suneet-s commented on PR #14396: URL: https://github.com/apache/druid/pull/14396#issuecomment-1591754667
> But is there going to be any drawback of this change? If the tasks start in a staggered fashion, would that affect processing throughput in any way? None that I can think of. The only thing I can imagine is if tasks are stuck in pending for such a long time, that it takes longer than the configured task handoff for all the tasks to cycle. But in that case, the tasks are still restarted from the earliest to latest, so I suspect everything should be ok. Each kafka task is handling reading form the partitions independently, so this should have no impact on ingestion throughput -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
