[
https://issues.apache.org/jira/browse/KAFKA-902?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14310963#comment-14310963
]
Jay Kreps commented on KAFKA-902:
---------------------------------
This could be accomplished by just adding +/-5 to the various backoff
parameters specified in the producer and consumer.
However we should still probably interpret 0 as a strict "don't backoff"
instruction.
> Randomize backoff on the clients for metadata requests
> ------------------------------------------------------
>
> Key: KAFKA-902
> URL: https://issues.apache.org/jira/browse/KAFKA-902
> Project: Kafka
> Issue Type: Bug
> Components: replication
> Affects Versions: 0.8.0
> Reporter: Neha Narkhede
> Assignee: Neha Narkhede
> Priority: Critical
> Labels: newbie
>
> If a Kafka broker dies and there are a large number of clients talking to the
> Kafka cluster, each of the clients can end up shooting metadata requests at
> around the same time. It is better to randomize the backoff on the clients so
> the metadata requests are more evenly spread out
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
