hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Owen O'Malley (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-39) Create a job-configurable best effort for job execution
Date Fri, 20 Apr 2007 23:24:15 GMT

     [ https://issues.apache.org/jira/browse/HADOOP-39?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Owen O'Malley updated HADOOP-39:
--------------------------------

    Description: I propose having a job option that when a tip fails 4 times, stops trying
to run that tip, but does not kill the job.  (was: I had a map job with side effects that
meant that any speculative tasks would fail.

Currently, the job tracker kills the job when the speculative task fails 4 times.

It would be better to stop scheduling speculative tasks for that fragment, but let the job
continue as long as one of the the instances of that fragment continue to run.)
        Summary: Create a job-configurable best effort for job execution  (was: Job killed
when backup tasks fail)

> Create a job-configurable best effort for job execution
> -------------------------------------------------------
>
>                 Key: HADOOP-39
>                 URL: https://issues.apache.org/jira/browse/HADOOP-39
>             Project: Hadoop
>          Issue Type: Bug
>          Components: mapred
>            Reporter: Owen O'Malley
>         Assigned To: Owen O'Malley
>
> I propose having a job option that when a tip fails 4 times, stops trying to run that
tip, but does not kill the job.

-- 
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