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

Posted to issues@flink.apache.org by "Ufuk Celebi (JIRA)" <ji...@apache.org> on 2015/04/29 13:56:05 UTC

[jira] [Created] (FLINK-1958) Improve error handling of receiver task failures

Ufuk Celebi created FLINK-1958:
----------------------------------

             Summary: Improve error handling of receiver task failures
                 Key: FLINK-1958
                 URL: https://issues.apache.org/jira/browse/FLINK-1958
             Project: Flink
          Issue Type: Improvement
          Components: Distributed Runtime
    Affects Versions: master
            Reporter: Ufuk Celebi


Currently, receiver task failures silently fail.

We need the following behaviour:
* Sender keeps going. May be back-pressured when no receiver pulls the data any more.
* Sender may be cancelled by JobManager
* Partition stays sane
* Netty channel needs to be closed
* Transfer needs to be canceled by a cancel message (receiver to sender)



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)