Yuan Mei created FLINK-19547:
--------------------------------
Summary: Partial record clean Up after receiver task fails and restart
Key: FLINK-19547
URL:
https://issues.apache.org/jira/browse/FLINK-19547 Project: Flink
Issue Type: Sub-task
Components: Runtime / Network
Affects Versions: 1.12.0
Reporter: Yuan Mei
In the mode of approximate local recovery, the problem of partial record occurs when a record is spanning over multiple buffers. If the first (several) buffers have already been sent over the network and then get lost due to the failure of the receiver task, the remaining data belonging to the same record in transition should be cleaned up.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)