[RFCv3 PATCH 33/48] sched: Energy-aware wake-up task placement

[Morten Rasmussen]

Let available compute capacity and estimated energy impact select
wake-up target cpu when energy-aware scheduling is enabled.
energy_aware_wake_cpu() attempts to find group of cpus with sufficient
compute capacity to accommodate the task and find a cpu with enough spare
capacity to handle the task within that group. Preference is given to
cpus with enough spare capacity at the current OPP. Finally, the energy
impact of the new target and the previous task cpu is compared to select
the wake-up target cpu.

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

Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
---
 kernel/sched/fair.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b371f32..8713310 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5091,6 +5091,92 @@ static int select_idle_sibling(struct task_struct *p, int target)
 done:
 	return target;
 }
+
+static unsigned long group_max_capacity(struct sched_group *sg)
+{
+	int max_idx;
+
+	if (!sg->sge)
+		return 0;
+
+	max_idx = sg->sge->nr_cap_states-1;
+
+	return sg->sge->cap_states[max_idx].cap;
+}
+
+static inline unsigned long task_utilization(struct task_struct *p)
+{
+	return p->se.avg.utilization_avg_contrib;
+}
+
+static int cpu_overutilized(int cpu, struct sched_domain *sd)
+{
+	return (capacity_orig_of(cpu) * 100) <
+				(get_cpu_usage(cpu) * sd->imbalance_pct);
+}
+
+static int energy_aware_wake_cpu(struct task_struct *p)
+{
+	struct sched_domain *sd;
+	struct sched_group *sg, *sg_target;
+	int target_max_cap = SCHED_CAPACITY_SCALE;
+	int target_cpu = task_cpu(p);
+	int i;
+
+	sd = rcu_dereference(per_cpu(sd_ea, task_cpu(p)));
+
+	if (!sd)
+		return -1;
+
+	sg = sd->groups;
+	sg_target = sg;
+	/* Find group with sufficient capacity */
+	do {
+		int sg_max_capacity = group_max_capacity(sg);
+
+		if (sg_max_capacity >= task_utilization(p) &&
+				sg_max_capacity <= target_max_cap) {
+			sg_target = sg;
+			target_max_cap = sg_max_capacity;
+		}
+	} while (sg = sg->next, sg != sd->groups);
+
+	/* Find cpu with sufficient capacity */
+	for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg_target)) {
+		int new_usage = get_cpu_usage(i) + task_utilization(p);
+
+		if (new_usage >	capacity_orig_of(i))
+			continue;
+
+		if (new_usage <	capacity_curr_of(i)) {
+			target_cpu = i;
+			if (!cpu_rq(i)->nr_running)
+				break;
+		}
+
+		/* cpu has capacity at higher OPP, keep it as fallback */
+		if (target_cpu == task_cpu(p))
+			target_cpu = i;
+	}
+
+	if (target_cpu != task_cpu(p)) {
+		struct energy_env eenv = {
+			.usage_delta	= task_utilization(p),
+			.src_cpu	= task_cpu(p),
+			.dst_cpu	= target_cpu,
+		};
+
+		/* Not enough spare capacity on previous cpu */
+		if (cpu_overutilized(task_cpu(p), sd))
+			return target_cpu;
+
+		if (energy_diff(&eenv) >= 0)
+			return task_cpu(p);
+	}
+
+	return target_cpu;
+}
+
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
  * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -5138,6 +5224,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 		prev_cpu = cpu;
 
 	if (sd_flag & SD_BALANCE_WAKE) {
+		if (energy_aware()) {
+			new_cpu = energy_aware_wake_cpu(p);
+			goto unlock;
+		}
 		new_cpu = select_idle_sibling(p, prev_cpu);
 		goto unlock;
 	}
-- 
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/