You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by mx...@apache.org on 2016/06/24 16:56:09 UTC
[5/6] flink git commit: [FLINK-4041] reduce log level for
JobManager->ResourceManager timeouts
[FLINK-4041] reduce log level for JobManager->ResourceManager timeouts
These timeouts can be recovered and don't have to be logged as error
with an Exception.
This closes #2137
Project: http://git-wip-us.apache.org/repos/asf/flink/repo
Commit: http://git-wip-us.apache.org/repos/asf/flink/commit/a5aa4e11
Tree: http://git-wip-us.apache.org/repos/asf/flink/tree/a5aa4e11
Diff: http://git-wip-us.apache.org/repos/asf/flink/diff/a5aa4e11
Branch: refs/heads/master
Commit: a5aa4e115814539518fcaa88cbbca47da9d7ede5
Parents: 9c15406
Author: Maximilian Michels <mx...@apache.org>
Authored: Mon Jun 20 16:49:26 2016 +0200
Committer: Maximilian Michels <mx...@apache.org>
Committed: Fri Jun 24 18:53:43 2016 +0200
----------------------------------------------------------------------
.../org/apache/flink/runtime/jobmanager/JobManager.scala | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/flink/blob/a5aa4e11/flink-runtime/src/main/scala/org/apache/flink/runtime/jobmanager/JobManager.scala
----------------------------------------------------------------------
diff --git a/flink-runtime/src/main/scala/org/apache/flink/runtime/jobmanager/JobManager.scala b/flink-runtime/src/main/scala/org/apache/flink/runtime/jobmanager/JobManager.scala
index 46f7ed2..60f0a97 100644
--- a/flink-runtime/src/main/scala/org/apache/flink/runtime/jobmanager/JobManager.scala
+++ b/flink-runtime/src/main/scala/org/apache/flink/runtime/jobmanager/JobManager.scala
@@ -21,7 +21,7 @@ package org.apache.flink.runtime.jobmanager
import java.io.{File, IOException}
import java.net.{BindException, ServerSocket, UnknownHostException, InetAddress, InetSocketAddress}
import java.util.UUID
-import java.util.concurrent.{TimeUnit, ExecutorService}
+import java.util.concurrent.{ExecutorService, TimeUnit, TimeoutException}
import akka.actor.Status.Failure
import akka.actor._
@@ -382,7 +382,12 @@ class JobManager(
// the resource manager is available and answered
self ! response
case scala.util.Failure(t) =>
- log.error("Failure while asking ResourceManager for RegisterResource", t)
+ t match {
+ case _: TimeoutException =>
+ log.info("Attempt to register resource at ResourceManager timed out. Retrying")
+ case _ =>
+ log.warn("Failure while asking ResourceManager for RegisterResource. Retrying", t)
+ }
// slow or unreachable resource manager, register anyway and let the rm reconnect
self ! decorateMessage(new RegisterResourceSuccessful(taskManager, msg))
self ! decorateMessage(new ReconnectResourceManager(rm))