Merge remote-tracking branch 'apache-github/master' into remove-binaries

Conflicts:
	core/src/test/scala/org/apache/spark/DriverSuite.scala
	docs/python-programming-guide.md

.gitignore

@@ -1,6 +1,8 @@
 *~
 *.swp
+*.ipr
 *.iml
+*.iws
 .idea/
 .settings
 .cache

README.md

@@ -19,14 +19,14 @@ which can be obtained [here](http://www.scala-sbt.org). To build Spark and its e
 
 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.
 

assembly/pom.xml

@@ -124,7 +124,17 @@
 
   <profiles>
     <profile>
-      <id>hadoop2-yarn</id>
+      <id>yarn-alpha</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-yarn-alpha_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
+    <profile>
+      <id>yarn</id>
       <dependencies>
         <dependency>
           <groupId>org.apache.spark</groupId>

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>

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

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
 

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
 

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-class → 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

spark-class2.cmd → 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%
 

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/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:

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/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))
     }

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

@@ -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)
     }
 

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

@@ -36,7 +36,7 @@ class DriverSuite extends FunSuite with Timeouts {
     forAll(masters) { (master: String) =>
       failAfter(60 seconds) {
         Utils.executeAndGetOutput(
-          Seq("./spark-class", "org.apache.spark.DriverWithoutCleanup", master),
+          Seq("./bin/spark-class", "org.apache.spark.DriverWithoutCleanup", master),
           new File(sparkHome), 
           Map("SPARK_TESTING" -> "1", "SPARK_HOME" -> sparkHome))
       }

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.

docs/building-with-maven.md

@@ -37,20 +37,16 @@ For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop versions wit
     # Cloudera CDH 4.2.0 with MapReduce v1
     $ mvn -Dhadoop.version=2.0.0-mr1-cdh4.2.0 -DskipTests clean package
 
-For Apache Hadoop 2.x, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions with YARN, you should enable the "hadoop2-yarn" profile and set the "yarn.version" property:
+For Apache Hadoop 2.x, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions with YARN, you should enable the "yarn-alpha" or "yarn" profile and set the "hadoop.version", "yarn.version" property:
 
     # Apache Hadoop 2.0.5-alpha
-    $ mvn -Phadoop2-yarn -Dhadoop.version=2.0.5-alpha -Dyarn.version=2.0.5-alpha -DskipTests clean package
+    $ mvn -Pyarn-alpha -Dhadoop.version=2.0.5-alpha -Dyarn.version=2.0.5-alpha -DskipTests clean package
 
     # Cloudera CDH 4.2.0 with MapReduce v2
-    $ mvn -Phadoop2-yarn -Dhadoop.version=2.0.0-cdh4.2.0 -Dyarn.version=2.0.0-chd4.2.0 -DskipTests clean package
+    $ mvn -Pyarn-alpha -Dhadoop.version=2.0.0-cdh4.2.0 -Dyarn.version=2.0.0-chd4.2.0 -DskipTests clean package
 
-Hadoop versions 2.2.x and newer can be built by setting the ```new-yarn``` and the ```yarn.version``` as follows:
-
-    # Apache Hadoop 2.2.X and newer
-    $ mvn -Dyarn.version=2.2.0 -Dhadoop.version=2.2.0 -Pnew-yarn
-
-The build process handles Hadoop 2.2.x as a special case that uses the directory ```new-yarn```, which supports the new YARN API. Furthermore, for this version, the build depends on artifacts published by the spark-project to enable Akka 2.0.5 to work with protobuf 2.5. 
+    # Apache Hadoop 2.2.X ( e.g. 2.2.0 as below ) and newer
+    $ mvn -Pyarn -Dhadoop.version=2.2.0 -Dyarn.version=2.2.0 -DskipTests clean package
 
 ## Spark Tests in Maven ##
 

docs/index.md

@@ -24,18 +24,18 @@ 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
 to connect to. This can be a [URL for a distributed cluster](scala-programming-guide.html#master-urls),
 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
 

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.

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: