Re: [patch] sched/fair: Move se->vruntime normalization state into struct sched_entity

[Mike Galbraith]

On Mon, 2016-05-23 at 11:19 +0200, Peter Zijlstra wrote:
> On Sun, May 22, 2016 at 09:00:01AM +0200, Mike Galbraith wrote:
> > On Sat, 2016-05-21 at 21:00 +0200, Mike Galbraith wrote:
> > > On Sat, 2016-05-21 at 16:04 +0200, Mike Galbraith wrote:
> > > 
> > > > Wakees that were not migrated/normalized eat an unwanted min_vruntime,
> > > > and likely take a size XXL latency hit.  Big box running master bled
> > > > profusely under heavy load until I turned TTWU_QUEUE off.
> > 
> > May as well make it official and against master.today.  Fly or die
> > little patchlet.
> > 
> > sched/fair: Move se->vruntime normalization state into struct sched_entity
> 
> Does this work?

Yup, bugs--.  Kinda funny, I considered ~this way first, but thought
you'd not that approach.. dang, got it back-assward ;-)

> ---
>  include/linux/sched.h |  1 +
>  kernel/sched/core.c   | 18 +++++++++++-------
>  2 files changed, 12 insertions(+), 7 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 1b43b45a22b9..a2001e01b3df 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1534,6 +1534,7 @@ struct task_struct {
>  	unsigned sched_reset_on_fork:1;
>  	unsigned sched_contributes_to_load:1;
>  	unsigned sched_migrated:1;
> +	unsigned sched_remote_wakeup:1;
>  	unsigned :0; /* force alignment to the next boundary */
>  
>  	/* unserialized, strictly 'current' */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 404c0784b1fc..7f2cae4620c7 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -1768,13 +1768,15 @@ void sched_ttwu_pending(void)
>  	cookie = lockdep_pin_lock(&rq->lock);
>  
>  	while (llist) {
> +		int wake_flags = 0;
> +
>  		p = llist_entry(llist, struct task_struct,
> wake_entry);
>  		llist = llist_next(llist);
> -		/*
> -		 * See ttwu_queue(); we only call
> ttwu_queue_remote() when
> -		 * its a x-cpu wakeup.
> -		 */
> -		ttwu_do_activate(rq, p, WF_MIGRATED, cookie);
> +
> +		if (p->sched_remote_wakeup)
> +			wake_flags = WF_MIGRATED;
> +
> +		ttwu_do_activate(rq, p, wake_flags, cookie);
>  	}
>  
>  	lockdep_unpin_lock(&rq->lock, cookie);
> @@ -1819,10 +1821,12 @@ void scheduler_ipi(void)
>  	irq_exit();
>  }
>  
> -static void ttwu_queue_remote(struct task_struct *p, int cpu)
> +static void ttwu_queue_remote(struct task_struct *p, int cpu, int
> wake_flags)
>  {
>  	struct rq *rq = cpu_rq(cpu);
>  
> +	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
> +
>  	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
>  		if (!set_nr_if_polling(rq->idle))
>  			smp_send_reschedule(cpu);
> @@ -1869,7 +1873,7 @@ static void ttwu_queue(struct task_struct *p,
> int cpu, int wake_flags)
>  #if defined(CONFIG_SMP)
>  	if (sched_feat(TTWU_QUEUE) &&
> !cpus_share_cache(smp_processor_id(), cpu)) {
>  		sched_clock_cpu(cpu); /* sync clocks x-cpu */
> -		ttwu_queue_remote(p, cpu);
> +		ttwu_queue_remote(p, cpu, wake_flags);
>  		return;
>  	}
>  #endif