Re: [PATCH 5/8] block: add code to track actual device queue depth

From: Jens Axboe
Date: Wed Nov 02 2016 - 11:02:32 EST

On 11/02/2016 08:59 AM, Christoph Hellwig wrote:
On Tue, Nov 01, 2016 at 03:08:48PM -0600, Jens Axboe wrote:
For blk-mq, ->nr_requests does track queue depth, at least at init
time. But for the older queue paths, it's simply a soft setting.
On top of that, it's generally larger than the hardware setting
on purpose, to allow backup of requests for merging.

Fill a hole in struct request with a 'queue_depth' member, that

That would be struct request_queue..

Good catch, will fix.

+ * blk_set_queue_depth - tell the block layer about the device queue depth
+ * @q: the request queue for the device
+ * @depth: queue depth
+ *
+ */
+void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
+ q->queue_depth = depth;

Do we really need this wrapper?

Not necessarily, just seems like a nicer API than manually setting the
field. Not a big deal to me, though.

+++ b/drivers/scsi/scsi.c
@@ -621,6 +621,9 @@ int scsi_change_queue_depth(struct scsi_device *sdev, int depth)

+ if (sdev->request_queue)
+ blk_set_queue_depth(sdev->request_queue, depth);
return sdev->queue_depth;

Can we kill the scsi_device queue_depth member and just always use
the request_queue one?

Yes. I'd prefer that we do that through the SCSI tree, once this is in

Jens Axboe