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 "Vinod K V (JIRA)" <ji...@apache.org> on 2009/05/15 12:44:45 UTC
[jira] Resolved: (HADOOP-4733) Decommissioning TaskTrackers
[ https://issues.apache.org/jira/browse/HADOOP-4733?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinod K V resolved HADOOP-4733.
-------------------------------
Resolution: Duplicate
Duplicate of HADOOP-5643
> Decommissioning TaskTrackers
> ----------------------------
>
> Key: HADOOP-4733
> URL: https://issues.apache.org/jira/browse/HADOOP-4733
> Project: Hadoop Core
> Issue Type: New Feature
> Components: mapred
> Reporter: Koji Noguchi
>
> From core-user@hadoop
> >>> Steve Loughran said:
> > At some point in the future, I could imagine it being handy to have the ability to decomission a task tracker,
> > which would tell it to stop accepting new work, and run the rest down. This would be good when tasks take time
> > to run but you still want to be agile in your cluster management.
> I believe our clusters would also have this need once we move out of hod.
> Currently, we flag the node 'offline' by torque and wait for the running jobs/tasks to finish.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.