark python/examples/wordcount.py
+    ./bin/pyspark python/examples/wordcount.py
 
 Each program prints usage help when run without arguments.
diff --git a/docs/quick-start.md b/docs/quick-start.md
index bdf127d404..2fa2bd718b 100644
--- a/docs/quick-start.md
+++ b/docs/quick-start.md
@@ -20,7 +20,7 @@ $ sbt/sbt assembly
 ## Basics
 
 Spark's interactive shell provides a simple way to learn the API, as well as a powerful tool to analyze datasets interactively.
-Start the shell by running `./spark-shell` in the Spark directory.
+Start the shell by running `./bin/spark-shell` in the Spark directory.
 
 Spark's primary abstraction is a distributed collection of items called a Resilient Distributed Dataset (RDD). RDDs can be created from Hadoop InputFormats (such as HDFS files) or by transforming other RDDs. Let's make a new RDD from the text of the README file in the Spark source directory:
 
@@ -99,7 +99,7 @@ scala> linesWithSpark.count()
 res9: Long = 15
 {% endhighlight %}
 
-It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark).
+It may seem silly to use Spark to explore and cache a 30-line text file. The interesting part is that these same functions can be used on very large data sets, even when they are striped across tens or hundreds of nodes. You can also do this interactively by connecting `bin/spark-shell` to a cluster, as described in the [programming guide](scala-programming-guide.html#initializing-spark).
 
 # A Standalone App in Scala
 Now say we wanted to write a standalone application using the Spark API. We will walk through a simple application in both Scala (with SBT), Java (with Maven), and Python. If you are using other build systems, consider using the Spark assembly JAR described in the developer guide.
@@ -277,11 +277,11 @@ We can pass Python functions to Spark, which are automatically serialized along
 For applications that use custom classes or third-party libraries, we can add those code dependencies to SparkContext to ensure that they will be available on remote machines; this is described in more detail in the [Python programming guide](python-programming-guide.html).
 `SimpleApp` is simple enough that we do not need to specify any code dependencies.
 
-We can run this application using the `pyspark` script:
+We can run this application using the `bin/pyspark` script:
 
 {% highlight python %}
 $ cd $SPARK_HOME
-$ ./pyspark SimpleApp.py
+$ ./bin/pyspark SimpleApp.py
 ...
 Lines with a: 46, Lines with b: 23
 {% endhighlight python %}
diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md
index 2c1b2cc294..e7c688d3cd 100644
--- a/docs/running-on-yarn.md
+++ b/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> ./bin/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 \
+        ./bin/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 \
@@ -107,12 +107,12 @@ For example:
 
     SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \
     SPARK_YARN_APP_JAR=examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \
-    ./run-example org.apache.spark.examples.SparkPi yarn-client
+    ./bin/run-example org.apache.spark.examples.SparkPi yarn-client
 
 
     SPARK_JAR=./assembly/target/scala-{{site.SCALA_VERSION}}/spark-assembly-{{site.SPARK_VERSION}}-hadoop2.0.5-alpha.jar \
     SPARK_YARN_APP_JAR=examples/target/scala-{{site.SCALA_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \
-    MASTER=yarn-client ./spark-shell
+    MASTER=yarn-client ./bin/spark-shell
 
 # Building Spark for Hadoop/YARN 2.2.x
 
diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md
index 1db255ca53..c1ef46a1cd 100644
--- a/docs/scala-programming-guide.md
+++ b/docs/scala-programming-guide.md
@@ -13,7 +13,7 @@ At a high level, every Spark application consists of a *driver program* that run
 
 A second abstraction in Spark is *shared variables* that can be used in parallel operations. By default, when Spark runs a function in parallel as a set of tasks on different nodes, it ships a copy of each variable used in the function to each task. Sometimes, a variable needs to be shared across tasks, or between tasks and the driver program. Spark supports two types of shared variables: *broadcast variables*, which can be used to cache a value in memory on all nodes, and *accumulators*, which are variables that are only "added" to, such as counters and sums.
 
-This guide shows each of these features and walks through some samples. It assumes some familiarity with Scala, especially with the syntax for [closures](http://www.scala-lang.org/node/133). Note that you can also run Spark interactively using the `spark-shell` script. We highly recommend doing that to follow along!
+This guide shows each of these features and walks through some samples. It assumes some familiarity with Scala, especially with the syntax for [closures](http://www.scala-lang.org/node/133). Note that you can also run Spark interactively using the `bin/spark-shell` script. We highly recommend doing that to follow along!
 
 # Linking with Spark
 
@@ -54,16 +54,16 @@ object for more advanced configuration.
 
 The `master` parameter is a string specifying a [Spark or Mesos cluster URL](#master-urls) to connect to, or a special "local" string to run in local mode, as described below. `appName` is a name for your application, which will be shown in the cluster web UI. Finally, the last two parameters are needed to deploy your code to a cluster if running in distributed mode, as described later.
 
-In the Spark shell, a special interpreter-aware SparkContext is already created for you, in the variable called `sc`. Making your own SparkContext will not work. You can set which master the context connects to using the `MASTER` environment variable, and you can add JARs to the classpath with the `ADD_JARS` variable. For example, to run `spark-shell` on four cores, use
+In the Spark shell, a special interpreter-aware SparkContext is already created for you, in the variable called `sc`. Making your own SparkContext will not work. You can set which master the context connects to using the `MASTER` environment variable, and you can add JARs to the classpath with the `ADD_JARS` variable. For example, to run `bin/spark-shell` on four cores, use
 
 {% highlight bash %}
-$ MASTER=local[4] ./spark-shell
+$ MASTER=local[4] ./bin/spark-shell
 {% endhighlight %}
 
 Or, to also add `code.jar` to its classpath, use:
 
 {% highlight bash %}
-$ MASTER=local[4] ADD_JARS=code.jar ./spark-shell
+$ MASTER=local[4] ADD_JARS=code.jar ./bin/spark-shell
 {% endhighlight %}
 
 ### Master URLs
@@ -95,7 +95,7 @@ If you want to run your application on a cluster, you will need to specify the t
 * `sparkHome`: The path at which Spark is installed on your worker machines (it should be the same on all of them).
 * `jars`: A list of JAR files on the local machine containing your application's code and any dependencies, which Spark will deploy to all the worker nodes. You'll need to package your application into a set of JARs using your build system. For example, if you're using SBT, the [sbt-assembly](https://github.com/sbt/sbt-assembly) plugin is a good way to make a single JAR with your code and dependencies.
 
-If you run `spark-shell` on a cluster, you can add JARs to it by specifying the `ADD_JARS` environment variable before you launch it.  This variable should contain a comma-separated list of JARs. For example, `ADD_JARS=a.jar,b.jar ./spark-shell` will launch a shell with `a.jar` and `b.jar` on its classpath. In addition, any new classes you define in the shell will automatically be distributed.
+If you run `bin/spark-shell` on a cluster, you can add JARs to it by specifying the `ADD_JARS` environment variable before you launch it.  This variable should contain a comma-separated list of JARs. For example, `ADD_JARS=a.jar,b.jar ./bin/spark-shell` will launch a shell with `a.jar` and `b.jar` on its classpath. In addition, any new classes you define in the shell will automatically be distributed.
 
 # Resilient Distributed Datasets (RDDs)
 
@@ -366,9 +366,9 @@ res2: Int = 10
 # Where to Go from Here
 
 You can see some [example Spark programs](http://spark.incubator.apache.org/examples.html) on the Spark website.
-In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `run-example` script included in Spark; for example:
+In addition, Spark includes several samples in `examples/src/main/scala`. Some of them have both Spark versions and local (non-parallel) versions, allowing you to see what had to be changed to make the program run on a cluster. You can run them using by passing the class name to the `bin/run-example` script included in Spark; for example:
 
-    ./run-example org.apache.spark.examples.SparkPi
+    ./bin/run-example org.apache.spark.examples.SparkPi
 
 Each example program prints usage help when run without any arguments.
 
diff --git a/docs/spark-debugger.md b/docs/spark-debugger.md
index d6315d97f4..11c51d5cde 100644
--- a/docs/spark-debugger.md
+++ b/docs/spark-debugger.md
@@ -39,7 +39,7 @@ where `path/to/event-log` is where you want the event log to go relative to `$SP
 
 ### Loading the event log into the debugger
 
-1. Run a Spark shell with `MASTER=<i>host</i> ./spark-shell`.
+1. Run a Spark shell with `MASTER=<i>host</i> ./bin/spark-shell`.
 2. Use `EventLogReader` to load the event log as follows:
     {% highlight scala %}
 spark> val r = new spark.EventLogReader(sc, Some("path/to/event-log"))
diff --git a/docs/spark-standalone.md b/docs/spark-standalone.md
index f7f0b78908..c851833a18 100644
--- a/docs/spark-standalone.md
+++ b/docs/spark-standalone.md
@@ -20,7 +20,7 @@ then modify `conf/spark-env.sh` in the `dist/` directory before deploying to all
 
 You can start a standalone master server by executing:
 
-    ./bin/start-master.sh
+    ./sbin/start-master.sh
 
 Once started, the master will print out a `spark://HOST:PORT` URL for itself, which you can use to connect workers to it,
 or pass as the "master" argument to `SparkContext`. You can also find this URL on
@@ -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
+    ./bin/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.
 
@@ -143,9 +143,9 @@ constructor](scala-programming-guide.html#initializing-spark).
 
 To run an interactive Spark shell against the cluster, run the following command:
 
-    MASTER=spark://IP:PORT ./spark-shell
+    MASTER=spark://IP:PORT ./bin/spark-shell
 
-Note that if you are running spark-shell from one of the spark cluster machines, the `spark-shell` script will
+Note that if you are running spark-shell from one of the spark cluster machines, the `bin/spark-shell` script will
 automatically set MASTER from the `SPARK_MASTER_IP` and `SPARK_MASTER_PORT` variables in `conf/spark-env.sh`.
 
 You can also pass an option `-c <numCores>` to control the number of cores that spark-shell uses on the cluster.
diff --git a/docs/streaming-programming-guide.md b/docs/streaming-programming-guide.md
index 6f97db6a3e..1c9ece6270 100644
--- a/docs/streaming-programming-guide.md
+++ b/docs/streaming-programming-guide.md
@@ -245,7 +245,7 @@ $ nc -lk 9999
 Then, in a different terminal, you can start NetworkWordCount by using
 
 {% highlight bash %}
-$ ./run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999
+$ ./bin/run-example org.apache.spark.streaming.examples.NetworkWordCount local[2] localhost 9999
 {% endhighlight %}
 
 This will make NetworkWordCount connect to the netcat server. Any lines typed in the terminal running the netcat server will be counted and printed on screen.
@@ -283,7 +283,7 @@ Time: 1357008430000 ms
 </td>
 </table>
 
-You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files.
+You can find more examples in `<Spark repo>/streaming/src/main/scala/org/apache/spark/streaming/examples/`. They can be run in the similar manner using `./bin/run-example org.apache.spark.streaming.examples....` . Executing without any parameter would give the required parameter list. Further explanation to run them can be found in comments in the files.
 
 # DStream Persistence
 Similar to RDDs, DStreams also allow developers to persist the stream's data in memory. That is, using `persist()` method on a DStream would automatically persist every RDD of that DStream in memory. This is useful if the data in the DStream will be computed multiple times (e.g., multiple operations on the same data). For window-based operations like `reduceByWindow` and `reduceByKeyAndWindow` and state-based operations like `updateStateByKey`, this is implicitly true. Hence, DStreams generated by window-based operations are automatically persisted in memory, without the developer calling `persist()`.
diff --git a/ec2/spark_ec2.py b/ec2/spark_ec2.py
index a2b0e7e7f4..d82a1e1490 100755
--- a/ec2/spark_ec2.py
+++ b/ec2/spark_ec2.py
@@ -436,7 +436,7 @@ def setup_cluster(conn, master_nodes, slave_nodes, opts, deploy_ssh_key):
 def setup_standalone_cluster(master, slave_nodes, opts):
   slave_ips = '\n'.join([i.public_dns_name for i in slave_nodes])
   ssh(master, opts, "echo \"%s\" > spark/conf/slaves" % (slave_ips))
-  ssh(master, opts, "/root/spark/bin/start-all.sh")
+  ssh(master, opts, "/root/spark/sbin/start-all.sh")
 
 def setup_spark_cluster(master, opts):
   ssh(master, opts, "chmod u+x spark-ec2/setup.sh")
diff --git a/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java b/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java
index 22994fb2ec..75b588e4b8 100644
--- a/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java
+++ b/examples/src/main/java/org/apache/spark/streaming/examples/JavaKafkaWordCount.java
@@ -41,7 +41,7 @@ import scala.Tuple2;
  *   <numThreads> is the number of threads the kafka consumer should use
  *
  * Example:
- *    `./run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02,
+ *    `./bin/run-example org.apache.spark.streaming.examples.JavaKafkaWordCount local[2] zoo01,zoo02,
  *    zoo03 my-consumer-group topic1,topic2 1`
  */
 
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala
index 2402409e6e..3641517934 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/ActorWordCount.scala
@@ -134,9 +134,9 @@ object FeederActor {
  *   <hostname> and <port> describe the AkkaSystem that Spark Sample feeder is running on.
  *
  * To run this example locally, you may run Feeder Actor as
- *    `$ ./run-example spark.streaming.examples.FeederActor 127.0.1.1 9999`
+ *    `$ ./bin/run-example spark.streaming.examples.FeederActor 127.0.1.1 9999`
  * and then run the example
- *    `$ ./run-example spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999`
+ *    `$ ./bin/run-example spark.streaming.examples.ActorWordCount local[2] 127.0.1.1 9999`
  */
 object ActorWordCount {
   def main(args: Array[String]) {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala
index bc8564b3ba..61be1ce4b1 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/HdfsWordCount.scala
@@ -28,7 +28,7 @@ import org.apache.spark.streaming.StreamingContext._
  *   <directory> is the directory that Spark Streaming will use to find and read new text files.
  *
  * To run this on your local machine on directory `localdir`, run this example
- *    `$ ./run-example spark.streaming.examples.HdfsWordCount local[2] localdir`
+ *    `$ ./bin/run-example spark.streaming.examples.HdfsWordCount local[2] localdir`
  * Then create a text file in `localdir` and the words in the file will get counted.
  */
 object HdfsWordCount {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala
index 570ba4c81a..8dc8a3531a 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/KafkaWordCount.scala
@@ -35,7 +35,7 @@ import org.apache.spark.streaming.util.RawTextHelper._
  *   <numThreads> is the number of threads the kafka consumer should use
  *
  * Example:
- *    `./run-example spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1`
+ *    `./bin/run-example spark.streaming.examples.KafkaWordCount local[2] zoo01,zoo02,zoo03 my-consumer-group topic1,topic2 1`
  */
 object KafkaWordCount {
   def main(args: Array[String]) {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala
index ff332a0282..ea138f55e8 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/MQTTWordCount.scala
@@ -79,9 +79,9 @@ object MQTTPublisher {
  *   <MqttbrokerUrl> and <topic> describe where Mqtt publisher is running.
  *
  * To run this example locally, you may run publisher as
- *    `$ ./run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo`
+ *    `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTPublisher tcp://localhost:1883 foo`
  * and run the example as
- *    `$ ./run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo`
+ *    `$ ./bin/run-example org.apache.spark.streaming.examples.MQTTWordCount local[2] tcp://localhost:1883 foo`
  */
 object MQTTWordCount {
 
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala
index e2487dca5f..ce8df8c502 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/NetworkWordCount.scala
@@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._
  * To run this on your local machine, you need to first run a Netcat server
  *    `$ nc -lk 9999`
  * and then run the example
- *    `$ ./run-example spark.streaming.examples.NetworkWordCount local[2] localhost 9999`
+ *    `$ ./bin/run-example spark.streaming.examples.NetworkWordCount local[2] localhost 9999`
  */
 object NetworkWordCount {
   def main(args: Array[String]) {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala
index cb30c4edb3..e55d71edfc 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/StatefulNetworkWordCount.scala
@@ -29,7 +29,7 @@ import org.apache.spark.streaming.StreamingContext._
  * To run this on your local machine, you need to first run a Netcat server
  *    `$ nc -lk 9999`
  * and then run the example
- *    `$ ./run-example spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999`
+ *    `$ ./bin/run-example spark.streaming.examples.StatefulNetworkWordCount local[2] localhost 9999`
  */
 object StatefulNetworkWordCount {
   def main(args: Array[String]) {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala
index e83ce78aa5..2948aa7cc4 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/ZeroMQWordCount.scala
@@ -62,9 +62,9 @@ object SimpleZeroMQPublisher {
  *   <zeroMQurl> and <topic> describe where zeroMq publisher is running.
  *
  * To run this example locally, you may run publisher as
- *    `$ ./run-example spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar`
+ *    `$ ./bin/run-example spark.streaming.examples.SimpleZeroMQPublisher tcp://127.0.1.1:1234 foo.bar`
  * and run the example as
- *    `$ ./run-example spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo`
+ *    `$ ./bin/run-example spark.streaming.examples.ZeroMQWordCount local[2] tcp://127.0.1.1:1234 foo`
  */
 object ZeroMQWordCount {
   def main(args: Array[String]) {
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala
index de70c50473..1a40fdb9a3 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewGenerator.scala
@@ -39,8 +39,8 @@ object PageView extends Serializable {
 /** Generates streaming events to simulate page views on a website.
   *
   * This should be used in tandem with PageViewStream.scala. Example:
-  * $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
-  * $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
+  * $ ./bin/run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
+  * $ ./bin/run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
   *
   * When running this, you may want to set the root logging level to ERROR in
   * conf/log4j.properties to reduce the verbosity of the output.
diff --git a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala
index 8282cc9269..968b578487 100644
--- a/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala
+++ b/examples/src/main/scala/org/apache/spark/streaming/examples/clickstream/PageViewStream.scala
@@ -25,8 +25,8 @@ import org.apache.spark.SparkContext._
   * operators available in Spark streaming.
   *
   * This should be used in tandem with PageViewStream.scala. Example:
-  * $ ./run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
-  * $ ./run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
+  * $ ./bin/run-example spark.streaming.examples.clickstream.PageViewGenerator 44444 10
+  * $ ./bin/run-example spark.streaming.examples.clickstream.PageViewStream errorRatePerZipCode localhost 44444
   */
 object PageViewStream {
   def main(args: Array[String]) {
diff --git a/make-distribution.sh b/make-distribution.sh
index 32bbdb90a5..0463d14762 100755
--- a/make-distribution.sh
+++ b/make-distribution.sh
@@ -31,10 +31,10 @@
 #
 # Recommended deploy/testing procedure (standalone mode):
 # 1) Rsync / deploy the dist/ dir to one host
-# 2) cd to deploy dir; ./bin/start-master.sh
+# 2) cd to deploy dir; ./sbin/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
+# 4) ./sbin/start-slave.sh 1 <<spark:// URL>>
+# 5) MASTER="spark://my-master-ip:7077" ./bin/spark-shell
 #
 
 # Figure out where the Spark framework is installed
@@ -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
diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py
index d8ca9fce00..c15add5237 100644
--- a/python/pyspark/java_gateway.py
+++ b/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 = "./bin/spark-class.cmd" if on_windows else "./bin/spark-class"
     command = [os.path.join(SPARK_HOME, script), "py4j.GatewayServer",
                "--die-on-broken-pipe", "0"]
     if not on_windows:
diff --git a/python/pyspark/shell.py b/python/pyspark/shell.py
index ef07eb437b..1602227a27 100644
--- a/python/pyspark/shell.py
+++ b/python/pyspark/shell.py
@@ -47,7 +47,7 @@ print "Spark context available as sc."
 if add_files != None:
     print "Adding files: [%s]" % ", ".join(add_files)
 
-# The ./pyspark script stores the old PYTHONSTARTUP value in OLD_PYTHONSTARTUP,
+# The ./bin/pyspark script stores the old PYTHONSTARTUP value in OLD_PYTHONSTARTUP,
 # which allows us to execute the user's PYTHONSTARTUP file:
 _pythonstartup = os.environ.get('OLD_PYTHONSTARTUP')
 if _pythonstartup and os.path.isfile(_pythonstartup):
diff --git a/python/run-tests b/python/run-tests
index 4b71fff7c1..feba97cee0 100755
--- a/python/run-tests
+++ b/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))
 }
 
diff --git a/repl-bin/src/deb/bin/run b/repl-bin/src/deb/bin/run
index 47bb654baf..3a6f22f41f 100755
--- a/repl-bin/src/deb/bin/run
+++ b/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
diff --git a/repl/pom.xml b/repl/pom.xml
index b0e7877bbb..2dfe7ac900 100644
--- a/repl/pom.xml
+++ b/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>
diff --git a/bin/slaves.sh b/sbin/slaves.sh
index c367c2fd8e..a5bc2183d8 100755
--- a/bin/slaves.sh
+++ b/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
diff --git a/bin/spark-config.sh b/sbin/spark-config.sh
index cd2c7b7b0d..cd2c7b7b0d 100755
--- a/bin/spark-config.sh
+++ b/sbin/spark-config.sh
diff --git a/bin/spark-daemon.sh b/sbin/spark-daemon.sh
index a0c0d44b58..2be2b3d7c0 100755
--- a/bin/spark-daemon.sh
+++ b/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"/bin/spark-class $command "$@" >> "$log" 2>&1 < /dev/null &
     newpid=$!
     echo $newpid > $pid
     sleep 2
diff --git a/bin/spark-daemons.sh b/sbin/spark-daemons.sh
index 64286cb2da..5d9f2bb51c 100755
--- a/bin/spark-daemons.sh
+++ b/sbin/spark-daemons.sh
@@ -27,9 +27,9 @@ 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"
 
-exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/spark-daemon.sh" "$@"
+exec "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/spark-daemon.sh" "$@"
diff --git a/spark-executor b/sbin/spark-executor
index 2c07c54843..de5bfab563 100755
--- a/spark-executor
+++ b/sbin/spark-executor
@@ -17,6 +17,7 @@
 # limitations under the License.
 #
 
-FWDIR="`dirname $0`"
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
 echo "Running spark-executor with framework dir = $FWDIR"
-exec $FWDIR/spark-class org.apache.spark.executor.MesosExecutorBackend
+exec $FWDIR/bin/spark-class org.apache.spark.executor.MesosExecutorBackend
diff --git a/bin/start-all.sh b/sbin/start-all.sh
index 0182f1ab24..2daf49db35 100755
--- a/bin/start-all.sh
+++ b/sbin/start-all.sh
@@ -21,14 +21,14 @@
 # Starts the master on this node.
 # Starts a worker on each node specified in conf/slaves
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
 # Load the Spark configuration
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 # Start Master
-"$bin"/start-master.sh
+"$sbin"/start-master.sh
 
 # Start Workers
-"$bin"/start-slaves.sh
+"$sbin"/start-slaves.sh
diff --git a/bin/start-master.sh b/sbin/start-master.sh
index 648c7ae75f..3dcf7cc348 100755
--- a/bin/start-master.sh
+++ b/sbin/start-master.sh
@@ -19,10 +19,10 @@
 
 # Starts the master on the machine this script is executed on.
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
   . "${SPARK_CONF_DIR}/spark-env.sh"
@@ -49,4 +49,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
     fi
 fi
 
-"$bin"/spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
+"$sbin"/spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT
diff --git a/bin/start-slave.sh b/sbin/start-slave.sh
index 4eefa20944..524be38c62 100755
--- a/bin/start-slave.sh
+++ b/sbin/start-slave.sh
@@ -20,8 +20,8 @@
 # Usage: start-slave.sh <worker#> <master-spark-URL>
 #   where <master-spark-URL> is like "spark://localhost:7077"
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
 # Set SPARK_PUBLIC_DNS so slaves can be linked in master web UI
 if [ "$SPARK_PUBLIC_DNS" = "" ]; then
@@ -32,4 +32,4 @@ if [ "$SPARK_PUBLIC_DNS" = "" ]; then
     fi
 fi
 
-"$bin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker "$@"
+"$sbin"/spark-daemon.sh start org.apache.spark.deploy.worker.Worker "$@"
diff --git a/bin/start-slaves.sh b/sbin/start-slaves.sh
index 00dc4888b2..fd5cdeb1e6 100755
--- a/bin/start-slaves.sh
+++ b/sbin/start-slaves.sh
@@ -17,10 +17,10 @@
 # limitations under the License.
 #
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
   . "${SPARK_CONF_DIR}/spark-env.sh"
@@ -37,12 +37,12 @@ fi
 
 # Launch the slaves
 if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
-  exec "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT
+  exec "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/start-slave.sh" 1 spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT
 else
   if [ "$SPARK_WORKER_WEBUI_PORT" = "" ]; then
     SPARK_WORKER_WEBUI_PORT=8081
   fi
   for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
-    "$bin/slaves.sh" cd "$SPARK_HOME" \; "$bin/start-slave.sh" $(( $i + 1 ))  spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT --webui-port $(( $SPARK_WORKER_WEBUI_PORT + $i ))
+    "$sbin/slaves.sh" cd "$SPARK_HOME" \; "$sbin/start-slave.sh" $(( $i + 1 ))  spark://$SPARK_MASTER_IP:$SPARK_MASTER_PORT --webui-port $(( $SPARK_WORKER_WEBUI_PORT + $i ))
   done
 fi
diff --git a/bin/stop-all.sh b/sbin/stop-all.sh
index b6c83a7ba4..60b358d374 100755
--- a/bin/stop-all.sh
+++ b/sbin/stop-all.sh
@@ -21,12 +21,12 @@
 # Run this on the master nde
 
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
 # Load the Spark configuration
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 # Stop the slaves, then the master
-"$bin"/stop-slaves.sh
-"$bin"/stop-master.sh
+"$sbin"/stop-slaves.sh
+"$sbin"/stop-master.sh
diff --git a/bin/stop-master.sh b/sbin/stop-master.sh
index 310e33bedc..2adabd4265 100755
--- a/bin/stop-master.sh
+++ b/sbin/stop-master.sh
@@ -19,9 +19,9 @@
 
 # Starts the master on the machine this script is executed on.
 
-bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+sbin=`dirname "$0"`
+sbin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
-"$bin"/spark-daemon.sh stop org.apache.spark.deploy.master.Master 1
+"$sbin"/spark-daemon.sh stop org.apache.spark.deploy.master.Master 1
diff --git a/bin/stop-slaves.sh b/sbin/stop-slaves.sh
index fcb8555d4e..c6b0b6ab66 100755
--- a/bin/stop-slaves.sh
+++ b/sbin/stop-slaves.sh
@@ -18,18 +18,18 @@
 #
 
 bin=`dirname "$0"`
-bin=`cd "$bin"; pwd`
+bin=`cd "$sbin"; pwd`
 
-. "$bin/spark-config.sh"
+. "$sbin/spark-config.sh"
 
 if [ -f "${SPARK_CONF_DIR}/spark-env.sh" ]; then
   . "${SPARK_CONF_DIR}/spark-env.sh"
 fi
 
 if [ "$SPARK_WORKER_INSTANCES" = "" ]; then
-  "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker 1
+  "$sbin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker 1
 else
   for ((i=0; i<$SPARK_WORKER_INSTANCES; i++)); do
-    "$bin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker $(( $i + 1 ))
+    "$sbin"/spark-daemons.sh stop org.apache.spark.deploy.worker.Worker $(( $i + 1 ))
   done
 fi