You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@flink.apache.org by "Zhijiang (Jira)" <ji...@apache.org> on 2020/03/11 05:40:00 UTC

[jira] [Created] (FLINK-16537) Implement ResultPartition state recovery for unaligned checkpoint

Zhijiang created FLINK-16537:
--------------------------------

             Summary: Implement ResultPartition state recovery for unaligned checkpoint
                 Key: FLINK-16537
                 URL: https://issues.apache.org/jira/browse/FLINK-16537
             Project: Flink
          Issue Type: Sub-task
          Components: Runtime / Checkpointing, Runtime / Network
            Reporter: Zhijiang
             Fix For: 1.11.0


During recovery process for unaligned checkpoint, the partition state should also be recovered besides with existing operator states.

The ResultPartition would request buffer from local pool and then interact with ChannelStateReader to fill in the state data.  The filled buffer would be inserted into respective ResultSubpartition queue  in normal way.

It should guarantee that op can not process any inputs before finishing all the output recovery to avoid mis-order issue.

Refer to more details by [https://docs.google.com/document/d/16_MOQymzxrKvUHXh6QFr2AAXIKt_2vPUf8vzKy4H_tU/edit]



--
This message was sent by Atlassian Jira
(v8.3.4#803005)