[
https://issues.apache.org/jira/browse/CASSANDRA-8692?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14299114#comment-14299114
]
Ariel Weisberg commented on CASSANDRA-8692:
-------------------------------------------
That's a good point no delay off provides most of the benefits in GCE and EC2.
Whenever I have tested Nagle there is no disadvantage even at low concurrency.
I have even found that latency is lower at low concurrency which is
counter-intuitive. I haven't measured that in C* yet.
I think we still might get into trouble if we run into situations where Nagle
does decide to hold packets.
GCE
Running with TCP no delay off
132254
132862
No delay on, no coalescing
118134
EC2
With no delay off
First set of runs
390264
387958
392322
After replacing 10 instances
366579
365818
378221
No delay on
162987
> Coalesce intra-cluster network messages
> ---------------------------------------
>
> Key: CASSANDRA-8692
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8692
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Reporter: Ariel Weisberg
> Assignee: Ariel Weisberg
> Attachments: batching-benchmark.png
>
>
> While researching CASSANDRA-8457 we found that it is effective and can be
> done without introducing additional latency at low concurrency/throughput.
> The patch from that was used and found to be useful in a real life scenario
> so I propose we implement this in 2.1 in addition to 3.0.
> The change set is a single file and is small enough to be reviewable.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
