he.org/projects/flink/flink-docs-release-1.10/dev/custom_serializers.html
?
( this is a bit off topic by this point now! )
On Thu, Mar 19, 2020 at 11:25 PM Matthew Rafael Magsombol <
raffy4...@gmail.com> wrote:
> Also as a follow up question with respect to state cleanup,
> I see
m them. It sounds like
rocksdb cleans these up via compaction but what about for states where we
use FSBackendState where we use the heap for in-flight data?
On Thu, Mar 19, 2020 at 7:07 PM Matthew Rafael Magsombol <
raffy4...@gmail.com> wrote:
> I see...
> The way we run our setup is t
I see...
The way we run our setup is that we run these in a kubernetes cluster where
we have one cluster running one job.
The total parallelism of the whole cluster is equal to the number of
taskmanagers where each task manager has 1 core cpu accounting for 1 slot.
If we add a state ttl, do you hav
