[ https://issues.apache.org/jira/browse/KAFKA-2406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14658909#comment-14658909 ]
Ashish K Singh commented on KAFKA-2406: --------------------------------------- [~junrao], [~becket_qin] it sounds like we are delaying ISR change propagation to fix this issue. Quick intimation of ISR change is a good thing, I believe. However, what [~becket_qin] ran into is certainly an issue that needs to be fixed. I think the issue will surface only when there are lot of changes happening in system, like during rolling bounce. Such scenarios are usually started by admins. If we just specify a way to turn off or delay ISR notifications only during such operations, we will still react fast to ISR changes and won;t hit this issue during rolling bounce like scenarios. Thoughts? > ISR propagation should be throttled to avoid overwhelming controller. > --------------------------------------------------------------------- > > Key: KAFKA-2406 > URL: https://issues.apache.org/jira/browse/KAFKA-2406 > Project: Kafka > Issue Type: Bug > Reporter: Jiangjie Qin > Assignee: Jiangjie Qin > Priority: Blocker > > This is a follow up patch for KAFKA-1367. > We need to throttle the ISR propagation rate to avoid flooding in controller > to broker traffic. This might significantly increase time of controlled > shutdown or cluster startup. -- This message was sent by Atlassian JIRA (v6.3.4#6332)