Re: [PATCH v2 1/2] blk-mq: fix nr_requests wrong value when modify it from sysfs

[weiping zhang]

On Thu, Sep 21, 2017 at 10:37:48AM -0600, Jens Axboe wrote:
> On 09/21/2017 09:17 AM, weiping zhang wrote:
> > if blk-mq use "none" io scheduler, nr_request get a wrong value when
> > input a number > tag_set->queue_depth. blk_mq_tag_update_depth will get
> > the smaller one min(nr, set->queue_depth), and then q->nr_request get a
> > wrong value.
> > 
> > Reproduce:
> > 
> > echo none > /sys/block/nvme0n1/queue/ioscheduler
> > echo 100 > /sys/block/nvme0n1/queue/nr_requests
> > cat /sys/block/nvme0n1/queue/nr_requests
> > 100
> > 
> > Signed-off-by: weiping zhang 
> > ---
> >  block/blk-mq.c | 8 ++--
> >  1 file changed, 6 insertions(+), 2 deletions(-)
> > 
> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index 98a1860..479c35a 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -2642,8 +2642,12 @@ int blk_mq_update_nr_requests(struct request_queue 
> > *q, unsigned int nr)
> >  * queue depth. This is similar to what the old code would do.
> >  */
> > if (!hctx->sched_tags) {
> > -   ret = blk_mq_tag_update_depth(hctx, >tags,
> > -   min(nr, 
> > set->queue_depth),
> > +   if (nr > set->queue_depth) {
> > +   ret = -EINVAL;
> > +   break;
> > +   }
> > +
> > +   ret = blk_mq_tag_update_depth(hctx, >tags, nr,
> > false);
> 
> What am I missing here? blk_mq_tag_update_depth() should already return
> -EINVAL for the case where we can't grow the tags. Looks like this patch
> should simply remove the min(nr, set->queue_depth) and just pass in 'nr'.
> Should not need the duplicated check for depth.
> 
Ya, you are right, I will send V3 later.

Thanks

Re: [PATCH v2 1/2] blk-mq: fix nr_requests wrong value when modify it from sysfs

[Jens Axboe]

On 09/21/2017 09:17 AM, weiping zhang wrote:
> if blk-mq use "none" io scheduler, nr_request get a wrong value when
> input a number > tag_set->queue_depth. blk_mq_tag_update_depth will get
> the smaller one min(nr, set->queue_depth), and then q->nr_request get a
> wrong value.
> 
> Reproduce:
> 
> echo none > /sys/block/nvme0n1/queue/ioscheduler
> echo 100 > /sys/block/nvme0n1/queue/nr_requests
> cat /sys/block/nvme0n1/queue/nr_requests
> 100
> 
> Signed-off-by: weiping zhang 
> ---
>  block/blk-mq.c | 8 ++--
>  1 file changed, 6 insertions(+), 2 deletions(-)
> 
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 98a1860..479c35a 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -2642,8 +2642,12 @@ int blk_mq_update_nr_requests(struct request_queue *q, 
> unsigned int nr)
>* queue depth. This is similar to what the old code would do.
>*/
>   if (!hctx->sched_tags) {
> - ret = blk_mq_tag_update_depth(hctx, >tags,
> - min(nr, 
> set->queue_depth),
> + if (nr > set->queue_depth) {
> + ret = -EINVAL;
> + break;
> + }
> +
> + ret = blk_mq_tag_update_depth(hctx, >tags, nr,
>   false);

What am I missing here? blk_mq_tag_update_depth() should already return
-EINVAL for the case where we can't grow the tags. Looks like this patch
should simply remove the min(nr, set->queue_depth) and just pass in 'nr'.
Should not need the duplicated check for depth.

-- 
Jens Axboe

[PATCH v2 1/2] blk-mq: fix nr_requests wrong value when modify it from sysfs

[weiping zhang]

if blk-mq use "none" io scheduler, nr_request get a wrong value when
input a number > tag_set->queue_depth. blk_mq_tag_update_depth will get
the smaller one min(nr, set->queue_depth), and then q->nr_request get a
wrong value.

Reproduce:

echo none > /sys/block/nvme0n1/queue/ioscheduler
echo 100 > /sys/block/nvme0n1/queue/nr_requests
cat /sys/block/nvme0n1/queue/nr_requests
100

Signed-off-by: weiping zhang 
---
 block/blk-mq.c | 8 ++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 98a1860..479c35a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2642,8 +2642,12 @@ int blk_mq_update_nr_requests(struct request_queue *q, 
unsigned int nr)
 * queue depth. This is similar to what the old code would do.
 */
if (!hctx->sched_tags) {
-   ret = blk_mq_tag_update_depth(hctx, >tags,
-   min(nr, 
set->queue_depth),
+   if (nr > set->queue_depth) {
+   ret = -EINVAL;
+   break;
+   }
+
+   ret = blk_mq_tag_update_depth(hctx, >tags, nr,
false);
} else {
ret = blk_mq_tag_update_depth(hctx, >sched_tags,
-- 
2.9.4