public inbox for linux-arm-kernel@lists.infradead.org 
 help / color / mirror / Atom feed
From: peterz@infradead•org (Peter Zijlstra)
To: linux-arm-kernel@lists•infradead.org
Subject: [PATCH v7 6/7] sched: replace capacity_factor by usage
Date: Thu, 9 Oct 2014 16:16:07 +0200	[thread overview]
Message-ID: <20141009141607.GR4750@worktop.programming.kicks-ass.net> (raw)
In-Reply-To: <1412684017-16595-7-git-send-email-vincent.guittot@linaro.org>

On Tue, Oct 07, 2014 at 02:13:36PM +0200, Vincent Guittot wrote:
> @@ -6214,17 +6178,21 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
>  
>  		/*
>  		 * In case the child domain prefers tasks go to siblings
> +		 * first, lower the sg capacity to one so that we'll try
>  		 * and move all the excess tasks away. We lower the capacity
>  		 * of a group only if the local group has the capacity to fit
> +		 * these excess tasks, i.e. group_capacity > 0. The
>  		 * extra check prevents the case where you always pull from the
>  		 * heaviest group when it is already under-utilized (possible
>  		 * with a large weight task outweighs the tasks on the system).
>  		 */
>  		if (prefer_sibling && sds->local &&
> +		    group_has_capacity(env, &sds->local_stat)) {
> +			if (sgs->sum_nr_running > 1)
> +				sgs->group_no_capacity = 1;
> +			sgs->group_capacity = min(sgs->group_capacity,
> +						SCHED_CAPACITY_SCALE);
> +		}
>  
>  		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
>  			sds->busiest = sg;

> @@ -6490,8 +6460,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
>  		goto force_balance;
>  
>  	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
> -	if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity &&
> -	    !busiest->group_has_free_capacity)
> +	if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
> +	    busiest->group_no_capacity)
>  		goto force_balance;
>  
>  	/*

This is two calls to group_has_capacity() on the local group. Why not
compute once in update_sd_lb_stats()?

  parent reply	other threads:[~2014-10-09 14:16 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-07 12:13 [PATCH v7 0/7] sched: consolidation of cpu_capacity Vincent Guittot
2014-10-07 12:13 ` [PATCH v7 1/7] sched: add per rq cpu_capacity_orig Vincent Guittot
2014-10-07 12:13 ` [PATCH v7 2/7] sched: move cfs task on a CPU with higher capacity Vincent Guittot
2014-10-09 11:23   ` Peter Zijlstra
2014-10-09 14:59     ` Vincent Guittot
2014-10-09 15:30       ` Peter Zijlstra
2014-10-10  7:46         ` Vincent Guittot
2014-10-07 12:13 ` [PATCH v7 3/7] sched: add utilization_avg_contrib Vincent Guittot
2014-10-08 17:04   ` Dietmar Eggemann
2014-10-07 12:13 ` [PATCH 4/7] sched: Track group sched_entity usage contributions Vincent Guittot
2014-10-07 20:15   ` bsegall at google.com
2014-10-08  7:16     ` Vincent Guittot
2014-10-08 11:13     ` Morten Rasmussen
2014-10-07 12:13 ` [PATCH v7 5/7] sched: get CPU's usage statistic Vincent Guittot
2014-10-09 11:36   ` Peter Zijlstra
2014-10-09 13:57     ` Vincent Guittot
2014-10-09 15:12       ` Peter Zijlstra
2014-10-10 14:38         ` Vincent Guittot
2014-10-07 12:13 ` [PATCH v7 6/7] sched: replace capacity_factor by usage Vincent Guittot
2014-10-09 12:16   ` Peter Zijlstra
2014-10-09 14:18     ` Vincent Guittot
2014-10-09 15:18       ` Peter Zijlstra
2014-10-10  7:17         ` Vincent Guittot
2014-10-10  7:18           ` Vincent Guittot
2014-11-23  1:03       ` Wanpeng Li
2014-11-24 10:16         ` Vincent Guittot
2014-10-09 14:16   ` Peter Zijlstra [this message]
2014-10-09 14:28     ` Vincent Guittot
2014-10-09 14:58   ` Peter Zijlstra
2014-10-21  7:38     ` Vincent Guittot
2014-10-07 12:13 ` [PATCH v7 7/7] sched: add SD_PREFER_SIBLING for SMT level Vincent Guittot

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=20141009141607.GR4750@worktop.programming.kicks-ass.net \
    --to=peterz@infradead$(echo .)org \
    --cc=linux-arm-kernel@lists$(echo .)infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox