LeonxLJX commented on issue #11663: URL: https://github.com/apache/seatunnel/issues/11663#issuecomment-5502694791
Thanks for the heads-up @JeremyXin! Since you've already taken this and worked out the implementation plan, I'll step back rather than duplicate the effort. One thing I'd flag while you're designing it, in case it's useful: for autoscaling it's worth deciding early whether scaling decisions are made on **slot-level utilization** or **worker-level utilization**, because the two can disagree — a worker can look busy on slots while being idle on CPU/memory (or vice versa) depending on whether tasks are CPU- or IO-bound. Pinning that down up front tends to avoid churn in the policy later. Happy to review the PR when it's up if that's helpful. -- 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]
