[
https://issues.apache.org/jira/browse/MAPREDUCE-7464?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17800232#comment-17800232
]
ASF GitHub Bot commented on MAPREDUCE-7464:
-------------------------------------------
liubin101 opened a new pull request, #6381:
URL: https://github.com/apache/hadoop/pull/6381
### Description of PR
When maps and reduces run simultaneously, if resources are insufficient,
reduces will be preempted.
Because the priority of reduce is higher than map, the preempted reduces
will first obtain resources when rerun, and then be preempted again, falling
into a loop.
We need to configure the priority of map higher than reduce to avoid this
situation.
### How was this patch tested?
unit test
> Make priority of mapreduce tasks configurable
> ---------------------------------------------
>
> Key: MAPREDUCE-7464
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-7464
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Reporter: liu bin
> Priority: Major
>
> When maps and reduces run simultaneously, if resources are insufficient,
> reduces will be preempted.
> Because the priority of reduce is higher than map, the preempted reduces will
> first obtain resources when rerun, and then be preempted again, falling into
> a loop.
> We need to configure the priority of map higher than reduce to avoid this
> situation.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
