Yang-LI-CS commented on PR #787: URL: https://github.com/apache/flink-kubernetes-operator/pull/787#issuecomment-1991128610
> I have some concerns about this change: > > 1. It doesn't work with custom slot sharing configuration which is very common > 2. It provides almost no benefit with large taskmanager sizes / low number of task slots. > 3. It goes against some basic design philosophy in the autoscaler such that we do not scale vertices beyond their target capacity. It ties to @mxm 's question why the logic wouldn't apply to all vertices? > > Taking that one step further why don't we scale all vertices to the same parallelism at that point? That would naturally cause more resource usage and less throughput. By the same logic I don't think we should scale even the largest ones further. @gyfora thanks for the comment! I see your point, indeed it's kind of against the basic design of autoscaler algorithm, I'll close this pr then 👍 , thanks @mxm also for your comments, looking forward to the next flink autoscaling release -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org