【负载均衡、负载计算】【propagate_entity_load_avg】

对于组调度而言，需要传播负载的变化到整个cfs列表里面。propagate_entity_load_avg就负责传播组调度负载的变化

propagate_entity_load_avg

/* Update task and its cfs_rq load average */
static inline int propagate_entity_load_avg(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq;
	//只有group下面才有cfs_rq,才需要传播
	if (entity_is_task(se))
		return 0;

	if (!test_and_clear_tg_cfs_propagate(se))
		return 0;
	/* 获取se所在的cfs_rq */
	cfs_rq = cfs_rq_of(se);

	set_tg_cfs_propagate(cfs_rq);
	/* 更新group se与其所在的cfs_rq中的负载 */
	update_tg_cfs_util(cfs_rq, se);
	update_tg_cfs_load(cfs_rq, se);

	trace_sched_load_cfs_rq(cfs_rq);
	trace_sched_load_se(se);

	return 1;
}

// 将cfs_rq->propagate_avg 设置为1
static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
{
	cfs_rq->propagate_avg = 1;
}

// 将cfs_rq->propagate_avg 设置为0
static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
{
	struct cfs_rq *cfs_rq = group_cfs_rq(se);

	if (!cfs_rq->propagate_avg)
		return 0;

	cfs_rq->propagate_avg = 0;
	return 1;
}

更新负载

update_tg_cfs_util

/* Take into account change of utilization of a child task group */
static inline void
update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
	/* 计算变化值 */
	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;

	/* Nothing to update */
	if (!delta)
		return;

	/* Set new sched_entity's utilization */
	/* group se的util_avg的等于其gcfs_rq的util_avg */
	se->avg.util_avg = gcfs_rq->avg.util_avg;
	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;

	/* Update parent cfs_rq utilization */
	/* 将util_avg的变化传播并更新到cfs_rq */
	add_positive(&cfs_rq->avg.util_avg, delta);
	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
}

/*
 * Signed add and clamp on underflow.
 *
 * Explicitly do a load-store to ensure the intermediate value never hits
 * memory. This allows lockless observations without ever seeing the negative
 * values.
 */
#define add_positive(_ptr, _val) do {                           \
	typeof(_ptr) ptr = (_ptr);                              \
	typeof(_val) val = (_val);                              \
	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
								\
	res = var + val;                                        \
								\
	if (val < 0 && res > var)                               \
		res = 0;                                        \
								\
	WRITE_ONCE(*ptr, res);                                  \
} while (0)

update_tg_cfs_load

/* Take into account change of load of a child task group */
static inline void
update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
	long delta, load = gcfs_rq->avg.load_avg;

	/*
	 * If the load of group cfs_rq is null, the load of the
	 * sched_entity will also be null so we can skip the formula
	 */
	if (load) {
		long tg_load;

		/* Get tg's load and ensure tg_load > 0 */
		tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;

		/* Ensure tg_load >= load and updated with current load*/
		tg_load -= gcfs_rq->tg_load_avg_contrib;
		tg_load += load;

		/*
		 * We need to compute a correction term in the case that the
		 * task group is consuming more CPU than a task of equal
		 * weight. A task with a weight equals to tg->shares will have
		 * a load less or equal to scale_load_down(tg->shares).
		 * Similarly, the sched_entities that represent the task group
		 * at parent level, can't have a load higher than
		 * scale_load_down(tg->shares). And the Sum of sched_entities'
		 * load must be <= scale_load_down(tg->shares).
		 */
		if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
			/* scale gcfs_rq's load into tg's shares*/
			load *= scale_load_down(gcfs_rq->tg->shares);
			load /= tg_load;
		}
	}

	delta = load - se->avg.load_avg;

	/* Nothing to update */
	if (!delta)
		return;

	/* Set new sched_entity's load */
	se->avg.load_avg = load;
	se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;

	/* Update parent cfs_rq load */
	add_positive(&cfs_rq->avg.load_avg, delta);
	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;

	/*
	 * If the sched_entity is already enqueued, we also have to update the
	 * runnable load avg.
	 */
	if (se->on_rq) {
		/* Update parent cfs_rq runnable_load_avg */
		add_positive(&cfs_rq->runnable_load_avg, delta);
		cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
	}
}