Gyula Fora created FLINK-30575:
----------------------------------
Summary: Autoscaler doesn't scale down on 0 load
Key: FLINK-30575
URL: https://issues.apache.org/jira/browse/FLINK-30575
Project: Flink
Issue Type: New Feature
Components: Kubernetes Operator
Reporter: Gyula Fora
The logic for computing true processing rates rely on recordsProcessed /
recordProcessingTime style computations which do not really work well when
everything is 0.
This leads to no scaling actions when the load suddenly drops to 0. We should
handle these special cases and scale the pipeline to some minimal parallelism.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
