[
https://issues.apache.org/jira/browse/CASSANDRA-15452?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17943938#comment-17943938
]
Jordan West commented on CASSANDRA-15452:
-----------------------------------------
[~benedict] looking at it closer, I do see how what you initially described you
saw in traces could happen. I don't think its super consequential, we are
allocating and de-allocating when we close the file but I agree with your
statement "we should probably first confirm we have a buffer to deallocate
before we do any cleanup". Its a wasteful allocation of a decent size buffer.
The issue is the call to {{getBlock()}} instead of {{block()}} and then
checking we have an allocated buffer. I believe I have a working patch – doing
some more testing – but we could probably open a new JIRA for this and address
it there as its not urgent. Thoughts?
> Improve disk access patterns during compaction and range reads
> --------------------------------------------------------------
>
> Key: CASSANDRA-15452
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15452
> Project: Apache Cassandra
> Issue Type: Improvement
> Components: Legacy/Local Write-Read Paths, Local/Compaction
> Reporter: Jon Haddad
> Assignee: Jordan West
> Priority: Normal
> Fix For: 5.0.4, 5.1
>
> Attachments: ci_summary_jrwest_jwest-15452-5.0_153.html, everyfs.txt,
> image-2024-11-22-16-17-23-194.png, image-2025-01-07-16-04-23-909.png,
> image-2025-01-07-16-56-12-853.png, image-2025-01-07-16-57-29-134.png,
> iostat-5.0-head.output, iostat-5.0-patched.output, iostat-ebs-15452.png,
> iostat-ebs-head.png, iostat-instance-15452.png, iostat-instance-head.png,
> results.txt, results_details_jrwest_jwest-15452-5.0_153.tar.xz,
> screenshot-1.png, screenshot-2.png, screenshot-3.png, screenshot-4.png,
> screenshot-5.png, screenshot-6.png, sequential.fio, throughput-1.png,
> throughput.png
>
> Time Spent: 9h 40m
> Remaining Estimate: 0h
>
> On read heavy workloads Cassandra performs much better when using a low read
> ahead setting. In my tests I've seen an 5x improvement in throughput and
> more than a 50% reduction in latency. However, I've also observed that it
> can have a negative impact on compaction and streaming throughput. It
> especially negatively impacts cloud environments where small reads incur high
> costs in IOPS due to tiny requests.
> # We should investigate using POSIX_FADV_DONTNEED on files we're compacting
> to see if we can improve performance and reduce page faults.
> # This should be combined with an internal read ahead style buffer that
> Cassandra manages, similar to a BufferedInputStream but with our own
> machinery. This buffer should read fairly large blocks of data off disk at
> at time. EBS, for example, allows 1 IOP to be up to 256KB. A considerable
> amount of time is spent in blocking I/O during compaction and streaming.
> Reducing the frequency we read from disk should speed up all sequential I/O
> operations.
> # We can reduce system calls by buffering writes as well, but I think it
> will have less of an impact than the reads
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
