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 "Harsh J (Commented) (JIRA)" <ji...@apache.org> on 2012/01/16 11:09:39 UTC
[jira] [Commented] (MAPREDUCE-2700) dynamic configuration of
mapred.map/reduce.tasks
[ https://issues.apache.org/jira/browse/MAPREDUCE-2700?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13186832#comment-13186832 ]
Harsh J commented on MAPREDUCE-2700:
------------------------------------
Agree that it makes sense to have #-reducers auto-tuned to cluster size.
> dynamic configuration of mapred.map/reduce.tasks
> ------------------------------------------------
>
> Key: MAPREDUCE-2700
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-2700
> Project: Hadoop Map/Reduce
> Issue Type: New Feature
> Components: job submission
> Reporter: Johannes Zillmann
> Priority: Minor
> Labels: newbie
>
> Since the optimal value for these 2 configuration properties heavily depends on the numer of nodes, also examined here
> http://wiki.apache.org/lucene-hadoop/HowManyMapsAndReduces
> would it be not more comfortable to configure relations to numberOfNodes ?
> So you hav'nt to change it all the time the number of nodes changes...
--
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