[RFCv6 PATCH 09/10] sched: deadline: use deadline bandwidth in scale_rt_capacity

[Steve Muckle]

From: Vincent Guittot <vincent.guittot@xxxxxxxxxx>

Instead of monitoring the exec time of deadline tasks to evaluate the
CPU capacity consumed by deadline scheduler class, we can directly
calculate it thanks to the sum of utilization of deadline tasks on the
CPU.  We can remove deadline tasks from rt_avg metric and directly use
the average bandwidth of deadline scheduler in scale_rt_capacity.

Based in part on a similar patch from Luca Abeni <luca.abeni@xxxxxxxx>.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Steve Muckle <smuckle@xxxxxxxxxx>
---
 kernel/sched/deadline.c | 33 +++++++++++++++++++++++++++++++--
 kernel/sched/fair.c     |  8 ++++++++
 kernel/sched/sched.h    |  2 ++
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b0a15e..9d9eb50 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,6 +43,24 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+static void add_average_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	u64 se_bw = dl_se->dl_bw;
+
+	dl_rq->avg_bw += se_bw;
+}
+
+static void clear_average_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	u64 se_bw = dl_se->dl_bw;
+
+	dl_rq->avg_bw -= se_bw;
+	if (dl_rq->avg_bw < 0) {
+		WARN_ON(1);
+		dl_rq->avg_bw = 0;
+	}
+}
+
 static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
@@ -494,6 +512,9 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
+	if (dl_se->dl_new)
+		add_average_bw(dl_se, dl_rq);
+
 	/*
 	 * The arrival of a new instance needs special treatment, i.e.,
 	 * the actual scheduling parameters have to be "renewed".
@@ -741,8 +762,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = rq_clock_task(rq);
 	cpuacct_charge(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
 	if (dl_runtime_exceeded(dl_se)) {
 		dl_se->dl_throttled = 1;
@@ -1241,6 +1260,8 @@ static void task_fork_dl(struct task_struct *p)
 static void task_dead_dl(struct task_struct *p)
 {
 	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	struct dl_rq *dl_rq = dl_rq_of_se(&p->dl);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	/*
 	 * Since we are TASK_DEAD we won't slip out of the domain!
@@ -1249,6 +1270,8 @@ static void task_dead_dl(struct task_struct *p)
 	/* XXX we should retain the bw until 0-lag */
 	dl_b->total_bw -= p->dl.dl_bw;
 	raw_spin_unlock_irq(&dl_b->lock);
+
+	clear_average_bw(&p->dl, &rq->dl);
 }
 
 static void set_curr_task_dl(struct rq *rq)
@@ -1556,7 +1579,9 @@ retry:
 	}
 
 	deactivate_task(rq, next_task, 0);
+	clear_average_bw(&next_task->dl, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
+	add_average_bw(&next_task->dl, &later_rq->dl);
 	activate_task(later_rq, next_task, 0);
 	ret = 1;
 
@@ -1644,7 +1669,9 @@ static void pull_dl_task(struct rq *this_rq)
 			resched = true;
 
 			deactivate_task(src_rq, p, 0);
+			clear_average_bw(&p->dl, &src_rq->dl);
 			set_task_cpu(p, this_cpu);
+			add_average_bw(&p->dl, &this_rq->dl);
 			activate_task(this_rq, p, 0);
 			dmin = p->dl.deadline;
 
@@ -1750,6 +1777,8 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (!start_dl_timer(p))
 		__dl_clear_params(p);
 
+	clear_average_bw(&p->dl, &rq->dl);
+
 	/*
 	 * Since this might be the only -deadline task on the rq,
 	 * this is the right place to try to pull some other one
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4c49f76..ce05f61 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6203,6 +6203,14 @@ static unsigned long scale_rt_capacity(int cpu)
 
 	used = div_u64(avg, total);
 
+	/*
+	 * deadline bandwidth is defined at system level so we must
+	 * weight this bandwidth with the max capacity of the system.
+	 * As a reminder, avg_bw is 20bits width and
+	 * scale_cpu_capacity is 10 bits width
+	 */
+	used += div_u64(rq->dl.avg_bw, arch_scale_cpu_capacity(NULL, cpu));
+
 	if (likely(used < SCHED_CAPACITY_SCALE))
 		return SCHED_CAPACITY_SCALE - used;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 08858d1..e44c6be 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -519,6 +519,8 @@ struct dl_rq {
 #else
 	struct dl_bw dl_bw;
 #endif
+	/* This is the "average utilization" for this runqueue */
+	s64 avg_bw;
 };
 
 #ifdef CONFIG_SMP
-- 
2.4.10

--
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/