[Patch 3/5 v2] sched: change how cpu load is calculated

From: Srivatsa Vaddagiri
Date: Mon Nov 26 2007 - 23:59:57 EST


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 (v2 of Patch 3/5) has a minor impact on code size
(but should have no runtime/functional impact) for !CONFIG_FAIR_GROUP_SCHED
case, but the overall code, IMHO, is neater compared to v1 of Patch 3/5
(because of lesser #ifdefs).

I prefer v2 of Patch 3/5.

Signed-off-by: Srivatsa Vaddagiri <vatsa@xxxxxxxxxxxxxxxxxx>

---
kernel/sched.c | 27 +++++++++++----------------
kernel/sched_fair.c | 31 +++++++++++++++++++++++++++----
kernel/sched_rt.c | 2 ++
3 files changed, 40 insertions(+), 20 deletions(-)

Index: current/kernel/sched.c
===================================================================
--- current.orig/kernel/sched.c
+++ current/kernel/sched.c
@@ -870,6 +870,16 @@ iter_move_one_task(struct rq *this_rq, i
struct rq_iterator *iterator);
#endif

+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);
+}
+
#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
@@ -880,26 +890,14 @@ iter_move_one_task(struct rq *this_rq, i

#define sched_class_highest (&rt_sched_class)

-static inline void inc_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_add(&rq->load, p->se.load.weight);
-}
-
-static inline void dec_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_sub(&rq->load, p->se.load.weight);
-}
-
static void inc_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running++;
- inc_load(rq, p);
}

static void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
- dec_load(rq, p);
}

static void set_load_weight(struct task_struct *p)
@@ -4071,10 +4069,8 @@ void set_user_nice(struct task_struct *p
goto out_unlock;
}
on_rq = p->se.on_rq;
- if (on_rq) {
+ if (on_rq)
dequeue_task(rq, p, 0);
- dec_load(rq, p);
- }

p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p);
@@ -4084,7 +4080,6 @@ void set_user_nice(struct task_struct *p

if (on_rq) {
enqueue_task(rq, p, 0);
- inc_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
Index: current/kernel/sched_fair.c
===================================================================
--- current.orig/kernel/sched_fair.c
+++ current/kernel/sched_fair.c
@@ -755,15 +755,26 @@ static inline struct sched_entity *paren
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;
+ 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 enqueue_task_fair(struct rq
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;
+ 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 @@ static void enqueue_task_rt(struct rq *r

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 @@ static void dequeue_task_rt(struct rq *r
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
-
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/