diff mbox series

[v3] block: fix deadline elevator drain for zoned block devices

Message ID 20180927015513.24020-1-damien.lemoal@wdc.com (mailing list archive)
State New, archived
Headers show
Series [v3] block: fix deadline elevator drain for zoned block devices | expand

Commit Message

Damien Le Moal Sept. 27, 2018, 1:55 a.m. UTC
When the deadline scheduler is used with a zoned block device, writes
to a zone will be dispatched one at a time. This causes the warning
message:

deadline: forced dispatching is broken (nr_sorted=X), please report this

to be displayed when switching to another elevator with the legacy I/O
path while write requests to a zone are being retained in the scheduler
queue.

Prevent this message from being displayed when executing
elv_drain_elevator() for a zoned block device. __blk_drain_queue() will
loop until all writes are dispatched and completed, resulting in the
desired elevator queue drain without extensive modifications to the
deadline code itself to handle forced-dispatch calls.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Fixes: 8dc8146f9c92 ("deadline-iosched: Introduce zone locking support")
Cc: stable@vger.kernel.org
---

Changes from v2:
* Move zoned block device test before 'printed' increment as suggested by Bart
* Added "Fixes" tag and cc stable

Changes from v1:
* Fixed typo in commit message

 block/elevator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Jens Axboe Sept. 27, 2018, 1:57 a.m. UTC | #1
On 9/26/18 7:55 PM, Damien Le Moal wrote:
> When the deadline scheduler is used with a zoned block device, writes
> to a zone will be dispatched one at a time. This causes the warning
> message:
> 
> deadline: forced dispatching is broken (nr_sorted=X), please report this
> 
> to be displayed when switching to another elevator with the legacy I/O
> path while write requests to a zone are being retained in the scheduler
> queue.
> 
> Prevent this message from being displayed when executing
> elv_drain_elevator() for a zoned block device. __blk_drain_queue() will
> loop until all writes are dispatched and completed, resulting in the
> desired elevator queue drain without extensive modifications to the
> deadline code itself to handle forced-dispatch calls.

Dropped the previous one and added this one.
diff mbox series

Patch

diff --git a/block/elevator.c b/block/elevator.c
index 6a06b5d040e5..fae58b2f906f 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -609,7 +609,7 @@  void elv_drain_elevator(struct request_queue *q)
 
 	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
-	if (q->nr_sorted && printed++ < 10) {
+	if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
 		       "(nr_sorted=%u), please report this\n",
 		       q->elevator->type->elevator_name, q->nr_sorted);