[
https://issues.apache.org/jira/browse/KAFKA-1183?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13847582#comment-13847582
]
Dragos Dena commented on KAFKA-1183:
------------------------------------
On further inspection, I noticed that the line was added and then removed in
KAFKA-1017 to prevent {{num_producers x num_partitions}} sockets. Thus, for our
use-case which involves a comparable number of producers and partitions coupled
with the need of partitions being as balanced as possible over a 2m-10m window,
the proposed solution would be lowering {{topic.metadata.refresh.interval.ms}}?
> DefaultEventHandler causes unbalanced distribution of messages across
> partitions
> --------------------------------------------------------------------------------
>
> Key: KAFKA-1183
> URL: https://issues.apache.org/jira/browse/KAFKA-1183
> Project: Kafka
> Issue Type: Bug
> Components: producer
> Affects Versions: 0.8.0
> Reporter: Dragos Dena
> Assignee: Jun Rao
> Fix For: 0.8.1, 0.9.0
>
> Attachments: KAFKA-1183-trunk.patch
>
>
> KAFKA-959 introduced an optimisation in {{DefaultEventHandler}} that was
> supposed to have the effect of sending all messages from the same batch to a
> single partition if no key is specified.
> The problem is that the {{sendPartitionPerTopicCache}} cache, which holds the
> current selected partition for each topic, isn't actually invalided at the
> start or end of each batch.
> The observed result is that, after the first request chooses a random
> partition, all subsequent messages from that producer land in the same
> partition. If you have a large number of producers, then it should be fine,
> but if your producer count is comparable to the partition count, then it will
> get unbalanced.
--
This message was sent by Atlassian JIRA
(v6.1.4#6159)
