[
https://issues.apache.org/jira/browse/FLINK-12997?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Chesnay Schepler closed FLINK-12997.
------------------------------------
Resolution: Fixed
master: 6f6cfde0cea12f8d6966c48ba3124c53db15c9bc
> Release partitions for reset vertices
> -------------------------------------
>
> Key: FLINK-12997
> URL: https://issues.apache.org/jira/browse/FLINK-12997
> Project: Flink
> Issue Type: Sub-task
> Components: Runtime / Coordination
> Reporter: Chesnay Schepler
> Assignee: Chesnay Schepler
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.9.0
>
> Time Spent: 20m
> Remaining Estimate: 0h
>
> If a vertex with is reset (e.g., due to a global failover) we also have to
> issue release calls to the TM to release said partition.
> This case is not handled by the partition release strategy as that one deals
> with releases that could be due to job _progress_ (i.e., a partition no
> longer being required because we have downstream partitions that we could
> back on instead in case of failures).
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)