[
https://issues.apache.org/jira/browse/CASSANDRA-19596?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18101988#comment-18101988
]
Berenguer Blasi commented on CASSANDRA-19596:
---------------------------------------------
Amended fix versions as I only see it merged 5.0+
> Improve IntervalTree build throughput
> -------------------------------------
>
> Key: CASSANDRA-19596
> URL: https://issues.apache.org/jira/browse/CASSANDRA-19596
> Project: Apache Cassandra
> Issue Type: Improvement
> Components: Local/Compaction, Local/SSTable
> Reporter: Ariel Weisberg
> Assignee: Ariel Weisberg
> Priority: Normal
> Fix For: 5.0.x, 6.0-alpha1, 6.0
>
> Attachments: IntervalTreePerfTest.java,
> ci_summary-cassandra-5.0-4386d87516a85ab54c5df44862a2f7fbcb5089d7.html,
> ci_summary-cassandra-5.0-dd23271944aa72b294054cab270c3e8f22100668.html,
> ci_summary-trunk-1a8b0b8957485a0cb74dd98554aef6ae9f81f0b1.html,
> ci_summary-trunk-b7ce75905807bde673382799f3c3bf247802bba4.html,
> ci_summary.html, trunk_ci_summary.html
>
> Time Spent: 40m
> Remaining Estimate: 0h
>
> With several terabytes of data and 8 compactors it’s possible for the
> compactors to spend a lot of time blocked waiting on IntervalTrees to be
> built.
> There is also a lot of wasted CPU because it’s updated optimistically so most
> of them end up being thrown away.
> This can end up being quite painful because it can block memtable flushing as
> well and then a single slow CFS can block unrelated CFS because the memtable
> post flush executor is single threaded and shared across all CFS.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
