linux-kernel - Re: [PATCH v3 3/7] sched: throttle cfs_rq entities which exceed their local quota

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: <AANLkTim4hA7CBshs5v0mO33VFVJa_o+qe6evyjBZ2N63@mail.gmail.com>
Date:	Wed, 13 Oct 2010 00:13:26 -0700
From:	Paul Turner <pjt@...gle.com>
To:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc:	bharata@...ux.vnet.ibm.com, linux-kernel@...r.kernel.org,
	Dhaval Giani <dhaval.giani@...il.com>,
	Balbir Singh <balbir@...ux.vnet.ibm.com>,
	Vaidyanathan Srinivasan <svaidy@...ux.vnet.ibm.com>,
	Srivatsa Vaddagiri <vatsa@...ibm.com>,
	Kamalesh Babulal <kamalesh@...ux.vnet.ibm.com>,
	Ingo Molnar <mingo@...e.hu>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Pavel Emelyanov <xemul@...nvz.org>,
	Herbert Poetzl <herbert@...hfloor.at>,
	Avi Kivity <avi@...hat.com>,
	Chris Friesen <cfriesen@...tel.com>,
	Paul Menage <menage@...gle.com>,
	Mike Waychison <mikew@...gle.com>,
	Nikhil Rao <ncrao@...gle.com>
Subject: Re: [PATCH v3 3/7] sched: throttle cfs_rq entities which exceed their
 local quota

On Wed, Oct 13, 2010 at 12:00 AM, KAMEZAWA Hiroyuki
<kamezawa.hiroyu@...fujitsu.com> wrote:
> On Tue, 12 Oct 2010 23:44:29 -0700
> Paul Turner <pjt@...gle.com> wrote:
>
>> On Tue, Oct 12, 2010 at 11:34 PM, KAMEZAWA Hiroyuki
>> <kamezawa.hiroyu@...fujitsu.com> wrote:
>> > On Tue, 12 Oct 2010 13:22:02 +0530
>> > Bharata B Rao <bharata@...ux.vnet.ibm.com> wrote:
>
>> >>  /*
>> >>   * Re-compute the task group their per cpu shares over the given domain.
>> >>   * This needs to be done in a bottom-up fashion because the rq weight of a
>> >> @@ -1688,7 +1691,14 @@ static int tg_shares_up(struct task_grou
>> >>       usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
>> >>
>> >>       for_each_cpu(i, sched_domain_span(sd)) {
>> >> -             weight = tg->cfs_rq[i]->load.weight;
>> >> +             /*
>> >> +              * bandwidth throttled entities cannot contribute to load
>> >> +              * balance
>> >> +              */
>> >> +             if (!cfs_rq_throttled(tg->cfs_rq[i]))
>> >> +                     weight = tg->cfs_rq[i]->load.weight;
>> >> +             else
>> >> +                     weight = 0;
>> >
>> > cpu.share and bandwidth control can't be used simultaneously or...
>> > is this fair ? I'm not familiar with scheduler but this allows boost this tg.
>> > Could you add a brief documentaion of a spec/feature. in the next post ?
>> >
>>
>> Bandwidth control is orthogonal to shares, shares continue controls
>> distribution of bandwidth when within quota.  Bandwidth control only
>> has 'perceivable' effect when you exceed your reservation within a
>> quota period.
>>
>> What the above is doing is removing any throttled entities from the
>> load-balancer's weight calculations (based on contribution from
>> throttled entities) since these entities are already dequeued and
>> cannot be balanced.
>>
>> Or have I misunderstood your question?
>>
>
> Thank you for quick reply.
> It seems I don't undestand what "cfs_rq_throttled()==1" means.

cfs_rq_throttled() == 1 correlates to cfs_rq->throttled == 1.

This is set when a cfs_rq exceeds it's local bandwidth quota and there
is no quota available in the global pool to refresh it.

At that point the cfs_rq is forcibly throttled, we accomplish this by

a) Ending its execution
b) Removing it from the entity tree (se->on_rq == 0)
c) Setting the throttled flag

The cfs_rq->throttled flag is required to track this state so that we
do not re-enqueue a throttled entity on child wake-up.

It also tells us here that we should update the accounting since these
se's, while containing runnable entities, are not actually on_rq.
>
> Thanks,
> -Kame
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/