From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1758689AbaDXRHy (ORCPT <rfc822;w@1wt.eu>);
	Thu, 24 Apr 2014 13:07:54 -0400
Received: from mga09.intel.com ([134.134.136.24]:35127 "EHLO mga09.intel.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754765AbaDXRHw (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Thu, 24 Apr 2014 13:07:52 -0400
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="4.97,920,1389772800"; 
   d="scan'208";a="527569001"
Subject: Re: [PATCH] sched: Skip double execution of pick_next_task_fair
From: Tim Chen <tim.c.chen@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>, linux-kernel@vger.kernel.org,
        Andi Kleen <ak@linux.intel.com>, Len Brown <len.brown@intel.com>
In-Reply-To: <20140424100047.GP11096@twins.programming.kicks-ass.net>
References: <1398292317.2970.63.camel@schen9-DESK>
	 <20140424100047.GP11096@twins.programming.kicks-ass.net>
Content-Type: text/plain; charset="UTF-8"
Date: Thu, 24 Apr 2014 10:06:07 -0700
Message-ID: <1398359167.2970.80.camel@schen9-DESK>
Mime-Version: 1.0
X-Mailer: Evolution 2.32.3 (2.32.3-1.fc14) 
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, 2014-04-24 at 12:00 +0200, Peter Zijlstra wrote:
> On Wed, Apr 23, 2014 at 03:31:57PM -0700, Tim Chen wrote:
> > The current code will call pick_next_task_fair a second time
> > in the slow path if we did not pull any task in our first try.
> > This is really unnecessary as we already know no task can
> > be pulled and it doubles the delay for the cpu to enter idle.
> > 
> > We instrumented some network workloads and that saw that
> > pick_next_task_fair is frequently called twice before a cpu enters idle.
> > The call to pick_next_task_fair can add
> > non trivial latency as it calls load_balance which runs find_busiest_group
> > on an hierarchy of sched domains spanning the cpus for a large system.  For
> > some 4 socket systems, we saw almost 0.25 msec spent per call
> > of pick_next_task_fair before a cpu can be idled.
> > 
> > This patch skips pick_next_task_fair in the slow path if it
> > has already been invoked.
> 
> How about something like so?

Yes, this version is more concise.

> 
> Its a little more contained.
> 
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2636,8 +2636,14 @@ pick_next_task(struct rq *rq, struct tas
>  	if (likely(prev->sched_class == class &&
>  		   rq->nr_running == rq->cfs.h_nr_running)) {
>  		p = fair_sched_class.pick_next_task(rq, prev);
> -		if (likely(p && p != RETRY_TASK))
> -			return p;
> +		if (unlikely(p == RETRY_TASK))
> +			goto again;
> +
> +		/* assumes fair_sched_class->next == idle_sched_class */
> +		if (unlikely(!p))
> +			p = pick_next_task_idle(rq, prev);
Should be 
			  p = idle_sched_class.pick_next_task(rq, prev);
> +
> +		return p;
>  	}
>  
>  again:

I'll respin the patch with these changes.

Thanks.

Tim