[
https://issues.apache.org/jira/browse/KAFKA-168?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15321545#comment-15321545
]
Dominic Chambers commented on KAFKA-168:
----------------------------------------
Jay, I'd really appreciate knowing why you closed this issue. I've read
everything I can find on the web and watched loads of your videos, but still
can't figure out why co-locating your processing next to the data it's going to
process isn't a more widely requested feature. Is there some fundamental reason
why this is a bad idea, is it just not technically possible due to Kafka's
architecture, or is still something you'd still accept a patch for?
> Support locality in consumer partition assignment algorithm
> -----------------------------------------------------------
>
> Key: KAFKA-168
> URL: https://issues.apache.org/jira/browse/KAFKA-168
> Project: Kafka
> Issue Type: Sub-task
> Components: core
> Reporter: Jay Kreps
>
> There are some use-cases where it makes sense to co-locate brokers and
> consumer processes. In this case it would be nice to optimize the assignment
> of partitions to consumers so that the consumer preferentially consumes from
> the broker with which it is co-located.
> If we are going to do KAFKA-167, moving the assignment to the broker, it
> would make sense to do that first so we only have to change the logic in one
> place.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
