[
https://issues.apache.org/jira/browse/HADOOP-4946?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Devaraj Das updated HADOOP-4946:
--------------------------------
Attachment: 4946.patch
Straightforward patch. I haven't tested it yet.
> Make the Reader for sampling TeraSort input multithreaded
> ---------------------------------------------------------
>
> Key: HADOOP-4946
> URL: https://issues.apache.org/jira/browse/HADOOP-4946
> Project: Hadoop Core
> Issue Type: Improvement
> Components: examples
> Affects Versions: 0.19.0
> Reporter: Devaraj Das
> Assignee: Devaraj Das
> Fix For: 0.21.0
>
> Attachments: 4946.patch
>
>
> The TeraSort sampler that reads from multiple splits to come up with the
> partition information can be made multi-threaded, where multiple threads
> would read from multiple splits concurrently. That should lead to better
> performance and also we could attempt at sampling more records to arrive at a
> better partition info.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
