[infinispan-issues] [JBoss JIRA] (ISPN-8550) Try to estimate malloc overhead and add to memory based eviction
William Burns (JIRA)
issues at jboss.org
Mon Nov 27 15:42:00 EST 2017
[ https://issues.jboss.org/browse/ISPN-8550?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13494397#comment-13494397 ]
William Burns edited comment on ISPN-8550 at 11/27/17 3:41 PM:
---------------------------------------------------------------
I was using valgrind like the following:
{quote}
valgrind --tool=massif --time-unit=ms --detailed-freq=10000 <cmd>
{quote}
I increased detailed-freq really high to try to remove the excess.
I took the memory usage after it was primed with inserts and then subtracted that from the peak memory usage. Looking at your spreadsheet I don't see excess JVM and others subtracted from the size in your calculation. In my tests it was about 7M of memory used by that, which can throw off your other numbers, or maybe I am not reading your spreadsheet correctly.
Also I am not quite sure about the baseline value of 72M, seems quite high.
was (Author: william.burns):
I was using valgrind like the following:
{quote}
valgrind --tool=massif --time-unit=ms --detailed-freq=10000 <cmd>
{quote}
I increased detailed-freq really high to try to remove the excess.
I took the memory usage after it was primed with inserts and then subtracted that from the peak memory usage. Looking at your spreadsheet I don't see excess JVM and others subtracted from the size in your calculation. In my tests it was about 7M of memory used by that, which can throw off your other numbers, or maybe I am not reading your spreadsheet correctly.
> Try to estimate malloc overhead and add to memory based eviction
> ----------------------------------------------------------------
>
> Key: ISPN-8550
> URL: https://issues.jboss.org/browse/ISPN-8550
> Project: Infinispan
> Issue Type: Sub-task
> Reporter: William Burns
> Assignee: William Burns
> Fix For: 9.2.0.Beta2, 9.1.4.Final
>
> Attachments: allocs.ods
>
>
> We should try to also estimate malloc overhead. We could do something like Dan mentioned at https://github.com/infinispan/infinispan/pull/5590#pullrequestreview-78054779
--
This message was sent by Atlassian JIRA
(v7.5.0#75005)
More information about the infinispan-issues
mailing list