mesos-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Benjamin Mahler <benjamin.mah...@gmail.com>
Subject Fwd: [jira] [Created] (MESOS-2353) Improve performance of the master's state.json endpoint for large clusters.
Date Thu, 05 Nov 2015 16:40:22 GMT
The benchmark can be written independently and should exist before the fix
so we can measure the improvement. Vinod sounds like you might be
interested in writing one while waiting for michael?

---------- Forwarded message ----------
From: *Vinod Kone (JIRA)* <jira@apache.org>
Date: Thursday, November 5, 2015
Subject: [jira] [Created] (MESOS-2353) Improve performance of the master's
state.json endpoint for large clusters.
To: benjamin.mahler@gmail.com



    [
https://issues.apache.org/jira/browse/MESOS-2353?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14991934#comment-14991934
]

Vinod Kone commented on MESOS-2353:
-----------------------------------

Sure. If reviews and design doc are out by monday, that should be fine. Can
you ping me on IRC when you are online? Want to get a sense of what's
coming.

> Improve performance of the master's state.json endpoint for large
clusters.
>
---------------------------------------------------------------------------
>
>                 Key: MESOS-2353
>                 URL: https://issues.apache.org/jira/browse/MESOS-2353
>             Project: Mesos
>          Issue Type: Improvement
>          Components: master
>            Reporter: Benjamin Mahler
>              Labels: newbie, scalability, twitter
>
> The master's state.json endpoint consistently takes a long time to
compute the JSON result, for large clusters:
> {noformat}
> $ time curl -s -o /dev/null localhost:5050/master/state.json
> Mon Jan 26 22:38:50 UTC 2015
> real  0m13.174s
> user  0m0.003s
> sys   0m0.022s
> {noformat}
> This can cause the master to get backlogged if there are many state.json
requests in flight.
> Looking at {{perf}} data, it seems most of the time is spent doing memory
allocation / de-allocation. This ticket will try to capture any low hanging
fruit to speed this up. Possibly we can leverage moves if they are not
already being used by the compiler.



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

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message