[
https://issues.apache.org/jira/browse/CASSANDRA-13754?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16188904#comment-16188904
]
Robert Stupp commented on CASSANDRA-13754:
------------------------------------------
I'll note that the fixed issue and what you're describing are probably two
different things.
It might also be that the combination of recycling the btree-builders _and_
many cells in a partition. This is technically different from what's been fixed.
It would help a lot, if someone can come up with steps (ideally some code) to
reproduce the issue as mat screenshots show that something happened but not why.
> BTree.Builder memory leak
> -------------------------
>
> Key: CASSANDRA-13754
> URL: https://issues.apache.org/jira/browse/CASSANDRA-13754
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Environment: Cassandra 3.11.0, Netty 4.0.44.Final, OpenJDK 8u141-b15
> Reporter: Eric Evans
> Assignee: Robert Stupp
> Fix For: 3.11.1
>
> Attachments: cassandra_3.11.1_Recycler_memleak.png,
> cassandra_3.11.1_snapshot_heaputilization.png, Screenshot from 2017-09-11
> 16-54-43.png, Screenshot from 2017-09-13 10-39-58.png
>
>
> After a chronic bout of {{OutOfMemoryError}} in our development environment,
> a heap analysis is showing that more than 10G of our 12G heaps are consumed
> by the {{threadLocals}} members (instances of {{java.lang.ThreadLocalMap}})
> of various {{io.netty.util.concurrent.FastThreadLocalThread}} instances.
> Reverting
> [cecbe17|https://git-wip-us.apache.org/repos/asf?p=cassandra.git;a=commit;h=cecbe17e3eafc052acc13950494f7dddf026aa54]
> fixes the issue.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
