[
https://issues.apache.org/jira/browse/ACCUMULO-847?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13498543#comment-13498543
]
Josh Elser commented on ACCUMULO-847:
-------------------------------------
I reran Eric's test on my box at home (8core, 16G of ram, 3 spinning disks for
data dirs) using the same Accumulo heap and native map sizes.
Relevant software versions:
* Sun JDK 1.6.0_37
* glibc-2.15-r3 (if it's important, I can resolve what Gentoo patched in the r3
version above 2.15 that the community tagged)
* Kernel 3.6.6
||Arenas||Thresh=0||Res Mem (GB)||
|0|0|2|
|0|1|1.9|
|1|0|1.3|
|1|1|1.3|
|4|0|1.6|
The big take-away I see from this is:
# Altering the number of arenas has the expected effect on resident memory
# On my system, I did *not* see resident memory rise out of reasonable bounds.
> out of memory error creating native thread
> ------------------------------------------
>
> Key: ACCUMULO-847
> URL: https://issues.apache.org/jira/browse/ACCUMULO-847
> Project: Accumulo
> Issue Type: Bug
> Components: tserver
> Environment: RHEL6
> Reporter: Eric Newton
> Assignee: Keith Turner
> Fix For: 1.5.0
>
>
> Long running tablet servers had many gigabytes of memory allocated above what
> was expected (native + jvm). Inspection of the heap did not show an unusual
> number of native objects allocated. Servers would eventually fail to create
> new threads.
> See HADOOP-7154 for the details.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
