StephanEwen opened a new pull request #10278: [FLINK-14735][scheduler] Improve scheduling of all-to-all partitions with ALL input constraint for legacy scheduler URL: https://github.com/apache/flink/pull/10278 ## What is the purpose of the change Avoid explosion in the number of input checks when scheduling a downstream vertex in a all-to-all blocking shuffle. This code is based on the discussion in [FLINK-14735](https://issues.apache.org/jira/browse/FLINK-14735) and is a modified version of @zhuzhurk's original patch. ## Brief change log - In the `ExecutionGraph`/ `Execution`, when scheduling downstream consumers, now collects all scheduling candidates in a set before checking their inputs and scheduling them. This avoid double checking of vertices. ## Verifying this change - This adds a unit test to validate the performance fix ## Does this pull request potentially affect one of the following parts: - Dependencies (does it add or upgrade a dependency): **no** - The public API, i.e., is any changed class annotated with `@Public(Evolving)`: **no** - The serializers: **no** - The runtime per-record code paths (performance sensitive): **no** - Anything that affects deployment or recovery: JobManager (and its components), Checkpointing, Yarn/Mesos, ZooKeeper: **yes** - The S3 file system connector: **no** ## Documentation - Does this pull request introduce a new feature? **no** - If yes, how is the feature documented? **not applicable**
---------------------------------------------------------------- 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
