sched: add RT-balance cpu-weight

Some RT tasks (particularly kthreads) are bound to one specific CPU.
It is fairly common for two or more bound tasks to get queued up at the
same time.  Consider, for instance, softirq_timer and softirq_sched.  A
timer goes off in an ISR which schedules softirq_thread to run at RT50.
Then the timer handler determines that it's time to smp-rebalance the
system so it schedules softirq_sched to run.  So we are in a situation
where we have two RT50 tasks queued, and the system will go into
rt-overload condition to request other CPUs for help.

This causes two problems in the current code:

1) If a high-priority bound task and a low-priority unbounded task queue
   up behind the running task, we will fail to ever relocate the unbounded
   task because we terminate the search on the first unmovable task.

2) We spend precious futile cycles in the fast-path trying to pull
   overloaded tasks over.  It is therefore optimial to strive to avoid the
   overhead all together if we can cheaply detect the condition before
   overload even occurs.

This patch tries to achieve this optimization by utilizing the hamming
weight of the task->cpus_allowed mask.  A weight of 1 indicates that
the task cannot be migrated.  We will then utilize this information to
skip non-migratable tasks and to eliminate uncessary rebalance attempts.

We introduce a per-rq variable to count the number of migratable tasks
that are currently running.  We only go into overload if we have more
than one rt task, AND at least one of them is migratable.

In addition, we introduce a per-task variable to cache the cpus_allowed
weight, since the hamming calculation is probably relatively expensive.
We only update the cached value when the mask is updated which should be
relatively infrequent, especially compared to scheduling frequency
in the fast path.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 57 insertions, 6 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index cae35b6b9aec..572c65bcc80f 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -130,6 +130,7 @@ extern struct group_info init_groups;
 	.normal_prio	= MAX_PRIO-20,					\
 	.policy		= SCHED_NORMAL,					\
 	.cpus_allowed	= CPU_MASK_ALL,					\
+	.nr_cpus_allowed = NR_CPUS,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
 	.run_list	= LIST_HEAD_INIT(tsk.run_list),			\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0846f1f9e196..b07a2cf76401 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -847,6 +847,7 @@ struct sched_class {
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p);
 	void (*task_new) (struct rq *rq, struct task_struct *p);
+	void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask);
 };
 
 struct load_weight {
@@ -956,6 +957,7 @@ struct task_struct {
 
 	unsigned int policy;
 	cpumask_t cpus_allowed;
+	int nr_cpus_allowed;
 	unsigned int time_slice;
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
diff --git a/kernel/fork.c b/kernel/fork.c
index 09c0b90a69cc..930c51865ab4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1242,6 +1242,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * parent's CPU). This avoids alot of nasty races.
 	 */
 	p->cpus_allowed = current->cpus_allowed;
+	p->nr_cpus_allowed = current->nr_cpus_allowed;
 	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
 			!cpu_online(task_cpu(p))))
 		set_task_cpu(p, smp_processor_id());
diff --git a/kernel/sched.c b/kernel/sched.c
index 357d3a084de8..66e99b419b31 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -343,6 +343,7 @@ struct rt_rq {
 	int rt_load_balance_idx;
 	struct list_head *rt_load_balance_head, *rt_load_balance_curr;
 	unsigned long rt_nr_running;
+	unsigned long rt_nr_migratory;
 	/* highest queued rt task prio */
 	int highest_prio;
 };
@@ -5144,7 +5145,13 @@ int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 		goto out;
 	}
 
-	p->cpus_allowed = new_mask;
+	if (p->sched_class->set_cpus_allowed)
+		p->sched_class->set_cpus_allowed(p, &new_mask);
+	else {
+		p->cpus_allowed    = new_mask;
+		p->nr_cpus_allowed = cpus_weight(new_mask);
+	}
+
 	/* Can the task run on the task's current CPU? If so, we're done */
 	if (cpu_isset(task_cpu(p), new_mask))
 		goto out;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c492fd2b2eec..ae4995c09aac 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -33,6 +33,14 @@ static inline void rt_clear_overload(struct rq *rq)
 	atomic_dec(&rto_count);
 	cpu_clear(rq->cpu, rt_overload_mask);
 }
+
+static void update_rt_migration(struct rq *rq)
+{
+	if (rq->rt.rt_nr_migratory && (rq->rt.rt_nr_running > 1))
+		rt_set_overload(rq);
+	else
+		rt_clear_overload(rq);
+}
 #endif /* CONFIG_SMP */
 
 /*
@@ -65,8 +73,10 @@ static inline void inc_rt_tasks(struct task_struct *p, struct rq *rq)
 #ifdef CONFIG_SMP
 	if (p->prio < rq->rt.highest_prio)
 		rq->rt.highest_prio = p->prio;
-	if (rq->rt.rt_nr_running > 1)
-		rt_set_overload(rq);
+	if (p->nr_cpus_allowed > 1)
+		rq->rt.rt_nr_migratory++;
+
+	update_rt_migration(rq);
 #endif /* CONFIG_SMP */
 }
 
@@ -88,8 +98,10 @@ static inline void dec_rt_tasks(struct task_struct *p, struct rq *rq)
 		} /* otherwise leave rq->highest prio alone */
 	} else
 		rq->rt.highest_prio = MAX_RT_PRIO;
-	if (rq->rt.rt_nr_running < 2)
-		rt_clear_overload(rq);
+	if (p->nr_cpus_allowed > 1)
+		rq->rt.rt_nr_migratory--;
+
+	update_rt_migration(rq);
 #endif /* CONFIG_SMP */
 }
 
@@ -182,7 +194,8 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    (cpu < 0 || cpu_isset(cpu, p->cpus_allowed)))
+	    (cpu < 0 || cpu_isset(cpu, p->cpus_allowed)) &&
+	    (p->nr_cpus_allowed > 1))
 		return 1;
 	return 0;
 }
@@ -584,6 +597,32 @@ move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	/* don't touch RT tasks */
 	return 0;
 }
+static void set_cpus_allowed_rt(struct task_struct *p, cpumask_t *new_mask)
+{
+	int weight = cpus_weight(*new_mask);
+
+	BUG_ON(!rt_task(p));
+
+	/*
+	 * Update the migration status of the RQ if we have an RT task
+	 * which is running AND changing its weight value.
+	 */
+	if (p->se.on_rq && (weight != p->nr_cpus_allowed)) {
+		struct rq *rq = task_rq(p);
+
+		if ((p->nr_cpus_allowed <= 1) && (weight > 1))
+			rq->rt.rt_nr_migratory++;
+		else if((p->nr_cpus_allowed > 1) && (weight <= 1)) {
+			BUG_ON(!rq->rt.rt_nr_migratory);
+			rq->rt.rt_nr_migratory--;
+		}
+
+		update_rt_migration(rq);
+	}
+
+	p->cpus_allowed    = *new_mask;
+	p->nr_cpus_allowed = weight;
+}
 #else /* CONFIG_SMP */
 # define schedule_tail_balance_rt(rq)	do { } while (0)
 # define schedule_balance_rt(rq, prev)	do { } while (0)
@@ -637,6 +676,7 @@ const struct sched_class rt_sched_class = {
 #ifdef CONFIG_SMP
 	.load_balance		= load_balance_rt,
 	.move_one_task		= move_one_task_rt,
+	.set_cpus_allowed       = set_cpus_allowed_rt,
 #endif
 
 	.set_curr_task          = set_curr_task_rt,