[
https://issues.apache.org/jira/browse/KAFKA-7149?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16615339#comment-16615339
]
Guozhang Wang commented on KAFKA-7149:
--------------------------------------
The {{Assignment}} object is sent one for each consumer, which includes the
assigned partitions and the userData which is decoded into {{AssignmentInfo}}.
Note that after the consumer -> assignment information is sent to the broker
coordinator, it will send this assignment to each corresponding consumer.
So it is actually a one-to-one mapping from {{Assignment}} to
{{AssignmentInfo}}, not one-to-many mapping.
As a result, each consumer will only get one decoded {{AssignmentInfo}}. Note
that each consumer indeed need to know the global tasksByHost map in order to
support interactive queries (users can ask any instance, where to ask for a
specific key, for example).
Does that make sense?
> Reduce assignment data size to improve kafka streams scalability
> ----------------------------------------------------------------
>
> Key: KAFKA-7149
> URL: https://issues.apache.org/jira/browse/KAFKA-7149
> Project: Kafka
> Issue Type: Improvement
> Components: streams
> Reporter: Ashish Surana
> Assignee: Ashish Surana
> Priority: Major
>
> We observed that when we have high number of partitions, instances or
> stream-threads, assignment-data size grows too fast and we start getting
> below RecordTooLargeException at kafka-broker.
> Workaround of this issue is commented at:
> https://issues.apache.org/jira/browse/KAFKA-6976
> Still it limits the scalability of kafka streams as moving around 100MBs of
> assignment data for each rebalancing affects performance & reliability
> (timeout exceptions starts appearing) as well. Also this limits kafka streams
> scale even with high max.message.bytes setting as data size increases pretty
> quickly with number of partitions, instances or stream-threads.
>
> Solution:
> To address this issue in our cluster, we are sending the compressed
> assignment-data. We saw assignment-data size reduced by 8X-10X. This improved
> the kafka streams scalability drastically for us and we could now run it with
> more than 8,000 partitions.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
