[
https://issues.apache.org/jira/browse/KAFKA-5358?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16137764#comment-16137764
]
ASF GitHub Bot commented on KAFKA-5358:
---------------------------------------
GitHub user huxihx opened a pull request:
https://github.com/apache/kafka/pull/3723
KAFKA-5358: Consumer perf tool should count rebalance time.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/huxihx/kafka KAFKA-5358
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/kafka/pull/3723.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #3723
----
commit 934f24e32479453ce437fef27a796c9e2b1b2514
Author: huxihx <huxi...@hotmail.com>
Date: 2017-08-23T02:07:18Z
As per Jason's comments, refined type from to a naive
----
> Consumer perf tool should count rebalance time separately
> ---------------------------------------------------------
>
> Key: KAFKA-5358
> URL: https://issues.apache.org/jira/browse/KAFKA-5358
> Project: Kafka
> Issue Type: Improvement
> Reporter: Jason Gustafson
> Assignee: huxihx
>
> It would be helpful to measure rebalance time separately in the performance
> tool so that throughput between different versions can be compared more
> easily in spite of improvements such as
> https://cwiki.apache.org/confluence/display/KAFKA/KIP-134%3A+Delay+initial+consumer+group+rebalance.
> At the moment, running the perf tool on 0.11.0 or trunk for a short amount
> of time will present a severely skewed picture since the overall time will be
> dominated by the join group delay.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
