[
https://issues.apache.org/jira/browse/CASSANDRA-8457?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14244239#comment-14244239
]
Ryan McGuire commented on CASSANDRA-8457:
-----------------------------------------
I've just tried to bring up a 25 node EC2 cluster on cstar_perf, and it did so
without hiccup. We have an automatic tool for installing cstar_perf.tool on
EC2, it's still lacking integration with the frontend though (meaning you can
run tests against it, with the frontend, if we attatch the cluster. You just
can't create the cluster from the frontend, yet.)
> nio MessagingService
> --------------------
>
> Key: CASSANDRA-8457
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8457
> Project: Cassandra
> Issue Type: New Feature
> Components: Core
> Reporter: Jonathan Ellis
> Assignee: Ariel Weisberg
> Labels: performance
> Fix For: 3.0
>
>
> Thread-per-peer (actually two each incoming and outbound) is a big
> contributor to context switching, especially for larger clusters. Let's look
> at switching to nio, possibly via Netty.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
