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 1000000 > /sys/block/nvme0n1/queue/nr_requests
> > cat /sys/block/nvme0n1/queue/nr_requests
> > 1000000
> >
> > Signed-off-by: weiping zhang <zhangweip...@didichuxing.com>
> > ---
> > 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, &hctx->tags,
> > - min(nr,
> > set->queue_depth),
> > + if (nr > set->queue_depth) {
> > + ret = -EINVAL;
> > + break;
> > + }
> > +
> > + ret = blk_mq_tag_update_depth(hctx, &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
