[ 
https://issues.apache.org/jira/browse/TS-3417?focusedWorklogId=30437&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-30437
 ]

ASF GitHub Bot logged work on TS-3417:
--------------------------------------

                Author: ASF GitHub Bot
            Created on: 11/Oct/16 21:44
            Start Date: 11/Oct/16 21:44
    Worklog Time Spent: 10m 
      Work Description: GitHub user jrushford opened a pull request:

    https://github.com/apache/trafficserver/pull/1097

    Make the use of madvise() with MADV_DONTDUMP configurable.

    We have seen high cpu loads and high time to serve problems in our 
production platform when using madvise() with the MADV_DONTDUMP option.   This 
appears to be a kernel issue with madvise().  in order to avoid having to 
rebuild ats, this PR uses a patch from TS-3417 to make the use of madvise() 
with the MADV_DONTDUMP flag configurable.

You can merge this pull request into a Git repository by running:

    $ git pull https://github.com/jrushford/trafficserver TS-4957

Alternatively you can review and apply these changes as the patch at:

    https://github.com/apache/trafficserver/pull/1097.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #1097
    
----
commit f1c37818622fc0fc4e05614c7f1f83a10fe8c063
Author: John J. Rushford <[email protected]>
Date:   2016-10-11T21:37:01Z

    Make the use of madvise() with MADV_DONTDUMP configurable.

----


Issue Time Tracking
-------------------

            Worklog Id:     (was: 30437)
            Time Spent: 10m
    Remaining Estimate: 0h

> Use madvise() with MADV_DONTDUMP option to limit core sizes
> -----------------------------------------------------------
>
>                 Key: TS-3417
>                 URL: https://issues.apache.org/jira/browse/TS-3417
>             Project: Traffic Server
>          Issue Type: New Feature
>          Components: Core
>            Reporter: Phil Sorber
>            Assignee: John Rushford
>             Fix For: 5.3.0
>
>          Time Spent: 10m
>  Remaining Estimate: 0h
>
> When ATS crashes it often leaves behind very large core files, in the 
> hundreds of gigabytes. A large percentage of these core files are useless 
> data in the IO buffers. We can limit the pages that the kernel dumps with 
> madvise().
> Note: This will only work on Linux 3.4+.



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

Reply via email to