sched/fair: Propagate an effective runnable_load_avg

The load balancer uses runnable_load_avg as load indicator. For
!cgroup this is:

  runnable_load_avg = \Sum se->avg.load_avg ; where se->on_rq

That is, a direct sum of all runnable tasks on that runqueue. As
opposed to load_avg, which is a sum of all tasks on the runqueue,
which includes a blocked component.

However, in the cgroup case, this comes apart since the group entities
are always runnable, even if most of their constituent entities are
blocked.

Therefore introduce a runnable_weight which for task entities is the
same as the regular weight, but for group entities is a fraction of
the entity weight and represents the runnable part of the group
runqueue.

Then propagate this load through the PELT hierarchy to arrive at an
effective runnable load avgerage -- which we should not confuse with
the canonical runnable load average.

Suggested-by: Tejun Heo <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: Peter Zijlstra

include/linux/sched.h

@@ -331,9 +331,11 @@ struct load_weight {
 struct sched_avg {
 	u64				last_update_time;
 	u64				load_sum;
+	u64				runnable_load_sum;
 	u32				util_sum;
 	u32				period_contrib;
 	unsigned long			load_avg;
+	unsigned long			runnable_load_avg;
 	unsigned long			util_avg;
 };
 
@@ -376,6 +378,7 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
+	unsigned long			runnable_weight;
 	struct rb_node			run_node;
 	struct list_head		group_node;
 	unsigned int			on_rq;

kernel/sched/debug.c

@@ -441,9 +441,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 		P_SCHEDSTAT(se->statistics.wait_count);
 	}
 	P(se->load.weight);
+	P(se->runnable_weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
+	P(se->avg.runnable_load_avg);
 #endif
 
 #undef PN_SCHEDSTAT
@@ -558,10 +560,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
+	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight);
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
 			cfs_rq->avg.load_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_load_avg",
-			cfs_rq->runnable_load_avg);
+			cfs_rq->avg.runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.load_avg",
@@ -1006,10 +1009,13 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		   "nr_involuntary_switches", (long long)p->nivcsw);
 
 	P(se.load.weight);
+	P(se.runnable_weight);
 #ifdef CONFIG_SMP
 	P(se.avg.load_sum);
+	P(se.avg.runnable_load_sum);
 	P(se.avg.util_sum);
 	P(se.avg.load_avg);
+	P(se.avg.runnable_load_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 #endif