load balancing

kernel/sched/fair.c — 진입, source 선택, migration 분기
kernel/sched/topology.c — sched domain 구성 확인
kernel/sched/sched.h — sched domain·rq 관련 정의 확인

static __latent_entropy 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;

	/*
	 * If this CPU has a pending nohz_balance_kick, then do the
	 * balancing on behalf of the other idle CPUs whose ticks are
	 * stopped. Do nohz_idle_balance *before* rebalance_domains to
	 * give the idle CPUs a chance to load balance. Else we may
	 * load balance only within the local sched_domain hierarchy
	 * and abort nohz_idle_balance altogether if we pull some load.
	 */
	if (nohz_idle_balance(this_rq, idle))
		return;

	/* normal load balance */
	update_blocked_averages(this_rq->cpu);
	rebalance_domains(this_rq, idle);
}

/*
 * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
 */
void trigger_load_balance(struct rq *rq)
{
	/*
	 * Don't need to rebalance while attached to NULL domain or
	 * runqueue CPU is not active
	 */
	if (unlikely(on_null_domain(rq) || !cpu_active(cpu_of(rq))))
		return;

	if (time_after_eq(jiffies, rq->next_balance))
		raise_softirq(SCHED_SOFTIRQ);

	nohz_balancer_kick(rq);
}

redo:
	if (!should_we_balance(&env)) {
		*continue_balancing = 0;
		goto out_balanced;
	}

	group = find_busiest_group(&env);
	if (!group) {
		schedstat_inc(sd->lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(&env, group);
	if (!busiest) {
		schedstat_inc(sd->lb_nobusyq[idle]);
		goto out_balanced;
	}

more_balance:
		rq_lock_irqsave(busiest, &rf);
		update_rq_clock(busiest);

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

		rq_unlock(busiest, &rf);

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

		local_irq_restore(rf.flags);