Received-SPF: pass (google.com: domain of linux-kernel+bounces-127583-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: <20240315015916.21545-1-daweilics@gmail.com> <ZgqOEJ5sCANkkk5N@linux.ibm.com>
 <CAG5MgCq3GT=CVj7Hz8rUMfNG1c9ypVsTSDKNESHV9tY_qWSt2g@mail.gmail.com> <e7d5bec3-be2a-4eea-b946-7f1739b0b4d0@linux.ibm.com>
In-Reply-To: <e7d5bec3-be2a-4eea-b946-7f1739b0b4d0@linux.ibm.com>
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Tue, 2 Apr 2024 10:49:56 +0200
Message-ID: <CAKfTPtCVQ7ooRuN-OroK90GGa2T7=HyK3kovmvJcgojvJhbwPQ@mail.gmail.com>
Subject: Re: [PATCH v2] sched/fair: fix initial util_avg calculation
To: Vishal Chourasia <vishalc@linux.ibm.com>
Cc: Dawei Li <daweilics@gmail.com>, Ingo Molnar <mingo@redhat.com>, 
	Peter Zijlstra <peterz@infradead.org>, Juri Lelli <juri.lelli@redhat.com>, 
	Dietmar Eggemann <dietmar.eggemann@arm.com>, Steven Rostedt <rostedt@goodmis.org>, 
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>, 
	Daniel Bristot de Oliveira <bristot@redhat.com>, Valentin Schneider <vschneid@redhat.com>, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Tue, 2 Apr 2024 at 10:44, Vishal Chourasia <vishalc@linux.ibm.com> wrote=
:
>
> On 02/04/24 11:17 am, Dawei Li wrote:
> > Hi Vishal
> >
> > Thanks for the comment!
> > Do you suggest using scale_load_down() in place of se_weight()?
> scale_load_down should be better.

se_weight is used for computing sched_entity's pelt signal so keep
using it looks better but all this clearly just nitpick because that
doesn't make any difference

> > It's a soft bug we should fix one way or another before what the
> > comment mentions really happens.
> IIUC, We should be moving towards using full load resolution
> for all the calculations. In that case, we need not worry about scaling l=
oad at
> all. Maybe someone could provide context here.
>
> > I am actually confused that we have both se_weight() and
> > scale_load_down(), and they do the same thing.
> >
> > Best regards,
> > Dawei
> >
> > On Mon, Apr 1, 2024 at 3:36=E2=80=AFAM Vishal Chourasia <vishalc@linux.=
ibm.com> wrote:
> >>
> >> On Thu, Mar 14, 2024 at 06:59:16PM -0700, Dawei Li wrote:
> >>> Change se->load.weight to se_weight(se) in the calculation for the
> >>> initial util_avg to avoid unnecessarily inflating the util_avg by 102=
4
> >>> times.
> >>>
> >>> The reason is that se->load.weight has the unit/scale as the scaled-u=
p
> >>> load, while cfs_rg->avg.load_avg has the unit/scale as the true task
> >>> weight (as mapped directly from the task's nice/priority value). With
> >>> CONFIG_32BIT, the scaled-up load is equal to the true task weight. Wi=
th
> >>> CONFIG_64BIT, the scaled-up load is 1024 times the true task weight.
> >>> Thus, the current code may inflate the util_avg by 1024 times. The
> >>> follow-up capping will not allow the util_avg value to go wild. But t=
he
> >>> calculation should have the correct logic.
> >>>
> >>> Signed-off-by: Dawei Li <daweilics@gmail.com>
> >>> ---
> >>> Changes in v2:
> >>> - update the commit message
> >>> ---
> >>>  kernel/sched/fair.c | 5 +++--
> >>>  1 file changed, 3 insertions(+), 2 deletions(-)
> >>>
> >>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> >>> index a19ea290b790..5f98f639bdb9 100644
> >>> --- a/kernel/sched/fair.c
> >>> +++ b/kernel/sched/fair.c
> >>> @@ -1031,7 +1031,8 @@ void init_entity_runnable_average(struct sched_=
entity *se)
> >>>   * With new tasks being created, their initial util_avgs are extrapo=
lated
> >>>   * based on the cfs_rq's current util_avg:
> >>>   *
> >>> - *   util_avg =3D cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.loa=
d.weight
> >>> + *   util_avg =3D cfs_rq->avg.util_avg / (cfs_rq->avg.load_avg + 1)
> >>> + *           * se_weight(se)
> >>>   *
> >>>   * However, in many cases, the above util_avg does not give a desire=
d
> >>>   * value. Moreover, the sum of the util_avgs may be divergent, such
> >>> @@ -1078,7 +1079,7 @@ void post_init_entity_util_avg(struct task_stru=
ct *p)
> >>>
> >>>       if (cap > 0) {
> >>>               if (cfs_rq->avg.util_avg !=3D 0) {
> >>> -                     sa->util_avg  =3D cfs_rq->avg.util_avg * se->lo=
ad.weight;
> >>> +                     sa->util_avg  =3D cfs_rq->avg.util_avg * se_wei=
ght(se);
> >> Hi,
> >>
> >> The comment above the declaration of se_weight function says we should=
 be
> >> using full load resolution and get rid of this helper.
> >>
> >> Should we be adding new user of the helper?
> >>
> >> /*
> >>  * XXX we want to get rid of these helpers and use the full load resol=
ution.
> >>  */
> >> static inline long se_weight(struct sched_entity *se)
> >> {
> >>         return scale_load_down(se->load.weight);
> >> }
> >>
> >>
> >>>                       sa->util_avg /=3D (cfs_rq->avg.load_avg + 1);
> >>>
> >>>                       if (sa->util_avg > cap)
> >>> --
> >>> 2.40.1
> >>>
>