Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758907AbZCYJPl (ORCPT ); Wed, 25 Mar 2009 05:15:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757932AbZCYJOO (ORCPT ); Wed, 25 Mar 2009 05:14:14 -0400 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:41264 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758287AbZCYJOL (ORCPT ); Wed, 25 Mar 2009 05:14:11 -0400 From: Gautham R Shenoy Subject: [RFC PATCH 06/11] sched: Create a helper function to calculate sched_domain stats for fbg() To: "Ingo Molnar" , Peter Zijlstra , "Vaidyanathan Srinivasan" Cc: linux-kernel@vger.kernel.org, Suresh Siddha , "Balbir Singh" , Nick Piggin , "Dhaval Giani" , Bharata B Rao , Gautham R Shenoy Date: Wed, 25 Mar 2009 14:44:01 +0530 Message-ID: <20090325091401.13992.88737.stgit@sofia.in.ibm.com> In-Reply-To: <20090325091239.13992.96090.stgit@sofia.in.ibm.com> References: <20090325091239.13992.96090.stgit@sofia.in.ibm.com> User-Agent: StGIT/0.14.2 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7238 Lines: 203 Create a helper function named update_sd_lb_stats() to update the various sched_domain related statistics in find_busiest_group(). With this we would have moved all the statistics computation out of find_busiest_group(). Credit: Vaidyanathan Srinivasan Signed-off-by: Gautham R Shenoy --- kernel/sched.c | 117 +++++++++++++++++++++++++++++++++++--------------------- 1 files changed, 73 insertions(+), 44 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index c1b92da..5e01162 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3261,32 +3261,33 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu, sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; } -/******* find_busiest_group() helpers end here *********************/ -/* - * find_busiest_group finds and returns the busiest CPU group within the - * domain. It calculates and returns the amount of weighted load which - * should be moved to restore balance via the imbalance parameter. +/** + * update_sd_lb_stats - Update sched_group's statistics for load balancing. + * @sd: sched_domain whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @sd_idle: Idle status of the sched_domain containing group. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sds: variable to hold the statistics for this sched_domain. */ -static struct sched_group * -find_busiest_group(struct sched_domain *sd, int this_cpu, - unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const struct cpumask *cpus, int *balance) +static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, + enum cpu_idle_type idle, int *sd_idle, + const struct cpumask *cpus, int *balance, + struct sd_lb_stats *sds) { - struct sd_lb_stats sds; struct sched_group *group = sd->groups; - unsigned long max_pull; + struct sg_lb_stats sgs; int load_idx; - memset(&sds, 0, sizeof(sds)); #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - sds.power_savings_balance = 1; - sds.min_nr_running = ULONG_MAX; + sds->power_savings_balance = 1; + sds->min_nr_running = ULONG_MAX; #endif load_idx = get_sd_load_idx(sd, idle); do { - struct sg_lb_stats sgs; int local_group; local_group = cpumask_test_cpu(this_cpu, @@ -3295,25 +3296,25 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle, local_group, cpus, balance, &sgs); - if (balance && !(*balance)) - goto ret; + if (local_group && balance && !(*balance)) + return; - sds.total_load += sgs.group_load; - sds.total_pwr += group->__cpu_power; + sds->total_load += sgs.group_load; + sds->total_pwr += group->__cpu_power; if (local_group) { - sds.this_load = sgs.avg_load; - sds.this = group; - sds.this_nr_running = sgs.sum_nr_running; - sds.this_load_per_task = sgs.sum_weighted_load; - } else if (sgs.avg_load > sds.max_load && + sds->this_load = sgs.avg_load; + sds->this = group; + sds->this_nr_running = sgs.sum_nr_running; + sds->this_load_per_task = sgs.sum_weighted_load; + } else if (sgs.avg_load > sds->max_load && (sgs.sum_nr_running > sgs.group_capacity || sgs.group_imb)) { - sds.max_load = sgs.avg_load; - sds.busiest = group; - sds.busiest_nr_running = sgs.sum_nr_running; - sds.busiest_load_per_task = sgs.sum_weighted_load; - sds.group_imb = sgs.group_imb; + sds->max_load = sgs.avg_load; + sds->busiest = group; + sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->group_imb = sgs.group_imb; } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -3330,15 +3331,15 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * no need to do power savings balance at this domain */ if (local_group && - (sds.this_nr_running >= sgs.group_capacity || - !sds.this_nr_running)) - sds.power_savings_balance = 0; + (sds->this_nr_running >= sgs.group_capacity || + !sds->this_nr_running)) + sds->power_savings_balance = 0; /* * If a group is already running at full capacity or idle, * don't include that group in power savings calculations */ - if (!sds.power_savings_balance || + if (!sds->power_savings_balance || sgs.sum_nr_running >= sgs.group_capacity || !sgs.sum_nr_running) goto group_next; @@ -3348,13 +3349,13 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * This is the group from where we need to pick up the load * for saving power */ - if ((sgs.sum_nr_running < sds.min_nr_running) || - (sgs.sum_nr_running == sds.min_nr_running && + if ((sgs.sum_nr_running < sds->min_nr_running) || + (sgs.sum_nr_running == sds->min_nr_running && group_first_cpu(group) > - group_first_cpu(sds.group_min))) { - sds.group_min = group; - sds.min_nr_running = sgs.sum_nr_running; - sds.min_load_per_task = sgs.sum_weighted_load / + group_first_cpu(sds->group_min))) { + sds->group_min = group; + sds->min_nr_running = sgs.sum_nr_running; + sds->min_load_per_task = sgs.sum_weighted_load / sgs.sum_nr_running; } @@ -3366,18 +3367,46 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (sgs.sum_nr_running > sgs.group_capacity - 1) goto group_next; - if (sgs.sum_nr_running > sds.leader_nr_running || - (sgs.sum_nr_running == sds.leader_nr_running && + if (sgs.sum_nr_running > sds->leader_nr_running || + (sgs.sum_nr_running == sds->leader_nr_running && group_first_cpu(group) < - group_first_cpu(sds.group_leader))) { - sds.group_leader = group; - sds.leader_nr_running = sgs.sum_nr_running; + group_first_cpu(sds->group_leader))) { + sds->group_leader = group; + sds->leader_nr_running = sgs.sum_nr_running; } group_next: #endif group = group->next; } while (group != sd->groups); +} +/******* find_busiest_group() helpers end here *********************/ + +/* + * find_busiest_group finds and returns the busiest CPU group within the + * domain. It calculates and returns the amount of weighted load which + * should be moved to restore balance via the imbalance parameter. + */ +static struct sched_group * +find_busiest_group(struct sched_domain *sd, int this_cpu, + unsigned long *imbalance, enum cpu_idle_type idle, + int *sd_idle, const struct cpumask *cpus, int *balance) +{ + struct sd_lb_stats sds; + unsigned long max_pull; + + memset(&sds, 0, sizeof(sds)); + + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, + balance, &sds); + + if (balance && !(*balance)) + goto ret; + if (!sds.busiest || sds.this_load >= sds.max_load || sds.busiest_nr_running == 0) goto out_balanced; -- 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/