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

Posted to dev@flink.apache.org by "Piotr Nowojski (JIRA)" <ji...@apache.org> on 2018/03/16 12:28:00 UTC

[jira] [Created] (FLINK-8984) Disabling credit based flow control deadlocks Flink on checkpoint

Piotr Nowojski created FLINK-8984:
-------------------------------------

             Summary: Disabling credit based flow control deadlocks Flink on checkpoint
                 Key: FLINK-8984
                 URL: https://issues.apache.org/jira/browse/FLINK-8984
             Project: Flink
          Issue Type: Bug
          Components: Network
    Affects Versions: 1.5.0
            Reporter: Piotr Nowojski
            Assignee: Piotr Nowojski
             Fix For: 1.5.0


This is configuration issue. There are two options: 

taskmanager.network.credit-based-flow-control.enabled

and

taskmanager.exactly-once.blocking.data.enabled

If we disable first one, but remain default value for the second one deadlocks will occur. I think we can safely drop the second config value altogether and always use blocking BarrierBuffer for credit based flow control and spilling BarrierBuffer for non credit based flow control.

cc [~zjwang]



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)