You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "ramkrishna.s.vasudevan (JIRA)" <ji...@apache.org> on 2016/09/01 11:00:30 UTC
[jira] [Updated] (FLINK-3322) MemoryManager creates too much GC
pressure with iterative jobs
[ https://issues.apache.org/jira/browse/FLINK-3322?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
ramkrishna.s.vasudevan updated FLINK-3322:
------------------------------------------
Attachment: FLINK-3322.docx
A simple doc explaining how we can approach this JIRA. I am not very sure if i have covered all the cases but seeing one of Stephan's older comment I could see the idea is pretty much similar. I had gone through the code first to know how things are working.
Feedback/comments are welcome. Also am not sure the future plans of memory manager so it would be great if we could align it with that.
> MemoryManager creates too much GC pressure with iterative jobs
> --------------------------------------------------------------
>
> Key: FLINK-3322
> URL: https://issues.apache.org/jira/browse/FLINK-3322
> Project: Flink
> Issue Type: Bug
> Components: Local Runtime
> Affects Versions: 1.0.0
> Reporter: Gabor Gevay
> Priority: Critical
> Fix For: 1.0.0
>
> Attachments: FLINK-3322.docx
>
>
> When taskmanager.memory.preallocate is false (the default), released memory segments are not added to a pool, but the GC is expected to take care of them. This puts too much pressure on the GC with iterative jobs, where the operators reallocate all memory at every superstep.
> See the following discussion on the mailing list:
> http://apache-flink-mailing-list-archive.1008284.n3.nabble.com/Memory-manager-behavior-in-iterative-jobs-tt10066.html
> Reproducing the issue:
> https://github.com/ggevay/flink/tree/MemoryManager-crazy-gc
> The class to start is malom.Solver. If you increase the memory given to the JVM from 1 to 50 GB, performance gradually degrades by more than 10 times. (It will generate some lookuptables to /tmp on first run for a few minutes.) (I think the slowdown might also depend somewhat on taskmanager.memory.fraction, because more unused non-managed memory results in rarer GCs.)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)