sched: incremental effective_load()

Increase the accuracy of the effective_load values.

Not only consider the current increment (as per the attempted wakeup), but
also consider the delta between when we last adjusted the shares and the
current situation.
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

kernel/sched.c

@@ -427,6 +427,11 @@ struct cfs_rq {
 	 * this cpu's part of tg->shares
 	 */
 	unsigned long shares;
+
+	/*
+	 * load.weight at the time we set shares
+	 */
+	unsigned long rq_weight;
 #endif
 #endif
 };
@@ -1527,6 +1532,7 @@ __update_group_shares_cpu(struct task_group *tg, int cpu,
 	 * record the actual number of shares, not the boosted amount.
 	 */
 	tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
+	tg->cfs_rq[cpu]->rq_weight = rq_weight;
 
 	if (shares < MIN_SHARES)
 		shares = MIN_SHARES;

kernel/sched_fair.c

@@ -1074,10 +1074,22 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 static const struct sched_class fair_sched_class;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static unsigned long effective_load(struct task_group *tg, int cpu,
-		unsigned long wl, unsigned long wg)
+static long effective_load(struct task_group *tg, int cpu,
+		long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
+	long more_w;
+
+	if (!tg->parent)
+		return wl;
+
+	/*
+	 * Instead of using this increment, also add the difference
+	 * between when the shares were last updated and now.
+	 */
+	more_w = se->my_q->load.weight - se->my_q->rq_weight;
+	wl += more_w;
+	wg += more_w;
 
 	for_each_sched_entity(se) {
 #define D(n) (likely(n) ? (n) : 1)
@@ -1086,7 +1098,7 @@ static unsigned long effective_load(struct task_group *tg, int cpu,
 
 		S = se->my_q->tg->shares;
 		s = se->my_q->shares;
-		rw = se->my_q->load.weight;
+		rw = se->my_q->rq_weight;
 
 		a = S*(rw + wl);
 		b = S*rw + s*wg;