From a08906f651100da2a67343df1036aea7bb4574bd Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 30 Jul 2015 16:53:30 +0100 Subject: [PATCH] sched: EAS & 'single cpu per cluster'/cpu hotplug interoperability For Energy-Aware Scheduling (EAS) to work properly, even in the case that there is only one cpu per cluster or that cpus are hot-plugged out, the Energy Model (EM) data on all energy-aware sched domains (sd) has to be present for all online cpus. Mainline sd hierarchy setup code will remove sd's which are not useful for task scheduling e.g. in the following situations: 1. Only 1 cpu is/remains in one cluster of a multi cluster system. This remaining cpu only has DIE and no MC sd. 2. A complete cluster in a two cluster system is hot-plugged out. The cpus of the remaining cluster only have MC and no DIE sd. To make sure that all online cpus keep all their energy-aware sd's, the sd degenerate functionality has been changed to not free a sd if its first sched group (sg) contains EM data in case: 1. There is only 1 cpu left in the sd. 2. There have to be at least 2 sg's if certain sd flags are set. Instead of freeing such a sd it now clears only its SD_LOAD_BALANCE flag. This will make sure that the EAS functionality will always see all energy-aware sd's for all online cpus. It will introduce a tiny performance degradation for operations on affected cpus since the hot-path macro for_each_domain() has to deal with sd's not contributing to task scheduling at all now. In most cases the exisiting code makes sure that task scheduling is not invoked on a sd with !SD_LOAD_BALANCE. However, a small change is necessary in update_sd_lb_stats() to make sure that sd->parent is only initialized to !NULL in case the parent sd contains more than 1 sg. The handling of newidle decay values before the SD_LOAD_BALANCE check in rebalance_domains() stays unchanged. Test (w/ CONFIG_SCHED_DEBUG): JUNO r0 default system: $ cat /proc/cpuinfo | grep "^CPU part" CPU part : 0xd03 CPU part : 0xd07 CPU part : 0xd07 CPU part : 0xd03 CPU part : 0xd03 CPU part : 0xd03 SD names and flags: $ cat /proc/sys/kernel/sched_domain/cpu*/domain*/name MC DIE MC DIE MC DIE MC DIE MC DIE MC DIE $ printf "%x\n" `cat /proc/sys/kernel/sched_domain/cpu*/domain*/flags` 832f 102f 832f 102f 832f 102f 832f 102f 832f 102f 832f 102f Test 1: Hotplug-out one A57 (CPU part 0xd07) cpu: $ echo 0 > /sys/devices/system/cpu/cpu1/online $ cat /proc/cpuinfo | grep "^CPU part" CPU part : 0xd03 CPU part : 0xd07 CPU part : 0xd03 CPU part : 0xd03 CPU part : 0xd03 SD names and flags for remaining A57 (cpu2) cpu: $ cat /proc/sys/kernel/sched_domain/cpu2/domain*/name MC DIE $ printf "%x\n" `cat /proc/sys/kernel/sched_domain/cpu2/domain*/flags` 832e <-- MC SD with !SD_LOAD_BALANCE 102f Test 2: Hotplug-out the entire A57 cluster: $ echo 0 > /sys/devices/system/cpu/cpu1/online $ echo 0 > /sys/devices/system/cpu/cpu2/online $ cat /proc/cpuinfo | grep "^CPU part" CPU part : 0xd03 CPU part : 0xd03 CPU part : 0xd03 CPU part : 0xd03 SD names and flags for the remaining A53 (CPU part 0xd03) cluster: $ cat /proc/sys/kernel/sched_domain/cpu*/domain*/name MC DIE MC DIE MC DIE MC DIE $ printf "%x\n" `cat /proc/sys/kernel/sched_domain/cpu*/domain*/flags` 832f 102e <-- DIE SD with !SD_LOAD_BALANCE 832f 102e 832f 102e 832f 102e Change-Id: If24aa2b2628f334abbf0207d39e2a86168d9d673 Signed-off-by: Dietmar Eggemann --- kernel/sched/core.c | 17 ++++++++++------- kernel/sched/fair.c | 7 +++++-- 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index defc88cda733..da44d13f2439 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5934,9 +5934,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!(sd->flags & SD_LOAD_BALANCE)) { printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); return -1; } @@ -6029,8 +6026,12 @@ static inline bool sched_debug(void) static int sd_degenerate(struct sched_domain *sd) { - if (cpumask_weight(sched_domain_span(sd)) == 1) - return 1; + if (cpumask_weight(sched_domain_span(sd)) == 1) { + if (sd->groups->sge) + sd->flags &= ~SD_LOAD_BALANCE; + else + return 1; + } /* Following flags need at least 2 groups */ if (sd->flags & (SD_LOAD_BALANCE | @@ -6076,6 +6077,10 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_PREFER_SIBLING | SD_SHARE_POWERDOMAIN | SD_SHARE_CAP_STATES); + if (parent->groups->sge) { + parent->flags &= ~SD_LOAD_BALANCE; + return 0; + } if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -7353,8 +7358,6 @@ static int build_sched_domains(const struct cpumask *cpu_map, *per_cpu_ptr(d.sd, i) = sd; if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) sd->flags |= SD_OVERLAP; - if (cpumask_equal(cpu_map, sched_domain_span(sd))) - break; } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d2479dc60e99..c84e15e3cd56 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7971,6 +7971,9 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) } #endif /* CONFIG_NUMA_BALANCING */ +#define lb_sd_parent(sd) \ + (sd->parent && sd->parent->groups != sd->parent->groups->next) + /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. @@ -8053,7 +8056,7 @@ next_group: env->src_grp_nr_running = sds->busiest_stat.sum_nr_running; - if (!env->sd->parent) { + if (!lb_sd_parent(env->sd)) { /* update overload indicator if we are at root domain */ if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; @@ -8561,7 +8564,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, int *continue_balancing) { int ld_moved, cur_ld_moved, active_balance = 0; - struct sched_domain *sd_parent = sd->parent; + struct sched_domain *sd_parent = lb_sd_parent(sd) ? sd->parent : NULL; struct sched_group *group; struct rq *busiest; unsigned long flags; -- 2.34.1