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

Posted to issues@mesos.apache.org by "Dominic Hamon (JIRA)" <ji...@apache.org> on 2015/02/17 23:02:11 UTC

[jira] [Commented] (MESOS-2361) Add metrics to status update manager to expose number of outstanding (un-ack'ed) status updates

    [ https://issues.apache.org/jira/browse/MESOS-2361?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14324975#comment-14324975 ] 

Dominic Hamon commented on MESOS-2361:
--------------------------------------

the queue length is easily exposed as it is on Master and the Scheduler driver already.

see src/master/metrics.hpp:157 - 159.

> Add metrics to status update manager to expose number of outstanding (un-ack'ed) status updates
> -----------------------------------------------------------------------------------------------
>
>                 Key: MESOS-2361
>                 URL: https://issues.apache.org/jira/browse/MESOS-2361
>             Project: Mesos
>          Issue Type: Task
>            Reporter: Niklas Quarfot Nielsen
>
> We have experienced custom executors with high volume of status updates cause congestion on the slave due to framework unavailability (either from being disconnected or not processing status updates fast enough). As a first step, it would be helpful to expose the status update stream/queue depths.



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