Merge remote-tracking branch 'upstream/master'

Author: srowen

.gitignore

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

README.md

@@ -13,20 +13,20 @@ This README file only contains basic setup instructions.
 ## Building
 
 Spark requires Scala 2.10. The project is built using Simple Build Tool (SBT),
-which is packaged with it. To build Spark and its example programs, run:
+which can be obtained [here](http://www.scala-sbt.org). To build Spark and its example programs, run:
 
-    sbt/sbt assembly
+    sbt assembly
 
 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.
 
@@ -36,7 +36,13 @@ All of the Spark samples take a `<master>` parameter that is the cluster URL
 to connect to. This can be a mesos:// or spark:// URL, or "local" to run
 locally with one thread, or "local[N]" to run locally with N threads.
 
+## Running tests
 
+Testing first requires [Building](#Building) Spark. Once Spark is built, tests
+can be run using:
+
+`sbt test`
+ 
 ## A Note About Hadoop Versions
 
 Spark uses the Hadoop core library to talk to HDFS and other Hadoop-supported
@@ -49,22 +55,22 @@ For Apache Hadoop versions 1.x, Cloudera CDH MRv1, and other Hadoop
 versions without YARN, use:
 
     # Apache Hadoop 1.2.1
-    $ SPARK_HADOOP_VERSION=1.2.1 sbt/sbt assembly
+    $ SPARK_HADOOP_VERSION=1.2.1 sbt assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v1
-    $ SPARK_HADOOP_VERSION=2.0.0-mr1-cdh4.2.0 sbt/sbt assembly
+    $ SPARK_HADOOP_VERSION=2.0.0-mr1-cdh4.2.0 sbt assembly
 
 For Apache Hadoop 2.2.X, 2.1.X, 2.0.X, 0.23.x, Cloudera CDH MRv2, and other Hadoop versions
 with YARN, also set `SPARK_YARN=true`:
 
     # Apache Hadoop 2.0.5-alpha
-    $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt/sbt assembly
+    $ SPARK_HADOOP_VERSION=2.0.5-alpha SPARK_YARN=true sbt assembly
 
     # Cloudera CDH 4.2.0 with MapReduce v2
-    $ SPARK_HADOOP_VERSION=2.0.0-cdh4.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ SPARK_HADOOP_VERSION=2.0.0-cdh4.2.0 SPARK_YARN=true sbt assembly
 
     # Apache Hadoop 2.2.X and newer
-    $ SPARK_HADOOP_VERSION=2.2.0 SPARK_YARN=true sbt/sbt assembly
+    $ SPARK_HADOOP_VERSION=2.2.0 SPARK_YARN=true sbt assembly
 
 When developing a Spark application, specify the Hadoop version by adding the
 "hadoop-client" artifact to your project's dependencies. For example, if you're

assembly/lib/PY4J_LICENSE.txt

@@ -67,7 +67,7 @@
     <dependency>
       <groupId>net.sf.py4j</groupId>
       <artifactId>py4j</artifactId>
-      <version>0.7</version>
+      <version>0.8.1</version>
     </dependency>
   </dependencies>
 
@@ -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/lib/PY4J_VERSION.txt

@@ -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>

assembly/lib/net/sf/py4j/py4j/0.7/py4j-0.7.jar

@@ -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