drcrallen commented on issue #6829: Don't force rebalance of the whole cluster all the time URL: https://github.com/apache/incubator-druid/pull/6829#issuecomment-454621197 Reconsidering this. https://github.com/apache/incubator-druid/pull/6829#issuecomment-453638872 is correct in that a log of things can be fixed with a custom balancer strategy. We do indeed have an issue with segment balancing and the reservoir step taking up too much time (even with caching and multiple parallel threads going). But I think that can be addressed in an extension. Closing this for now as it is not clear that needing to change the to and from pool sizes is required.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
