[jira] [Commented] (TS-4198) Excessive memory allocations from HostDB with huge tables enabled

["ASF GitHub Bot (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/TS-4198?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15144756#comment-15144756 ] 

ASF GitHub Bot commented on TS-4198:
------------------------------------

GitHub user PSUdaemon opened a pull request:

    https://github.com/apache/trafficserver/pull/472

    TS-4198: Restore sync buffer cleanup.

    

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

    $ git pull https://github.com/PSUdaemon/trafficserver cache_dir_hugepage_free

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

    https://github.com/apache/trafficserver/pull/472.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 #472
    
----

----


> Excessive memory allocations from HostDB with huge tables enabled
> -----------------------------------------------------------------
>
>                 Key: TS-4198
>                 URL: https://issues.apache.org/jira/browse/TS-4198
>             Project: Traffic Server
>          Issue Type: Bug
>          Components: Cache
>            Reporter: Leif Hedstrom
>            Assignee: Phil Sorber
>             Fix For: 6.2.0
>
>
> [~psudaemon] and I have been debugging some memory issues for a while now, and with the new debug tags Phil added, we believe we've tracked it down to a missing release of cachedir buffers. This became significant amount of RAM with HostDB allocations (which by default is 32MB, but can be much bigger).
> The suggestion is to restore the previous cleanup, with huge pages logic added.



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