Robert, thank you for your reply!
I tried to remove "cluster.evenly-spread-out-slots", and then tested two
scenarios: 1) restart the leader job manager; 2) restart a single task manager.
These tests are done in a testing environment where I have six task managers
and only four tasks to schedul
Hi,
from my understanding of the code [1], the task scheduling first considers
the state location, and then uses the evenly spread out scheduling strategy
as a fall back. So in my understanding of the code, the local recovery
should have preference over the evenly spread out strategy.
If you can e
We also have this configuration set in case it makes any difference when
allocation tasks: cluster.evenly-spread-out-slots.
On 2021/09/08 18:09:52, Xiang Zhang wrote:
> Hello,
>
> We have an app running on Flink 1.10.2 deployed in standalone mode. We
> enabled task-local recovery by setting bo
Hello,
We have an app running on Flink 1.10.2 deployed in standalone mode. We
enabled task-local recovery by setting both *state.backend.local-recovery *and
*state.backend.rocksdb.localdir*. The app has over 100 task managers and 2
job managers (active and passive).
This is what we have observed.
