On Fri, Nov 30, 2018 at 09:01:18AM -0700, Jens Axboe wrote:
> Even if we have no waiters on any of the sbitmap_queue wait states, we
> still have to loop every entry to check. We do this for every IO, so
> the cost adds up.
>
> Shift a bit of the cost to the slow path, when we actually have waiter
Even if we have no waiters on any of the sbitmap_queue wait states, we
still have to loop every entry to check. We do this for every IO, so
the cost adds up.
Shift a bit of the cost to the slow path, when we actually have waiters.
Wrap prepare_to_wait_exclusive() and finish_wait(), so we can maint
Even if we have no waiters on any of the sbitmap_queue wait states, we
still have to loop every entry to check. We do this for every IO, so
the cost adds up.
Shift a bit of the cost to the slow path, when we actually have waiters.
Wrap prepare_to_wait_exclusive() and finish_wait(), so we can maint
