At original linux design, RT & CFS scheduler are independent.
Current RT task placement policy will select the first cpu in
lowest_mask, even if the first CPU is running a CFS task.
This may put RT task to a running cpu and let CFS task runnable.
So we select idle cpu in lowest_mask first to avoid preempting
CFS task.
Signed-off-by: Jing-Ting Wu <jing-ting...@mediatek.com>
---
kernel/sched/rt.c | 42 +++++++++++++++++-------------------------
1 file changed, 17 insertions(+), 25 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a532558..626ca27 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1388,7 +1388,6 @@ static void yield_task_rt(struct rq *rq)
static int
select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
{
- struct task_struct *curr;
struct rq *rq;
/* For anything but wake ups, just return the task_cpu */
@@ -1398,33 +1397,15 @@ static void yield_task_rt(struct rq *rq)
rq = cpu_rq(cpu);
rcu_read_lock();
- curr = READ_ONCE(rq->curr); /* unlocked access */
/*
- * If the current task on @p's runqueue is an RT task, then
- * try to see if we can wake this RT task up on another
- * runqueue. Otherwise simply start this RT task
- * on its current runqueue.
- *
- * We want to avoid overloading runqueues. If the woken
- * task is a higher priority, then it will stay on this CPU
- * and the lower prio task should be moved to another CPU.
- * Even though this will probably make the lower prio task
- * lose its cache, we do not want to bounce a higher task
- * around just because it gave up its CPU, perhaps for a
- * lock?
- *
- * For equal prio tasks, we just let the scheduler sort it out.
- *
- * Otherwise, just let it ride on the affined RQ and the
- * post-schedule router will push the preempted task away
- *
- * This test is optimistic, if we get it wrong the load-balancer
- * will have to sort it out.
+ * If the task p is allowed to put more than one CPU or
+ * it is not allowed to put on this CPU.
+ * Let p use find_lowest_rq to choose other idle CPU first,
+ * instead of choose this cpu and preempt curr cfs task.
*/
- if (curr && unlikely(rt_task(curr)) &&
- (curr->nr_cpus_allowed < 2 ||
- curr->prio <= p->prio)) {
+ if ((p->nr_cpus_allowed > 1) ||
+ (!cpumask_test_cpu(cpu, p->cpus_ptr))) {
int target = find_lowest_rq(p);
/*
@@ -1648,6 +1629,7 @@ static int find_lowest_rq(struct task_struct *task)
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ int i;
/* Make sure the mask is initialized first */
if (unlikely(!lowest_mask))
@@ -1659,6 +1641,16 @@ static int find_lowest_rq(struct task_struct *task)
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
return -1; /* No targets found */
+ /* Choose previous cpu if it is idle and it fits lowest_mask */
+ if (cpumask_test_cpu(cpu, lowest_mask) && idle_cpu(cpu))
+ return cpu;
+
+ /* Choose idle_cpu among lowest_mask */
+ for_each_cpu(i, lowest_mask) {
+ if (idle_cpu(i))
+ return i;
+ }
+
/*
* At this point we have built a mask of CPUs representing the
* lowest priority tasks in the system. Now we want to elect
--
1.7.9.5
