hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Arun C Murthy (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-279) Map-Reduce 2.0
Date Sat, 19 Feb 2011 20:20:38 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-279?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12996851#comment-12996851
] 

Arun C Murthy commented on MAPREDUCE-279:
-----------------------------------------

Jeff, the prototype uses significant amount of Hadoop MapReduce, especially the MapReduce
ApplicationMaster for running MR jobs. There is a new ResourceManager/NodeManager, but we
still need to co-evolve and stabilize the entire codebase for serving our primary aim: running
Hadoop MapReduce applications. After all, this is a re-factor of Hadoop MapReduce.

Moving to different projects is premature... it will be very reminiscent of the issues we
have with Common and HDFS i.e. every change might be spread over multiple projects, which
is a logistical nightmare for developers. Eventually, once we have a few releases under our
belt and successful deployments etc., we might be in a better place to revisit this proposal.
Make sense?

> Map-Reduce 2.0
> --------------
>
>                 Key: MAPREDUCE-279
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-279
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>          Components: jobtracker, tasktracker
>            Reporter: Arun C Murthy
>            Assignee: Arun C Murthy
>             Fix For: 0.23.0
>
>
> Re-factor MapReduce into a generic resource scheduler and a per-job, user-defined component
that manages the application execution. 

-- 
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message