kfaraz commented on PR #13354: URL: https://github.com/apache/druid/pull/13354#issuecomment-1322093346
> The idea is that they aren't doing very much, just handling scheduled retries, so we don't need very many. I'm not sure if 4 threads is always going to be enough but I don't have a better idea about what to set it to. I did do some testing with MSQ shuffle (another user of this) and found that it was not limiting to set this to 4, even when sending a lot of data around. I figure that if we ever discover it isn't enough, we could adjust it at that time. Thanks for the clarification. Since this has been working fine with a cluster with ~1k tasks, I guess it'll hold up. -- 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]
