Repository: spark Updated Branches: refs/heads/branch-1.2 36f70de83 -> d89964f86
SPARK-5613: Catch the ApplicationNotFoundException exception to avoid thread from getting killed on yarn restart. [SPARK-5613] Added a catch block to catch the ApplicationNotFoundException. Without this catch block the thread gets killed on occurrence of this exception. This Exception occurs when yarn restarts and tries to find an application id for a spark job which got interrupted due to yarn getting stopped. See the stacktrace in the bug for more details. Author: Kashish Jain <kashish.j...@guavus.com> Closes #4392 from kasjain/branch-1.2 and squashes the following commits: 4831000 [Kashish Jain] SPARK-5613: Catch the ApplicationNotFoundException exception to avoid thread from getting killed on yarn restart. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/d89964f8 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/d89964f8 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/d89964f8 Branch: refs/heads/branch-1.2 Commit: d89964f86e288dbdd67e08f4eb97f374c4d437f3 Parents: 36f70de Author: Kashish Jain <kashish.j...@guavus.com> Authored: Fri Feb 6 13:47:23 2015 -0800 Committer: Andrew Or <and...@databricks.com> Committed: Fri Feb 6 13:47:23 2015 -0800 ---------------------------------------------------------------------- .../scheduler/cluster/YarnClientSchedulerBackend.scala | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/d89964f8/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala ---------------------------------------------------------------------- diff --git a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala index 09597bd..15f8049 100644 --- a/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ b/yarn/common/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala @@ -20,6 +20,7 @@ package org.apache.spark.scheduler.cluster import scala.collection.mutable.ArrayBuffer import org.apache.hadoop.yarn.api.records.{ApplicationId, YarnApplicationState} +import org.apache.hadoop.yarn.exceptions.ApplicationNotFoundException import org.apache.spark.{SparkException, Logging, SparkContext} import org.apache.spark.deploy.yarn.{Client, ClientArguments} @@ -132,8 +133,14 @@ private[spark] class YarnClientSchedulerBackend( val t = new Thread { override def run() { while (!stopping) { - val report = client.getApplicationReport(appId) - val state = report.getYarnApplicationState() + var state : YarnApplicationState = null + try { + val report = client.getApplicationReport(appId) + state = report.getYarnApplicationState() + } catch { + case e : ApplicationNotFoundException => + state = YarnApplicationState.KILLED + } if (state == YarnApplicationState.FINISHED || state == YarnApplicationState.KILLED || state == YarnApplicationState.FAILED) { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org