diff --git a/README.md b/README.md
index e2d1dcb5672ff46897dd3aef457b311675eec585..9c2e32b90f162dea95f38837eed4ae85fc76b012 100644
--- a/README.md
+++ b/README.md
@@ -39,17 +39,22 @@ And run the following command, which should also return 1000:
 ## Example Programs
 
 Spark also comes with several sample programs in the `examples` directory.
-To run one of them, use `./bin/run-example <class> <params>`. For example:
+To run one of them, use `./bin/run-example <class> [params]`. For example:
 
-    ./bin/run-example org.apache.spark.examples.SparkLR local[2]
+    ./bin/run-example org.apache.spark.examples.SparkLR
 
-will run the Logistic Regression example locally on 2 CPUs.
+will run the Logistic Regression example locally.
 
-Each of the example programs prints usage help if no params are given.
+You can set the MASTER environment variable when running examples to submit
+examples to a cluster. This can be a mesos:// or spark:// URL, 
+"yarn-cluster" or "yarn-client" to run on YARN, and "local" to run 
+locally with one thread, or "local[N]" to run locally with N threads. You 
+can also use an abbreviated class name if the class is in the `examples`
+package. For instance:
 
-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.
+    MASTER=spark://host:7077 ./bin/run-example SparkPi
+
+Many of the example programs print usage help if no params are given.
 
 ## Running Tests
 
diff --git a/bin/pyspark b/bin/pyspark
index f5558853e8a4e5c26d3cf2aa53510920711d92fa..10e35e0f1734e061feeca77ebd234083d37360ec 100755
--- a/bin/pyspark
+++ b/bin/pyspark
@@ -31,7 +31,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
   ls "$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
+    echo "You need to build Spark before running this program" >&2
     exit 1
   fi
 fi
diff --git a/bin/run-example b/bin/run-example
index d8a94f2e31e0722e8689bd17de7dc6d4db61a1f1..146951ac0ee569c87079875c34a84b38ce9f7079 100755
--- a/bin/run-example
+++ b/bin/run-example
@@ -17,28 +17,10 @@
 # limitations under the License.
 #
 
-cygwin=false
-case "`uname`" in
-    CYGWIN*) cygwin=true;;
-esac
-
 SCALA_VERSION=2.10
 
-# Figure out where the Scala framework is installed
 FWDIR="$(cd `dirname $0`/..; pwd)"
-
-# Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
-
-. $FWDIR/bin/load-spark-env.sh
-
-if [ -z "$1" ]; then
-  echo "Usage: run-example <example-class> [<args>]" >&2
-  exit 1
-fi
-
-# Figure out the JAR file that our examples were packaged into. This includes a bit of a hack
-# to avoid the -sources and -doc packages that are built by publish-local.
 EXAMPLES_DIR="$FWDIR"/examples
 
 if [ -f "$FWDIR/RELEASE" ]; then
@@ -49,46 +31,29 @@ fi
 
 if [[ -z $SPARK_EXAMPLES_JAR ]]; then
   echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" >&2
-  echo "You need to build Spark with sbt/sbt assembly before running this program" >&2
+  echo "You need to build Spark before running this program" >&2
   exit 1
 fi
 
+EXAMPLE_MASTER=${MASTER:-"local[*]"}
 
-# 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=`$FWDIR/bin/compute-classpath.sh`
-CLASSPATH="$SPARK_EXAMPLES_JAR:$CLASSPATH"
-
-if $cygwin; then
-    CLASSPATH=`cygpath -wp $CLASSPATH`
-    export SPARK_EXAMPLES_JAR=`cygpath -w $SPARK_EXAMPLES_JAR`
-fi
-
-# Find java binary
-if [ -n "${JAVA_HOME}" ]; then
-  RUNNER="${JAVA_HOME}/bin/java"
-else
-  if [ `command -v java` ]; then
-    RUNNER="java"
-  else
-    echo "JAVA_HOME is not set" >&2
-    exit 1
-  fi
-fi
-
-# Set JAVA_OPTS to be able to load native libraries and to set heap size
-JAVA_OPTS="$SPARK_JAVA_OPTS"
-# 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`"
+if [ -n "$1" ]; then
+  EXAMPLE_CLASS="$1"
+  shift
+else 
+  echo "usage: ./bin/run-example <example-class> [example-args]" 
+  echo "  - set MASTER=XX to use a specific master"
+  echo "  - can use abbreviated example class name (e.g. SparkPi, mllib.MovieLensALS)"
+  echo
+  exit -1
 fi
-export JAVA_OPTS
 
-if [ "$SPARK_PRINT_LAUNCH_COMMAND" == "1" ]; then
-  echo -n "Spark Command: "
-  echo "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
-  echo "========================================"
-  echo
+if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then
+  EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS"
 fi
 
-exec "$RUNNER" -cp "$CLASSPATH" $JAVA_OPTS "$@"
+./bin/spark-submit \
+  --master $EXAMPLE_MASTER \
+  --class $EXAMPLE_CLASS \
+  $SPARK_EXAMPLES_JAR \
+  "$@"
diff --git a/bin/spark-class b/bin/spark-class
index 72f8b9bf9a495b2491cc25c657c33f67aa365cbe..6480ccb58d6aa429c37280d074d8715b0e008f2d 100755
--- a/bin/spark-class
+++ b/bin/spark-class
@@ -114,7 +114,7 @@ if [ ! -f "$FWDIR/RELEASE" ]; then
   jars_list=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar")
   if [ "$num_jars" -eq "0" ]; then
     echo "Failed to find Spark assembly in $FWDIR/assembly/target/scala-$SCALA_VERSION/" >&2
-    echo "You need to build Spark with 'sbt/sbt assembly' before running this program." >&2
+    echo "You need to build Spark before running this program." >&2
     exit 1
   fi
   if [ "$num_jars" -gt "1" ]; then
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
index a1ca612cc9a09e5ab65cfcde40dde5a698ab96ec..9d8d8044f07ebcb3eb8e00f2cf12517712fa8892 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -330,9 +330,9 @@ abstract class RDD[T: ClassTag](
     if (shuffle) {
       // include a shuffle step so that our upstream tasks are still distributed
       new CoalescedRDD(
-        new ShuffledRDD[T, Null, (T, Null)](map(x => (x, null)),
+        new ShuffledRDD[Int, T, (Int, T)](map(x => (Utils.random.nextInt(), x)),
         new HashPartitioner(numPartitions)),
-        numPartitions).keys
+        numPartitions).values
     } else {
       new CoalescedRDD(this, numPartitions)
     }
diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md
index 68183ee8b46132400f058ba87eb349c1696a032f..c563594296802a67ad7898cf8fc091110c1ca2a2 100644
--- a/docs/running-on-yarn.md
+++ b/docs/running-on-yarn.md
@@ -53,7 +53,7 @@ For example:
         --driver-memory 4g \
         --executor-memory 2g \
         --executor-cores 1
-        examples/target/scala-{{site.SCALA_BINARY_VERSION}}/spark-examples-assembly-{{site.SPARK_VERSION}}.jar \
+        lib/spark-examples*.jar \
         yarn-cluster 5
 
 The above starts a YARN client program which starts the default Application Master. Then SparkPi will be run as a child thread of Application Master. The client will periodically poll the Application Master for status updates and display them in the console. The client will exit once your application has finished running.  Refer to the "Viewing Logs" section below for how to see driver and executor logs.
diff --git a/make-distribution.sh b/make-distribution.sh
index 759e555b4b69ad4dd016005f0ab7305020cf79ed..1cc2844703fbbf78c068814642ce120af9f38aa6 100755
--- a/make-distribution.sh
+++ b/make-distribution.sh
@@ -40,6 +40,8 @@
 #
 
 set -o pipefail
+set -e
+
 # Figure out where the Spark framework is installed
 FWDIR="$(cd `dirname $0`; pwd)"
 DISTDIR="$FWDIR/dist"