[RFCv3 PATCH 40/48] sched: Introduce energy awareness into update_sd_lb_stats

[Morten Rasmussen]

From: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>

Energy-aware load balancing has to work alongside the conventional load
based functionality. This includes the tipping point feature, i.e. being
able to fall back from energy aware to the conventional load based
functionality during an ongoing load balancing action.
That is why this patch introduces an additional reference to hold the
least efficient sched group (costliest) as well its statistics in form of
an extra sg_lb_stats structure (costliest_stat).
The function update_sd_pick_costliest is used to assign the least
efficient sched group parallel to the existing update_sd_pick_busiest.

cc: Ingo Molnar <mingo@xxxxxxxxxx>
cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
---
 kernel/sched/fair.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bfa335e..36f3c77 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6363,12 +6363,14 @@ struct sg_lb_stats {
  */
 struct sd_lb_stats {
 	struct sched_group *busiest;	/* Busiest group in this sd */
+	struct sched_group *costliest;	/* Least efficient group in this sd */
 	struct sched_group *local;	/* Local group in this sd */
 	unsigned long total_load;	/* Total load of all groups in sd */
 	unsigned long total_capacity;	/* Total capacity of all groups in sd */
 	unsigned long avg_load;	/* Average load across all groups in sd */
 
 	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
+	struct sg_lb_stats costliest_stat;/* Statistics of the least efficient group */
 	struct sg_lb_stats local_stat;	/* Statistics of the local group */
 };
 
@@ -6390,6 +6392,9 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 			.sum_nr_running = 0,
 			.group_type = group_other,
 		},
+		.costliest_stat = {
+			.group_eff = ULONG_MAX,
+		},
 	};
 }
 
@@ -6782,6 +6787,17 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	return false;
 }
 
+static noinline bool update_sd_pick_costliest(struct sd_lb_stats *sds,
+					      struct sg_lb_stats *sgs)
+{
+	struct sg_lb_stats *costliest = &sds->costliest_stat;
+
+	if (sgs->group_eff < costliest->group_eff)
+		return true;
+
+	return false;
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
 {
@@ -6872,6 +6888,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 			sds->busiest_stat = *sgs;
 		}
 
+		if (env->use_ea && update_sd_pick_costliest(sds, sgs)) {
+			sds->costliest = sg;
+			sds->costliest_stat = *sgs;
+		}
+
 next_group:
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/