linux-kernel - Re: [PATCH] sched/fair: improve spreading of utilization

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAKfTPtCopLDoUsC+Mt6k99Hdn52pcKkrNYQsYNRW5LdgyMg4Nw@mail.gmail.com>
Date:   Fri, 13 Mar 2020 18:12:28 +0100
From:   Vincent Guittot <vincent.guittot@...aro.org>
To:     Valentin Schneider <valentin.schneider@....com>
Cc:     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>, Mel Gorman <mgorman@...e.de>,
        linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] sched/fair: improve spreading of utilization

On Fri, 13 Mar 2020 at 17:57, Valentin Schneider
<valentin.schneider@....com> wrote:
>
>
> On Fri, Mar 13 2020, Vincent Guittot wrote:
>
> >> Good point on the capacity reduction vs group_is_overloaded.
> >>
> >> That said, can't we also reach this with migrate_task? Say the local
> >
> > The test has only been added for migrate_util so migrate_task is not impacted
> >
> >> group is entirely idle, and the busiest group has a few non-idle CPUs
> >> but they all have at most 1 running task. AFAICT we would still go to
> >> calculate_imbalance(), and try to balance out the number of idle CPUs.
> >
> > such case is handled by migrate_task when we try to even the number of
> > tasks between groups
> >
> >>
> >> If the migration_type is migrate_util, that can't happen because of this
> >> change. Since we have this progressive balancing strategy (tasks -> util
> >> -> load), it's a bit odd to have this "gap" in the middle where we get
> >> one less possibility to trigger active balance, don't you think? That
> >> is, providing I didn't say nonsense again :)
> >
> > Right now, I can't think of a use case that could trigger such
> > situation because we use migrate_util when source is overloaded which
> > means that there is at least one waiting task and we favor this task
> > in priority
> >
>
> Right, what I was trying to say is that AIUI migration_type ==
> migrate_task with <= 1 running task per CPU in the busiest group can
> *currently* lead to a balance attempt, and thus a potential active
> balance.
>
> Consider a local group of 4 idle CPUs, and a busiest group of 3 busy 1
> idle CPUs, each busy having only 1 running task. That busiest group
> would be group_has_spare, so we would compute an imbalance of
> (4-1) / 2 == 1 task to move. We'll proceed with the load balance, but
> we'll only move things if we go through an active_balance.

yes because we want to even as much as possible the number of tasks per group

>
> My point is that if we prevent this for migrate_util, it would make
> sense to prevent it for migrate_task, but it's not straightforward since

hmm but we don't want to prevent this active balance for migrate_task
because of cases like the one you mentioned above.

we might consider to finally select a CPU with only 1 running task
with migrate_util if there is no other CPU with more than 1 task. But
this would complexify the code and I don't think it's possible because
migrate_util is used to pull some utilizations from an overloaded
group which must have a CPU with a waiting task to be overloaded.

> we have things like ASYM_PACKING.
>
> >>
> >> It's not a super big deal, but I think it's nice if we can maintain a
> >> consistent / gradual migration policy.
> >>
> >> >>
> >> >> > might be hard to notice in benchmarks.