sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage

[cascardo/linux.git] / kernel / sched / fair.c

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 10f84c3..471193b 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4781,6 +4781,33 @@ next:
 done:
        return target;
 }
+/*
+ * 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
+ * compare the usage with the capacity of the CPU that is available for CFS
+ * task (ie cpu_capacity).
+ * cfs.utilization_load_avg is the sum of running time of runnable tasks on a
+ * CPU. It represents the amount of utilization of a CPU in the range
+ * [0..SCHED_LOAD_SCALE].  The usage of a CPU can't be higher than the full
+ * capacity of the CPU because it's about the running time on this CPU.
+ * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE
+ * because of unfortunate rounding in avg_period and running_load_avg or just
+ * after migrating tasks until the average stabilizes with the new running
+ * time. So we need to check that the usage stays into the range
+ * [0..cpu_capacity_orig] and cap if necessary.
+ * Without capping the usage, a group could be seen as overloaded (CPU0 usage
+ * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ */
+static int get_cpu_usage(int cpu)
+{
+       unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg;
+       unsigned long capacity = capacity_orig_of(cpu);
+
+       if (usage >= SCHED_LOAD_SCALE)
+               return capacity;
+
+       return (usage * capacity) >> SCHED_LOAD_SHIFT;
+}
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
@@ -5907,6 +5934,7 @@ struct sg_lb_stats {
        unsigned long sum_weighted_load; /* Weighted load of group's tasks */
        unsigned long load_per_task;
        unsigned long group_capacity;
+       unsigned long group_usage; /* Total usage of the group */
        unsigned int sum_nr_running; /* Nr tasks running in the group */
        unsigned int group_capacity_factor;
        unsigned int idle_cpus;
@@ -6255,6 +6283,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                        load = source_load(i, load_idx);
 
                sgs->group_load += load;
+               sgs->group_usage += get_cpu_usage(i);
                sgs->sum_nr_running += rq->cfs.h_nr_running;
 
                if (rq->nr_running > 1)