All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavan Kondeti <pkondeti@codeaurora.org>
To: Valentin Schneider <valentin.schneider@arm.com>
Cc: linux-kernel@vger.kernel.org, mingo@redhat.com,
	peterz@infradead.org, vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com, morten.rasmussen@arm.com,
	qperret@google.com, adharmap@codeaurora.org
Subject: Re: [PATCH v3 1/3] sched/fair: Add asymmetric CPU capacity wakeup scan
Date: Tue, 28 Jan 2020 11:52:45 +0530	[thread overview]
Message-ID: <20200128062245.GA27398@codeaurora.org> (raw)
In-Reply-To: <20200126200934.18712-2-valentin.schneider@arm.com>

Hi Valentin,

On Sun, Jan 26, 2020 at 08:09:32PM +0000, Valentin Schneider wrote:
>  
> +static inline int check_cpu_capacity(struct rq *rq, struct sched_domain *sd);
> +
> +/*
> + * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which
> + * the task fits. If no CPU is big enough, but there are idle ones, try to
> + * maximize capacity.
> + */
> +static int select_idle_capacity(struct task_struct *p, int target)
> +{
> +	unsigned long best_cap = 0;
> +	struct sched_domain *sd;
> +	struct cpumask *cpus;
> +	int best_cpu = -1;
> +	struct rq *rq;
> +	int cpu;
> +
> +	if (!static_branch_unlikely(&sched_asym_cpucapacity))
> +		return -1;
> +
> +	sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
> +	if (!sd)
> +		return -1;
> +
> +	sync_entity_load_avg(&p->se);
> +
> +	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
> +	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
> +
> +	for_each_cpu_wrap(cpu, cpus, target) {
> +		rq = cpu_rq(cpu);
> +
> +		if (!available_idle_cpu(cpu))
> +			continue;
> +		if (task_fits_capacity(p, rq->cpu_capacity))
> +			return cpu;

I have couple of questions.

(1) Any particular reason for not checking sched_idle_cpu() as a backup
for the case where all eligible CPUs are busy? select_idle_cpu() does
that.

(2) Assuming all CPUs are busy, we return -1 from here and end up
calling select_idle_cpu(). The traversal in select_idle_cpu() may be
waste in cases where sd_llc == sd_asym_cpucapacity . For example SDM845.
Should we worry about this?

> +
> +		/*
> +		 * It would be silly to keep looping when we've found a CPU
> +		 * of highest available capacity. Just check that it's not been
> +		 * too pressured lately.
> +		 */
> +		if (rq->cpu_capacity_orig == READ_ONCE(rq->rd->max_cpu_capacity) &&
> +		    !check_cpu_capacity(rq, sd))
> +			return cpu;
> +
> +		if (rq->cpu_capacity > best_cap) {
> +			best_cap = rq->cpu_capacity;
> +			best_cpu = cpu;
> +		}
> +	}
> +
> +	return best_cpu;
> +}
> +
>  /*
>   * Try and locate an idle core/thread in the LLC cache domain.
>   */
> @@ -5902,6 +5956,11 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
>  	struct sched_domain *sd;
>  	int i, recent_used_cpu;
>  
> +	/* For asymmetric capacities, try to be smart about the placement */
> +	i = select_idle_capacity(p, target);
> +	if ((unsigned)i < nr_cpumask_bits)
> +		return i;
> +
>  	if (available_idle_cpu(target) || sched_idle_cpu(target))
>  		return target;
>  
> -- 
> 2.24.0
> 

Thanks,
Pavan

-- 
Qualcomm India Private Limited, on behalf of Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project.

  reply	other threads:[~2020-01-28  6:23 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-26 20:09 [PATCH v3 0/3] sched/fair: Capacity aware wakeup rework Valentin Schneider
2020-01-26 20:09 ` [PATCH v3 1/3] sched/fair: Add asymmetric CPU capacity wakeup scan Valentin Schneider
2020-01-28  6:22   ` Pavan Kondeti [this message]
2020-01-28 11:30     ` Valentin Schneider
2020-01-29  3:52       ` Pavan Kondeti
2020-01-29  8:16         ` Qais Yousef
2020-01-29  9:25         ` Valentin Schneider
2020-01-29 10:38       ` Dietmar Eggemann
2020-01-29 12:10         ` Valentin Schneider
2020-01-29 11:04   ` Dietmar Eggemann
2020-01-29 12:10     ` Valentin Schneider
2020-01-26 20:09 ` [PATCH v3 2/3] sched/topology: Remove SD_BALANCE_WAKE on asymmetric capacity systems Valentin Schneider
2020-01-29 16:27   ` Dietmar Eggemann
2020-01-30 11:06     ` Valentin Schneider
2020-01-26 20:09 ` [PATCH v3 3/3] sched/fair: Kill wake_cap() Valentin Schneider
2020-01-28  9:24 ` [PATCH v3 0/3] sched/fair: Capacity aware wakeup rework Dietmar Eggemann
2020-01-28 11:34   ` Valentin Schneider

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200128062245.GA27398@codeaurora.org \
    --to=pkondeti@codeaurora.org \
    --cc=adharmap@codeaurora.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=qperret@google.com \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.