acherla commented on issue #13692: URL: https://github.com/apache/druid/issues/13692#issuecomment-1465470062
> cachingCost can help if both run rules (loading - dropping) and balancing are slow. If balancing is significantly slow while run rules are not, segment selection for balancing is likely the culprit. Please try using batched segment sampling in the coordinator dynamic config in that case Caching cost was configured on the onset, ultimately lowering percentOfSegmentsToConsiderPerMove yielded the best benefit, potentially at the cost of hot spots on the cluster. Either way we will be upgrading to 25.0.0 by next week as we've seen the performance significantly improve after some of the new optimizations were pushed in. -- 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]
