You are viewing a plain text version of this content. The canonical link for it is here.

Posted to common-dev@hadoop.apache.org by "Amareshwari Sriramadasu (JIRA)" <ji...@apache.org> on 2008/03/25 07:57:33 UTC

[jira] Updated: (HADOOP-3080) Remove flush calls from JobHistory

     [ https://issues.apache.org/jira/browse/HADOOP-3080?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Amareshwari Sriramadasu updated HADOOP-3080:
--------------------------------------------

    Attachment: patch-3080.txt

> Remove flush calls from JobHistory
> ----------------------------------
>
>                 Key: HADOOP-3080
>                 URL: https://issues.apache.org/jira/browse/HADOOP-3080
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: mapred
>    Affects Versions: 0.17.0
>            Reporter: Devaraj Das
>            Assignee: Amareshwari Sriramadasu
>            Priority: Blocker
>             Fix For: 0.17.0
>
>         Attachments: patch-3080.txt
>
>
> The flush calls from JobHistory should be removed. This has performance impact when lots of events are being logged to the history files since the JT lock (e.g. lostTracker where the tracker had ran a lot of tasks, and we call failedTask in a loop, etc.)

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