[
https://issues.apache.org/jira/browse/CASSANDRA-16201?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17231443#comment-17231443
]
Michael Semb Wever commented on CASSANDRA-16201:
------------------------------------------------
Out of the ticket scope… why are the microbench classes all in the
{{org.apache.cassandra.test.microbench}} ? They are already separate under
{{src/testmicrobench/}}, and by re-packaging them like this it means accessed
methods: eg {{bs.getMutations(..)}} ; have to be made public instead of
package-protected. It would be nice to keep methods package-protected where
possible.
AFAIK we also don't CI run the microbench classes anywhere, so there's no
guarantee they remain runnable over time. I could add them to the ci-cassandra
pipeline, though ideally a dedicated bare-metal server would be needed to make
[use|https://plugins.jenkins.io/jmh-report/] of the runtime
[reports|https://www.jenkins.io/blog/2019/06/21/performance-testing-jenkins/].
+1 on all branch patches (including [~yifanc] review comments above).
> Reduce amount of allocations during batch statement execution
> -------------------------------------------------------------
>
> Key: CASSANDRA-16201
> URL: https://issues.apache.org/jira/browse/CASSANDRA-16201
> Project: Cassandra
> Issue Type: Bug
> Components: Local/Other
> Reporter: Thomas Steinmaurer
> Assignee: Marcus Eriksson
> Priority: Normal
> Fix For: 3.0.x, 3.11.x, 4.0-beta
>
> Attachments: 16201_jfr_3023_alloc.png, 16201_jfr_3023_obj.png,
> 16201_jfr_3118_alloc.png, 16201_jfr_3118_obj.png, 16201_jfr_40b3_alloc.png,
> 16201_jfr_40b3_obj.png, screenshot-1.png, screenshot-2.png, screenshot-3.png,
> screenshot-4.png
>
>
> In a Cas 2.1 / 3.0 / 3.11 / 4.0b2 comparison test with the same load profile,
> we see 4.0b2 going OOM from time to time. According to a heap dump, we have
> multiple NTR threads in a 3-digit MB range.
> This is likely related to object array pre-allocations at the size of
> {{BatchUpdatesCollector.updatedRows}} per {{BTree}} although there is always
> only 1 {{BTreeRow}} in the {{BTree}}.
> !screenshot-1.png|width=100%!
> So it seems we have many, many 20K elemnts pre-allocated object arrays
> resulting in a shallow heap of 80K each, although there is only one element
> in the array.
> This sort of pre-allocation is causing a lot of memory pressure.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
