Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220916080305.29574-1-vincent.guittot@linaro.org>
 <20220916080305.29574-7-vincent.guittot@linaro.org> <000c2893-feb4-373d-2234-2ca74be94714@arm.com>
 <CAKfTPtASminP4ogVRhcvQ4R3-x-E+UUzuMaEu-xQU_MtLr9+Xg@mail.gmail.com>
 <YyioI4iBFq8ib9JT@slm.duckdns.org> <20220921155521.qb3jb74nbjoenau6@airbuntu> <YytAa9a8DSyuJWhT@slm.duckdns.org>
In-Reply-To: <YytAa9a8DSyuJWhT@slm.duckdns.org>
From:   Vincent Guittot <vincent.guittot@linaro.org>
Date:   Wed, 21 Sep 2022 19:02:57 +0200
Message-ID: <CAKfTPtBCUu80dpGneyhsZneTtcqcm3DrVVoqv6rH60oX_vEz+Q@mail.gmail.com>
Subject: Re: [PATCH v4 6/8] sched/fair: Add sched group latency support
To:     Tejun Heo <tj@kernel.org>
Cc:     Qais Yousef <qais.yousef@arm.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>, mingo@redhat.com,
        peterz@infradead.org, juri.lelli@redhat.com, rostedt@goodmis.org,
        bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
        vschneid@redhat.com, linux-kernel@vger.kernel.org,
        parth@linux.ibm.com, chris.hyser@oracle.com,
        valentin.schneider@arm.com, patrick.bellasi@matbug.net,
        David.Laight@aculab.com, pjt@google.com, pavel@ucw.cz,
        qperret@google.com, tim.c.chen@linux.intel.com, joshdon@google.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, 21 Sept 2022 at 18:48, Tejun Heo <tj@kernel.org> wrote:
>
> Hello,
>
> On Wed, Sep 21, 2022 at 05:07:38PM +0100, Qais Yousef wrote:
> > Wouldn't cpu.latency.nice be enough? I think the latency_offset is
> > implementation detail that userspace shouldn't be concerned about.
>
> One option could be just using the same mapping as cpu.weight so that 100
> maps to neutral, 10000 maps close to -20, 1 maps close to 19. It isn't great
> that the value can't be interpreted in any intuitive way (e.g. a time
> duration based interface would be a lot easier to grok even if it still is
> best effort) but if that's what the per-task interface is gonna be, it'd be
> best to keep cgroup interface in line.

I would prefer a signed range like the [-1000:1000] as the behavior is
different for sensitive and non sensitive task unlike the cpu.weight
which is reflect that a bigger value get more

>
> As for whether a single value would fit the bill, it's again something which
> should be answered for both task and cgroup based interface at the same
> time. That said, my not-too-throught-through opinion is that a single value
> for per-task / per-cgroup interface + system level knobs to fine tune how
> that actually applies is likely enough and probably better than exposing
> exposing a host of internal details to applications directly.
>
> Thanks.
>
> --
> tejun