reswqa opened a new pull request, #20796:
URL: https://github.com/apache/flink/pull/20796
## What is the purpose of the change
*Hybrid shuffle relies on the index to read the disk data. Since the spilled
data may be consumed from memory, the readable status is introduced. For the
readable buffer, FileDataManager does not pre-load it. However, when the
downstream fails, the previous readable status will be used incorrectly,
resulting in that some buffer cannot be read correctly.*
## Brief change log
- *Change the logical of compute readable region to support
subpartitionReader register multiple times.*
- *Avoid possible deadlock in SubpartitionView and FileDataManager.*
## Verifying this change
This change added tests.
## 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: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
