Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <2ED1BDF5-BC0C-47CD-8F33-9A46C738F8CF@linux.vnet.ibm.com>
 <CAKfTPtDrHv4OOfPvwOE2DMNoucXQJ=yvvEpTVKrXghSdKEnZcA@mail.gmail.com>
 <20210622143154.GA804@vingu-book> <53968DDE-9E93-4CB4-B5E4-526230B6E154@linux.vnet.ibm.com>
 <20210623071935.GA29143@vingu-book> <CCB4222F-000A-44E8-8D61-F69893704688@linux.vnet.ibm.com>
 <6C676AB3-5D06-471A-8715-60AABEBBE392@linux.vnet.ibm.com> <20210623120835.GB29143@vingu-book>
 <CAFpoUr01xb9ZJF9mb2nmZDpUHXFH3VSbY3AU8-1owV-_7wVTPg@mail.gmail.com>
 <CAKfTPtB++3y4VnbKE_n=bgsqCfqXuF0KUsdB_cFhi9xAnMRubw@mail.gmail.com> <CAFpoUr3bHzrwvumw6R=2JVbKa_wmtT9cMf-mdDHxY0Png-N9Jw@mail.gmail.com>
In-Reply-To: <CAFpoUr3bHzrwvumw6R=2JVbKa_wmtT9cMf-mdDHxY0Png-N9Jw@mail.gmail.com>
From:   Vincent Guittot <vincent.guittot@linaro.org>
Date:   Wed, 23 Jun 2021 15:55:47 +0200
Message-ID: <CAKfTPtAev0VgCmK3AUyTCoVA38YmskpB98q0kTrbEPK6e=1dTA@mail.gmail.com>
Subject: Re: [powerpc][next-20210621] WARNING at kernel/sched/fair.c:3277
 during boot
To:     Odin Ugedal <odin@uged.al>
Cc:     Sachin Sant <sachinp@linux.vnet.ibm.com>,
        Linux Next Mailing List <linux-next@vger.kernel.org>,
        linuxppc-dev@lists.ozlabs.org,
        open list <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, 23 Jun 2021 at 14:37, Odin Ugedal <odin@uged.al> wrote:
>
> ons. 23. jun. 2021 kl. 14:22 skrev Vincent Guittot <vincent.guittot@linaro.org>:
> >
> > In theory it should not because _sum should be always larger or equal
> > to _avg * divider. Otherwise, it means that we have something wrong
> > somewhere else
>
> Yeah, that might be the case. Still trying to wrap my head around
> this. I might be wrong, but isn't there a possibility
> that avg->period_contrib is increasing in PELTs accumulate_sum,
> without _sum is increasing. This makes the pelt divider increase,
> making the statement "_sum should be always larger or equal to _avg *"
> false? Or am I missing something obvious here?

The pelt value of sched_entity is synced with  cfs and its contrib
before being removed.
Then, we start to remove this load in update_cfs_rq_load_avg() before
calling __update_load_avg_cfs_rq so contrib should not have change and
we should be safe

>
> Still unable to reproduce what Sachin is reporting tho.
>
> Odin