reswqa opened a new pull request, #20429:
URL: https://github.com/apache/flink/pull/20429
## What is the purpose of the change
*In hybrid shuffle mode, there are currently two strategies to control
spilling. For the full spilling strategy, the data is guaranteed to be
persistent to the disk after task finished. When a failover occurs, if the
upstream has been finished, the data should be recovered directly from the disk
file without re-compute. For selective spilling strategy, the entire topology
must be restarted.*
## Brief change log
- *Split HYBRID result partition type to HYBRID_FULL and HYBRID_SELECTIVE.*
- *RestartPipelinedRegionFailoverStrategy takes reConsumable into account
when decide partition available.*
- **
## Verifying this change
This change added new test methods in related test class.
## 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: no
- The S3 file system connector: no
## Documentation
- Does this pull request introduce a new feature? no
--
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]
