You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@flink.apache.org by "Stephan Weinwurm (Jira)" <ji...@apache.org> on 2022/11/21 23:50:00 UTC
[jira] [Created] (FLINK-30120) Flink Statefun Task Failure causes restart of all tasks
Stephan Weinwurm created FLINK-30120:
----------------------------------------
Summary: Flink Statefun Task Failure causes restart of all tasks
Key: FLINK-30120
URL: https://issues.apache.org/jira/browse/FLINK-30120
Project: Flink
Issue Type: Improvement
Components: Stateful Functions
Affects Versions: statefun-3.1.1, statefun-3.2.0, statefun-3.0.0
Reporter: Stephan Weinwurm
Hey all,
We've noticed that a single task failure causes all of the Statefun tasks to be restarted.
For example, a single task fails because of some Statefun Endpoint unavailability or if one of our Kuberentes TaskManager pods go down.
Flink then determines that the `region` failover strategy requires all tasks to be restarted so we see this in the logs:
```
Nov 17 10:20:30 org.apache.flink.runtime.executiongraph.failover.flip1.RestartPipelinedRegionFailoverStrategy [] - Calculating tasks to restart to recover the failed task 31284d56d1e2112b0f20099ee448a6a9_11.
Nov 17 10:20:30 org.apache.flink.runtime.executiongraph.failover.flip1.RestartPipelinedRegionFailoverStrategy [] - 5650 tasks should be restarted to recover the failed task 31284d56d1e2112b0f20099ee448a6a9_11.
```
Our tasks are all fully independent so I would like that only the one failed task to get restarted or moved to a different TaskManager slot.
Is there a way to tell Flink to only restart the failed task? Or is there a specific reason why the region failover strategy decides to restart all tasks?
Thanks in advance!
Stephan
--
This message was sent by Atlassian Jira
(v8.20.10#820010)