[Patch 3/4 v1] sched: change how cpu load is calculated

[Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>]

This patch changes how the cpu load exerted by fair_sched_class tasks
is calculated. Load exerted by fair_sched_class tasks on a cpu is now a
summation of the group weights, rather than summation of task weights.
Weight exerted by a group on a cpu is dependent on the shares allocated to it.

This version of patch (v1 of Patch 3/4) has zero impact for 
!CONFIG_FAIR_GROUP_SCHED case.

Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>

---
 kernel/sched.c      |   38 ++++++++++++++++++++++++++++++--------
 kernel/sched_fair.c |   31 +++++++++++++++++++++++++++----
 kernel/sched_rt.c   |    2 ++
 3 files changed, 59 insertions(+), 12 deletions(-)

Index: current/kernel/sched.c
===================================================================
--- current.orig/kernel/sched.c
+++ current/kernel/sched.c
@@ -869,15 +869,25 @@
 		   struct rq_iterator *iterator);
 #endif
 
-#include "sched_stats.h"
-#include "sched_idletask.c"
-#include "sched_fair.c"
-#include "sched_rt.c"
-#ifdef CONFIG_SCHED_DEBUG
-# include "sched_debug.c"
-#endif
+#ifdef CONFIG_FAIR_GROUP_SCHED
 
-#define sched_class_highest (&rt_sched_class)
+static inline void inc_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_add(&rq->load, load);
+}
+
+static inline void dec_cpu_load(struct rq *rq, unsigned long load)
+{
+	update_load_sub(&rq->load, load);
+}
+
+static inline void inc_load(struct rq *rq, const struct task_struct *p) { }
+static inline void dec_load(struct rq *rq, const struct task_struct *p) { }
+
+#else	/* CONFIG_FAIR_GROUP_SCHED */
+
+static inline void inc_cpu_load(struct rq *rq, unsigned long load) { }
+static inline void dec_cpu_load(struct rq *rq, unsigned long load) { }
 
 static inline void inc_load(struct rq *rq, const struct task_struct *p)
 {
@@ -889,6 +899,18 @@
 	update_load_sub(&rq->load, p->se.load.weight);
 }
 
+#endif	/* CONFIG_FAIR_GROUP_SCHED */
+
+#include "sched_stats.h"
+#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
+#ifdef CONFIG_SCHED_DEBUG
+# include "sched_debug.c"
+#endif
+
+#define sched_class_highest (&rt_sched_class)
+
 static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running++;
Index: current/kernel/sched_fair.c
===================================================================
--- current.orig/kernel/sched_fair.c
+++ current/kernel/sched_fair.c
@@ -755,15 +755,26 @@
 static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
+	struct sched_entity *se = &p->se,
+			    *topse = NULL;	/* Highest schedulable entity */
+	int incload = 1;
 
 	for_each_sched_entity(se) {
-		if (se->on_rq)
+		topse = se;
+		if (se->on_rq) {
+			incload = 0;
 			break;
+		}
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, wakeup);
 		wakeup = 1;
 	}
+	/* Increment cpu load if we just enqueued the first task of a group on
+	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
+	 * at the highest grouping level.
+	 */
+	if (incload)
+		inc_cpu_load(rq, topse->load.weight);
 }
 
 /*
@@ -774,16 +785,28 @@
 static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
+	struct sched_entity *se = &p->se,
+			    *topse = NULL; 	/* Highest schedulable entity */
+	int decload = 1;
 
 	for_each_sched_entity(se) {
+		topse = se;
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, sleep);
 		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight)
+		if (cfs_rq->load.weight) {
+			if (parent_entity(se))
+				decload = 0;
 			break;
+		}
 		sleep = 1;
 	}
+	/* Decrement cpu load if we just dequeued the last task of a group on
+	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
+	 * at the highest grouping level.
+	 */
+	if (decload)
+		dec_cpu_load(rq, topse->load.weight);
 }
 
 /*
Index: current/kernel/sched_rt.c
===================================================================
--- current.orig/kernel/sched_rt.c
+++ current/kernel/sched_rt.c
@@ -31,6 +31,7 @@
 
 	list_add_tail(&p->run_list, array->queue + p->prio);
 	__set_bit(p->prio, array->bitmap);
+	inc_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -45,6 +46,7 @@
 	list_del(&p->run_list);
 	if (list_empty(array->queue + p->prio))
 		__clear_bit(p->prio, array->bitmap);
+	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*


-- 
Regards,
vatsa