cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jonathan Ellis (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-4316) Compaction Throttle too bursty with large rows
Date Thu, 24 Jan 2013 01:34:11 GMT


Jonathan Ellis commented on CASSANDRA-4316:

Not thrilled about pushing this down into RAR.  Feels like we're violating encapsulation too

What if we did this?
# Make compaction truly single-pass (there's a ticket for this somewhere)
# Introduce a SequentialReader to replace RAR
# Subclass SR to CompactionReader and add throttling there

(I suppose we could subclass RAR already for CompactionReader, but since I want to do #1 and
#2 anyway, it would be less work to do it in this order... :)
> Compaction Throttle too bursty with large rows
> ----------------------------------------------
>                 Key: CASSANDRA-4316
>                 URL:
>             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:

View raw message