[ 
https://issues.apache.org/jira/browse/CASSANDRA-1470?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

T Jake Luciani updated CASSANDRA-1470:
--------------------------------------

    Attachment: CASSANDRA-1470-v14-0.7.patch

v14 does the following:

  * removes directIO from BRAF
  * adds fadvise hooks to BRAF
  * caps active pages in BRAF to 128mb (reads+writes)
      
I have the following results

{code}
op    | current | fadvise
write | 126 | 137 
read  | 112 | 187
read  | 19  | 23
write | 139 | 134
read  | 281 | 59
{code}

You can see the initial read is slower in the new method because the page cache 
isn't available after the first write
as it is in the current version, but it handles re-reading after a major 
compaction plus writes much much better.

We could allow the 128mb page cache size to be configured for folks with write 
heavy workloads.

I'm happy with the performance now, I think active pages for reads and writes 
does the trick.



> use direct io for compaction
> ----------------------------
>
>                 Key: CASSANDRA-1470
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-1470
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Jonathan Ellis
>            Assignee: Pavel Yaskevich
>             Fix For: 0.7.1
>
>         Attachments: 1470-v2.txt, 1470.txt, CASSANDRA-1470-for-0.6.patch, 
> CASSANDRA-1470-v10-for-0.7.patch, CASSANDRA-1470-v11-for-0.7.patch, 
> CASSANDRA-1470-v12-0.7.patch, CASSANDRA-1470-v13-0.7.patch, 
> CASSANDRA-1470-v14-0.7.patch, CASSANDRA-1470-v2.patch, 
> CASSANDRA-1470-v3-0.7-with-LastErrorException-support.patch, 
> CASSANDRA-1470-v4-for-0.7.patch, CASSANDRA-1470-v5-for-0.7.patch, 
> CASSANDRA-1470-v6-for-0.7.patch, CASSANDRA-1470-v7-for-0.7.patch, 
> CASSANDRA-1470-v8-for-0.7.patch, CASSANDRA-1470-v9-for-0.7.patch, 
> CASSANDRA-1470.patch, 
> use.DirectIORandomAccessFile.for.commitlog.against.1022235.patch
>
>
> When compaction scans through a group of sstables, it forces the data in the 
> os buffer cache being used for hot reads, which can have a dramatic negative 
> effect on performance.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

Reply via email to