Re: [RESEND RFC PATCH 2/8] block: Allow sending a batch of requests from the scheduler to hardware

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Mon, Mar 23, 2020 at 04:22:38PM +0800, Baolin Wang wrote:
> On Mon, Mar 23, 2020 at 3:27 PM Ming Lei <ming.lei@xxxxxxxxxx> wrote:
> >
> > On Mon, Mar 23, 2020 at 01:36:34PM +0800, Baolin Wang wrote:
> > > On Mon, Mar 23, 2020 at 11:44 AM Ming Lei <ming.lei@xxxxxxxxxx> wrote:
> > > >
> > > > On Fri, Mar 20, 2020 at 06:27:41PM +0800, Baolin Wang wrote:
> > > > > Hi Ming,
> > > > >
> > > > > On Wed, Mar 18, 2020 at 6:26 PM Baolin Wang <baolin.wang7@xxxxxxxxx> wrote:
> > > > > >
> > > > > > Hi Ming,
> > > > > >
> > > > > > On Wed, Mar 18, 2020 at 6:01 PM Ming Lei <ming.lei@xxxxxxxxxx> wrote:
> > > > > > >
> > > > > > > On Mon, Mar 16, 2020 at 06:01:19PM +0800, Baolin Wang wrote:
> > > > > > > > As we know, some SD/MMC host controllers can support packed request,
> > > > > > > > that means we can package several requests to host controller at one
> > > > > > > > time to improve performence. So the hardware driver expects the blk-mq
> > > > > > > > can dispatch a batch of requests at one time, and driver can use bd.last
> > > > > > > > to indicate if it is the last request in the batch to help to combine
> > > > > > > > requests as much as possible.
> > > > > > > >
> > > > > > > > Thus we should add batch requests setting from the block driver to tell
> > > > > > > > the scheduler how many requests can be dispatched in a batch, as well
> > > > > > > > as changing the scheduler to dispatch more than one request if setting
> > > > > > > > the maximum batch requests number.
> > > > > > > >
> > > > > > >
> > > > > > > I feel this batch dispatch style is more complicated, and some other
> > > > > > > drivers(virtio blk/scsi) still may get benefit if we can pass real 'last' flag in
> > > > > > > .queue_rq().
> > > > > > >
> > > > > > > So what about the following way by extending .commit_rqs() to this usage?
> > > > > > > And you can do whatever batch processing in .commit_rqs() which will be
> > > > > > > guaranteed to be called if BLK_MQ_F_FORCE_COMMIT_RQS is set by driver.
> > > > > >
> > > > > > I'm very appreciated for your good suggestion, which is much simpler than mine.
> > > > > > It seems to solve my problem, and I will try it on my platform to see
> > > > > > if it can work and give you the feadback. Thanks again.
> > > > >
> > > > > I tried your approach on my platform, but met some problems, see below.
> > > > >
> > > > > >
> > > > > > > diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
> > > > > > > index 856356b1619e..cd2bbe56f83f 100644
> > > > > > > --- a/block/blk-mq-sched.c
> > > > > > > +++ b/block/blk-mq-sched.c
> > > > > > > @@ -85,11 +85,12 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
> > > > > > >   * its queue by itself in its completion handler, so we don't need to
> > > > > > >   * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
> > > > > > >   */
> > > > > > > -static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
> > > > > > > +static bool blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
> > > > > > >  {
> > > > > > >         struct request_queue *q = hctx->queue;
> > > > > > >         struct elevator_queue *e = q->elevator;
> > > > > > >         LIST_HEAD(rq_list);
> > > > > > > +       bool ret = false;
> > > > > > >
> > > > > > >         do {
> > > > > > >                 struct request *rq;
> > > > > > > @@ -112,7 +113,10 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
> > > > > > >                  * in blk_mq_dispatch_rq_list().
> > > > > > >                  */
> > > > > > >                 list_add(&rq->queuelist, &rq_list);
> > > > > > > -       } while (blk_mq_dispatch_rq_list(q, &rq_list, true));
> > > > > > > +               ret = blk_mq_dispatch_rq_list(q, &rq_list, true);
> > > > > > > +       } while (ret);
> > > > > > > +
> > > > > > > +       return ret;
> > > > > > >  }
> > > > > > >
> > > > > > >  static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
> > > > > > > @@ -131,11 +135,12 @@ static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
> > > > > > >   * its queue by itself in its completion handler, so we don't need to
> > > > > > >   * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
> > > > > > >   */
> > > > > > > -static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
> > > > > > > +static bool blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
> > > > > > >  {
> > > > > > >         struct request_queue *q = hctx->queue;
> > > > > > >         LIST_HEAD(rq_list);
> > > > > > >         struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);
> > > > > > > +       bool ret = false;
> > > > > > >
> > > > > > >         do {
> > > > > > >                 struct request *rq;
> > > > > > > @@ -161,10 +166,12 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
> > > > > > >
> > > > > > >                 /* round robin for fair dispatch */
> > > > > > >                 ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);
> > > > > > > -
> > > > > > > -       } while (blk_mq_dispatch_rq_list(q, &rq_list, true));
> > > > > > > +               ret = blk_mq_dispatch_rq_list(q, &rq_list, true);
> > > > > > > +       } while (ret);
> > > > > > >
> > > > > > >         WRITE_ONCE(hctx->dispatch_from, ctx);
> > > > > > > +
> > > > > > > +       return ret;
> > > > > > >  }
> > > > > > >
> > > > > > >  void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
> > > > > > > @@ -173,6 +180,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
> > > > > > >         struct elevator_queue *e = q->elevator;
> > > > > > >         const bool has_sched_dispatch = e && e->type->ops.dispatch_request;
> > > > > > >         LIST_HEAD(rq_list);
> > > > > > > +       bool dispatch_ret;
> > > > > > >
> > > > > > >         /* RCU or SRCU read lock is needed before checking quiesced flag */
> > > > > > >         if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
> > > > > > > @@ -206,20 +214,26 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
> > > > > > >          */
> > > > > > >         if (!list_empty(&rq_list)) {
> > > > > > >                 blk_mq_sched_mark_restart_hctx(hctx);
> > > > > > > -               if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
> > > > > > > +               dispatch_ret = blk_mq_dispatch_rq_list(q, &rq_list, false);
> > > > > > > +               if (dispatch_ret) {
> > > > > > >                         if (has_sched_dispatch)
> > > > > > > -                               blk_mq_do_dispatch_sched(hctx);
> > > > > > > +                               dispatch_ret = blk_mq_do_dispatch_sched(hctx);
> > > > >
> > > > > If we dispatched a request successfully by blk_mq_dispatch_rq_list(),
> > > > > and got dispatch_ret = true now. Then we will try to dispatch more
> > > > > reuqests from scheduler by blk_mq_do_dispatch_sched(), but if now no
> > > > > more requests in scheduler, then we will got dispatch_ret = false. In
> > > >
> > > > 'dispatch_ret' always holds result of the last blk_mq_do_dispatch_sched().
> > > > When any one request has been dispatched successfully, 'dispatch_ret'
> > > > is true. New request is always added to list before calling
> > > > blk_mq_do_dispatch_sched(), so once blk_mq_do_dispatch_sched() returns
> > > > false, it means that .commit_rqs() has been called.
> > >
> > > Not really, if no requests int the IO cheduler, we will break the loop
> > > in blk_mq_do_dispatch_sched() and return false without calling
> > > .commit_rqs().
> >
> > If there isn't any request to dispatch, false is returned. Otherwise,
> > always return the return value of last 'blk_mq_dispatch_rq_list'.
> >
> > >
> > > So in this case, blk_mq_do_dispatch_sched() will return 'false', which
> > > overlapped the return value of 'true' from blk_mq_dispatch_rq_list(),
> > > and did not call .commit_rqs(). Then the IO processing will be stuck.
> >
> > See below.
> >
> > >
> > > static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
> > > {
> > >         struct request_queue *q = hctx->queue;
> > >         struct elevator_queue *e = q->elevator;
> > >         LIST_HEAD(rq_list);
> > >         bool ret = false;
> >
> > The above initialization is just done once.
> >
> > >
> > >        do {
> > >               struct request *rq;
> > >
> > >               if (e->type->ops.has_work && !e->type->ops.has_work(hctx))
> > >                      break;
> > >
> > >               .......
> >                             ret = blk_mq_dispatch_rq_list(q, list, ...);
> >
> > list includes one request, so blk_mq_dispatch_rq_list() won't return
> > false in case of no request in list.
> >
> > >        } while (ret);
> > >
> > >        return ret;
> >
> > 'ret' is always updated by return value of last blk_mq_dispatch_rq_list()
> > if at least one request is dispatched. So if it becomes false, the loop
> > breaks, that means .commit_rqs() has been called cause 'list' does
> > include one request for blk_mq_dispatch_rq_list(). Otherwise, true is
> > still returned.
> 
> Sorry for my confusing description, let me try again to describe the problem.
> When I try to mount the block device, I got the IO stuck with your
> patch, and I did some debugging. I found we missed calling
> commit_rqs() for one case:
> 
> void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
> @@ -173,6 +180,7 @@ void blk_mq_sched_dispatch_requests(struct
> blk_mq_hw_ctx *hctx)
>         struct elevator_queue *e = q->elevator;
>         const bool has_sched_dispatch = e && e->type->ops.dispatch_request;
>         LIST_HEAD(rq_list);
> +       bool dispatch_ret;
> 
>         /* RCU or SRCU read lock is needed before checking quiesced flag */
>         if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
> @@ -206,20 +214,26 @@ void blk_mq_sched_dispatch_requests(struct
> blk_mq_hw_ctx *hctx)
>          */
>         if (!list_empty(&rq_list)) {
>                 blk_mq_sched_mark_restart_hctx(hctx);
> -               if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
> +               dispatch_ret = blk_mq_dispatch_rq_list(q, &rq_list, false);
> 
> Suppose we dispatch one request to block driver, and return 'true' here.
> 
> +               if (dispatch_ret) {
>                         if (has_sched_dispatch)
> -                               blk_mq_do_dispatch_sched(hctx);
> +                               dispatch_ret = blk_mq_do_dispatch_sched(hctx);
> 
> Then we will continue to try to dispatch more requests from IO
> scheduler, but if there are no requests in IO scheduler now, it will
> return 'false' here, and set dispatch_ret as false.
> 
>                         else
> -                               blk_mq_do_dispatch_ctx(hctx);
> +                               dispatch_ret = blk_mq_do_dispatch_ctx(hctx);

OK, this one is an issue, but it can be fixed simply by not updating
'dispatch_ret' for the following dispatch, something like the below
way:

	if (dispatch_ret) {
	        if (has_sched_dispatch)
	                blk_mq_do_dispatch_sched(hctx);
	        else
	                blk_mq_do_dispatch_ctx(hctx);
	}


Thanks,
Ming




[Index of Archives]     [Linux RAID]     [Linux SCSI]     [Linux ATA RAID]     [IDE]     [Linux Wireless]     [Linux Kernel]     [ATH6KL]     [Linux Bluetooth]     [Linux Netdev]     [Kernel Newbies]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Device Mapper]

  Powered by Linux