You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mesos.apache.org by "Benjamin Mahler (JIRA)" <ji...@apache.org> on 2013/07/07 23:37:48 UTC
[jira] [Commented] (MESOS-451) Always update resources for
re-registered executors.
[ https://issues.apache.org/jira/browse/MESOS-451?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13701674#comment-13701674 ]
Benjamin Mahler commented on MESOS-451:
---------------------------------------
Bumping, we'll need to make sure this one is fixed for 0.13.0.
> Always update resources for re-registered executors.
> ----------------------------------------------------
>
> Key: MESOS-451
> URL: https://issues.apache.org/jira/browse/MESOS-451
> Project: Mesos
> Issue Type: Task
> Reporter: Benjamin Mahler
> Assignee: Vinod Kone
> Fix For: 0.13.0
>
>
> Given the presence of the --cgroups_enable_cfs flag, we will want to ensure that all recovered executors have hard cpu limiting retroactively applied to them after recovery.
> Currently, since we only call Isolator::resourcesChanged() when there are pending status updates, we *sometimes* retroactively enforce hard limiting.
> It would be better to always call Isolator::resourcesChanged() when executors re-register to ensure we keep things consistent.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira