[
https://issues.apache.org/jira/browse/CASSANDRA-2594?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13088027#comment-13088027
]
paul cannon commented on CASSANDRA-2594:
----------------------------------------
+1 in theory. I haven't been able to find hardware on which to test to confirm
myself that the allocation nodes get unbalanced under the default numa policy,
but if Peter has confirmed it and that --interleave=all alleviates the problem,
that's good enough for me.
> run cassandra under numactl --interleave=all
> --------------------------------------------
>
> Key: CASSANDRA-2594
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2594
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Peter Schuller
> Assignee: Peter Schuller
> Priority: Minor
> Fix For: 0.8.5
>
> Attachments: CASSANDRA-2594-trunkk.txt
>
>
> By default, Linux attempts to be smart about memory allocations such that
> data is close to the NUMA node on which it runs. For big database type of
> applications, this is not the best thing to do if the priority is to avoid
> disk I/O. In particular with Cassandra, we're heavily multi-threaded anyway
> and there is no particular reason to believe that one NUMA node is "better"
> than another.
> Consequences of allocating unevenly among NUMA nodes can include excessive
> page cache eviction when the kernel tries to allocate memory - such as when
> restarting the JVM.
> With that briefly stated background, I propse the following patch to make the
> Cassandra script run Cassandra with numactl --interleave=all if numactl seems
> to be available.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
