Date:	Wed, 25 Jun 2014 10:40:48 -0700
From:	bsegall@...gle.com
To:	Kirill Tkhai <ktkhai@...allels.com>
Cc:	<linux-kernel@...r.kernel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>,
	Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
	Mike Galbraith <umgwanakikbuti@...il.com>,
	<khorenko@...allels.com>, Paul Turner <pjt@...gle.com>,
	<tkhai@...dex.ru>
Subject: Re: [PATCH v2 1/3] sched/fair: Disable runtime_enabled on dying rq

Kirill Tkhai <ktkhai@...allels.com> writes:

> В Ср, 25/06/2014 в 09:52 -0700, bsegall@...gle.com пишет:
>> Kirill Tkhai <ktkhai@...allels.com> writes:
>> 
>> > В Вт, 24/06/2014 в 23:26 +0400, Kirill Tkhai пишет:
>> >> On 24.06.2014 23:13, bsegall@...gle.com wrote:
>> >> > Kirill Tkhai <tkhai@...dex.ru> writes:
>> >> > 
>> >> >> On 24.06.2014 21:03, bsegall@...gle.com wrote:
>> >> >>> Kirill Tkhai <ktkhai@...allels.com> writes:
>> >> >>>
>> >> >>>> We kill rq->rd on the CPU_DOWN_PREPARE stage:
>> >> >>>>
>> >> >>>> 	cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains ->
>> >> >>>> 	-> cpu_attach_domain -> rq_attach_root -> set_rq_offline
>> >> >>>>
>> >> >>>> This unthrottles all throttled cfs_rqs.
>> >> >>>>
>> >> >>>> But the cpu is still able to call schedule() till
>> >> >>>>
>> >> >>>> 	take_cpu_down->__cpu_disable()
>> >> >>>>
>> >> >>>> is called from stop_machine.
>> >> >>>>
>> >> >>>> This case the tasks from just unthrottled cfs_rqs are pickable
>> >> >>>> in a standard scheduler way, and they are picked by dying cpu.
>> >> >>>> The cfs_rqs becomes throttled again, and migrate_tasks()
>> >> >>>> in migration_call skips their tasks (one more unthrottle
>> >> >>>> in migrate_tasks()->CPU_DYING does not happen, because rq->rd
>> >> >>>> is already NULL).
>> >> >>>>
>> >> >>>> Patch sets runtime_enabled to zero. This guarantees, the runtime
>> >> >>>> is not accounted, and the cfs_rqs won't exceed given
>> >> >>>> cfs_rq->runtime_remaining = 1, and tasks will be pickable
>> >> >>>> in migrate_tasks(). runtime_enabled is recalculated again
>> >> >>>> when rq becomes online again.
>> >> >>>>
>> >> >>>> Ben Segall also noticed, we always enable runtime in
>> >> >>>> tg_set_cfs_bandwidth(). Actually, we should do that for online
>> >> >>>> cpus only. To fix that, we check if a cpu is online when
>> >> >>>> its rq is locked. This guarantees we do not have races with
>> >> >>>> set_rq_offline(), which also requires rq->lock.
>> >> >>>>
>> >> >>>> v2: Fix race with tg_set_cfs_bandwidth().
>> >> >>>>     Move cfs_rq->runtime_enabled=0 above unthrottle_cfs_rq().
>> >> >>>>
>> >> >>>> Signed-off-by: Kirill Tkhai <ktkhai@...allels.com>
>> >> >>>> CC: Konstantin Khorenko <khorenko@...allels.com>
>> >> >>>> CC: Ben Segall <bsegall@...gle.com>
>> >> >>>> CC: Paul Turner <pjt@...gle.com>
>> >> >>>> CC: Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
>> >> >>>> CC: Mike Galbraith <umgwanakikbuti@...il.com>
>> >> >>>> CC: Peter Zijlstra <peterz@...radead.org>
>> >> >>>> CC: Ingo Molnar <mingo@...nel.org>
>> >> >>>> ---
>> >> >>>>  kernel/sched/core.c |   15 +++++++++++----
>> >> >>>>  kernel/sched/fair.c |   22 ++++++++++++++++++++++
>> >> >>>>  2 files changed, 33 insertions(+), 4 deletions(-)
>> >> >>>>
>> >> >>>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> >> >>>> index 7f3063c..707a3c5 100644
>> >> >>>> --- a/kernel/sched/core.c
>> >> >>>> +++ b/kernel/sched/core.c
>> >> >>>> @@ -7842,11 +7842,18 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
>> >> >>>>  		struct rq *rq = cfs_rq->rq;
>> >> >>>>  
>> >> >>>>  		raw_spin_lock_irq(&rq->lock);
>> >> >>>> -		cfs_rq->runtime_enabled = runtime_enabled;
>> >> >>>> -		cfs_rq->runtime_remaining = 0;
>> >> >>>> +		/*
>> >> >>>> +		 * Do not enable runtime on offline runqueues. We specially
>> >> >>>> +		 * make it disabled in unthrottle_offline_cfs_rqs().
>> >> >>>> +		 */
>> >> >>>> +		if (cpu_online(i)) {
>> >> >>>> +			cfs_rq->runtime_enabled = runtime_enabled;
>> >> >>>> +			cfs_rq->runtime_remaining = 0;
>> >> >>>> +
>> >> >>>> +			if (cfs_rq->throttled)
>> >> >>>> +				unthrottle_cfs_rq(cfs_rq);
>> >> >>>> +		}
>> >> >>>
>> >> >>> We can just do for_each_online_cpu, yes? Also we probably need
>> >> >>> get_online_cpus/put_online_cpus, and/or want cpu_active_mask instead
>> >> >>> right?
>> >> >>>
>> >> >>
>> >> >> Yes, we can use for_each_online_cpu/for_each_active_cpu with
>> >> >> get_online_cpus() taken. But it adds one more lock dependence.
>> >> >> This looks worse for me.
>> >> > 
>> >> > I mean, you need get_online_cpus anyway - cpu_online is just a test
>> >> > against the same mask that for_each_online_cpu uses, and without taking
>> >> > the lock you can still race with offlining and reset runtime_enabled.
>> >> > 
>> >> 
>> >> Oh, I see. Thanks.
>> >
>> > But we can check for rq->online, don't we? How about this?
>> 
>> Yeah, that should work.
>
> We can't base on it because rq->offline is not available in !SMP.
> Could you review the message from [PATCH v3 1/3] topic?

I'm not sure what you mean here. The patch just checking cpu_online
won't work, is there another version you want me to look at?
--
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/

Powered by blists - more mailing lists