hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Chris Douglas (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-5222) Add offset in client trace
Date Wed, 11 Feb 2009 21:49:59 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-5222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12672797#action_12672797
] 

Chris Douglas commented on HADOOP-5222:
---------------------------------------

The offset should probably be added after the client id, so the DataNode format remains a
superset of the TaskTracker clienttrace. It's probably not useful to add the offset to the
shuffle trace, but it's available if you wanted to be consistent.

Out of curiosity, how are you using the offsets in your performance analysis?

> Add offset in client trace
> --------------------------
>
>                 Key: HADOOP-5222
>                 URL: https://issues.apache.org/jira/browse/HADOOP-5222
>             Project: Hadoop Core
>          Issue Type: Improvement
>          Components: dfs
>    Affects Versions: 0.21.0
>            Reporter: Lei Xu
>            Priority: Minor
>             Fix For: 0.21.0
>
>         Attachments: clienttrace.patch
>
>
> By adding offset in client trace, the client trace information can provide more accurately
information about I/O.
> It is useful for performance analyzing.
> Since there is  no random write now, the offset of writing is always zero.

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


Mime
View raw message