Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <44fa1cee-08db-e4ab-e5ab-08d6fbd421d7@linux.alibaba.com>
 <20200303195245.GF2596@hirez.programming.kicks-ass.net> <xm26o8tc3qkv.fsf@bsegall-linux.svl.corp.google.com>
 <1180c6cd-ff61-2c9f-d689-ffe58f8c5a68@linux.alibaba.com> <CAKfTPtCaPz2KBmagzpEurh5S9aNFzUomHGh1pDWBx6L_29w5hw@mail.gmail.com>
 <12f79b83-491c-4b4b-0581-d23bdcec7c0c@linux.alibaba.com>
In-Reply-To: <12f79b83-491c-4b4b-0581-d23bdcec7c0c@linux.alibaba.com>
From:   Vincent Guittot <vincent.guittot@linaro.org>
Date:   Fri, 6 Mar 2020 09:04:45 +0100
Message-ID: <CAKfTPtD+He8UULUavz0csUeUV3TBdjShV9kUPQY6rpLswUAm4g@mail.gmail.com>
Subject: Re: [RFC PATCH] sched: fix the nonsense shares when load of cfs_rq is
 too, small
To:     =?UTF-8?B?546L6LSH?= <yun.wang@linux.alibaba.com>
Cc:     Ben Segall <bsegall@google.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Mel Gorman <mgorman@suse.de>,
        "open list:SCHEDULER" <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Fri, 6 Mar 2020 at 05:23, =E7=8E=8B=E8=B4=87 <yun.wang@linux.alibaba.com=
> wrote:
>
>
>
> On 2020/3/5 =E4=B8=8B=E5=8D=883:53, Vincent Guittot wrote:
> > On Thu, 5 Mar 2020 at 02:14, =E7=8E=8B=E8=B4=87 <yun.wang@linux.alibaba=
.com> wrote:
> [snip]
> >>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> >>> index fcc968669aea..6d7a9d72d742 100644
> >>> --- a/kernel/sched/fair.c
> >>> +++ b/kernel/sched/fair.c
> >>> @@ -3179,9 +3179,9 @@ static long calc_group_shares(struct cfs_rq *cf=
s_rq)
> >>>         long tg_weight, tg_shares, load, shares;
> >>>         struct task_group *tg =3D cfs_rq->tg;
> >>>
> >>> -       tg_shares =3D READ_ONCE(tg->shares);
> >>> +       tg_shares =3D scale_load_down(READ_ONCE(tg->shares));
> >>>
> >>> -       load =3D max(scale_load_down(cfs_rq->load.weight), cfs_rq->av=
g.load_avg);
> >>> +       load =3D max(cfs_rq->load.weight, scale_load(cfs_rq->avg.load=
_avg));
> >>>
> >>>         tg_weight =3D atomic_long_read(&tg->load_avg);
> >>
> >> Get the point, but IMHO fix scale_load_down() sounds better, to
> >> cover all the similar cases, let's first try that way see if it's
> >> working :-)
> >
> > The problem with this solution is that the avg.load_avg of gse or
> > cfs_rq might stay to 0 because it uses
> > scale_load_down(se/cfs_rq->load.weight)
>
> Will cfs_rq->load.weight be zero too without scale down?

cfs_rq->load.weight will never be 0, it's min is 2

>
> If cfs_rq->load.weight got at least something, the load will not be
> zero after pick the max, correct?

But the cfs_rq->avg.load_avg will never be other than 0 what ever
there are heavy or light tasks in the group

>
> Regards,
> Michael Wang
>
> >
> >>
> >> Regards,
> >> Michael Wang
> >>
> >>>
> >>>
> >>>