David Jeffery df034c93f1 sbitmap: only queue kyber's wait callback if not already active
Under heavy loads where the kyber I/O scheduler hits the token limits for
its scheduling domains, kyber can become stuck.  When active requests
complete, kyber may not be woken up leaving the I/O requests in kyber
stuck.

This stuck state is due to a race condition with kyber and the sbitmap
functions it uses to run a callback when enough requests have completed.
The running of a sbt_wait callback can race with the attempt to insert the
sbt_wait.  Since sbitmap_del_wait_queue removes the sbt_wait from the list
first then sets the sbq field to NULL, kyber can see the item as not on a
list but the call to sbitmap_add_wait_queue will see sbq as non-NULL. This
results in the sbt_wait being inserted onto the wait list but ws_active
doesn't get incremented.  So the sbitmap queue does not know there is a
waiter on a wait list.

Since sbitmap doesn't think there is a waiter, kyber may never be
informed that there are domain tokens available and the I/O never advances.
With the sbt_wait on a wait list, kyber believes it has an active waiter
so cannot insert a new waiter when reaching the domain's full state.

This race can be fixed by only adding the sbt_wait to the queue if the
sbq field is NULL.  If sbq is not NULL, there is already an action active
which will trigger the re-running of kyber.  Let it run and add the
sbt_wait to the wait list if still needing to wait.

Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Jeffery <djeffery@redhat.com>
Reported-by: John Pittman <jpittman@redhat.com>
Tested-by: John Pittman <jpittman@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-12-20 16:51:54 -07:00
..
2019-09-20 09:06:26 -07:00
2019-12-09 18:55:03 +01:00
2018-08-22 10:52:48 -07:00
2018-10-12 09:17:46 +02:00
2018-08-16 12:14:42 -07:00
2018-08-22 10:52:48 -07:00
2019-12-03 13:58:22 -08:00
2017-02-24 17:46:57 -08:00
2019-12-07 11:00:19 -08:00
2019-12-07 11:00:19 -08:00
2019-12-07 11:00:19 -08:00
2019-12-05 11:43:31 -08:00
2018-10-16 13:45:44 +02:00
2019-07-11 15:17:41 -07:00
2019-07-11 15:17:41 -07:00
2018-06-27 18:58:49 +03:00
2018-10-15 16:31:29 -04:00
2019-12-01 12:59:05 -08:00
2017-08-15 09:02:07 -07:00