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 <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 09518c387c0e8713984c6458a9617f1d7e5dab13..39b012641cb74fbf1abb48d262cc162e5b6bfb69 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5153,6 +5153,8 @@ 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
@@ -5163,6 +5165,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
        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
@@ -5202,9 +5205,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                update_cfs_group(se);
        }
 
-       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);
 }
 
@@ -8063,11 +8069,12 @@ 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;
@@ -8105,6 +8112,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
                    !sgs->group_misfit_task && rq->misfit_task)
                        sgs->group_misfit_task = capacity_of(i);
+
+               if (cpu_overutilized(i))
+                       *overutilized = true;
        }
 
        /* Adjust by relative CPU capacity of the group */
@@ -8261,7 +8271,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
        struct sg_lb_stats *local = &sds->local_stat;
        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;
@@ -8306,7 +8316,7 @@ 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;
@@ -8351,6 +8361,13 @@ next_group:
                /* 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;
        }
 }
 
@@ -9841,6 +9858,9 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
                task_tick_numa(rq, curr);
 
        rq->misfit_task = !task_fits_capacity(curr, capacity_of(rq->cpu));
+
+       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 0dab02acac26d58c75608556d1b4202b7325abfe..549cbda7bff910bb8737bc940a1ebe8bb2949e34 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -627,6 +627,9 @@ 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).