[
https://issues.apache.org/jira/browse/MAPREDUCE-5352?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Siddharth Seth updated MAPREDUCE-5352:
--------------------------------------
Attachment: MAPREDUCE-5352.1.txt
Patch with the changes described in the previous comment. Have not added
additional unit tests since a test already exists for equal distribution of
splits across nodes.
For a specific workload - this increased locality from about 75% to a little
over 90%. All generated splits were local to a single node. Looking at why the
scheduling was not - and will open follow up jiras if necessary.
> Optimize node local splits generated by CombineFileInputFormat
> ---------------------------------------------------------------
>
> Key: MAPREDUCE-5352
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-5352
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Affects Versions: 2.0.5-alpha
> Reporter: Siddharth Seth
> Assignee: Siddharth Seth
> Attachments: MAPREDUCE-5352.1.txt
>
>
> CombineFileInputFormat currently walks through all available nodes and
> generates multiple (maxSplitsPerNode) splits on a single node before
> attempting to generate splits on subsequent nodes. This ends up reducing the
> possibility of generating splits for subsequent nodes - since these blocks
> will no longer be available for subsequent nodes. Allowing splits to go 1
> block above the max-split-size makes this worse.
> Allocating a single split per node in one iteration, should help increase the
> distribution of splits across nodes - so the subsequent nodes will have more
> blocks to choose from.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
