cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Yuki Morishita (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-4316) Compaction Throttle too bursty with large rows
Date Tue, 22 Jan 2013 20:28:14 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-4316?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13559979#comment-13559979
] 

Yuki Morishita commented on CASSANDRA-4316:
-------------------------------------------

If we are compaction 32 SSTables at once, we are currently throttling every 32 rows read.
If we are using LazilyCompactedRow for wide rows, the row is read twice to write out compacted
row (for now). And I don't know if that "N = 1MB / average row size" above fits well for various
row sizes. "1MB" sounds like the same as 1000 in current "% 1000" approach.
So instead pushing down throttling at SSTableScanner level, we can throttle more accurately.
Maybe we can go further and use RateLimiter in RandomAccessReader for more accuracy.
                
> Compaction Throttle too bursty with large rows
> ----------------------------------------------
>
>                 Key: CASSANDRA-4316
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-4316
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>    Affects Versions: 0.8.0
>            Reporter: Wayne Lewis
>            Assignee: Yuki Morishita
>             Fix For: 1.2.1
>
>         Attachments: 4316-1.2.txt, 4316-1.2-v2.txt
>
>
> In org.apache.cassandra.db.compaction.CompactionIterable the check for compaction throttling
occurs once every 1000 rows. In our workload this is much too large as we have many large
rows (16 - 100 MB).
> With a 100 MB row, about 100 GB is read (and possibly written) before the compaction
throttle sleeps. This causes bursts of essentially unthrottled compaction IO followed by a
long sleep which yields inconsistence performance and high error rates during the bursts.
> We applied a workaround to check throttle every row which solved our performance and
error issues:
> line 116 in org.apache.cassandra.db.compaction.CompactionIterable:
>                 if ((row++ % 1000) == 0)
> replaced with
>                 if ((row++ % 1) == 0)
> I think the better solution is to calculate how often throttle should be checked based
on the throttle rate to apply sleeps more consistently. E.g. if 16MB/sec is the limit then
check for sleep after every 16MB is read so sleeps are spaced out about every second.

--
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

Mime
View raw message