On 02/02/2017 04:42 PM, Omar Sandoval wrote:
From: Omar Sandoval <redacted>
There's a weird inconsistency that flushes are mostly hidden from the
scheduler, but it needs to be aware of them in ->insert_requests().
Instead of having every scheduler call blk_mq_sched_bypass_insert(),
let's do it in the common framework.
Thanks Omar, looks good to me. After a cycle or two, we can kill
the debug loop in blk_mq_sched_insert_requests().
--
Jens Axboe