[
https://issues.apache.org/jira/browse/HADOOP-5338?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12678732#action_12678732
]
Ramya R commented on HADOOP-5338:
---------------------------------
Tested the above patch on a 500node cluster and the reducers are no longer
stuck and the job successfully completes after multiple JT restarts.
However, there is one thing to notice. The situation where "reducers wait for
maps when none are running" still occurs. But due to the above patch,this
situation is handled in a way that the reducers don't hang infinitely. Instead
the TT pulls back all the events and completes the task successfully.
> Reduce tasks are stuck waiting for map outputs when none are in progress
> ------------------------------------------------------------------------
>
> Key: HADOOP-5338
> URL: https://issues.apache.org/jira/browse/HADOOP-5338
> Project: Hadoop Core
> Issue Type: Bug
> Components: mapred
> Affects Versions: 0.20.0
> Reporter: Ramya R
> Assignee: Amar Kamat
> Priority: Blocker
> Fix For: 0.20.0
>
> Attachments: HADOOP-5338-v2.1.patch, log.txt
>
>
> When JT is restarted several times, a situation is encountered when the
> reduce tasks are stuck forever waiting for map outputs. However 100%map is
> complete and none of the map tasks are in progress. The reduce tasks wait
> infinitely.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
