[
https://issues.apache.org/jira/browse/CASSANDRA-9237?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14693631#comment-14693631
]
Benedict commented on CASSANDRA-9237:
-------------------------------------
I don't mind.
I have a slight preference for introducing an extra queue for priority
messages, as you suggested, and limiting our TCP send buffer size to 1/10s of
whatever our stream throttling is for the end point.
However for most users and the current architecture, the burden of the extra
threads and buffers is probably not significant, and Jonathan seems to have a
strong preference for that approach.
It's worth noting that a basic NIO connection facility without a major
rearchitecture of MS should also be pretty simple to add.
> Gossip messages subject to head of line blocking by other intra-cluster
> traffic
> -------------------------------------------------------------------------------
>
> Key: CASSANDRA-9237
> URL: https://issues.apache.org/jira/browse/CASSANDRA-9237
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Ariel Weisberg
> Assignee: Ariel Weisberg
> Fix For: 3.0.0 rc1
>
>
> Reported as an issue over less than perfect networks like VPNs between data
> centers.
> Gossip goes over the small message socket where small is 64k which isn't
> particularly small. This is done for performance to keep most traffic on one
> hot socket.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
