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 "Matei Zaharia (JIRA)" <ji...@apache.org> on 2009/06/12 01:25:07 UTC
[jira] Created: (HADOOP-6015) Allow a pool to hold onto its
reservation for a while even if it contains no jobs
Allow a pool to hold onto its reservation for a while even if it contains no jobs
---------------------------------------------------------------------------------
Key: HADOOP-6015
URL: https://issues.apache.org/jira/browse/HADOOP-6015
Project: Hadoop Core
Issue Type: New Feature
Components: contrib/fair-share
Reporter: Matei Zaharia
Assignee: Matei Zaharia
Priority: Minor
To better handle the case where a pool is submitting a sequence of jobs one at a time, it could be useful to let a pool hold onto its min share of slots for some timeout after its last job finishes. If no new job is submitted during this timeout, the slots can go back to being shared by other pools.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-6015) Allow a pool to hold onto its
reservation for a while even if it contains no jobs
Posted by "Matei Zaharia (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-6015?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Matei Zaharia updated HADOOP-6015:
----------------------------------
Assignee: (was: Matei Zaharia)
> Allow a pool to hold onto its reservation for a while even if it contains no jobs
> ---------------------------------------------------------------------------------
>
> Key: HADOOP-6015
> URL: https://issues.apache.org/jira/browse/HADOOP-6015
> Project: Hadoop Core
> Issue Type: New Feature
> Components: contrib/fair-share
> Reporter: Matei Zaharia
> Priority: Minor
>
> To better handle the case where a pool is submitting a sequence of jobs one at a time, it could be useful to let a pool hold onto its min share of slots for some timeout after its last job finishes. If no new job is submitted during this timeout, the slots can go back to being shared by other pools.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.