You are viewing a plain text version of this content. The canonical link for it is here.

Posted to mapreduce-dev@hadoop.apache.org by "Ramkumar Vadali (JIRA)" <ji...@apache.org> on 2010/10/12 22:49:30 UTC

[jira] Created: (MAPREDUCE-2130) Better distribution of files among DistRaid map tasks

Better distribution of files among DistRaid map tasks
-----------------------------------------------------

                 Key: MAPREDUCE-2130
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2130
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
          Components: contrib/raid
            Reporter: Ramkumar Vadali
            Assignee: Ramkumar Vadali


Currently the map tasks get a random subset of the files to be raided. But a disproportionately large file could make a map task extremely slow. We need to give approximately the same amount of data to each map task.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.