You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-issues@hadoop.apache.org by "Luke Lu (Commented) (JIRA)" <ji...@apache.org> on 2012/04/07 02:19:18 UTC
[jira] [Commented] (MAPREDUCE-3612) Task.TaskReporter.done method
blocked for some time when task is finishing
[ https://issues.apache.org/jira/browse/MAPREDUCE-3612?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13249084#comment-13249084 ]
Luke Lu commented on MAPREDUCE-3612:
------------------------------------
See MAPREDUCE-2450 for why this is needed. We saw a fairly significant performance regression (vs. 0.20.2) in Hadoop 1.x for some small jobs workloads due to this issue as well.
Regarding the patch, I don't think it address the issue in MAPREDUCE-2450. Will post a patch later.
> Task.TaskReporter.done method blocked for some time when task is finishing
> --------------------------------------------------------------------------
>
> Key: MAPREDUCE-3612
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3612
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Reporter: Binglin Chang
> Assignee: Binglin Chang
> Attachments: MAPREDUCE-3612.patch
>
>
> We recently have done some tests to evaluate performances of different Hadoop versions(1.0, 0.23, Baidu internal version), and found some weird results. One of them is in 1.0 Task.TaskReporter.done() takes too much time, about 2s, this is bad for small tasks. After reviewing source code and add some log, the following code block Task.TaskReporter.done
> {code:title=src/mapred/org/apache/hadoop/mapred/Task.java}
> 658 try {
> 659 Thread.sleep(PROGRESS_INTERVAL);
> 660 }
> 723 public void stopCommunicationThread() throws InterruptedException {
> 724 // Updating resources specified in ResourceCalculatorPlugin
> 725 if (pingThread != null) {
> 726 synchronized(lock) {
> 727 while(!done) {
> 728 lock.wait();
> 729 }
> 730 }
> 731 pingThread.interrupt();
> 732 pingThread.join();
> 733 }
> 734 }
> {code}
> Originally line 724-730 don't exists, I don't know why it is added. If it is needed, we can replace Thread.sleep with Object.wait(timeout) and Object.notify instead, so it won't block.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira