The scheduler tries to compute how many tasks a group of CPUs can handle by assuming that a task's load is SCHED_LOAD_SCALE and a CPU capacity is SCHED_CAPACITY_SCALE but the capacity_factor is hardly working for SMT system, it sometimes works for big cores but fails to do the right thing for little cores.
Below are two examples to illustrate the problem that this patch solves:
1 - capacity_factor makes the assumption that max capacity of a CPU is SCHED_CAPACITY_SCALE and the load of a thread is always is SCHED_LOAD_SCALE. It compares the output of these figures with the sum of nr_running to decide if a group is overloaded or not.
But if the default capacity of a CPU is less than SCHED_CAPACITY_SCALE (640 as an example), a group of 3 CPUS will have a max capacity_factor of 2 ( div_round_closest(3x640/1024) = 2) which means that it will be seen as overloaded if we have only one task per CPU.
2 - Then, if the default capacity of a CPU is greater than SCHED_CAPACITY_SCALE (1512 as an example), a group of 4 CPUs will have a capacity_factor of 4 (at max and thanks to the fix[0] for SMT system that prevent the apparition of ghost CPUs) but if one CPU is fully used by a rt task (and its capacity is reduced to nearly nothing), the capacity factor of the group will still be 4 (div_round_closest(3*1512/1024) = 5).
So, this patch tries to solve this issue by removing capacity_factor and replacing it with the 2 following metrics : -The available CPU's capacity for CFS tasks which is the already used by load_balance. -The usage of the CPU by the CFS tasks. For the latter, I have re-introduced the utilization_avg_contrib which is in the range [0..SCHED_CPU_LOAD] whatever the capacity of the CPU is.
This implementation of utilization_avg_contrib doesn't solve the scaling in-variance problem, so i have to scale the utilization with original capacity of the CPU in order to get the CPU usage and compare it with the capacity. Once the scaling invariance will have been added in utilization_avg_contrib, we will remove the scale of utilization_avg_contrib by cpu_capacity_orig in get_cpu_usage. But the scaling invariance will come in another patchset.
Finally, the sched_group->sched_group_capacity->capacity_orig has been removed because it's more used during load balance.
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org --- kernel/sched/core.c | 12 ----- kernel/sched/fair.c | 131 ++++++++++++++++++++------------------------------- kernel/sched/sched.h | 2 +- 3 files changed, 52 insertions(+), 93 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e20f203..c7c8ac4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5342,17 +5342,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; }
- /* - * Even though we initialize ->capacity to something semi-sane, - * we leave capacity_orig unset. This allows us to detect if - * domain iteration is still funny without causing /0 traps. - */ - if (!group->sgc->capacity_orig) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); - break; - } - if (!cpumask_weight(sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); @@ -5837,7 +5826,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->capacity_orig = sg->sgc->capacity;
/* * Make sure the first group of this domain contains the diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4097e3f..2ba278c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5676,11 +5676,10 @@ struct sg_lb_stats { unsigned long group_capacity; unsigned long group_usage; /* Total usage of the group */ unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; enum group_type group_type; - int group_has_free_capacity; + int group_out_of_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -5821,7 +5820,6 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) capacity >>= SCHED_CAPACITY_SHIFT;
cpu_rq(cpu)->cpu_capacity_orig = capacity; - sdg->sgc->capacity_orig = capacity;
if (sched_feat(ARCH_CAPACITY)) capacity *= arch_scale_freq_capacity(sd, cpu); @@ -5844,7 +5842,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long capacity, capacity_orig; + unsigned long capacity; unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval); @@ -5856,7 +5854,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) return; }
- capacity_orig = capacity = 0; + capacity = 0;
if (child->flags & SD_OVERLAP) { /* @@ -5876,19 +5874,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu) * Use capacity_of(), which is set irrespective of domains * in update_cpu_capacity(). * - * This avoids capacity/capacity_orig from being 0 and + * This avoids capacity from being 0 and * causing divide-by-zero issues on boot. - * - * Runtime updates will correct capacity_orig. */ if (unlikely(!rq->sd)) { - capacity_orig += capacity_orig_of(cpu); capacity += capacity_of(cpu); continue; }
sgc = rq->sd->groups->sgc; - capacity_orig += sgc->capacity_orig; capacity += sgc->capacity; } } else { @@ -5899,42 +5893,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
group = child->groups; do { - capacity_orig += group->sgc->capacity_orig; capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); }
- sdg->sgc->capacity_orig = capacity_orig; sdg->sgc->capacity = capacity; }
/* - * Try and fix up capacity for tiny siblings, this is needed when - * things like SD_ASYM_PACKING need f_b_g to select another sibling - * which on its own isn't powerful enough. - * - * See update_sd_pick_busiest() and check_asym_packing(). - */ -static inline int -fix_small_capacity(struct sched_domain *sd, struct sched_group *group) -{ - /* - * Only siblings can have significantly less than SCHED_CAPACITY_SCALE - */ - if (!(sd->flags & SD_SHARE_CPUCAPACITY)) - return 0; - - /* - * If ~90% of the cpu_capacity is still there, we're good. - */ - if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) - return 1; - - return 0; -} - -/* * Check whether the capacity of the rq has been noticeably reduced by side * activity. The imbalance_pct is used for the threshold. * Return true is the capacity is reduced @@ -5980,38 +5947,37 @@ static inline int sg_imbalanced(struct sched_group *group) return group->sgc->imbalance; }
-/* - * Compute the group capacity factor. - * - * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by - * first dividing out the smt factor and computing the actual number of cores - * and limit unit capacity with that. - */ -static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) +static inline int group_has_free_capacity(struct sg_lb_stats *sgs, + struct lb_env *env) { - unsigned int capacity_factor, smt, cpus; - unsigned int capacity, capacity_orig; + if ((sgs->group_capacity * 100) > + (sgs->group_usage * env->sd->imbalance_pct)) + return true;
- capacity = group->sgc->capacity; - capacity_orig = group->sgc->capacity_orig; - cpus = group->group_weight; + if (sgs->sum_nr_running < sgs->group_weight) + return true;
- /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ - smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); - capacity_factor = cpus / smt; /* cores */ + return false; +}
- capacity_factor = min_t(unsigned, - capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group); +static inline int group_is_overloaded(struct sg_lb_stats *sgs, + struct lb_env *env) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false;
- return capacity_factor; + if ((sgs->group_capacity * 100) < + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; }
static enum group_type -group_classify(struct sched_group *group, struct sg_lb_stats *sgs) +group_classify(struct sched_group *group, struct sg_lb_stats *sgs, + struct lb_env *env) { - if (sgs->sum_nr_running > sgs->group_capacity_factor) + if (group_is_overloaded(sgs, env)) return group_overloaded;
if (sg_imbalanced(group)) @@ -6072,11 +6038,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
sgs->group_weight = group->group_weight; - sgs->group_capacity_factor = sg_capacity_factor(env, group); - sgs->group_type = group_classify(group, sgs);
- if (sgs->group_capacity_factor > sgs->sum_nr_running) - sgs->group_has_free_capacity = 1; + sgs->group_type = group_classify(group, sgs, env); + + sgs->group_out_of_capacity = group_is_overloaded(sgs, env); }
/** @@ -6198,17 +6163,21 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
/* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity factor to one so that we'll try + * first, lower the sg capacity to one so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity_factor. The + * these excess tasks, i.e. group_capacity > 0. The * extra check prevents the case where you always pull from the * heaviest group when it is already under-utilized (possible * with a large weight task outweighs the tasks on the system). */ if (prefer_sibling && sds->local && - sds->local_stat.group_has_free_capacity) - sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); + group_has_free_capacity(&sds->local_stat, env)) { + if (sgs->sum_nr_running > 1) + sgs->group_out_of_capacity = 1; + sgs->group_capacity = min(sgs->group_capacity, + SCHED_CAPACITY_SCALE); + }
if (update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; @@ -6387,11 +6356,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (busiest->group_type == group_overloaded && local->group_type == group_overloaded) { - load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity_factor); - - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); - load_above_capacity /= busiest->group_capacity; + load_above_capacity = busiest->sum_nr_running * + SCHED_LOAD_SCALE; + if (load_above_capacity > busiest->group_capacity) + load_above_capacity -= busiest->group_capacity; + else + load_above_capacity = ~0UL; }
/* @@ -6454,6 +6424,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) local = &sds.local_stat; busiest = &sds.busiest_stat;
+ /* ASYM feature bypasses nice load balance check */ if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && check_asym_packing(env, &sds)) return sds.busiest; @@ -6474,8 +6445,9 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance;
/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && - !busiest->group_has_free_capacity) + if (env->idle == CPU_NEWLY_IDLE && + group_has_free_capacity(local, env) && + busiest->group_out_of_capacity) goto force_balance;
/* @@ -6533,7 +6505,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, int i;
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long capacity, capacity_factor, wl; + unsigned long capacity, wl; enum fbq_type rt;
rq = cpu_rq(i); @@ -6562,9 +6534,6 @@ static struct rq *find_busiest_queue(struct lb_env *env, continue;
capacity = capacity_of(i); - capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group);
wl = weighted_cpuload(i);
@@ -6572,7 +6541,9 @@ static struct rq *find_busiest_queue(struct lb_env *env, * When comparing with imbalance, use weighted_cpuload() * which is not scaled with the cpu capacity. */ - if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) + + if (rq->nr_running == 1 && wl > env->imbalance && + !check_cpu_capacity(rq, env->sd)) continue;
/* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3ccb136..8d224c5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -750,7 +750,7 @@ struct sched_group_capacity { * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity * for a single CPU. */ - unsigned int capacity, capacity_orig; + unsigned int capacity; unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ /*