sched: group scheduling, change how cpu load is calculated
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 has a minor impact on code size, but should have
no runtime/functional impact for !CONFIG_FAIR_GROUP_SCHED.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index cfa6958..c915f3e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -886,6 +886,16 @@
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#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"
@@ -896,26 +906,14 @@
#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)
@@ -4087,10 +4085,8 @@
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);
@@ -4100,7 +4096,6 @@
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:
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c5fdce..30ae9c2 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -760,15 +760,26 @@
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);
}
/*
@@ -779,16 +790,28 @@
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);
}
/*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 9ba3daa..cefcd51 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -32,6 +32,7 @@
list_add_tail(&p->run_list, array->queue + p->prio);
__set_bit(p->prio, array->bitmap);
+ inc_cpu_load(rq, p->se.load.weight);
}
/*
@@ -46,6 +47,7 @@
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);
}
/*