[SPARK-10649][STREAMING] Prevent inheriting job group and irrelevant job description in streaming jobs

core/src/main/scala/org/apache/spark/util/ThreadUtils.scala

@@ -21,6 +21,7 @@ package org.apache.spark.util
 import java.util.concurrent._
 
 import scala.concurrent.{ExecutionContext, ExecutionContextExecutor}
+import scala.util.control.NonFatal
 
 import com.google.common.util.concurrent.{MoreExecutors, ThreadFactoryBuilder}
 
@@ -86,4 +87,62 @@ private[spark] object ThreadUtils {
     val threadFactory = new ThreadFactoryBuilder().setDaemon(true).setNameFormat(threadName).build()
     Executors.newSingleThreadScheduledExecutor(threadFactory)
   }
+
+  /**
+   * Run a piece of code in a new thread, and the get result. Exception in the new thread is
+   * thrown in the caller thread with an adjusted stack trace that removes references to this
+   * method for clarity. The exception stack traces will be like the following
+   *
+   * SomeException: exception-message
+   *   at CallerClass.body-method (sourcefile.scala)
+   *   at ... run in separate thread using org.apache.spark.util.ThreadUtils ... ()
+   *   at CallerClass.caller-method (sourcefile.scala)
+   *   ...
+   */
+  def runInNewThread[T](
+      threadName: String,
+      isDaemon: Boolean = true)(body: => T): T = {
+    @volatile var exception: Option[Throwable] = None
+    @volatile var result: T = null.asInstanceOf[T]
+
+    val thread = new Thread(threadName) {
+      override def run(): Unit = {
+        try {
+          result = body
+        } catch {
+          case NonFatal(e) =>
+            exception = Some(e)
+        }
+      }
+    }
+    thread.setDaemon(isDaemon)
+    thread.start()
+    thread.join()
+
+    exception match {
+      case Some(realException) =>
+        // Remove the part of the stack that shows method calls into this helper method
+        // This means drop everything from the top until the stack element
+        // ThreadUtils.runInNewThread(), and then drop that as well (hence the `drop(1)`).
+        val baseStackTrace = Thread.currentThread().getStackTrace().dropWhile(
+          ! _.getClassName.contains(this.getClass.getSimpleName)).drop(1)
+
+        // Remove the part of the new thread stack that shows methods call from this helper method
+        val extraStackTrace = realException.getStackTrace.takeWhile(
+          ! _.getClassName.contains(this.getClass.getSimpleName))
+
+        // Combine the two stack traces, with a place holder just specifying that there
+        // was a helper method used, without any further details of the helper
+        val placeHolderStackElem = new StackTraceElement(
+          s"... run in separate thread using ${ThreadUtils.getClass.getName.stripSuffix("$")} ..",
+          " ", "", -1)
+        val finalStackTrace = extraStackTrace ++ Seq(placeHolderStackElem) ++ baseStackTrace
+
+        // Update the stack trace and rethrow the exception in the caller thread
+        realException.setStackTrace(finalStackTrace)
+        throw realException
+      case None =>
+        result
+    }
+  }
 }

core/src/test/scala/org/apache/spark/util/ThreadUtilsSuite.scala

@@ -20,8 +20,8 @@ package org.apache.spark.util
 
 import java.util.concurrent.{CountDownLatch, TimeUnit}
 
-import scala.concurrent.{Await, Future}
 import scala.concurrent.duration._
+import scala.concurrent.{Await, Future}
 
 import org.apache.spark.SparkFunSuite
 
@@ -66,4 +66,24 @@ class ThreadUtilsSuite extends SparkFunSuite {
     val futureThreadName = Await.result(f, 10.seconds)
     assert(futureThreadName === callerThreadName)
   }
+
+  test("runInNewThread") {
+    import ThreadUtils._
+    assert(runInNewThread("thread-name") { Thread.currentThread().getName } === "thread-name")
+    assert(runInNewThread("thread-name") { Thread.currentThread().isDaemon } === true)
+    assert(
+      runInNewThread("thread-name", isDaemon = false) { Thread.currentThread().isDaemon } === false
+    )
+    val exception = intercept[IllegalArgumentException] {
+      runInNewThread("thread-name") { throw new IllegalArgumentException("test") }
+    }
+    assert(exception.asInstanceOf[IllegalArgumentException].getMessage.contains("test"))
+    assert(exception.getStackTrace.mkString("\n").contains(
+      "... run in separate thread using org.apache.spark.util.ThreadUtils ...") === true,
+      "stack trace does not contain expected place holder"
+    )
+    assert(exception.getStackTrace.mkString("\n").contains("ThreadUtils.scala") === false,
+      "stack trace contains unexpected references to ThreadUtils"
+    )
+  }
 }

streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala

@@ -44,7 +44,7 @@ import org.apache.spark.streaming.dstream._
 import org.apache.spark.streaming.receiver.{ActorReceiver, ActorSupervisorStrategy, Receiver}
 import org.apache.spark.streaming.scheduler.{JobScheduler, StreamingListener}
 import org.apache.spark.streaming.ui.{StreamingJobProgressListener, StreamingTab}
-import org.apache.spark.util.{CallSite, ShutdownHookManager, Utils}
+import org.apache.spark.util.{CallSite, ShutdownHookManager, ThreadUtils}
 
 /**
  * Main entry point for Spark Streaming functionality. It provides methods used to create
@@ -588,12 +588,16 @@ class StreamingContext private[streaming] (
     state match {
       case INITIALIZED =>
         startSite.set(DStream.getCreationSite())
-        sparkContext.setCallSite(startSite.get)
         StreamingContext.ACTIVATION_LOCK.synchronized {
           StreamingContext.assertNoOtherContextIsActive()
           try {
             validate()
-            scheduler.start()
+            ThreadUtils.runInNewThread("streaming-start") {
+              sparkContext.setCallSite(startSite.get)
+              sparkContext.clearJobGroup()
+              sparkContext.setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, "false")
+              scheduler.start()
+            }
             state = StreamingContextState.ACTIVE
           } catch {
             case NonFatal(e) =>
@@ -610,14 +614,15 @@ class StreamingContext private[streaming] (
         assert(env.metricsSystem != null)
         env.metricsSystem.registerSource(streamingSource)
         uiTab.foreach(_.attach())
-        logInfo("StreamingContext started")
+        this.logInfo("StreamingContext started")
       case ACTIVE =>
         logWarning("StreamingContext has already been started")
       case STOPPED =>
         throw new IllegalStateException("StreamingContext has already been stopped")
     }
   }
 
+
   /**
    * Wait for the execution to stop. Any exceptions that occurs during the execution
    * will be thrown in this thread.

streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala

@@ -180,6 +180,38 @@ class StreamingContextSuite extends SparkFunSuite with BeforeAndAfter with Timeo
     assert(ssc.scheduler.isStarted === false)
   }
 
+  test("start should set job group correctly") {
+    ssc = new StreamingContext(conf, batchDuration)
+    ssc.sc.setJobGroup("non-streaming", "non-streaming", true)
+    val sc = ssc.sc
+
+    @volatile var jobGroupFound: String = ""
+    @volatile var jobDescFound: String = ""
+    @volatile var jobInterruptFound: String = ""
+    @volatile var allFound: Boolean = false
+
+    addInputStream(ssc).foreachRDD { rdd =>
+      jobGroupFound = sc.getLocalProperty(SparkContext.SPARK_JOB_GROUP_ID)
+      jobDescFound = sc.getLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION)
+      jobInterruptFound = sc.getLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL)
+      allFound = true
+    }
+    ssc.start()
+
+    eventually(timeout(5 seconds), interval(10 milliseconds)) {
+      assert(allFound === true)
+    }
+
+    // Verify streaming jobs have expected thread-local properties
+    assert(jobGroupFound === null)
+    assert(jobDescFound === null)
+    assert(jobInterruptFound === "false")
+
+    // Verify current thread's thread-local properties have not changed
+    assert(sc.getLocalProperty(SparkContext.SPARK_JOB_GROUP_ID) === "non-streaming")
+    assert(sc.getLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION) === "non-streaming")
+    assert(sc.getLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL) === "true")
+  }
 
   test("start multiple times") {
     ssc = new StreamingContext(master, appName, batchDuration)