You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by "Xiao Kang (JIRA)" <ji...@apache.org> on 2010/04/01 14:12:27 UTC

[jira] Updated: (HADOOP-6672) BytesWritable.write(buf) use much more CPU in writeInt() then write(buf)

     [ https://issues.apache.org/jira/browse/HADOOP-6672?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Xiao Kang updated HADOOP-6672:
------------------------------

    Attachment: screenshot-1.jpg

A YJP screenshot attached.

comparing as following:

BytesWritable.write(DataOutput)  30%, 308k times
   DataOutputStream.writeInt()       23%, 308k times
       $Buffer.write()                             21%, 1235k times
   DataOutputStream.write()            6%, 308k times
       $Buffer.write()                             5%, 308k times

> BytesWritable.write(buf) use much more CPU in writeInt() then write(buf)
> ------------------------------------------------------------------------
>
>                 Key: HADOOP-6672
>                 URL: https://issues.apache.org/jira/browse/HADOOP-6672
>             Project: Hadoop Common
>          Issue Type: Improvement
>          Components: io
>    Affects Versions: 0.20.2
>            Reporter: Xiao Kang
>         Attachments: screenshot-1.jpg
>
>
> BytesWritable.write() use nearly 4 times of CPU in wirteInt() as write buffer. It may be optimized.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.