Linux 4.0 CFS负载均衡原理

负载计算

在不考虑EAS的情况下，负载采用PELT计算；

struct sched_avg {
	/*
	 * These sums represent an infinite geometric series and so are bound
	 * above by 1024/(1-y).  Thus we only need a u32 to store them for all
	 * choices of y < 1-2^(-32)*1024.
	 */
	u32 runnable_avg_sum, runnable_avg_period;  /* 两个衰减值 */
	u64 last_runnable_update; /* 上次更新的时间 */
	s64 decay_count;
	/* 计算出来的平均负载 */
	unsigned long load_avg_contrib;
};

负载更新

/* Update a sched_entity's runnable average */
static inline void update_entity_load_avg(struct sched_entity *se,
					  int update_cfs_rq)
{
	struct cfs_rq *cfs_rq = cfs_rq_of(se);
	long contrib_delta;
	u64 now;

	/*
	 * For a group entity we need to use their owned cfs_rq_clock_task() in
	 * case they are the parent of a throttled hierarchy.
	 */
	if (entity_is_task(se))
		now = cfs_rq_clock_task(cfs_rq);
	else
		now = cfs_rq_clock_task(group_cfs_rq(se));

	/* 1：如果是唤醒入队的话调用，se->on_rq=0 入队的时候只做衰减！！！！
	* 更新sched_avg的三个参数：last_runnable_update、runnable_avg_sum、runnable_avg_period。如果上次更新到本次不足1024
us，不做衰减计算，不计算负载贡献度
	*/
	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
		return;

	/* 返回本次的贡献度 */
	contrib_delta = __update_entity_load_avg_contrib(se);

	if (!update_cfs_rq)
		return;

	/* 如果在队列中，累加到cfs_rq中 */
	if (se->on_rq)
		cfs_rq->runnable_load_avg += contrib_delta;
	else
		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
}

/*
 * We can represent the historical contribution to runnable average as the
 * coefficients of a geometric series.  To do this we sub-divide our runnable
 * history into segments of approximately 1ms (1024us); label the segment that
 * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
 *
 * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
 *      p0            p1           p2
 *     (now)       (~1ms ago)  (~2ms ago)
 *
 * Let u_i denote the fraction of p_i that the entity was runnable.
 *
 * We then designate the fractions u_i as our co-efficients, yielding the
 * following representation of historical load:
 *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
 *
 * We choose y based on the with of a reasonably scheduling period, fixing:
 *   y^32 = 0.5
 *
 * This means that the contribution to load ~32ms ago (u_32) will be weighted
 * approximately half as much as the contribution to load within the last ms
 * (u_0).
 *
 * When a period "rolls over" and we have new u_0`, multiplying the previous
 * sum again by y is sufficient to update:
 *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
 *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
 */
static __always_inline int __update_entity_runnable_avg(u64 now,
							struct sched_avg *sa,
							int runnable)
{
	u64 delta, periods;
	u32 runnable_contrib;
	int delta_w, decayed = 0;

	/* 距离上一次更新的时间点 */
	delta = now - sa->last_runnable_update;
	/*
	 * This should only happen when time goes backwards, which it
	 * unfortunately does during sched clock init when we swap over to TSC.
	 */
	if ((s64)delta < 0) {
		sa->last_runnable_update = now;
		return 0;
	}

	/*
	 * Use 1024ns as the unit of measurement since it's a reasonable
	 * approximation of 1us and fast to compute.
	 */
	/* 这时候delta的单位为us，原本的时间单位为ns  */
	delta >>= 10;
	if (!delta)
		return 0;
	sa->last_runnable_update = now;

	/* delta_w is the amount already accumulated against our next period */
	/* delta_w是上次剩余的不能凑成1024整数倍的时间 */
	delta_w = sa->runnable_avg_period % 1024;
	
	if (delta + delta_w >= 1024) {
		/* period roll-over */
		decayed = 1;

		/*
		 * Now that we know we're crossing a period boundary, figure
		 * out how much from delta we need to complete the current
		 * period and accrue it.
		 */
		delta_w = 1024 - delta_w;
		if (runnable)
			sa->runnable_avg_sum += delta_w;
		sa->runnable_avg_period += delta_w;

		delta -= delta_w;

		/* Figure out how many additional periods this update spans */
		periods = delta / 1024;
		delta %= 1024;

		/* 1： 计算runnable_avg_sum第n个周期前的的衰减值 */
		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
						  periods + 1);
		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
						     periods + 1);

		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
		/* 2： __compute_runnable_contrib计算n个PI周期的负载累计贡献值 */
		runnable_contrib = __compute_runnable_contrib(periods);
		if (runnable)
			sa->runnable_avg_sum += runnable_contrib;
		sa->runnable_avg_period += runnable_contrib;
	}

	/* 3：计算剩余的负载 */
	/* Remainder of delta accrued against u_0` */
	if (runnable)
		sa->runnable_avg_sum += delta;
	sa->runnable_avg_period += delta;

	return decayed;
}

2 负载均衡时机

1. scheduler_tick
2. pick_next_task_fair
3. try_to_wake_up

2.1 scheduler_tick

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 */
void scheduler_tick(void)
{
	int cpu = smp_processor_id();
	struct rq *rq = cpu_rq(cpu);
	struct task_struct *curr = rq->curr;

	sched_clock_tick();

	raw_spin_lock(&rq->lock);
	update_rq_clock(rq);
	/* 更新task的vruntime */
	curr->sched_class->task_tick(rq, curr, 0);

	/* 更新CPU负载 */
	update_cpu_load_active(rq);

	raw_spin_unlock(&rq->lock);

	/* perf_evnt_task_tick */
	perf_event_task_tick();

#ifdef CONFIG_SMP
	rq->idle_balance = idle_cpu(cpu);

	/* 触发负载均衡 */
	trigger_load_balance(rq);
#endif

	/* rq->last_sched_tick = jiffies */
	rq_last_tick_reset(rq);
}

__init void init_sched_fair_class(void)
{
#ifdef CONFIG_SMP
	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);

#ifdef CONFIG_NO_HZ_COMMON
	nohz.next_balance = jiffies;
	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
	cpu_notifier(sched_ilb_notifier, 0);
#endif
#endif /* SMP */

}

static void run_rebalance_domains(struct softirq_action *h)
{
	struct rq *this_rq = this_rq();
	enum cpu_idle_type idle = this_rq->idle_balance ?
						CPU_IDLE : CPU_NOT_IDLE;

	rebalance_domains(this_rq, idle);

	/*
	 * If this cpu has a pending nohz_balance_kick, then do the
	 * balancing on behalf of the other idle cpus whose ticks are
	 * stopped.
	 */
	nohz_idle_balance(this_rq, idle);
}

/*
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in init_sched_domains.
 */
static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
{
	int continue_balancing = 1;
	int cpu = rq->cpu;
	unsigned long interval;
	struct sched_domain *sd;
	/* Earliest time when we have to do rebalance again */
	unsigned long next_balance = jiffies + 60*HZ; /* 60S 调用一次 */
	int update_next_balance = 0;
	int need_serialize, need_decay = 0;
	u64 max_cost = 0;

	update_blocked_averages(cpu);

	rcu_read_lock();
	/* 从下到上遍历调度域           */
	for_each_domain(cpu, sd) {
		/*
		 * Decay the newidle max times here because this is a regular
		 * visit to all the domains. Decay ~1% per second.
		 */
		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
			sd->max_newidle_lb_cost =
				(sd->max_newidle_lb_cost * 253) / 256;
			sd->next_decay_max_lb_cost = jiffies + HZ;
			need_decay = 1;
		}
		max_cost += sd->max_newidle_lb_cost;

		/* 判断该调度域是否可以负载均衡               */
		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		/*
		 * Stop the load balance at this level. There is another
		 * CPU in our sched group which is doing load balancing more
		 * actively.
		 */
		if (!continue_balancing) {
			if (need_decay)
				continue;
			break;
		}

		interval = get_sd_balance_interval(sd, idle != CPU_IDLE);

		need_serialize = sd->flags & SD_SERIALIZE;
		if (need_serialize) {
			if (!spin_trylock(&balancing))
				goto out;
		}

		if (time_after_eq(jiffies, sd->last_balance + interval)) {

			/* 真正调用负载均衡的地方             */
			if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
				/*
				 * The LBF_DST_PINNED logic could have changed
				 * env->dst_cpu, so we can't know our idle
				 * state even if we migrated tasks. Update it.
				 */
				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
			}
			sd->last_balance = jiffies;
			interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
		}
		if (need_serialize)
			spin_unlock(&balancing);
out:
		if (time_after(next_balance, sd->last_balance + interval)) {
			next_balance = sd->last_balance + interval;
			update_next_balance = 1;
		}
	}
	if (need_decay) {
		/*
		 * Ensure the rq-wide value also decays but keep it at a
		 * reasonable floor to avoid funnies with rq->avg_idle.
		 */
		rq->max_idle_balance_cost =
			max((u64)sysctl_sched_migration_cost, max_cost);
	}
	rcu_read_unlock();

	/*
	 * next_balance will be updated only when there is a need.
	 * When the cpu is attached to null domain for ex, it will not be
	 * updated.
	 */
	if (likely(update_next_balance))
		rq->next_balance = next_balance;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 */
static int load_balance(int this_cpu, struct rq *this_rq,
			struct sched_domain *sd, enum cpu_idle_type idle,
			int *continue_balancing)
{
	int ld_moved, cur_ld_moved, active_balance = 0;
	struct sched_domain *sd_parent = sd->parent;
	struct sched_group *group;
	struct rq *busiest;
	unsigned long flags;
	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);

	/* 本地变量 */
	struct lb_env env = {
		.sd		= sd,
		.dst_cpu	= this_cpu, /*  dstcpu是当前cpu   */
		.dst_rq		= this_rq,
		.dst_grpmask    = sched_group_cpus(sd->groups),
		.idle		= idle,
		.loop_break	= sched_nr_migrate_break,
		.cpus		= cpus,/*  ????  */
		.fbq_type	= all,
		.tasks		= LIST_HEAD_INIT(env.tasks),
	};

	/*
	 * For NEWLY_IDLE load_balancing, we don't need to consider
	 * other cpus in our group
	 */
	if (idle == CPU_NEWLY_IDLE)
		env.dst_grpmask = NULL;

	cpumask_copy(cpus, cpu_active_mask);

	schedstat_inc(sd, lb_count[idle]);

redo:
	/* 当前CPU空闲或者是这个组的第一个CPU */
	if (!should_we_balance(&env)) {
		*continue_balancing = 0;
		goto out_balanced;
	}

	/* 发现最繁忙的组 */
	group = find_busiest_group(&env);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	/* 找到最繁忙组的最繁忙CPU */
	busiest = find_busiest_queue(&env, group);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

	BUG_ON(busiest == env.dst_rq);

	schedstat_add(sd, lb_imbalance[idle], env.imbalance);

	ld_moved = 0;
	/* CPU 在运行任务大于1    */
	if (busiest->nr_running > 1) {
		/*
		 * Attempt to move tasks. If find_busiest_group has found
		 * an imbalance but busiest->nr_running <= 1, the group is
		 * still unbalanced. ld_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
		env.flags |= LBF_ALL_PINNED;
		env.src_cpu   = busiest->cpu;
		env.src_rq    = busiest;
		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);

more_balance:
		raw_spin_lock_irqsave(&busiest->lock, flags);

		/*
		 * cur_ld_moved - load moved in current iteration
		 * ld_moved     - cumulative load moved across iterations
		 */

		/* 迁移 */
		cur_ld_moved = detach_tasks(&env);

		/*
		 * We've detached some tasks from busiest_rq. Every
		 * task is masked "TASK_ON_RQ_MIGRATING", so we can safely
		 * unlock busiest->lock, and we are able to be sure
		 * that nobody can manipulate the tasks in parallel.
		 * See task_rq_lock() family for the details.
		 */

		raw_spin_unlock(&busiest->lock);

		if (cur_ld_moved) {
			attach_tasks(&env);
			ld_moved += cur_ld_moved;
		}

		local_irq_restore(flags);

		if (env.flags & LBF_NEED_BREAK) {
			env.flags &= ~LBF_NEED_BREAK;
			goto more_balance;
		}

		/*
		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
		 * us and move them to an alternate dst_cpu in our sched_group
		 * where they can run. The upper limit on how many times we
		 * iterate on same src_cpu is dependent on number of cpus in our
		 * sched_group.
		 *
		 * This changes load balance semantics a bit on who can move
		 * load to a given_cpu. In addition to the given_cpu itself
		 * (or a ilb_cpu acting on its behalf where given_cpu is
		 * nohz-idle), we now have balance_cpu in a position to move
		 * load to given_cpu. In rare situations, this may cause
		 * conflicts (balance_cpu and given_cpu/ilb_cpu deciding
		 * _independently_ and at _same_ time to move some load to
		 * given_cpu) causing exceess load to be moved to given_cpu.
		 * This however should not happen so much in practice and
		 * moreover subsequent load balance cycles should correct the
		 * excess load moved.
		 */
		if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {

			/* Prevent to re-select dst_cpu via env's cpus */
			cpumask_clear_cpu(env.dst_cpu, env.cpus);

			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
			env.dst_cpu	 = env.new_dst_cpu;
			env.flags	&= ~LBF_DST_PINNED;
			env.loop	 = 0;
			env.loop_break	 = sched_nr_migrate_break;

			/*
			 * Go back to "more_balance" rather than "redo" since we
			 * need to continue with same src_cpu.
			 */
			goto more_balance;
		}

		/*
		 * We failed to reach balance because of affinity.
		 */
		if (sd_parent) {
			int *group_imbalance = &sd_parent->groups->sgc->imbalance;

			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0)
				*group_imbalance = 1;
		}

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(env.flags & LBF_ALL_PINNED)) {
			cpumask_clear_cpu(cpu_of(busiest), cpus);
			if (!cpumask_empty(cpus)) {
				env.loop = 0;
				env.loop_break = sched_nr_migrate_break;
				goto redo;
			}
			goto out_all_pinned;
		}
	}

	if (!ld_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		/*
		 * Increment the failure counter only on periodic balance.
		 * We do not want newidle balance, which can be very
		 * frequent, pollute the failure counter causing
		 * excessive cache_hot migrations and active balances.
		 */
		if (idle != CPU_NEWLY_IDLE)
			sd->nr_balance_failed++;

		if (need_active_balance(&env)) {
			raw_spin_lock_irqsave(&busiest->lock, flags);

			/* don't kick the active_load_balance_cpu_stop,
			 * if the curr task on busiest cpu can't be
			 * moved to this_cpu
			 */
			if (!cpumask_test_cpu(this_cpu,
					tsk_cpus_allowed(busiest->curr))) {
				raw_spin_unlock_irqrestore(&busiest->lock,
							    flags);
				env.flags |= LBF_ALL_PINNED;
				goto out_one_pinned;
			}

			/*
			 * ->active_balance synchronizes accesses to
			 * ->active_balance_work.  Once set, it's cleared
			 * only after active load balance is finished.
			 */
			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
				active_balance = 1;
			}
			raw_spin_unlock_irqrestore(&busiest->lock, flags);

			if (active_balance) {
				stop_one_cpu_nowait(cpu_of(busiest),
					active_load_balance_cpu_stop, busiest,
					&busiest->active_balance_work);
			}

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
			sd->nr_balance_failed = sd->cache_nice_tries+1;
		}
	} else
		sd->nr_balance_failed = 0;

	if (likely(!active_balance)) {
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
	} else {
		/*
		 * If we've begun active balancing, start to back off. This
		 * case may not be covered by the all_pinned logic if there
		 * is only 1 task on the busy runqueue (because we don't call
		 * detach_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
	}

	goto out;

out_balanced:
	/*
	 * We reach balance although we may have faced some affinity
	 * constraints. Clear the imbalance flag if it was set.
	 */
	if (sd_parent) {
		int *group_imbalance = &sd_parent->groups->sgc->imbalance;

		if (*group_imbalance)
			*group_imbalance = 0;
	}

out_all_pinned:
	/*
	 * We reach balance because all tasks are pinned at this level so
	 * we can't migrate them. Let the imbalance flag set so parent level
	 * can try to migrate them.
	 */
	schedstat_inc(sd, lb_balanced[idle]);

	sd->nr_balance_failed = 0;

out_one_pinned:
	/* tune up the balancing interval */
	if (((env.flags & LBF_ALL_PINNED) &&
			sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

	ld_moved = 0;
out:
	return ld_moved;
}

2.2 pick_next_task_fair

当cfs_rq->nr_running =0时，会触发idle_balance流程；

static struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev)
{
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;
	struct task_struct *p;
	int new_tasks;

/* 1：again 流程 带调度组的流程  
*  2: simple流程 不带调度组的流程
*  3：idle流程  没有任务了，需要核间平衡下
*/
again:
#ifdef CONFIG_FAIR_GROUP_SCHED
	if (!cfs_rq->nr_running)
		goto idle;

	if (prev->sched_class != &fair_sched_class)
		goto simple;

	/*
	 * Because of the set_next_buddy() in dequeue_task_fair() it is rather
	 * likely that a next task is from the same cgroup as the current.
	 *
	 * Therefore attempt to avoid putting and setting the entire cgroup
	 * hierarchy, only change the part that actually changes.
	 */

	/* 初始的cfs_rq=rq->cfs */
	do {
		struct sched_entity *curr = cfs_rq->curr;

		/*
		 * Since we got here without doing put_prev_entity() we also
		 * have to consider cfs_rq->curr. If it is still a runnable
		 * entity, update_curr() will update its vruntime, otherwise
		 * forget we've ever seen it.
		 */
		if (curr && curr->on_rq)
			update_curr(cfs_rq);
		else
			curr = NULL;

		/*
		 * This call to check_cfs_rq_runtime() will do the throttle and
		 * dequeue its entity in the parent(s). Therefore the 'simple'
		 * nr_running test will indeed be correct.
		 */
		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
			goto simple;

		/* 从当前调度队里的红黑树中选择最合适调度实体，这个调度实体可能代表一个任务也可能代表调度组 */
		se = pick_next_entity(cfs_rq, curr);

		/* 如果cfs_rq=NULL cfs_rq代表任务
		*  如果cfs_rq!=NULL cfs_rq代表调度组
		*/
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);/* 如果是调度组接着循环，在调度组中再找到合适的额调度实体 */

	/* 到这已经找到了最合适的调度实体，即是一个任务 */
	p = task_of(se);

	/*
	 * Since we haven't yet done put_prev_entity and if the selected task
	 * is a different task than we started out with, try and touch the
	 * least amount of cfs_rqs.
	 */
	/* 若当前选择的ptask与之前运行的task不是同一个task,则需要将prev重新放入队列 */
	if (prev != p) {
		struct sched_entity *pse = &prev->se;

		while (!(cfs_rq = is_same_group(se, pse))) {
			int se_depth = se->depth;
			int pse_depth = pse->depth;

			if (se_depth <= pse_depth) {
				put_prev_entity(cfs_rq_of(pse), pse);
				pse = parent_entity(pse);
			}
			if (se_depth >= pse_depth) {
				set_next_entity(cfs_rq_of(se), se);
				se = parent_entity(se);
			}
		}

		put_prev_entity(cfs_rq, pse);
		set_next_entity(cfs_rq, se);
	}

	if (hrtick_enabled(rq))
		hrtick_start_fair(rq, p);

	return p;
simple:
	cfs_rq = &rq->cfs;
#endif

	if (!cfs_rq->nr_running)
		goto idle;

	put_prev_task(rq, prev);

	do {
		/*  */
		se = pick_next_entity(cfs_rq, NULL);
		/* set_next_entity会调用__dequeue_entity把选中的进程从红黑树移除，并更新红黑树 */
		set_next_entity(cfs_rq, se);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);/* 如果没有配置调度组，这个循环只会执行一次 */

	p = task_of(se);

	if (hrtick_enabled(rq))
		hrtick_start_fair(rq, p);

	return p;

idle:
	new_tasks = idle_balance(rq);
	/*
	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
	 * possible for any higher priority task to appear. In that case we
	 * must re-start the pick_next_entity() loop.
	 */
	if (new_tasks < 0)
		return RETRY_TASK;

	if (new_tasks > 0)
		goto again;

	return NULL;
}

/*
 * idle_balance is called by schedule() if this_cpu is about to become
 * idle. Attempts to pull tasks from other CPUs.
 */
static int idle_balance(struct rq *this_rq)
{
	unsigned long next_balance = jiffies + HZ;
	int this_cpu = this_rq->cpu;
	struct sched_domain *sd;
	int pulled_task = 0;
	u64 curr_cost = 0;

	idle_enter_fair(this_rq);

	/*
	 * We must set idle_stamp _before_ calling idle_balance(), such that we
	 * measure the duration of idle_balance() as idle time.
	 */
	this_rq->idle_stamp = rq_clock(this_rq);

	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
	    !this_rq->rd->overload) {
		rcu_read_lock();
		sd = rcu_dereference_check_sched_domain(this_rq->sd);
		if (sd)
			update_next_balance(sd, 0, &next_balance);
		rcu_read_unlock();

		goto out;
	}

	/*
	 * Drop the rq->lock, but keep IRQ/preempt disabled.
	 */
	raw_spin_unlock(&this_rq->lock);

	update_blocked_averages(this_cpu);
	rcu_read_lock();
	for_each_domain(this_cpu, sd) {
		int continue_balancing = 1;
		u64 t0, domain_cost;

		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
			update_next_balance(sd, 0, &next_balance);
			break;
		}

		if (sd->flags & SD_BALANCE_NEWIDLE) {
			t0 = sched_clock_cpu(this_cpu);

			pulled_task = load_balance(this_cpu, this_rq,
						   sd, CPU_NEWLY_IDLE,
						   &continue_balancing);

			domain_cost = sched_clock_cpu(this_cpu) - t0;
			if (domain_cost > sd->max_newidle_lb_cost)
				sd->max_newidle_lb_cost = domain_cost;

			curr_cost += domain_cost;
		}

		update_next_balance(sd, 0, &next_balance);

		/*
		 * Stop searching for tasks to pull if there are
		 * now runnable tasks on this rq.
		 */
		if (pulled_task || this_rq->nr_running > 0)
			break;
	}
	rcu_read_unlock();

	raw_spin_lock(&this_rq->lock);

	if (curr_cost > this_rq->max_idle_balance_cost)
		this_rq->max_idle_balance_cost = curr_cost;

	/*
	 * While browsing the domains, we released the rq lock, a task could
	 * have been enqueued in the meantime. Since we're not going idle,
	 * pretend we pulled a task.
	 */
	if (this_rq->cfs.h_nr_running && !pulled_task)
		pulled_task = 1;

out:
	/* Move the next balance forward */
	if (time_after(this_rq->next_balance, next_balance))
		this_rq->next_balance = next_balance;

	/* Is there a task of a high priority class? */
	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
		pulled_task = -1;

	if (pulled_task) {
		idle_exit_fair(this_rq);
		this_rq->idle_stamp = 0;
	}

	return pulled_task;
}

2.3 try_to_wake_up

try_to_wake_up
----->select_task_rq
------------>select_task_rq_fair

static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
	unsigned long flags;
	int cpu, success = 0;

	/*
	 * If we are going to wake up a thread waiting for CONDITION we
	 * need to ensure that CONDITION=1 done by the caller can not be
	 * reordered with p->state check below. This pairs with mb() in
	 * set_current_state() the waiting thread does.
	 */
	smp_mb__before_spinlock();
	raw_spin_lock_irqsave(&p->pi_lock, flags);
	if (!(p->state & state))
		goto out;

	success = 1; /* we're going to change ->state */
	cpu = task_cpu(p);

	if (p->on_rq && ttwu_remote(p, wake_flags))
		goto stat;

#ifdef CONFIG_SMP
	/*
	 * If the owning (remote) cpu is still in the middle of schedule() with
	 * this task as prev, wait until its done referencing the task.
	 */
	while (p->on_cpu)
		cpu_relax();
	/*
	 * Pairs with the smp_wmb() in finish_lock_switch().
	 */
	smp_rmb();

	p->sched_contributes_to_load = !!task_contributes_to_load(p);
	p->state = TASK_WAKING;

	if (p->sched_class->task_waking)
		p->sched_class->task_waking(p);

	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
	if (task_cpu(p) != cpu) {
		wake_flags |= WF_MIGRATED;
		set_task_cpu(p, cpu);
	}
#endif /* CONFIG_SMP */

	ttwu_queue(p, cpu);
stat:
	ttwu_stat(p, cpu, wake_flags);
out:
	raw_spin_unlock_irqrestore(&p->pi_lock, flags);

	return success;
}

/*
 * select_task_rq_fair: Select target runqueue for the waking task in domains
 * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
 * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
 *
 * Balances load by selecting the idlest cpu in the idlest group, or under
 * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
 *
 * Returns the target cpu number.
 *
 * preempt must be disabled.
 */
static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
	int cpu = smp_processor_id();
	int new_cpu = cpu;
	int want_affine = 0;
	int sync = wake_flags & WF_SYNC;

	if (sd_flag & SD_BALANCE_WAKE)
		want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p));

	rcu_read_lock();
	for_each_domain(cpu, tmp) {
		if (!(tmp->flags & SD_LOAD_BALANCE))
			continue;

		/*
		 * If both cpu and prev_cpu are part of this domain,
		 * cpu is a valid SD_WAKE_AFFINE target.
		 */
		/* p之前运行的CPU与当前的CPU属于同一调度组，设置affine_sd */
		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
			affine_sd = tmp;
			break;
		}

		if (tmp->flags & sd_flag)
			sd = tmp;
	}

	/* prev_cpu与cpu进行负载对比 */
	if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync))
		prev_cpu = cpu;

	if (sd_flag & SD_BALANCE_WAKE) {
		new_cpu = select_idle_sibling(p, prev_cpu);
		goto unlock;
	}

	while (sd) {
		struct sched_group *group;
		int weight;

		if (!(sd->flags & sd_flag)) {
			sd = sd->child;
			continue;
		}

		/* 查找最空闲的调度组 */
		group = find_idlest_group(sd, p, cpu, sd_flag);
		if (!group) {
			sd = sd->child;
			continue;
		}

		/* 查找最空闲的CPU */
		new_cpu = find_idlest_cpu(group, p, cpu);
		if (new_cpu == -1 || new_cpu == cpu) {
			/* Now try balancing at a lower domain level of cpu */
			sd = sd->child;
			continue;
		}

		/* Now try balancing at a lower domain level of new_cpu */
		cpu = new_cpu;
		weight = sd->span_weight;
		sd = NULL;
		for_each_domain(cpu, tmp) {
			if (weight <= tmp->span_weight)
				break;
			if (tmp->flags & sd_flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}
unlock:
	rcu_read_unlock();

	return new_cpu;
}