gyfora opened a new pull request, #22592:
URL: https://github.com/apache/flink/pull/22592
## What is the purpose of the change
Flink does not really do a good job at distributing the tasks uniformly
across the taskmanagers of the cluster.
The reason is that there is no strategy for spreading out the tasks, they
are simply assigned to the next available slots. This PR improves this by
simply sorting the available slots in a way that slots from different TMs are
interleaving as evenly as possible.
This works for both the the Default and Adaptive scheduler. The new
behaviour can be turned on and off by a new config.
## Verifying this change
New unit tests have been added.
## 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, Kubernetes/Yarn, ZooKeeper: yes
- The S3 file system connector: no
## Documentation
- Does this pull request introduce a new feature? yes
- If yes, how is the feature documented? not documented
--
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
