Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760690AbYHDG0b (ORCPT ); Mon, 4 Aug 2008 02:26:31 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755463AbYHDG0M (ORCPT ); Mon, 4 Aug 2008 02:26:12 -0400 Received: from viefep32-int.chello.at ([62.179.121.50]:48905 "EHLO viefep32-int.chello.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754783AbYHDG0L (ORCPT ); Mon, 4 Aug 2008 02:26:11 -0400 Subject: Re: VolanoMark regression with 2.6.27-rc1 From: Peter Zijlstra To: Dhaval Giani Cc: "Zhang, Yanmin" , Ingo Molnar , LKML , Srivatsa Vaddagiri , Aneesh Kumar KV , Balbir Singh In-Reply-To: <20080804055339.GB5444@linux.vnet.ibm.com> References: <1217474425.25608.150.camel@ymzhang> <1217489463.25608.157.camel@ymzhang> <1217489949.8157.78.camel@twins> <1217490560.25608.168.camel@ymzhang> <1217551154.25608.169.camel@ymzhang> <20080801051407.GA5232@linux.vnet.ibm.com> <1217826278.25608.198.camel@ymzhang> <20080804052228.GA5444@linux.vnet.ibm.com> <1217828278.25608.206.camel@ymzhang> <20080804055339.GB5444@linux.vnet.ibm.com> Content-Type: text/plain Date: Mon, 04 Aug 2008 08:26:11 +0200 Message-Id: <1217831171.9016.42.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.22.3.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6824 Lines: 257 On Mon, 2008-08-04 at 11:23 +0530, Dhaval Giani wrote: > Peter, vatsa, any ideas? --- Revert: a7be37ac8e1565e00880531f4e2aff421a21c803 sched: revert the revert of: weight calculations c9c294a630e28eec5f2865f028ecfc58d45c0a5a sched: fix calc_delta_asym() ced8aa16e1db55c33c507174c1b1f9e107445865 sched: fix calc_delta_asym, #2 --- diff --git a/kernel/sched.c b/kernel/sched.c index 21f7da9..7afb0fc 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1244,9 +1244,6 @@ static void resched_task(struct task_struct *p) */ #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) -/* - * delta *= weight / lw - */ static unsigned long calc_delta_mine(unsigned long delta_exec, unsigned long weight, struct load_weight *lw) @@ -1274,6 +1271,12 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); } +static inline unsigned long +calc_delta_fair(unsigned long delta_exec, struct load_weight *lw) +{ + return calc_delta_mine(delta_exec, NICE_0_LOAD, lw); +} + static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index cf2cd6c..593af05 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -334,34 +334,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* - * delta *= w / rw - */ -static inline unsigned long -calc_delta_weight(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - se->load.weight, &cfs_rq_of(se)->load); - } - - return delta; -} - -/* - * delta *= rw / w - */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - cfs_rq_of(se)->load.weight, &se->load); - } - - return delta; -} - -/* * The idea is to set a period in which each task runs once. * * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch @@ -390,80 +362,47 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return calc_delta_weight(__sched_period(cfs_rq->nr_running), se); + u64 slice = __sched_period(cfs_rq->nr_running); + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + slice *= se->load.weight; + do_div(slice, cfs_rq->load.weight); + } + + + return slice; } /* * We calculate the vruntime slice of a to be inserted task * - * vs = s*rw/w = p + * vs = s/w = p/rw */ static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se) { unsigned long nr_running = cfs_rq->nr_running; + unsigned long weight; + u64 vslice; if (!se->on_rq) nr_running++; - return __sched_period(nr_running); -} - -/* - * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in - * that it favours >=0 over <0. - * - * -20 | - * | - * 0 --------+------- - * .' - * 19 .' - * - */ -static unsigned long -calc_delta_asym(unsigned long delta, struct sched_entity *se) -{ - struct load_weight lw = { - .weight = NICE_0_LOAD, - .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT) - }; + vslice = __sched_period(nr_running); for_each_sched_entity(se) { - struct load_weight *se_lw = &se->load; - unsigned long rw = cfs_rq_of(se)->load.weight; - -#ifdef CONFIG_FAIR_SCHED_GROUP - struct cfs_rq *cfs_rq = se->my_q; - struct task_group *tg = NULL - - if (cfs_rq) - tg = cfs_rq->tg; - - if (tg && tg->shares < NICE_0_LOAD) { - /* - * scale shares to what it would have been had - * tg->weight been NICE_0_LOAD: - * - * weight = 1024 * shares / tg->weight - */ - lw.weight *= se->load.weight; - lw.weight /= tg->shares; - - lw.inv_weight = 0; - - se_lw = &lw; - rw += lw.weight - se->load.weight; - } else -#endif + cfs_rq = cfs_rq_of(se); - if (se->load.weight < NICE_0_LOAD) { - se_lw = &lw; - rw += NICE_0_LOAD - se->load.weight; - } + weight = cfs_rq->load.weight; + if (!se->on_rq) + weight += se->load.weight; - delta = calc_delta_mine(delta, rw, se_lw); + vslice *= NICE_0_LOAD; + do_div(vslice, weight); } - return delta; + return vslice; } /* @@ -480,7 +419,11 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); + delta_exec_weighted = delta_exec; + if (unlikely(curr->load.weight != NICE_0_LOAD)) { + delta_exec_weighted = calc_delta_fair(delta_exec_weighted, + &curr->load); + } curr->vruntime += delta_exec_weighted; } @@ -687,17 +630,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (!initial) { /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS)) { - unsigned long thresh = sysctl_sched_latency; - - /* - * convert the sleeper threshold into virtual time - */ - if (sched_feat(NORMALIZED_SLEEPER)) - thresh = calc_delta_fair(thresh, se); - - vruntime -= thresh; - } + if (sched_feat(NEW_FAIR_SLEEPERS)) + vruntime -= sysctl_sched_latency; /* ensure we never gain time by being placed backwards. */ vruntime = max_vruntime(se->vruntime, vruntime); @@ -1277,13 +1211,11 @@ static unsigned long wakeup_gran(struct sched_entity *se) unsigned long gran = sysctl_sched_wakeup_granularity; /* - * More easily preempt - nice tasks, while not making it harder for - * + nice tasks. + * More easily preempt - nice tasks, while not making + * it harder for + nice tasks. */ - if (sched_feat(ASYM_GRAN)) - gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se); - else - gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se); + if (unlikely(se->load.weight > NICE_0_LOAD)) + gran = calc_delta_fair(gran, &se->load); return gran; } diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 862b06b..6cd8734 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -1,5 +1,4 @@ SCHED_FEAT(NEW_FAIR_SLEEPERS, 1) -SCHED_FEAT(NORMALIZED_SLEEPER, 1) SCHED_FEAT(WAKEUP_PREEMPT, 1) SCHED_FEAT(START_DEBIT, 1) SCHED_FEAT(AFFINE_WAKEUPS, 1) @@ -7,7 +6,6 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1) SCHED_FEAT(SYNC_WAKEUPS, 1) SCHED_FEAT(HRTICK, 1) SCHED_FEAT(DOUBLE_TICK, 0) -SCHED_FEAT(ASYM_GRAN, 1) SCHED_FEAT(LB_BIAS, 0) SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/