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;
Date:   Wed, 30 Oct 2019 13:29:20 -0400
From:   Phil Auld <pauld@redhat.com>
To:     Valentin Schneider <valentin.schneider@arm.com>
Cc:     Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Ingo Molnar <mingo@kernel.org>,
        Mel Gorman <mgorman@techsingularity.net>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
        Quentin Perret <quentin.perret@arm.com>,
        Morten Rasmussen <Morten.Rasmussen@arm.com>,
        Hillf Danton <hdanton@sina.com>,
        Parth Shah <parth@linux.ibm.com>,
        Rik van Riel <riel@surriel.com>
Subject: Re: [PATCH v4 00/10] sched/fair: rework the CFS load balance
Message-ID: <20191030172920.GH1686@pauld.bos.csb>
References: <20191024123844.GB2708@pauld.bos.csb>
 <20191024134650.GD2708@pauld.bos.csb>
 <CAKfTPtB0VruWXq+wGgvNOMFJvvZQiZyi2AgBoJP3Uaeduu2Lqg@mail.gmail.com>
 <20191025133325.GA2421@pauld.bos.csb>
 <CAKfTPtDWV7AkzMNuJtkN-pLmDcK41LwNiX0Wr8UT+vMFHAx6Qg@mail.gmail.com>
 <20191030143937.GC1686@pauld.bos.csb>
 <564ca629-5c34-dbd1-8e64-2da6910b18a3@arm.com>
 <bf96be8a-2358-b9ab-b8eb-d0b8b94ed0d7@arm.com>
 <20191030171914.GF1686@pauld.bos.csb>
 <4c52d81f-4b3b-d7e8-c124-b90b4584a6d3@arm.com>
MIME-Version: 1.0
In-Reply-To: <4c52d81f-4b3b-d7e8-c124-b90b4584a6d3@arm.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Content-Type: text/plain; charset=WINDOWS-1252
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Oct 30, 2019 at 06:25:09PM +0100 Valentin Schneider wrote:
> On 30/10/2019 18:19, Phil Auld wrote:
> >> Well from the code nobody but us (asymmetric capacity systems) set
> >> SD_BALANCE_WAKE. I was however curious if there were some folks who se=
t it
> >> with out of tree code for some reason.
> >>
> >> As Dietmar said, not having SD_BALANCE_WAKE means you'll never go thro=
ugh
> >> the slow path on wakeups, because there is no domain with SD_BALANCE_W=
AKE for
> >> the domain loop to find. Depending on your topology you most likely wi=
ll
> >> go through it on fork or exec though.
> >>
> >> IOW wake_wide() is not really widening the wakeup scan on wakeups usin=
g
> >> mainline topology code (disregarding asymmetric capacity systems), whi=
ch
> >> sounds a bit... off.
> >=20
> > Thanks. It's not currently set. I'll set it and re-run to see if it mak=
es
> > a difference.=20
> >=20
>=20
> Note that it might do more harm than good, it's not set in the default
> topology because it's too aggressive, see=20
>=20
>   182a85f8a119 ("sched: Disable wakeup balancing")
>=20

Heh, yeah... even as it's running I can see that this killing it :)


> >=20
> > However, I'm not sure why it would be making a difference for only the =
cgroup
> > case. If this is causing issues I'd expect it to effect both runs.=20
> >=20
> > In general I think these threads want to wake up the last cpu they were=
 on.
> > And given there are fewer cpu bound tasks that CPUs that wake cpu shoul=
d,
> > more often than not, be idle.=20
> >=20
> >=20
> > Cheers,
> > Phil
> >=20
> >=20
> >=20

--=20