[
https://issues.apache.org/jira/browse/CASSANDRA-6861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13985278#comment-13985278
]
Benedict commented on CASSANDRA-6861:
-------------------------------------
See CASSANDRA-7045 for one possible explanation. For comparison see performance
of async and hsha thrift, which in my experiments perform, either as poorly, or
half as poorly. Further evidence for this hypothesis is that the gap narrows
for larger messages.
> Optimise our Netty 4 integration
> --------------------------------
>
> Key: CASSANDRA-6861
> URL: https://issues.apache.org/jira/browse/CASSANDRA-6861
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Reporter: Benedict
> Assignee: T Jake Luciani
> Priority: Minor
> Labels: performance
> Fix For: 2.1 beta2
>
>
> Now we've upgraded to Netty 4, we're generating a lot of garbage that could
> be avoided, so we should probably stop that. Should be reasonably easy to
> hook into Netty's pooled buffers, returning them to the pool once a given
> message is completed.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
