Message-ID: <CAKfTPtDbyrcZtzPPsdQFOxOkreg-ejn=ABGOGqYjdVpeFPEzPw@mail.gmail.com>
Date:   Fri, 6 Nov 2020 14:33:56 +0100
From:   Vincent Guittot <vincent.guittot@...aro.org>
To:     Mel Gorman <mgorman@...hsingularity.net>
Cc:     Phil Auld <pauld@...hat.com>, Peter Puhov <peter.puhov@...aro.org>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Robert Foley <robert.foley@...aro.org>,
        Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>,
        Jirka Hladky <jhladky@...hat.com>
Subject: Re: [PATCH v1] sched/fair: update_pick_idlest() Select group with
 lowest group_util when idle_cpus are equal

On Fri, 6 Nov 2020 at 13:03, Mel Gorman <mgorman@...hsingularity.net> wrote:
>
> On Wed, Nov 04, 2020 at 09:42:05AM +0000, Mel Gorman wrote:
> > While it's possible that some other factor masked the impact of the patch,
> > the fact it's neutral for two workloads in 5.10-rc2 is suspicious as it
> > indicates that if the patch was implemented against 5.10-rc2, it would
> > likely not have been merged. I've queued the tests on the remaining
> > machines to see if something more conclusive falls out.
> >
>
> It's not as conclusive as I would like. fork_test generally benefits
> across the board but I do not put much weight in that.
>
> Otherwise, it's workload and machine-specific.
>
> schbench: (wakeup latency sensitive), all machines benefitted from the
>         revert at the low utilisation except one 2-socket haswell machine
>         which showed higher variability when the machine was fully
>         utilised.

There is a pending patch to should improve this bench:
https://lore.kernel.org/patchwork/patch/1330614/

>
> hackbench: Neutral except for the same 2-socket Haswell machine which
>         took an 8% performance penalty of 8% for smaller number of groups
>         and 4% for higher number of groups.
>
> pipetest: Mostly neutral except for the *same* machine showing an 18%
>         performance gain by reverting.
>
> kernbench: Shows small gains at low job counts across the board -- 0.84%
>         lowest gain up to 5.93% depending on the machine
>
> gitsource: low utilisation execution of the git test suite. This was
>         mostly a win for the revert. For the list of machines tested it was
>
>          14.48% gain (2 socket but SNC enabled to 4 NUMA nodes)
>         neutral      (2 socket broadwell)
>         36.37% gain  (1 socket skylake machine)
>          3.18% gain  (2 socket broadwell)
>          4.4%        (2 socket EPYC 2)
>          1.85% gain  (2 socket EPYC 1)
>
> While it was clear-cut for 5.9, it's less clear-cut for 5.10-rc2 although
> the gitsource shows some severe differences depending on the machine that
> is worth being extremely cautious about. I would still prefer a revert
> but I'm also extremely biased and I know there are other patches in the

This one from Julia can also impact

> pipeline that may change the picture. A wider battery of tests might
> paint a clearer picture but may not be worth the time investment.

hackbench and pipetest are those that i usually run and where not
facing regression it was either neutral or small gain which seems
aligned with the fact that there is no much fork/exec involved in
these bench
My machine has faced some connections issues the last couple of days
so I don't have all results; And especially the git source and
kernbench one

>
> So maybe lets just keep an eye on this one. When the scheduler pipeline
> dies down a bit (does that happen?), we should at least revisit it.
>
> --
> Mel Gorman
> SUSE Labs

Powered by blists - more mailing lists