From 237ff0550a99ada0cffde12845e13e52e69143a1 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Sat, 9 May 2015 16:49:57 +0100 Subject: [PATCH 59/92] sched: Add over-utilization/tipping point indicator Energy-aware scheduling is only meant to be active while the system is _not_ over-utilized. That is, there are spare cycles available to shift tasks around based on their actual utilization to get a more energy-efficient task distribution without depriving any tasks. When above the tipping point task placement is done the traditional way based on load_avg, spreading the tasks across as many cpus as possible based on priority scaled load to preserve smp_nice. Below the tipping point we want to use util_avg instead. We need to define a criteria for when we make the switch. The util_avg for each cpu converges towards 100% (1024) regardless of how many task additional task we may put on it. If we define over-utilized as: sum_{cpus}(rq.cfs.avg.util_avg) + margin > sum_{cpus}(rq.capacity) some individual cpus may be over-utilized running multiple tasks even when the above condition is false. That should be okay as long as we try to spread the tasks out to avoid per-cpu over-utilization as much as possible and if all tasks have the _same_ priority. If the latter isn't true, we have to consider priority to preserve smp_nice. For example, we could have n_cpus nice=-10 util_avg=55% tasks and n_cpus/2 nice=0 util_avg=60% tasks. Balancing based on util_avg we are likely to end up with nice=-10 tasks sharing cpus and nice=0 tasks getting their own as we 1.5*n_cpus tasks in total and 55%+55% is less over-utilized than 55%+60% for those cpus that have to be shared. The system utilization is only 85% of the system capacity, but we are breaking smp_nice. To be sure not to break smp_nice, we have defined over-utilization conservatively as when any cpu in the system is fully utilized at it's highest frequency instead: cpu_rq(any).cfs.avg.util_avg + margin > cpu_rq(any).capacity IOW, as soon as one cpu is (nearly) 100% utilized, we switch to load_avg to factor in priority to preserve smp_nice. With this definition, we can skip periodic load-balance as no cpu has an always-running task when the system is not over-utilized. All tasks will be periodic and we can balance them at wake-up. This conservative condition does however mean that some scenarios that could benefit from energy-aware decisions even if one cpu is fully utilized would not get those benefits. For system where some cpus might have reduced capacity on some cpus (RT-pressure and/or big.LITTLE), we want periodic load-balance checks as soon a just a single cpu is fully utilized as it might one of those with reduced capacity and in that case we want to migrate it. cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Morten Rasmussen (cherry picked from commit e402a7e2f2a45377f32b2925197a747f04ca1668) Signed-off-by: Gaku Inami --- kernel/sched/fair.c | 31 +++++++++++++++++++++++++------ kernel/sched/sched.h | 3 +++ 2 files changed, 28 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5e13787..db732bd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4715,6 +4715,8 @@ static inline void hrtick_update(struct rq *rq) } #endif +static bool cpu_overutilized(int cpu); + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -4725,6 +4727,7 @@ static inline void hrtick_update(struct rq *rq) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int task_new = !(flags & ENQUEUE_WAKEUP); /* * If in_iowait is set, the code below may not trigger any cpufreq @@ -4764,9 +4767,12 @@ static inline void hrtick_update(struct rq *rq) update_cfs_shares(cfs_rq); } - if (!se) + if (!se) { add_nr_running(rq, 1); - + if (!task_new && !rq->rd->overutilized && + cpu_overutilized(rq->cpu)) + rq->rd->overutilized = true; + } hrtick_update(rq); } @@ -7578,11 +7584,12 @@ group_type group_classify(struct sched_group *group, * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. * @overload: Indicate more than one runnable task for any CPU. + * @overutilized: Indicate overutilization for any CPU. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, int local_group, struct sg_lb_stats *sgs, - bool *overload) + bool *overload, bool *overutilized) { unsigned long load; int i, nr_running; @@ -7616,6 +7623,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, */ if (!nr_running && idle_cpu(i)) sgs->idle_cpus++; + + if (cpu_overutilized(i)) + *overutilized = true; } /* Adjust by relative CPU capacity of the group */ @@ -7744,7 +7754,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats tmp_sgs; int load_idx, prefer_sibling = 0; - bool overload = false; + bool overload = false, overutilized = false; if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; @@ -7766,7 +7776,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd } update_sg_lb_stats(env, sg, load_idx, local_group, sgs, - &overload); + &overload, &overutilized); if (local_group) goto next_group; @@ -7810,8 +7820,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd /* update overload indicator if we are at root domain */ if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; - } + /* Update over-utilization (tipping point, U >= 0) indicator */ + if (env->dst_rq->rd->overutilized != overutilized) + env->dst_rq->rd->overutilized = overutilized; + } else { + if (!env->dst_rq->rd->overutilized && overutilized) + env->dst_rq->rd->overutilized = true; + } } /** @@ -9192,6 +9208,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + + if (!rq->rd->overutilized && cpu_overutilized(task_cpu(curr))) + rq->rd->overutilized = true; } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b24cefa..fa98ab3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -563,6 +563,9 @@ struct root_domain { /* Indicate more than one runnable task for any CPU */ bool overload; + /* Indicate one or more cpus over-utilized (tipping point) */ + bool overutilized; + /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). -- 1.9.1