[
https://issues.apache.org/jira/browse/MAPREDUCE-1893?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12882398#action_12882398
]
Konstantin Shvachko commented on MAPREDUCE-1893:
------------------------------------------------
Slive maps output different stats of the operations performed by the test. The
stats are currently aggregated by a single reducer, which may run for a long
time if the amount of generated data is large.
I propose to add a parameter to Slive args, which specifies the number of
reducers R. Then SlivePartitioner for each output stat calculates a hash value
of the operation type, modular R. This defines the reducer number.
> Multiple reducers for Slive
> ---------------------------
>
> Key: MAPREDUCE-1893
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-1893
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Components: benchmarks, test
> Affects Versions: 0.22.0
> Reporter: Konstantin Shvachko
> Assignee: Konstantin Shvachko
> Fix For: 0.22.0
>
>
> Slive currently uses single reducer. It could use multiple ones.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
