+1 have seen scenarios where operators that don't utilize large state
management take a while to load state from recovery.

On Tue, Oct 11, 2016 at 5:05 PM, Sandesh Hegde <[email protected]>
wrote:

> Hi All,
>
> Operators that are not making progress are killed after
> TIMEOUT_WINDOW_COUNT. But this doesn't take the operator recovery into
> account. Operators that are recovering may need more time than what is set
> in TIMEOUT_WINDOW_COUNT.
>
> The new attribute, RECOVERY_WINDOW_TIMEOUT_COUNT, will be used to decide
> the timeout when the operators are recovering.
>
> Thoughts?
>

Reply via email to