From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757422AbdAKL3v (ORCPT ); Wed, 11 Jan 2017 06:29:51 -0500 Received: from foss.arm.com ([217.140.101.70]:46828 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750955AbdAKL3u (ORCPT ); Wed, 11 Jan 2017 06:29:50 -0500 Subject: Re: [PATCH] sched/fair: fix calc_cfs_shares fixed point arithmetics To: Peter Zijlstra References: <20161219224014.GA28238@var.home> <20161219230713.GD2895@var.home> <20161219232926.GH2895@var.home> <20161219234525.GI2895@var.home> <20161220131557.GN3124@twins.programming.kicks-ass.net> Cc: Samuel Thibault , Paul Turner , LKML , Thomas Gleixner , Ingo Molnar From: Dietmar Eggemann Message-ID: Date: Wed, 11 Jan 2017 11:29:47 +0000 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.5.1 MIME-Version: 1.0 In-Reply-To: <20161220131557.GN3124@twins.programming.kicks-ass.net> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 20/12/16 13:15, Peter Zijlstra wrote: > On Tue, Dec 20, 2016 at 02:04:34PM +0100, Dietmar Eggemann wrote: >> Hi Samuel, >> >> On 12/20/2016 12:45 AM, Samuel Thibault wrote: >>> Paul Turner, on Mon 19 Dec 2016 15:32:15 -0800, wrote: >>>> On Mon, Dec 19, 2016 at 3:29 PM, Samuel Thibault >>>> wrote: >>>>> Paul Turner, on Mon 19 Dec 2016 15:26:19 -0800, wrote: >> >> [...] >> >>>> The MIN_SHARES you are seeing here is overloaded. >>>> In the unscaled case this needs to be MIN_SHARES, and in the scaled >>>> case, the subdivision of the scaled values must still be >=2. >>> >>> Ok, now I understand. I have to say this overloading is confusing. >>> >>> Samuel >> >> this had been already discussed back in August when I posted the original >> patch. > > Maybe we should put a comment in to avoid getting more of these ;-) > Maybe something like this? Mainly what Paul taught us plus an example from a discussion I had with Vincent. -- >8 -- Subject: [PATCH] sched/fair: Explain why MIN_SHARES isn't scaled in calc_cfs_shares() Signed-off-by: Dietmar Eggemann --- kernel/sched/fair.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6559d197e08a..a0ca9b11b1b3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2657,6 +2657,18 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) if (tg_weight) shares /= tg_weight; + /* + * MIN_SHARES has to be unscaled here to support per-cpu partitioning + * of a group with small tg->shares value. It is a floor value which is + * assigned as a minimum load.weight to the sched_entity representing + * the group on a cpu. + * + * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024 + * on an 8 core system with 8 tasks each runnable on one cpu shares has + * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In + * case no task is runnable on a cpu MIN_SHARES=2 should be returned + * instead of 0. + */ if (shares < MIN_SHARES) shares = MIN_SHARES; if (shares > tg->shares) -- 2.11.0