[
https://issues.apache.org/jira/browse/CASSANDRA-21134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18063184#comment-18063184
]
Sam Lightfoot commented on CASSANDRA-21134:
-------------------------------------------
Throttled (128 MiB/s) compaction results added. The benefits of Direct IO are
larger than I expected under throttling - buffered compaction still triggers
significant direct reclaim stalls even at constrained throughput. This appears
to be driven by write-back flush storms: the kernel batches dirty pages and
flushes them in bursts that spike device queue depth and block reclaim,
regardless of the steady-state compaction rate. Direct IO eliminates this
entirely by writing steadily to disk, bypassing the page cache.
> Direct IO support for compaction writes
> ---------------------------------------
>
> Key: CASSANDRA-21134
> URL: https://issues.apache.org/jira/browse/CASSANDRA-21134
> Project: Apache Cassandra
> Issue Type: Improvement
> Components: Local/Compaction
> Reporter: Sam Lightfoot
> Assignee: Sam Lightfoot
> Priority: Normal
> Fix For: 5.x
>
> Attachments: image-2026-02-11-17-22-58-361.png,
> image-2026-02-11-17-25-58-329.png
>
>
> Follow-up from the implementation for compaction reads (CASSANDRA-19987)
> Notable points
> * Update the start-up check that impacts DIO writes
> ({_}checkKernelBug1057843{_})
> * RocksDB uses 1 MB flush buffer. This should be configurable and
> performance tested (256KB vs 1MB)
> * Introduce compaction_write_disk_access_mode /
> backgroud_write_disk_access_mode
> * Support for the compressed path would be most beneficial
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
