linux-kernel - Re: [PATCH] sched/fair: Sync task util before slow-path wakeup

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: <8760e6rtf2.fsf@arm.com>
Date:   Wed, 02 Aug 2017 14:27:45 +0100
From:   Brendan Jackman <brendan.jackman@....com>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
        Joel Fernandes <joelaf@...gle.com>,
        Andres Oportus <andresoportus@...gle.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Josef Bacik <josef@...icpanda.com>,
        Morten Rasmussen <morten.rasmussen@....com>
Subject: Re: [PATCH] sched/fair: Sync task util before slow-path wakeup


On Wed, Aug 02 2017 at 13:24, Peter Zijlstra wrote:
> On Wed, Aug 02, 2017 at 02:10:02PM +0100, Brendan Jackman wrote:
>> We use task_util in find_idlest_group via capacity_spare_wake. This
>> task_util is updated in wake_cap. However wake_cap is not the only
>> reason for ending up in find_idlest_group - we could have been sent
>> there by wake_wide. So explicitly sync the task util with prev_cpu
>> when we are about to head to find_idlest_group.
>>
>> We could simply do this at the beginning of
>> select_task_rq_fair (i.e. irrespective of whether we're heading to
>> select_idle_sibling or find_idlest_group & co), but I didn't want to
>> slow down the select_idle_sibling path more than necessary.
>>
>> Don't do this during fork balancing, we won't need the task_util and
>> we'd just clobber the last_update_time, which is supposed to be 0.
>
> So I remember Morten explicitly not aging util of tasks on wakeup
> because the old util was higher and better representative of what the
> new util would be, or something along those lines.
>
> Morten?
>
>> Signed-off-by: Brendan Jackman <brendan.jackman@....com>
>> Cc: Dietmar Eggemann <dietmar.eggemann@....com>
>> Cc: Vincent Guittot <vincent.guittot@...aro.org>
>> Cc: Josef Bacik <josef@...icpanda.com>
>> Cc: Ingo Molnar <mingo@...hat.com>
>> Cc: Morten Rasmussen <morten.rasmussen@....com>
>> Cc: Peter Zijlstra <peterz@...radead.org>
>> ---
>>  kernel/sched/fair.c | 8 ++++++++
>>  1 file changed, 8 insertions(+)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index c95880e216f6..62869ff252b4 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -5913,6 +5913,14 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
>>  			new_cpu = cpu;
>>  	}
>>
>> +	if (sd && !(sd_flag & SD_BALANCE_FORK))
>> +		/*
>> +		 * We're going to need the task's util for capacity_spare_wake
>> +		 * in select_idlest_group. Sync it up to prev_cpu's
>> +		 * last_update_time.
>> +		 */
>> +		sync_entity_load_avg(&p->se);
>> +
>
> That has missing {}

OK. Also just noticed it refers to "select_idlest_group", will change to
"find_idlest_group".

>
>
>>  	if (!sd) {
>>   pick_cpu:
>
> And if this patch lives, can you please fix up that broken label indent?

Sure.

>>  		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */

Cheers,
Brendan