hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Todd Lipcon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-7339) Introduce a buffered checksum for avoiding frequently calls on Checksum.update()
Date Mon, 30 May 2011 06:06:47 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-7339?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13041010#comment-13041010

Todd Lipcon commented on HADOOP-7339:

I understand how this could make a big difference using the builtin CRC32. But, with PureJavaCrc32,
there shouldn't be any particularly large advantage to buffering like this.

Did you see a speedup in terasort performance? Just seeing fewer calls doesn't necessarily
mean it's an improvement.

> Introduce a buffered checksum for avoiding frequently calls on Checksum.update()
> --------------------------------------------------------------------------------
>                 Key: HADOOP-7339
>                 URL: https://issues.apache.org/jira/browse/HADOOP-7339
>             Project: Hadoop Common
>          Issue Type: Improvement
>          Components: util
>            Reporter: Min Zhou
>             Fix For: 0.22.0
>         Attachments: HADOOP-7339-v1.diff, HADOOP-7339-v2.diff
> We found that PureJavaCRC32/CRC32.update() is the TOP 1 of the methods consuming CPU
in a map side, and in reduce side, it cost a lots of CPU too.
> IFileOutputStream would frequently call Checksum.update() during writing a record. It's
very common a MR key/value less than 512 bytes. Checksum.update() would be called every time
writing a key/value. 
> Test case: terasort 100MB. 
> Checksum.update() calls has be reduced from 4030348 to 28069.  This method is not a hotspot

This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

View raw message