sched: mix tasks and groups
This patch allows tasks and groups to exist in the same cfs_rq. With this
change the CFS group scheduling follows a 1/(M+N) model from a 1/(1+N)
fairness model where M tasks and N groups exist at the cfs_rq level.
[a.p.zijlstra@chello.nl: rt bits and assorted fixes]
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 022e036..3dde0f0 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1133,6 +1133,17 @@
return 0;
}
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+ int depth = 0;
+
+ for_each_sched_entity(se)
+ depth++;
+
+ return depth;
+}
+
/*
* Preempt the current task with a newly woken task if needed:
*/
@@ -1141,6 +1152,7 @@
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
+ int se_depth, pse_depth;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
@@ -1165,6 +1177,27 @@
if (!sched_feat(WAKEUP_PREEMPT))
return;
+ /*
+ * preemption test can be made between sibling entities who are in the
+ * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+ * both tasks until we find their ancestors who are siblings of common
+ * parent.
+ */
+
+ /* First walk up until both entities are at same depth */
+ se_depth = depth_se(se);
+ pse_depth = depth_se(pse);
+
+ while (se_depth > pse_depth) {
+ se_depth--;
+ se = parent_entity(se);
+ }
+
+ while (pse_depth > se_depth) {
+ pse_depth--;
+ pse = parent_entity(pse);
+ }
+
while (!is_same_group(se, pse)) {
se = parent_entity(se);
pse = parent_entity(pse);
@@ -1223,13 +1256,22 @@
static struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
{
- struct task_struct *p;
+ struct task_struct *p = NULL;
+ struct sched_entity *se;
if (!curr)
return NULL;
- p = rb_entry(curr, struct task_struct, se.run_node);
- cfs_rq->rb_load_balance_curr = rb_next(curr);
+ /* Skip over entities that are not tasks */
+ do {
+ se = rb_entry(curr, struct sched_entity, run_node);
+ curr = rb_next(curr);
+ } while (curr && !entity_is_task(se));
+
+ cfs_rq->rb_load_balance_curr = curr;
+
+ if (entity_is_task(se))
+ p = task_of(se);
return p;
}
@@ -1489,9 +1531,6 @@
{
struct cfs_rq *cfs_rq;
-#ifdef CONFIG_FAIR_GROUP_SCHED
- print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
-#endif
rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);