[
https://issues.apache.org/jira/browse/FLINK-34525?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
junzhong qin updated FLINK-34525:
---------------------------------
Description: In our scenario, with redundant task managers enabled, we
observed that it will take a considerable amount of time to restart the job if
a taskmanager will killed. (was: In our case, when we enabled redundant task
managers, we still found it would take a considerable amount of time to restart
the job when the operator have shuffling data or not.)
> When redundant task managers are enabled, it will still take a considerable
> amount of time to restart a job if a task manager is killed.
> ----------------------------------------------------------------------------------------------------------------------------------------
>
> Key: FLINK-34525
> URL: https://issues.apache.org/jira/browse/FLINK-34525
> Project: Flink
> Issue Type: Improvement
> Reporter: junzhong qin
> Priority: Not a Priority
>
> In our scenario, with redundant task managers enabled, we observed that it
> will take a considerable amount of time to restart the job if a taskmanager
> will killed.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
