[
https://issues.apache.org/jira/browse/CASSANDRA-5661?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Pavel Yaskevich updated CASSANDRA-5661:
---------------------------------------
Attachment: CASSANDRA-5661-global-multiway-cache.patch
attaching patch with supports the latest version of multiway pool (and latest
trunk) and adds (C)RAR deallocation on object removal. Sorry I didn't run the
test sooner, I was quiet busy with other things... So I see that with this
version 95-99.9 have degraded comparing to previous by ~3 ms but they don't
shake as they used too - it's around ~5 ms now (I'm testing with
expireAfterAccess).
> Discard pooled readers for cold data
> ------------------------------------
>
> Key: CASSANDRA-5661
> URL: https://issues.apache.org/jira/browse/CASSANDRA-5661
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Affects Versions: 1.2.1
> Reporter: Jonathan Ellis
> Assignee: Pavel Yaskevich
> Fix For: 2.0.1
>
> Attachments: CASSANDRA-5661-global-multiway-cache.patch,
> CASSANDRA-5661.patch, DominatorTree.png, Histogram.png
>
>
> Reader pooling was introduced in CASSANDRA-4942 but pooled
> RandomAccessReaders are never cleaned up until the SSTableReader is closed.
> So memory use is "the worst case simultaneous RAR we had open for this file,
> forever."
> We should introduce a global limit on how much memory to use for RAR, and
> evict old ones.
--
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
