sched: update shares on wakeup

We found that the affine wakeup code needs rather accurate load figures
to be effective. The trouble is that updating the load figures is fairly
expensive with group scheduling. Therefore ratelimit the updating.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/sched.h

@@ -783,6 +783,8 @@ struct sched_domain {
 	unsigned int balance_interval;	/* initialise to 1. units in ms. */
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
+	u64 last_update;
+
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
@@ -1605,6 +1607,7 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_shares_ratelimit;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
 		struct file *file, void __user *buffer, size_t *length,

kernel/sched.c

@@ -777,6 +777,12 @@ late_initcall(sched_init_debug);
  */
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
+/*
+ * ratelimit for updating the group shares.
+ * default: 0.5ms
+ */
+const_debug unsigned int sysctl_sched_shares_ratelimit = 500000;
+
 /*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
@@ -1590,7 +1596,13 @@ tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
 
 static void update_shares(struct sched_domain *sd)
 {
+	u64 now = cpu_clock(raw_smp_processor_id());
+	s64 elapsed = now - sd->last_update;
+
+	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
+		sd->last_update = now;
 		walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
+	}
 }
 
 static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
@@ -2199,6 +2211,22 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (!sched_feat(SYNC_WAKEUPS))
 		sync = 0;
 
+#ifdef CONFIG_SMP
+	if (sched_feat(LB_WAKEUP_UPDATE)) {
+		struct sched_domain *sd;
+
+		this_cpu = raw_smp_processor_id();
+		cpu = task_cpu(p);
+
+		for_each_domain(this_cpu, sd) {
+			if (cpu_isset(cpu, sd->span)) {
+				update_shares(sd);
+				break;
+			}
+		}
+	}
+#endif
+
 	smp_wmb();
 	rq = task_rq_lock(p, &flags);
 	old_state = p->state;

kernel/sched_features.h

@@ -9,3 +9,4 @@ SCHED_FEAT(HRTICK, 1)
 SCHED_FEAT(DOUBLE_TICK, 0)
 SCHED_FEAT(ASYM_GRAN, 1)
 SCHED_FEAT(LB_BIAS, 0)
+SCHED_FEAT(LB_WAKEUP_UPDATE, 1)

kernel/sysctl.c

@@ -264,6 +264,14 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_shares_ratelimit",
+		.data		= &sysctl_sched_shares_ratelimit,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_child_runs_first",