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 its
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 systems 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: Quentin Perret <quentin.perret@arm.com>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 976778dde0c759f878ae8637462d5b99e140cae3..e8724c85eca300ed7a36c3e60776ce6e44d1e225 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4977,6 +4977,24 @@ static inline void hrtick_update(struct rq *rq)
 }
 #endif
 
+#ifdef CONFIG_SMP
+static inline unsigned long cpu_util(int cpu);
+static unsigned long capacity_of(int cpu);
+
+static inline bool cpu_overutilized(int cpu)
+{
+       return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+static inline void update_overutilized_status(struct rq *rq)
+{
+       if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+               WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+}
+#else
+static inline void update_overutilized_status(struct rq *rq) { }
+#endif
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5034,8 +5052,17 @@ 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);
+               /*
+                * The utilization of a new task is 'wrong' so wait for it
+                * to build some utilization history before trying to detect
+                * the overutilized flag.
+                */
+               if (flags & ENQUEUE_WAKEUP)
+                       update_overutilized_status(rq);
+
+       }
 
        hrtick_update(rq);
 }
@@ -7765,6 +7792,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                if (nr_running > 1)
                        *sg_status |= SG_OVERLOAD;
 
+               if (cpu_overutilized(i))
+                       *sg_status |= SG_OVERUTILIZED;
+
 #ifdef CONFIG_NUMA_BALANCING
                sgs->nr_numa_running += rq->nr_numa_running;
                sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -7974,8 +8004,15 @@ next_group:
                env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 
        if (!env->sd->parent) {
+               struct root_domain *rd = env->dst_rq->rd;
+
                /* update overload indicator if we are at root domain */
-               env->dst_rq->rd->overload = sg_status & SG_OVERLOAD;
+               rd->overload = sg_status & SG_OVERLOAD;
+
+               /* Update over-utilization (tipping point, U >= 0) indicator */
+               WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+       } else if (sg_status & SG_OVERUTILIZED) {
+               WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
        }
 }
 
@@ -8195,6 +8232,11 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
         * this level.
         */
        update_sd_lb_stats(env, &sds);
+
+       if (rd_freq_domain(env->dst_rq->rd) &&
+                               !READ_ONCE(env->dst_rq->rd->overutilized))
+               goto out_balanced;
+
        local = &sds.local_stat;
        busiest = &sds.busiest_stat;
 
@@ -9552,6 +9594,8 @@ 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);
+
+       update_overutilized_status(task_rq(curr));
 }
 
 /*

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 95c7701a76d293f2fedc7341bf61ac0faa09c076..f4f1f4c7ee6676074b8cfd2272b97702bf86957c 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -709,6 +709,7 @@ struct freq_domain {
 
 /* Scheduling group status flags */
 #define SG_OVERLOAD            0x1 /* More than one runnable task on a CPU. */
+#define SG_OVERUTILIZED                0x2 /* One or more CPUs are over-utilized. */
 
 /*
  * We add the notion of a root-domain which will be used to define per-domain
@@ -728,6 +729,9 @@ struct root_domain {
        /* Indicate more than one runnable task for any CPU */
        int                     overload;
 
+       /* Indicate one or more cpus over-utilized (tipping point) */
+       int                     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).