[
https://issues.apache.org/jira/browse/CASSANDRA-8457?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15965767#comment-15965767
]
Jason Brown commented on CASSANDRA-8457:
----------------------------------------
bq. you seem to have squashed everything ...
Yes, that's correct, as it makes rebasing a more manageable task with these
longer-lived projects. However, I always make a backup of a branch before
squashing and rebasing, and here's the last one:
[8457_pre-2017Mar16-rebase|https://github.com/jasobrown/cassandra/tree/8457_pre-2017Mar16-rebase].
It has everything the squashed version does except for the commit to fix ssl
hostname verification (sha {{5ccdd50624ef166eb46ea559aca3c4b264d8b124}}).
I'll address your other comments ASAP
> nio MessagingService
> --------------------
>
> Key: CASSANDRA-8457
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8457
> Project: Cassandra
> Issue Type: New Feature
> Reporter: Jonathan Ellis
> Assignee: Jason Brown
> Priority: Minor
> Labels: netty, performance
> Fix For: 4.x
>
>
> 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
(v6.3.15#6346)
