Linux内核分析之CPU动态调频

目前CPU都应该支持动态调频机制以达到节能的目的，现在我们来看看这个机制的主要实现代码。

static void do_dbs_timer(struct work_struct *work)//dbs（demandedbased switch）
{
	struct cpu_dbs_info_s *dbs_info =
		container_of(work, struct cpu_dbs_info_s, work.work);
	unsigned int cpu = dbs_info->cpu;

	/* We want all CPUs to do sampling nearly on same jiffy */
	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);

	delay -= jiffies % delay;

	mutex_lock(&dbs_info->timer_mutex);

	dbs_check_cpu(dbs_info);  //关键函数

	schedule_delayed_work_on(cpu, &dbs_info->work, delay);
	mutex_unlock(&dbs_info->timer_mutex);
}

这个函数的实现是很容易看懂的，我们来看其关键函数：

	dbs_check_cpu(dbs_info);  //关键函数

static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
{
	unsigned int max_load_freq;

	struct cpufreq_policy *policy;
	unsigned int j;

	this_dbs_info->freq_lo = 0;
	policy = this_dbs_info->cur_policy;

	/*
	 * Every sampling_rate, we check, if current idle time is less
	 * than 20% (default), then we try to increase frequency
	 * Every sampling_rate, we look for a the lowest
	 * frequency which can sustain the load while keeping idle time over
	 * 30%. If such a frequency exist, we try to decrease to this frequency.
	 *
	 * Any frequency increase takes it to the maximum frequency.
	 * Frequency reduction happens at minimum steps of
	 * 5% (default) of current frequency
	 */

	/* Get Absolute Load - in terms of freq */
	max_load_freq = 0;

	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info_s *j_dbs_info;
		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
		unsigned int idle_time, wall_time, iowait_time;
		unsigned int load, load_freq;
		int freq_avg;

		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);

		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
		cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);

		wall_time = (unsigned int) cputime64_sub(cur_wall_time,
				j_dbs_info->prev_cpu_wall);
		j_dbs_info->prev_cpu_wall = cur_wall_time;

		idle_time = (unsigned int) cputime64_sub(cur_idle_time,
				j_dbs_info->prev_cpu_idle);
		j_dbs_info->prev_cpu_idle = cur_idle_time;

		iowait_time = (unsigned int) cputime64_sub(cur_iowait_time,
				j_dbs_info->prev_cpu_iowait);
		j_dbs_info->prev_cpu_iowait = cur_iowait_time;

		if (dbs_tuners_ins.ignore_nice) {
			cputime64_t cur_nice;
			unsigned long cur_nice_jiffies;

			cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice,
					 j_dbs_info->prev_cpu_nice);
			/*
			 * Assumption: nice time between sampling periods will
			 * be less than 2^32 jiffies for 32 bit sys
			 */
			cur_nice_jiffies = (unsigned long)
					cputime64_to_jiffies64(cur_nice);

			j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
			idle_time += jiffies_to_usecs(cur_nice_jiffies);
		}

		/*

		 * For the purpose of ondemand, waiting for disk IO is an
		 * indication that you're performance critical, and not that
		 * the system is actually idle. So subtract the iowait time
		 * from the cpu idle time.
		 */

		if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
			idle_time -= iowait_time;

		if (unlikely(!wall_time || wall_time < idle_time))
			continue;
/*

wall_time是最近一次统计的CPU的工作时间；idle_time是最近一次统计的CPU的idle的时间；CPU的load的计算公式如下：

*/
		load = 100 * (wall_time - idle_time) / wall_time;

		freq_avg = __cpufreq_driver_getavg(policy, j);
		if (freq_avg <= 0)
			freq_avg = policy->cur;

		load_freq = load * freq_avg;
		if (load_freq > max_load_freq)
			max_load_freq = load_freq;
	}

	/* Check for frequency increase */
	if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
		/* If switching to max speed, apply sampling_down_factor */
		if (policy->cur < policy->max)  //如果当前CPU的主频小于CPU能够承载的最大的主频
			this_dbs_info->rate_mult =
				dbs_tuners_ins.sampling_down_factor;
		dbs_freq_increase(policy, policy->max);
		return;
	}

	/* Check for frequency decrease */
	/* if we cannot reduce the frequency anymore, break out early */
	if (policy->cur == policy->min)  //如果当前CPU的频率已经是最小频率了，那么就直接返回
		return;

	/*
	 * The optimal frequency is the frequency that is the lowest that
	 * can support the current CPU usage without triggering the up
	 * policy. To be safe, we focus 10 points under the threshold.
	 */
	if (max_load_freq <
	    (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential) *
	     policy->cur) {
		unsigned int freq_next;
		freq_next = max_load_freq /
				(dbs_tuners_ins.up_threshold -
				 dbs_tuners_ins.down_differential);

		/* No longer fully busy, reset rate_mult */
		this_dbs_info->rate_mult = 1;

		if (freq_next < policy->min)
			freq_next = policy->min;

		if (!dbs_tuners_ins.powersave_bias) {
			__cpufreq_driver_target(policy, freq_next,
					CPUFREQ_RELATION_L);
		} else {
			int freq = powersave_bias_target(policy, freq_next,
					CPUFREQ_RELATION_L);
			__cpufreq_driver_target(policy, freq,
				CPUFREQ_RELATION_L);
		}
	}
}