From 4564c527a6b89b6640ef3fed84fea072a6109aa4 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 8 Dec 2016 17:56:54 +0100 Subject: [PATCH] sched/core: Use load_avg for selecting idlest group find_idlest_group() only compares the runnable_load_avg when looking for the least loaded group. But on fork intensive use case like hackbench where tasks blocked quickly after the fork, this can lead to selecting the same CPU instead of other CPUs, which have similar runnable load but a lower load_avg. When the runnable_load_avg of 2 CPUs are close, we now take into account the amount of blocked load as a 2nd selection factor. There is now 3 zones for the runnable_load of the rq: - [0 .. (runnable_load - imbalance)]: Select the new rq which has significantly less runnable_load - [(runnable_load - imbalance) .. (runnable_load + imbalance)]: The runnable loads are close so we use load_avg to chose between the 2 rq - [(runnable_load + imbalance) .. ULONG_MAX]: Keep the current rq which has significantly less runnable_load The scale factor that is currently used for comparing runnable_load, doesn't work well with small value. As an example, the use of a scaling factor fails as soon as this_runnable_load == 0 because we always select local rq even if min_runnable_load is only 1, which doesn't really make sense because they are just the same. So instead of scaling factor, we use an absolute margin for runnable_load to detect CPUs with similar runnable_load and we keep using scaling factor for blocked load. For use case like hackbench, this enable the scheduler to select different CPUs during the fork sequence and to spread tasks across the system. Tests have been done on a Hikey board (ARM based octo cores) for several kernel. The result below gives min, max, avg and stdev values of 18 runs with each configuration. The patches depend on the "no missing update_rq_clock()" work. hackbench -P -g 1 ea86cb4b7621 7dc603c9028e v4.8 v4.8+patches min 0.049 0.050 0.051 0,048 avg 0.057 0.057(0%) 0.057(0%) 0,055(+5%) max 0.066 0.068 0.070 0,063 stdev +/-9% +/-9% +/-8% +/-9% More performance numbers here: https://lkml.kernel.org/r/20161203214707.GI20785@codeblueprint.co.uk Orabug: 25862897 Tested-by: Matt Fleming Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Matt Fleming Cc: Linus Torvalds Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dietmar.eggemann@arm.com Cc: kernellwp@gmail.com Cc: umgwanakikbuti@gmail.com Cc: yuyang.du@intel.comc Link: http://lkml.kernel.org/r/1481216215-24651-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar (cherry picked from commit 6b94780e45c17b83e3e75f8aaca5a328db583c74) Conflicts: kernel/sched/fair.c Signed-off-by: subhra mazumdar Reviewed-by: Atish Patra --- kernel/sched/fair.c | 161 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 150 insertions(+), 11 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3a7f8a4e66de..d826ff7ef349 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4671,6 +4671,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) return 1; } +static inline int task_util(struct task_struct *p); +static int cpu_util_wake(int cpu, struct task_struct *p); + +static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +{ + return capacity_orig_of(cpu) - cpu_util_wake(cpu, p); +} + /* * find_idlest_group finds and returns the least busy CPU group within the * domain. @@ -4680,15 +4688,21 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu, int sd_flag) { struct sched_group *idlest = NULL, *group = sd->groups; - unsigned long min_load = ULONG_MAX, this_load = 0; + struct sched_group *most_spare_sg = NULL; + unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0; + unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0; + unsigned long most_spare = 0, this_spare = 0; int load_idx = sd->forkexec_idx; - int imbalance = 100 + (sd->imbalance_pct-100)/2; + int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; + unsigned long imbalance = scale_load_down(NICE_0_LOAD) * + (sd->imbalance_pct-100) / 100; if (sd_flag & SD_BALANCE_WAKE) load_idx = sd->wake_idx; do { - unsigned long load, avg_load; + unsigned long load, avg_load, runnable_load; + unsigned long spare_cap, max_spare_cap; int local_group; int i; @@ -4700,8 +4714,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(group)); - /* Tally up the load of all CPUs in the group */ + /* + * Tally up the load of all CPUs in the group and find + * the group containing the CPU with most spare capacity. + */ avg_load = 0; + runnable_load = 0; + max_spare_cap = 0; for_each_cpu(i, sched_group_cpus(group)) { /* Bias balancing toward cpus of our domain */ @@ -4710,22 +4729,84 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, else load = target_load(i, load_idx); - avg_load += load; + runnable_load += load; + + avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); + + spare_cap = capacity_spare_wake(i, p); + + if (spare_cap > max_spare_cap) + max_spare_cap = spare_cap; } /* Adjust by relative CPU capacity of the group */ - avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / + group->sgc->capacity; + runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) / + group->sgc->capacity; if (local_group) { - this_load = avg_load; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; + this_runnable_load = runnable_load; + this_avg_load = avg_load; + this_spare = max_spare_cap; + } else { + if (min_runnable_load > (runnable_load + imbalance)) { + /* + * The runnable load is significantly smaller + * so we can pick this new cpu + */ + min_runnable_load = runnable_load; + min_avg_load = avg_load; + idlest = group; + } else if ((runnable_load < (min_runnable_load + imbalance)) && + (100*min_avg_load > imbalance_scale*avg_load)) { + /* + * The runnable loads are close so take the + * blocked load into account through avg_load. + */ + min_avg_load = avg_load; + idlest = group; + } + + if (most_spare < max_spare_cap) { + most_spare = max_spare_cap; + most_spare_sg = group; + } } } while (group = group->next, group != sd->groups); - if (!idlest || 100*this_load < imbalance*min_load) + /* + * The cross-over point between using spare capacity or least load + * is too conservative for high utilization tasks on partially + * utilized systems if we require spare_capacity > task_util(p), + * so we allow for some task stuffing by using + * spare_capacity > task_util(p)/2. + * + * Spare capacity can't be used for fork because the utilization has + * not been set yet, we must first select a rq to compute the initial + * utilization. + */ + if (sd_flag & SD_BALANCE_FORK) + goto skip_spare; + + if (this_spare > task_util(p) / 2 && + imbalance_scale*this_spare > 100*most_spare) + return NULL; + + if (most_spare > task_util(p) / 2) + return most_spare_sg; + +skip_spare: + if (!idlest) + return NULL; + + if (min_runnable_load > (this_runnable_load + imbalance)) return NULL; + + if ((this_runnable_load < (min_runnable_load + imbalance)) && + (100*this_avg_load < imbalance_scale*min_avg_load)) + return NULL; + return idlest; } @@ -4822,6 +4903,64 @@ next: done: return target; } + +/* + * cpu_util returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the utilization with the capacity of the CPU that is available for + * CFS task (ie cpu_capacity). + * + * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the + * recent utilization of currently non-runnable tasks on a CPU. It represents + * the amount of utilization of a CPU in the range [0..capacity_orig] where + * capacity_orig is the cpu_capacity available at the highest frequency + * (arch_scale_freq_capacity()). + * The utilization of a CPU converges towards a sum equal to or less than the + * current capacity (capacity_curr <= capacity_orig) of the CPU because it is + * the running time on this CPU scaled by capacity_curr. + * + * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even + * higher than capacity_orig because of unfortunate rounding in + * cfs.avg.util_avg or just after migrating tasks and new task wakeups until + * the average stabilizes with the new running time. We need to check that the + * utilization stays within the range of [0..capacity_orig] and cap it if + * necessary. Without utilization capping, a group could be seen as overloaded + * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of + * available capacity. We allow utilization to overshoot capacity_curr (but not + * capacity_orig) as it useful for predicting the capacity required after task + * migrations (scheduler-driven DVFS). + */ +static int cpu_util(int cpu) +{ + unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg; + unsigned long capacity = capacity_orig_of(cpu); + + return (util >= capacity) ? capacity : util; +} + +static inline int task_util(struct task_struct *p) +{ + return p->se.avg.util_avg; +} + +/* + * cpu_util_wake: Compute cpu utilization with any contributions from + * the waking task p removed. + */ +static int cpu_util_wake(int cpu, struct task_struct *p) +{ + unsigned long util, capacity; + + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !p->se.avg.last_update_time) + return cpu_util(cpu); + + capacity = capacity_orig_of(cpu); + util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0); + + return (util >= capacity) ? capacity : util; +} + /* * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS * tasks. The unit of the return value must be the one of capacity so we can -- 2.50.1