All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Ingo Molnar <mingo@redhat.com>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linaro-kernel@lists.linaro.org
Subject: Re: [PATCH v2 2/2] sched/fair: leverage the idle state info when choosing the "idlest" cpu
Date: Fri, 19 Sep 2014 02:05:45 +0200	[thread overview]
Message-ID: <20140919000545.GR2848@worktop.localdomain> (raw)
In-Reply-To: <1409844730-12273-3-git-send-email-nicolas.pitre@linaro.org>

On Thu, Sep 04, 2014 at 11:32:10AM -0400, Nicolas Pitre wrote:
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index bfa3c86d0d..416329e1a6 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -23,6 +23,7 @@
>  #include <linux/latencytop.h>
>  #include <linux/sched.h>
>  #include <linux/cpumask.h>
> +#include <linux/cpuidle.h>
>  #include <linux/slab.h>
>  #include <linux/profile.h>
>  #include <linux/interrupt.h>
> @@ -4428,20 +4429,48 @@ static int
>  find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
>  {
>  	unsigned long load, min_load = ULONG_MAX;
> -	int idlest = -1;
> +	unsigned int min_exit_latency = UINT_MAX;
> +	u64 latest_idle_timestamp = 0;
> +	int least_loaded_cpu = this_cpu;
> +	int shallowest_idle_cpu = -1;
>  	int i;
>  
>  	/* Traverse only the allowed CPUs */
>  	for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
> -		load = weighted_cpuload(i);
> -
> -		if (load < min_load || (load == min_load && i == this_cpu)) {
> -			min_load = load;
> -			idlest = i;
> +		if (idle_cpu(i)) {
> +			struct rq *rq = cpu_rq(i);
> +			struct cpuidle_state *idle = idle_get_state(rq);
> +			if (idle && idle->exit_latency < min_exit_latency) {
> +				/*
> +				 * We give priority to a CPU whose idle state
> +				 * has the smallest exit latency irrespective
> +				 * of any idle timestamp.
> +				 */
> +				min_exit_latency = idle->exit_latency;
> +				latest_idle_timestamp = rq->idle_stamp;
> +				shallowest_idle_cpu = i;
> +			} else if ((!idle || idle->exit_latency == min_exit_latency) &&
> +				   rq->idle_stamp > latest_idle_timestamp) {
> +				/*
> +				 * If equal or no active idle state, then
> +				 * the most recently idled CPU might have
> +				 * a warmer cache.
> +				 */
> +				latest_idle_timestamp = rq->idle_stamp;
> +				shallowest_idle_cpu = i;
> +			}
> +			cpuidle_put_state(rq);

Right, matching the other changes, I killed that line. The rest looks
ok.

> +		} else {
> +			load = weighted_cpuload(i);
> +			if (load < min_load ||
> +			    (load == min_load && i == this_cpu)) {
> +				min_load = load;
> +				least_loaded_cpu = i;
> +			}
>  		}
>  	}
>  
> -	return idlest;
> +	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
>  }


  parent reply	other threads:[~2014-09-19 15:10 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-04 15:32 [PATCH v2 0/2] sched/idle : find the best idle CPU with cpuidle info Nicolas Pitre
2014-09-04 15:32 ` [PATCH v2 1/2] sched: let the scheduler see CPU idle states Nicolas Pitre
2014-09-18 17:37   ` Paul E. McKenney
2014-09-18 17:39     ` Paul E. McKenney
2014-09-18 23:15       ` Peter Zijlstra
2014-09-18 18:32     ` Nicolas Pitre
2014-09-18 23:17       ` Peter Zijlstra
2014-09-18 23:28         ` Peter Zijlstra
2014-09-19 18:30           ` Nicolas Pitre
2014-09-04 15:32 ` [PATCH v2 2/2] sched/fair: leverage the idle state info when choosing the "idlest" cpu Nicolas Pitre
2014-09-05  7:52   ` Daniel Lezcano
2014-09-18 23:46   ` Peter Zijlstra
2014-09-19  0:05   ` Peter Zijlstra [this message]
2014-09-19  4:49   ` Yao Dongdong
2014-09-19  4:49     ` Yao Dongdong
2014-09-30 21:58   ` Rik van Riel
2014-09-30 23:15     ` Nicolas Pitre
2014-10-02 17:15       ` [PATCH RFC] sched,idle: teach select_idle_sibling about idle states Rik van Riel
2014-10-03  6:04         ` Mike Galbraith
2014-10-03  6:23         ` Mike Galbraith
2014-10-03  7:50           ` Peter Zijlstra
2014-10-03 13:05             ` Mike Galbraith
2014-10-03 14:28             ` Rik van Riel
2014-10-03 14:46               ` Peter Zijlstra
2014-10-03 15:37                 ` Rik van Riel
2014-10-09 16:04                   ` Peter Zijlstra
2014-10-03 18:52               ` Nicolas Pitre
2014-09-10 21:35 ` [PATCH v2 0/2] sched/idle : find the best idle CPU with cpuidle info Nicolas Pitre
2014-09-10 22:50   ` Rafael J. Wysocki
2014-09-10 23:25     ` Nicolas Pitre
2014-09-10 23:28       ` Nicolas Pitre
2014-09-10 23:50       ` Rafael J. Wysocki
2014-09-18  0:39   ` Nicolas Pitre
2014-09-18 23:24     ` Peter Zijlstra
2014-09-19 18:22       ` Nicolas Pitre

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=20140919000545.GR2848@worktop.localdomain \
    --to=peterz@infradead.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=linaro-kernel@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=nicolas.pitre@linaro.org \
    --cc=rjw@rjwysocki.net \
    /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.