[SPARK-17696][core] Partial backport of SPARK-12330 to branch-1.6.

drcrallen · Marcelo Vanzin · commit 715c90adee80 · 2016-09-27T15:37:29.000-07:00
From the original commit message: This PR also fixes a regression caused by [SPARK-10987] whereby submitting a shutdown causes a race between the local shutdown procedure and the notification of the scheduler driver disconnection. If the scheduler driver disconnection wins the race, the coarse executor incorrectly exits with status 1 (instead of the proper status 0) Author: Charles Allen <charles@allen-net.com> (cherry picked from commit 2eaeafe)
diff --git a/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala b/core/src/main/scala/org/apache/spark/executor/CoarseGrainedExecutorBackend.scala
@@ -19,6 +19,7 @@ package org.apache.spark.executor
 
 import java.net.URL
 import java.nio.ByteBuffer
+import java.util.concurrent.atomic.AtomicBoolean
 
 import org.apache.hadoop.conf.Configuration
 
@@ -45,6 +46,7 @@ private[spark] class CoarseGrainedExecutorBackend(
     env: SparkEnv)
   extends ThreadSafeRpcEndpoint with ExecutorBackend with Logging {
 
+  private[this] val stopping = new AtomicBoolean(false)
   var executor: Executor = null
   @volatile var driver: Option[RpcEndpointRef] = None
 
@@ -106,19 +108,23 @@ private[spark] class CoarseGrainedExecutorBackend(
       }
 
     case StopExecutor =>
+      stopping.set(true)
       logInfo("Driver commanded a shutdown")
       // Cannot shutdown here because an ack may need to be sent back to the caller. So send
       // a message to self to actually do the shutdown.
       self.send(Shutdown)
 
     case Shutdown =>
+      stopping.set(true)
       executor.stop()
       stop()
       rpcEnv.shutdown()
   }
 
   override def onDisconnected(remoteAddress: RpcAddress): Unit = {
-    if (driver.exists(_.address == remoteAddress)) {
+    if (stopping.get()) {
+      logInfo(s"Driver from $remoteAddress disconnected during shutdown")
+    } else if (driver.exists(_.address == remoteAddress)) {
       logError(s"Driver $remoteAddress disassociated! Shutting down.")
       System.exit(1)
     } else {
