From 2846a357f32bfa129bc37f4d1cbe9e19caaf69c9 Mon Sep 17 00:00:00 2001 From: WangTaoTheTonic Date: Wed, 10 Jun 2015 13:34:19 -0700 Subject: [SPARK-8273] Driver hangs up when yarn shutdown in client mode In client mode, if yarn was shut down with spark application running, the application will hang up after several retries(default: 30) because the exception throwed by YarnClientImpl could not be caught by upper level, we should exit in case that user can not be aware that. The exception we wanna catch is [here](https://github.com/apache/hadoop/blob/branch-2.7.0/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/retry/RetryInvocationHandler.java#L122), and I try to fix it refer to [MR](https://github.com/apache/hadoop/blob/branch-2.7.0/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/ClientServiceDelegate.java#L320). Author: WangTaoTheTonic Closes #6717 from WangTaoTheTonic/SPARK-8273 and squashes the following commits: 28752d6 [WangTaoTheTonic] catch the throwed exception --- yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'yarn') diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala index f4d43214b0..9296e79ccf 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -28,6 +28,7 @@ import scala.collection.JavaConversions._ import scala.collection.mutable.{ArrayBuffer, HashMap, HashSet, ListBuffer, Map} import scala.reflect.runtime.universe import scala.util.{Try, Success, Failure} +import scala.util.control.NonFatal import com.google.common.base.Objects import com.google.common.io.Files @@ -771,6 +772,9 @@ private[spark] class Client( case e: ApplicationNotFoundException => logError(s"Application $appId not found.") return (YarnApplicationState.KILLED, FinalApplicationStatus.KILLED) + case NonFatal(e) => + logError(s"Failed to contact YARN for application $appId.", e) + return (YarnApplicationState.FAILED, FinalApplicationStatus.FAILED) } val state = report.getYarnApplicationState -- cgit v1.2.3