[
https://issues.apache.org/jira/browse/HADOOP-2425?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12554092
]
Owen O'Malley commented on HADOOP-2425:
---------------------------------------
Chris ran a benchmark that writes 2g of data through before and after the patch
and posted them in the comment before yours. *smile* (Thanks, Chris!) With no
compression, this patch saved 63% of the time.
> TextOutputFormat should special case Text
> -----------------------------------------
>
> Key: HADOOP-2425
> URL: https://issues.apache.org/jira/browse/HADOOP-2425
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Reporter: Owen O'Malley
> Assignee: Owen O'Malley
> Fix For: 0.16.0
>
> Attachments: text-out-format-2.patch, text-out-format.patch
>
>
> TextOutputFormat is spending a noticeable amount of time encoding and then
> decoding the bytes in Text objects before they are sent to the output. We
> should handle this as a special case.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
