[jira] Commented: (CASSANDRA-1470) use direct io for compaction

["Jonathan Ellis (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/CASSANDRA-1470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12906316#action_12906316 ] 

Jonathan Ellis commented on CASSANDRA-1470:
-------------------------------------------

The best option looks like using direct io to bypass the os cache during this (and, similarly, for range scans) -- see http://chbits.blogspot.com/2010/06/lucene-and-fadvisemadvise.html for why posix_fadvise won't work.  Looking at the source, posix_madvise doesn't look good either (VM_SEQ_READ and VM_RAND_READ are ignored once set).

> 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
>             Fix For: 0.6.6
>
>
> 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.