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>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 21a4cda8c5ff3a9c696c28f7cfe0076488a15630..d6b6e59e63ebe7051565af1dcfba9e7f01de28db 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4160,6 +4160,8 @@ 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
@@ -4170,6 +4172,7 @@ 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);
 
        for_each_sched_entity(se) {
                if (se->on_rq)
@@ -4201,9 +4204,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                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);
 }
 
@@ -6672,11 +6678,12 @@ 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;
@@ -6706,6 +6713,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                sgs->sum_weighted_load += weighted_cpuload(i);
                if (idle_cpu(i))
                        sgs->idle_cpus++;
+
+               if (cpu_overutilized(i))
+                       *overutilized = true;
        }
 
        /* Adjust by relative CPU capacity of the group */
@@ -6811,7 +6821,7 @@ 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;
@@ -6833,7 +6843,7 @@ 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;
@@ -6877,8 +6887,14 @@ 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;
+       }
 }
 
 /**
@@ -8271,6 +8287,9 @@ 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 f4b2bcb017a30bc2826b81bc3cf5ab66979904c8..60a6cbc1eb7a18dc0c2e71d4f30a523bc558850b 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -528,6 +528,9 @@ 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).