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

Posted to issues@flink.apache.org by "shuai.xu (JIRA)" <ji...@apache.org> on 2017/02/21 10:42:44 UTC

[jira] [Created] (FLINK-5866) The implementation of FailoverRegion.

shuai.xu created FLINK-5866:
-------------------------------

             Summary: The implementation of FailoverRegion.
                 Key: FLINK-5866
                 URL: https://issues.apache.org/jira/browse/FLINK-5866
             Project: Flink
          Issue Type: Sub-task
          Components: JobManager
            Reporter: shuai.xu
            Assignee: shuai.xu


In flip1, FailoverRegion will manage the failover of a minimal pipelined conncected executions.
One job graph may has several FailoverRegions and they will be calculated statically after job graph is attached.
FailoverRegion has serval states, CREATED, CANCELING, CANCELED, RUNNING, it will transforms its state according to the state of the ExectionVertexes it contains and drives the failover during state transformation.
A FailoverRegion may have preceding and succeeding FailoverRegions. It will wait for its preceding ones and notice its succeeding ones when finishing.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)