jiajunwang opened a new issue #660: Controller leader switch may trigger some additional (unexpected) rebalance in the WAGED rebalancer URL: https://github.com/apache/helix/issues/660 1. Since the WAGED rebalancer determines the rebalance scope by comparing in-memory cluster data cache, it is possible that a controller leader switch impacts this scope calculating. Then the scope could be enlarged or shrank. 2. In addition, if the leader switch happened while a rebalance pipeline is proceeding, we might see 2 versions output of the best possible state from the different controller (need to confirm if the pipeline would continue once the leadership switch happens. If that's the case, some partitions might be moved back and forth. To solve this, 1. Considering reset the data change detector on new session handling. 2. We need to confirm that a rebalance pipeline will be stopped once the leadership of the controller has been switched.
---------------------------------------------------------------- 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. 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]
