The blog is now published to
https://blogs.apache.org/kafka/entry/apache-kafka-supports-more-partitions
Thanks,
Jun
On Fri, Nov 2, 2018 at 2:36 PM, Jun Rao wrote:
> Hi, Mayuresh,
>
> Most of the controlled shutdown time is in leader election. The controller
> currently doesn't wait for
Hi, Mayuresh,
Most of the controlled shutdown time is in leader election. The controller
currently doesn't wait for LeaderAndIsrRequest to be sent out before
responding to the controlled shutdown request.
Thanks,
Jun
On Fri, Nov 2, 2018 at 1:58 PM, Mayuresh Gharat
wrote:
> Thanks Jun for
Hi, Harsha,
The recommendation is the upper bound for partitions. One can certainly
have more than 50 brokers in a cluster if there are fewer partitions per
broker. I will clarify this in the blog.
Thanks,
Jun
On Fri, Nov 2, 2018 at 12:07 PM, wrote:
> Thanks Jun for sharing the post.
> Minor
Thanks Jun for sharing this. Looks nice !
Do we intend to shed light on how much time is required, on an average, for
new Leader election. Also would it be good to add "if the controller waits
for the LeaderAndIsrResponses before sending shutDown_OK to the shutting
down broker".
Thanks,
Thanks Jun for sharing the post.
Minor Nit: Date says December 16, 2019.
Did this test measured the replication affects on the overall cluster health
and performance?
It looks like we are suggesting with 200k partitions and 4k per broker max size
of a cluster should be around 50 brokers?
