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;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   Joel Fernandes <joel@joelfernandes.org>
Mime-Version: 1.0 (1.0)
Subject: Re: [PATCH 14/17] sched/eevdf: Better handle mixed slice length
Date:   Sun, 16 Apr 2023 07:10:12 +0200
Message-Id: <A0A2A612-B872-477E-A3B6-A1792EDF691E@joelfernandes.org>
References: <20230414111808.GA144166@lorien.usersys.redhat.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Vincent Guittot <vincent.guittot@linaro.org>, mingo@kernel.org,
        linux-kernel@vger.kernel.org, juri.lelli@redhat.com,
        dietmar.eggemann@arm.com, rostedt@goodmis.org, bsegall@google.com,
        mgorman@suse.de, bristot@redhat.com, corbet@lwn.net,
        qyousef@layalina.io, chris.hyser@oracle.com,
        patrick.bellasi@matbug.net, pjt@google.com, pavel@ucw.cz,
        qperret@google.com, tim.c.chen@linux.intel.com, joshdon@google.com,
        timj@gnu.org, kprateek.nayak@amd.com, yu.c.chen@intel.com,
        youssefesmat@chromium.org, efault@gmx.de
In-Reply-To: <20230414111808.GA144166@lorien.usersys.redhat.com>
To:     Phil Auld <pauld@redhat.com>
Precedence: bulk


> On Apr 14, 2023, at 1:18 PM, Phil Auld <pauld@redhat.com> wrote:
>=20
> =EF=BB=BFOn Wed, Apr 05, 2023 at 04:05:55PM -0400 Joel Fernandes wrote:
>>> On Wed, Apr 5, 2023 at 4:36=E2=80=AFAM Peter Zijlstra <peterz@infradead.=
org> wrote:
>>>=20
>>> On Tue, Apr 04, 2023 at 01:50:50PM +0000, Joel Fernandes wrote:
>>>>> On Tue, Apr 04, 2023 at 11:29:36AM +0200, Peter Zijlstra wrote:
>>>=20
>>>>> Heh, this is actually the correct behaviour. If you have a u=3D1 and a=

>>>>> u=3D.5 task, you should distribute time on a 2:1 basis, eg. 67% vs 33%=
.
>>>>=20
>>>> Splitting like that sounds like starvation of the sleeper to me. If som=
ething
>>>> sleeps a lot, it will get even less CPU time on an average than it woul=
d if
>>>> there was no contention from the u=3D1 task.
>>>=20
>>> No, sleeping, per definition, means you're not contending for CPU. What
>>> CFS does, giving them a little boost, is strictly yuck and messes with
>>> latency -- because suddenly you have a task that said it wasn't
>>> competing appear as if it were, but you didn't run it (how could you, it=

>>> wasn't there to run) -- but it still needs to catch up.
>>>=20
>>> The reason it does that, is mostly because at the time we didn't want to=

>>> do the whole lag thing -- it's somewhat heavy on the u64 mults and 32bit=

>>> computing was still a thing :/ So hacks happened.
>>=20
>> Also you have the whole "boost tasks" that sleep a lot with CFS right?
>> Like a task handling user input sleeps a lot, but when it wakes up,
>> it gets higher dynamic priority as its vruntime did not advance. I
>> guess EEVDF also gets you the same thing but still messes with the CPU
>> usage?
>>=20
>>> That said; I'm starting to regret not pushing the EEVDF thing harder
>>> back in 2010 when I first wrote it :/
>>>=20
>>>> And also CGroups will be even more weird than it already is in such a w=
orld,
>>>> 2 different containers will not get CPU time distributed properly- say i=
f
>>>> tasks in one container sleep a lot and tasks in another container are C=
PU
>>>> bound.
>>>=20
>>> Cgroups are an abomination anyway :-) /me runs like hell. But no, I
>>> don't actually expect too much trouble there.
>>=20
>> So, with 2 equally weighted containers, if one has a task that sleeps
>> 50% of the time, and another has a 100% task, then the sleeper will
>> only run 33% of the time? I can see people running containers having a
>> problem with that (a customer running one container gets less CPU than
>> the other.). Sorry if I missed something.
>>=20
>=20
> But the 50% sleeper is _asking_ for less CPU.  Doing 50% for each would
> mean that when the sleeper task was awake it always ran, always won, to
> the exclusion of any one else. (Assuming 1 CPU...)
>=20

It sounds like you are saying that if the task busy looped instead of sleepi=
ng, it would get more CPU during the time it is not busy looping but doing s=
ome real work. That sounds like encouraging abuse to get more perf.

But again, I have not looked too closely at EEVDF or Peters patches. I was j=
ust going by Vincents test and was cautioning to not break users who depend o=
n CFS shares..

Cheers,

- Joel


> Cheers,
> Phil
>=20
>> But yeah I do find the whole EEVDF idea interesting but I admit I have
>> to research it more.
>>=20
>> - Joel
>>=20
>=20
> --=20
>=20