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

Posted to issues@aurora.apache.org by "Bill Farner (JIRA)" <ji...@apache.org> on 2014/09/02 18:45:20 UTC

[jira] [Commented] (AURORA-608) GcExecutorLauncher should throttle initial activity spike

    [ https://issues.apache.org/jira/browse/AURORA-608?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14118334#comment-14118334 ] 

Bill Farner commented on AURORA-608:
------------------------------------

To tease apart the problems here - are we trying to avoid lost tasks, or avoid overwhelming the master?  If it's the former, it's not clear to me how the initial launch delay would help.

> GcExecutorLauncher should throttle initial activity spike
> ---------------------------------------------------------
>
>                 Key: AURORA-608
>                 URL: https://issues.apache.org/jira/browse/AURORA-608
>             Project: Aurora
>          Issue Type: Task
>          Components: Scheduler
>            Reporter: Maxim Khutornenko
>            Assignee: Maxim Khutornenko
>
> The current implementation of the GcExecutorLauncher randomizes the GC activity by spreading different host GC execution over the hour. It does not, however, protect from the startup spike of accepted GC offers before the host cache is populated. This proved to be a perf problem for Mesos master under certain conditions.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)