Merge branch 'master' into master-merge

Conflicts:
	core/pom.xml
	core/src/main/scala/spark/MapOutputTracker.scala
	core/src/main/scala/spark/RDD.scala
	core/src/main/scala/spark/RDDCheckpointData.scala
	core/src/main/scala/spark/SparkContext.scala
	core/src/main/scala/spark/Utils.scala
	core/src/main/scala/spark/api/python/PythonRDD.scala
	core/src/main/scala/spark/deploy/client/Client.scala
	core/src/main/scala/spark/deploy/master/MasterWebUI.scala
	core/src/main/scala/spark/deploy/worker/Worker.scala
	core/src/main/scala/spark/deploy/worker/WorkerWebUI.scala
	core/src/main/scala/spark/rdd/BlockRDD.scala
	core/src/main/scala/spark/rdd/ZippedRDD.scala
	core/src/main/scala/spark/scheduler/cluster/StandaloneSchedulerBackend.scala
	core/src/main/scala/spark/storage/BlockManager.scala
	core/src/main/scala/spark/storage/BlockManagerMaster.scala
	core/src/main/scala/spark/storage/BlockManagerMasterActor.scala
	core/src/main/scala/spark/storage/BlockManagerUI.scala
	core/src/main/scala/spark/util/AkkaUtils.scala
	core/src/test/scala/spark/SizeEstimatorSuite.scala
	pom.xml
	project/SparkBuild.scala
	repl/src/main/scala/spark/repl/SparkILoop.scala
	repl/src/test/scala/spark/repl/ReplSuite.scala
	streaming/src/main/scala/spark/streaming/StreamingContext.scala
	streaming/src/main/scala/spark/streaming/api/java/JavaStreamingContext.scala
	streaming/src/main/scala/spark/streaming/dstream/KafkaInputDStream.scala
	streaming/src/main/scala/spark/streaming/util/MasterFailureTest.scala

3 files changed, 29 insertions, 0 deletions

diff --git a/core/src/hadoop1/scala/org/apache/hadoop/mapred/HadoopMapRedUtil.scala b/core/src/hadoop1/scala/org/apache/hadoop/mapred/HadoopMapRedUtil.scala
index ca9f7219de..f286f2cf9c 100644
--- a/core/src/hadoop1/scala/org/apache/hadoop/mapred/HadoopMapRedUtil.scala
+++ b/core/src/hadoop1/scala/org/apache/hadoop/mapred/HadoopMapRedUtil.scala
@@ -4,4 +4,7 @@ trait HadoopMapRedUtil {
   def newJobContext(conf: JobConf, jobId: JobID): JobContext = new JobContext(conf, jobId)
 
   def newTaskAttemptContext(conf: JobConf, attemptId: TaskAttemptID): TaskAttemptContext = new TaskAttemptContext(conf, attemptId)
+
+  def newTaskAttemptID(jtIdentifier: String, jobId: Int, isMap: Boolean, taskId: Int, attemptId: Int) = new TaskAttemptID(jtIdentifier,
+    jobId, isMap, taskId, attemptId)
 }
diff --git a/core/src/hadoop1/scala/org/apache/hadoop/mapreduce/HadoopMapReduceUtil.scala b/core/src/hadoop1/scala/org/apache/hadoop/mapreduce/HadoopMapReduceUtil.scala
index de7b0f81e3..264d421d14 100644
--- a/core/src/hadoop1/scala/org/apache/hadoop/mapreduce/HadoopMapReduceUtil.scala
+++ b/core/src/hadoop1/scala/org/apache/hadoop/mapreduce/HadoopMapReduceUtil.scala
@@ -6,4 +6,7 @@ trait HadoopMapReduceUtil {
   def newJobContext(conf: Configuration, jobId: JobID): JobContext = new JobContext(conf, jobId)
 
   def newTaskAttemptContext(conf: Configuration, attemptId: TaskAttemptID): TaskAttemptContext = new TaskAttemptContext(conf, attemptId)
+
+  def newTaskAttemptID(jtIdentifier: String, jobId: Int, isMap: Boolean, taskId: Int, attemptId: Int) = new TaskAttemptID(jtIdentifier,
+    jobId, isMap, taskId, attemptId)
 }
diff --git a/core/src/hadoop1/scala/spark/deploy/SparkHadoopUtil.scala b/core/src/hadoop1/scala/spark/deploy/SparkHadoopUtil.scala
new file mode 100644
index 0000000000..a0fb4fe25d
--- /dev/null
+++ b/core/src/hadoop1/scala/spark/deploy/SparkHadoopUtil.scala
@@ -0,0 +1,23 @@
+package spark.deploy
+import org.apache.hadoop.conf.Configuration
+
+
+/**
+ * Contains util methods to interact with Hadoop from spark.
+ */
+object SparkHadoopUtil {
+
+  def getUserNameFromEnvironment(): String = {
+    // defaulting to -D ...
+    System.getProperty("user.name")
+  }
+
+  def runAsUser(func: (Product) => Unit, args: Product) {
+
+    // Add support, if exists - for now, simply run func !
+    func(args)
+  }
+
+  // Return an appropriate (subclass) of Configuration. Creating config can initializes some hadoop subsystems
+  def newConfiguration(): Configuration = new Configuration()
+}