Repository: spark Updated Branches: refs/heads/master a89e8b612 -> ca0690b5e
[SPARK-4117][YARN] Spark on Yarn handle AM being told command from RM Spark on Yarn handle AM being told command from RM When RM throws ApplicationAttemptNotFoundException for allocate invocation, making the ApplicationMaster to finish immediately without any retries. Author: Devaraj K <deva...@apache.org> Closes #10129 from devaraj-kavali/SPARK-4117. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/ca0690b5 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/ca0690b5 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/ca0690b5 Branch: refs/heads/master Commit: ca0690b5ef10b14ce57a0c30d5308eb02f163f39 Parents: a89e8b6 Author: Devaraj K <deva...@apache.org> Authored: Tue Dec 15 18:30:59 2015 -0800 Committer: Andrew Or <and...@databricks.com> Committed: Tue Dec 15 18:30:59 2015 -0800 ---------------------------------------------------------------------- .../org/apache/spark/deploy/yarn/ApplicationMaster.scala | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/ca0690b5/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala ---------------------------------------------------------------------- diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index 1970f7d..fc742df 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -376,7 +376,14 @@ private[spark] class ApplicationMaster( case i: InterruptedException => case e: Throwable => { failureCount += 1 - if (!NonFatal(e) || failureCount >= reporterMaxFailures) { + // this exception was introduced in hadoop 2.4 and this code would not compile + // with earlier versions if we refer it directly. + if ("org.apache.hadoop.yarn.exceptions.ApplicationAttemptNotFoundException" == + e.getClass().getName()) { + logError("Exception from Reporter thread.", e) + finish(FinalApplicationStatus.FAILED, ApplicationMaster.EXIT_REPORTER_FAILURE, + e.getMessage) + } else if (!NonFatal(e) || failureCount >= reporterMaxFailures) { finish(FinalApplicationStatus.FAILED, ApplicationMaster.EXIT_REPORTER_FAILURE, "Exception was thrown " + s"$failureCount time(s) from Reporter thread.") --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org