[
https://issues.apache.org/jira/browse/CASSANDRA-11623?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15256004#comment-15256004
]
Marcus Eriksson commented on CASSANDRA-11623:
---------------------------------------------
I updated the patch and pushed it here:
https://github.com/krummas/cassandra/commits/tpetracca/11623-trunk
- return chunkOffset
- rename the method to getEstimatedOnDiskBytesWritten
- reverted the test change as behavior should be exactly the same as before now
and tests are running here:
http://cassci.datastax.com/view/Dev/view/krummas/job/krummas-tpetracca-11623-trunk-dtest/
http://cassci.datastax.com/view/Dev/view/krummas/job/krummas-tpetracca-11623-trunk-testall/
And unless there is a dramatic compaction performance difference I think we
should only commit this to trunk
[~philipthompson] or [~mshuler] could you test that branch for compaction
performance?
> Compactions w/ Short Rows Spending Time in getOnDiskFilePointer
> ---------------------------------------------------------------
>
> Key: CASSANDRA-11623
> URL: https://issues.apache.org/jira/browse/CASSANDRA-11623
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Tom Petracca
> Priority: Minor
> Attachments: compactiontask_profile.png
>
>
> Been doing some performance tuning and profiling of my cassandra cluster and
> noticed that compaction speeds for my tables that I know to have very short
> rows were going particularly slowly. Profiling shows a ton of time being
> spent in BigTableWriter.getOnDiskFilePointer(), and attaching strace to a
> CompactionTask shows that a majority of time is being spent lseek (called by
> getOnDiskFilePointer), and not read or write.
> Going deeper it looks like we call getOnDiskFilePointer each row (sometimes
> multiple times per row) in order to see if we've reached our expected sstable
> size and should start a new writer. This is pretty unnecessary.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
