[
https://issues.apache.org/jira/browse/HADOOP-1965?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12540179
]
Devaraj Das commented on HADOOP-1965:
-------------------------------------
There is a tradeoff between the benefits between, sort & collect happening in
separate threads, and, the number of seeks we do on the final set of spills.
Although the benchmarks demonstrate that we do better with threading, I thought
it is good to discuss the issue before we conclude on the benefits of this
optimization.
> Handle map output buffers better
> --------------------------------
>
> Key: HADOOP-1965
> URL: https://issues.apache.org/jira/browse/HADOOP-1965
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Affects Versions: 0.16.0
> Reporter: Devaraj Das
> Assignee: Amar Kamat
> Fix For: 0.16.0
>
> Attachments: 1965_single_proc_150mb_gziped.jpeg,
> 1965_single_proc_150mb_gziped.pdf, 1965_single_proc_150mb_gziped_breakup.png,
> HADOOP-1965-1.patch
>
>
> Today, the map task stops calling the map method while sort/spill is using
> the (single instance of) map output buffer. One improvement that can be done
> to improve performance of the map task is to have another buffer for writing
> the map outputs to, while sort/spill is using the first buffer.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
