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: <20210601155328.19487-1-vincent.guittot@linaro.org> <CAFpoUr0NUVqxCtRefu+MUv=SSA+7ie5OxtPqYZ=AT=JNc+0t=Q@mail.gmail.com>
In-Reply-To: <CAFpoUr0NUVqxCtRefu+MUv=SSA+7ie5OxtPqYZ=AT=JNc+0t=Q@mail.gmail.com>
From:   Vincent Guittot <vincent.guittot@linaro.org>
Date:   Thu, 3 Jun 2021 14:47:48 +0200
Message-ID: <CAKfTPtCDPGJW=J6JmZ+Gs5kcptfWUwAsFs=xyCcoJ_hF--EkAA@mail.gmail.com>
Subject: Re: [PATCH] sched/pelt: check that *_avg are null when *_sum are
To:     Odin Ugedal <odin@uged.al>
Cc:     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>,
        Benjamin Segall <bsegall@google.com>,
        Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        open list <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Thu, 3 Jun 2021 at 13:06, Odin Ugedal <odin@uged.al> wrote:
>
> Hi,
>
> Is there an idea to add tg_load_avg_contrib as well, to avoid
> regressions where that is not set to zero?

TBH I wondered while preparing this patch if tg_load_avg_contrib
should be checked as well but I came to the conclusion that we should
keep this looking at PELT metrics only. If tg_load_avg_contrib != 0
but load_avg ==0, it means that we failed to update
tg_load_avg_contrib somewhere else

>
> Otherwise:
>
> Acked-by: Odin Ugedal <odin@uged.al>