Received-SPF: pass (google.com: domain of linux-kernel+bounces-58883-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Precedence: bulk
MIME-Version: 1.0
References: <20240208093136.178797-1-zhaoyang.huang@unisoc.com>
 <20240208093136.178797-3-zhaoyang.huang@unisoc.com> <5f934ebf-4e2a-44f9-993f-8b2c8d358370@acm.org>
In-Reply-To: <5f934ebf-4e2a-44f9-993f-8b2c8d358370@acm.org>
From: Zhaoyang Huang <huangzhaoyang@gmail.com>
Date: Fri, 9 Feb 2024 07:52:21 +0800
Message-ID: <CAGWkznGvwBZWv+g7=0JxRpeQ+chMoN27TDmuSAVU2O37fGNCDg@mail.gmail.com>
Subject: Re: [PATCH 3/3] block: introducing a bias over deadline's fifo_time
To: Bart Van Assche <bvanassche@acm.org>
Cc: "zhaoyang.huang" <zhaoyang.huang@unisoc.com>, Jens Axboe <axboe@kernel.dk>, 
	Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>, 
	Juri Lelli <juri.lelli@redhat.com>, Vincent Guittot <vincent.guittot@linaro.org>, 
	Yu Zhao <yuzhao@google.com>, linux-block@vger.kernel.org, 
	linux-kernel@vger.kernel.org, steve.kang@unisoc.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, Feb 9, 2024 at 1:46=E2=80=AFAM Bart Van Assche <bvanassche@acm.org>=
 wrote:
>
> On 2/8/24 01:31, zhaoyang.huang wrote:
> > diff --git a/block/mq-deadline.c b/block/mq-deadline.c
> > index f958e79277b8..43c08c3d6f18 100644
> > --- a/block/mq-deadline.c
> > +++ b/block/mq-deadline.c
> > @@ -15,6 +15,7 @@
> >   #include <linux/compiler.h>
> >   #include <linux/rbtree.h>
> >   #include <linux/sbitmap.h>
> > +#include "../kernel/sched/sched.h"
>
> Is kernel/sched/sched.h perhaps a private scheduler kernel header file? S=
houldn't
> block layer code only include public scheduler header files?
>
> > @@ -840,7 +842,9 @@ static void dd_insert_request(struct blk_mq_hw_ctx =
*hctx, struct request *rq,
> >               /*
> >                * set expire time and add to fifo list
> >                */
> > -             rq->fifo_time =3D jiffies + dd->fifo_expire[data_dir];
> > +             fifo_expire =3D task_is_realtime(current) ? dd->fifo_expi=
re[data_dir] :
> > +                     CFS_PROPORTION(current, dd->fifo_expire[data_dir]=
);
> > +             rq->fifo_time =3D jiffies + fifo_expire;
> >               insert_before =3D &per_prio->fifo_list[data_dir];
> >   #ifdef CONFIG_BLK_DEV_ZONED
> >               /*
>
> Making the mq-deadline request expiry time dependent on the task priority=
 seems wrong
> to me.
But bio_set_ioprio has done this before
>
> Thanks,
>
> Bart.