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.
