From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752345Ab3EFIeX (ORCPT ); Mon, 6 May 2013 04:34:23 -0400 Received: from e28smtp01.in.ibm.com ([122.248.162.1]:49704 "EHLO e28smtp01.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752133Ab3EFIeV (ORCPT ); Mon, 6 May 2013 04:34:21 -0400 Message-ID: <51876AFE.80906@linux.vnet.ibm.com> Date: Mon, 06 May 2013 16:34:06 +0800 From: Michael Wang User-Agent: Mozilla/5.0 (X11; Linux i686; rv:16.0) Gecko/20121011 Thunderbird/16.0.1 MIME-Version: 1.0 To: Alex Shi CC: pjt@google.com, mingo@redhat.com, peterz@infradead.org, tglx@linutronix.de, akpm@linux-foundation.org, bp@alien8.de, namhyung@kernel.org, efault@gmx.de, morten.rasmussen@arm.com, vincent.guittot@linaro.org, preeti@linux.vnet.ibm.com, viresh.kumar@linaro.org, linux-kernel@vger.kernel.org, mgorman@suse.de, riel@redhat.com Subject: Re: [PATCH v5 7/7] sched: consider runnable load average in effective_load References: <1367804711-30308-1-git-send-email-alex.shi@intel.com> <1367804711-30308-8-git-send-email-alex.shi@intel.com> <518724D1.9040006@linux.vnet.ibm.com> <51874229.8050202@intel.com> <5187609C.5050209@linux.vnet.ibm.com> <518763B0.30200@intel.com> In-Reply-To: <518763B0.30200@intel.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-TM-AS-MML: No X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13050608-4790-0000-0000-0000082CDF71 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/06/2013 04:02 PM, Alex Shi wrote: > On 05/06/2013 03:49 PM, Michael Wang wrote: >> On 05/06/2013 01:39 PM, Alex Shi wrote: >> [snip] >> >> Rough test done: >> >>> >>> 1, change back the tg_weight in calc_tg_weight() to use tg_load_contrib not direct load. >> >> This way stop the regression of patch 7. >> >>> >>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >>> index 6f4f14b..c770f8d 100644 >>> --- a/kernel/sched/fair.c >>> +++ b/kernel/sched/fair.c >>> @@ -1037,8 +1037,8 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) >>> * update_cfs_rq_load_contribution(). >>> */ >>> tg_weight = atomic64_read(&tg->load_avg); >>> - tg_weight -= cfs_rq->tg_load_contrib; >>> - tg_weight += cfs_rq->load.weight; >>> + //tg_weight -= cfs_rq->tg_load_contrib; >>> + //tg_weight += cfs_rq->load.weight; >>> >>> return tg_weight; >>> } >>> >>> 2, another try is follow the current calc_tg_weight, so remove the follow change. >> >> This way show even better results than only patch 1~6. > > how much better to the first change? Nevermind, it's just a rough test, consider them as same... >> >> But the way Preeti suggested doesn't works... > > What's the Preeti suggestion? :) Paste at last. >> >> May be we should record some explanation about this change here, do we? > > I don't know why we need this, PJT, would you like to tell us why the > calc_tg_weight use cfs_rq->load.weight not cfs_rq->tg_load_contrib? The comment said this is more accurate, but that was for the world without decay load I suppose... But if it using 'cfs_rq->load.weight', which means denominator M contain that factor, than numerator w has to contain it also... Regards, Michael Wang > > >> >> Regards, >> Michael Wang >> sched: Modify effective_load() to use runnable load average From: Preeti U Murthy The runqueue weight distribution should update the runnable load average of the cfs_rq on which the task will be woken up. However since the computation of se->load.weight takes into consideration the runnable load average in update_cfs_shares(),no need to modify this in effective_load(). --- kernel/sched/fair.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 790e23d..5489022 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3045,7 +3045,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) /* * w = rw_i + @wl */ - w = se->my_q->load.weight + wl; + w = se->my_q->runnable_load_avg + wl; /* * wl = S * s'_i; see (2) @@ -3066,6 +3066,9 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) /* * wl = dw_i = S * (s'_i - s_i); see (3) */ + /* Do not modify the below as it already contains runnable + * load average in its computation + */ wl -= se->load.weight; /* @@ -3112,14 +3115,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) */ if (sync) { tg = task_group(current); - weight = current->se.load.weight; + weight = current->se.avg.load_avg_contrib; this_load += effective_load(tg, this_cpu, -weight, -weight); load += effective_load(tg, prev_cpu, 0, -weight); } tg = task_group(p); - weight = p->se.load.weight; + weight = p->se.avg.load_avg_contrib; /* * In low-load situations, where prev_cpu is idle and this_cpu is idle Regards Preeti U Murthy