linux4.0 RT负载均衡原理

RT 负载均衡

在SMP情况下：RT负载均衡的目标是要保证TopN的线程都能及时执行；
负载平衡的时机如下：

• pick_next_task_rt
• select_task_rq_rt
• task_woken_rt

pick_next_task_rt

/* rq 当前cpu的运行队列 */

static struct task_struct *
pick_next_task_rt(struct rq *rq, struct task_struct *prev)
{
	struct task_struct *p;
	struct rt_rq *rt_rq = &rq->rt;

	/* 最高优先级任务切换时，需要判断是否需要pull一些任务过来，以保证TopN运行 */
	if (need_pull_rt_task(rq, prev)) {
		pull_rt_task(rq);
		/*
		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
		 * means a dl or stop task can slip in, in which case we need
		 * to re-start task selection.
		 */
		if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
			     rq->dl.dl_nr_running))
			return RETRY_TASK;
	}

	/*
	 * We may dequeue prev's rt_rq in put_prev_task().
	 * So, we update time before rt_nr_running check.
	 */
	if (prev->sched_class == &rt_sched_class)
		update_curr_rt(rq);

	if (!rt_rq->rt_queued)
		return NULL;

	put_prev_task(rq, prev);

	p = _pick_next_task_rt(rq);

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);

	set_post_schedule(rq);

	return p;
}

static int pull_rt_task(struct rq *this_rq)
{
	int this_cpu = this_rq->cpu, ret = 0, cpu;
	struct task_struct *p;
	struct rq *src_rq;

	if (likely(!rt_overloaded(this_rq)))
		return 0;

	/*
	 * Match the barrier from rt_set_overloaded; this guarantees that if we
	 * see overloaded we must also see the rto_mask bit.
	 */
	smp_rmb();

	for_each_cpu(cpu, this_rq->rd->rto_mask) {
		if (this_cpu == cpu)
			continue;

		src_rq = cpu_rq(cpu);

		/* 
		* 只需要判断第二优先级是否比当前rq的优先级高，因为第一优先级一定在运行；
		*/
		/*
		 * Don't bother taking the src_rq->lock if the next highest
		 * task is known to be lower-priority than our current task.
		 * This may look racy, but if this value is about to go
		 * logically higher, the src_rq will push this task away.
		 * And if its going logically lower, we do not care
		 */
		if (src_rq->rt.highest_prio.next >=
		    this_rq->rt.highest_prio.curr)
			continue;

		/*
		 * We can potentially drop this_rq's lock in
		 * double_lock_balance, and another CPU could
		 * alter this_rq
		 */
		double_lock_balance(this_rq, src_rq);

		/* 从src_rq的pushable_tasks中选取一个优先级最高的任务 */
		/*
		 * We can pull only a task, which is pushable
		 * on its rq, and no others.
		 */
		p = pick_highest_pushable_task(src_rq, this_cpu);

		/*
		 * Do we have an RT task that preempts
		 * the to-be-scheduled task?
		 */
		/* 再次判断优先级 */
		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
			WARN_ON(p == src_rq->curr);
			WARN_ON(!task_on_rq_queued(p));

			/*
			 * There's a chance that p is higher in priority
			 * than what's currently running on its cpu.
			 * This is just that p is wakeing up and hasn't
			 * had a chance to schedule. We only pull
			 * p if it is lower in priority than the
			 * current task on the run queue
			 */
			if (p->prio < src_rq->curr->prio)
				goto skip;

			ret = 1;

			/* 从src_rq出队，入this_rq */
			deactivate_task(src_rq, p, 0);
			set_task_cpu(p, this_cpu);
			activate_task(this_rq, p, 0);
			/*
			 * We continue with the search, just in
			 * case there's an even higher prio task
			 * in another runqueue. (low likelihood
			 * but possible)
			 */
		}
skip:
		double_unlock_balance(this_rq, src_rq);
	}

	return ret;
}

try_to_wake_up

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 */
	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
		goto out;

	rq = cpu_rq(cpu);

	rcu_read_lock();
	curr = ACCESS_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.
	 */
	 /* 
	 * curr是RT线程 
	 * curr->nr_cpus_allowed ==1 ||  curr->prio <= p->prio  即唤醒的线程比当前运行的线程优先级低寻找其他CPU来运行 */
	if (curr && unlikely(rt_task(curr)) &&  
	    (curr->nr_cpus_allowed < 2 ||       
	     curr->prio <= p->prio)) {
		int target = find_lowest_rq(p);

		/*
		 * Don't bother moving it if the destination CPU is
		 * not running a lower priority task.
		 */
		/* 如果p的优先级比target的优先级高的时候才会选择该target；否则使用当前CPU */
		if (target != -1 &&
		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
			cpu = target;
	}
	rcu_read_unlock();

out:
	return cpu;
}

task_woken_rt

static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
	
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    has_pushable_tasks(rq) &&
	    p->nr_cpus_allowed > 1 &&
	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
	    (rq->curr->nr_cpus_allowed < 2 ||        /* 唤醒任务的优先级比当前rq的优先级高，需要push */
	     rq->curr->prio <= p->prio))
	     
		push_rt_tasks(rq);
}