wsry opened a new pull request #13924:
URL: https://github.com/apache/flink/pull/13924
## What is the purpose of the change
This patch introduces SortMergeShuffleIOScheduler which is responsible for
scheduling the sort-merge blocking shuffle data read requests. The scheduler
always reads shuffle data in order of file offset which maximums the sequential
read so the shuffle performance can be improved. We may also introduce this
mechanism to the hash-based blocking shuffle in the future.
## Brief change log
- Introduces SortMergeShuffleIOScheduler which is responsible for
scheduling the sort-merge blocking shuffle data read requests.
## Verifying this change
Verified by both existing and newly added test cases.
## Does this pull request potentially affect one of the following parts:
- Dependencies (does it add or upgrade a dependency): (yes / **no**)
- The public API, i.e., is any changed class annotated with
`@Public(Evolving)`: (yes / **no**)
- The serializers: (yes / **no** / don't know)
- The runtime per-record code paths (performance sensitive): (yes / **no**
/ don't know)
- Anything that affects deployment or recovery: JobManager (and its
components), Checkpointing, Kubernetes/Yarn/Mesos, ZooKeeper: (yes / **no** /
don't know)
- The S3 file system connector: (yes / **no** / don't know)
## Documentation
- Does this pull request introduce a new feature? (yes / **no**)
- If yes, how is the feature documented? (**not applicable** / docs /
JavaDocs / 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.
For queries about this service, please contact Infrastructure at:
[email protected]
