Frequence Scaling: Mi date una mano???

[Andmart]

Ciao a Tutti! Mi trovo in una situazione un po' particolare.... Sul mio portatile Acer Aspire 1300 vorrei configurare un supporto impeccabile per il frequence scaling...Altrimenti la temperatura della CPU schizza a 70°.... Purtroppo ondemand aumenta troppo e troppo velocemente la potenza mentre conservative è troppo lento. Una buona via di mezzo era condemand: http://www.uwsg.iu.edu/hypermail/lin...06.3/0316.html

Peccato che non funzioni... Qualcuno di voi potrebbe drimi come posso modificare conservative in modo che sia un po' più reattivo (responsible) ma che non segua la logica del dammi tutta la potenza e dammela ora? Cioè in modo che aumenti prontamente la potenza ma gradualmente... Sono sicuro che basta modificare qualcosa nel modulo conservative... Peccato non sappia esattamente cosa.... In ogni caso allego il codice di condemand (che non va)

/*
 *  drivers/cpufreq/cpufreq_condemand.c
 *
 *  Copyright (C)  2005 Paolo Marchetti <natryum@gmail.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/ctype.h>
#include <linux/cpufreq.h>
#include <linux/sysctl.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/sched.h>
#include <linux/kmod.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.h>

/*
 * dbs is used in this file as a shortform for demandbased switching
 * It helps to keep variable names smaller, simpler
 */

#define DEF_FREQUENCY_UP_THRESHOLD		(80)
#define MIN_FREQUENCY_UP_THRESHOLD		(11)
#define MAX_FREQUENCY_UP_THRESHOLD		(100)

/*
 * The polling frequency of this governor depends on the capability of
 * the processor. Default polling frequency is 1000 times the transition
 * latency of the processor. The governor will work on any processor with
 * transition latency <= 10mS, using appropriate sampling
 * rate.
 * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
 * this governor will not work.
 * All times here are in uS.
 */
static unsigned int 				def_sampling_rate;
#define MIN_SAMPLING_RATE			(def_sampling_rate / 2)
#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
#define DEF_SAMPLING_DOWN_FACTOR		(1)
#define MAX_SAMPLING_DOWN_FACTOR		(10)
#define TRANSITION_LATENCY_LIMIT		(10 * 1000)

static void do_dbs_timer(void *data);

struct cpu_dbs_info_s {
	struct cpufreq_policy 	*cur_policy;
	unsigned int 		prev_cpu_idle_up;
	unsigned int 		prev_cpu_idle_down;
	unsigned int 		enable;
};
static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);

static unsigned int dbs_enable;	/* number of CPUs using this policy */

static DECLARE_MUTEX 	(dbs_sem);
static DECLARE_WORK	(dbs_work, do_dbs_timer, NULL);

struct dbs_tuners {
	unsigned int 		sampling_rate;
	unsigned int		sampling_down_factor;
	unsigned int		up_threshold;
	unsigned int		ignore_nice;
	unsigned int		freq_step;
};

static struct dbs_tuners dbs_tuners_ins = {
	.up_threshold 		= DEF_FREQUENCY_UP_THRESHOLD,
	.sampling_down_factor 	= DEF_SAMPLING_DOWN_FACTOR,
};

static inline unsigned int get_cpu_idle_time(unsigned int cpu)
{
	return	kstat_cpu(cpu).cpustat.idle +
		kstat_cpu(cpu).cpustat.iowait +
		( !dbs_tuners_ins.ignore_nice ?
		  kstat_cpu(cpu).cpustat.nice :
		  0);
}

/************************** sysfs interface ************************/
static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
{
	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
}

static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
{
	return sprintf (buf, "%u\n", MIN_SAMPLING_RATE);
}

#define define_one_ro(_name) 					\
static struct freq_attr _name =  				\
__ATTR(_name, 0444, show_##_name, NULL)

define_one_ro(sampling_rate_max);
define_one_ro(sampling_rate_min);

/* cpufreq_condemand Governor Tunables */
#define show_one(file_name, object)					\
static ssize_t show_##file_name						\
(struct cpufreq_policy *unused, char *buf)				\
{									\
	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
}
show_one(sampling_rate, sampling_rate);
show_one(sampling_down_factor, sampling_down_factor);
show_one(up_threshold, up_threshold);
show_one(ignore_nice, ignore_nice);
show_one(freq_step, freq_step);

static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);
	if (ret != 1 )
		return -EINVAL;

	if (input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
		return -EINVAL;

	down(&dbs_sem);
	dbs_tuners_ins.sampling_down_factor = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_sampling_rate(struct cpufreq_policy *unused, 
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);

	down(&dbs_sem);
	if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) {
		up(&dbs_sem);
		return -EINVAL;
	}

	dbs_tuners_ins.sampling_rate = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_up_threshold(struct cpufreq_policy *unused,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);

	down(&dbs_sem);
	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD ||
			input < MIN_FREQUENCY_UP_THRESHOLD) {
		up(&dbs_sem);
		return -EINVAL;
	}

	dbs_tuners_ins.up_threshold = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_ignore_nice(struct cpufreq_policy *policy,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	unsigned int j;
	
	ret = sscanf (buf, "%u", &input);
	if ( ret != 1 )
		return -EINVAL;

	if ( input > 1 )
		input = 1;
	
	down(&dbs_sem);
	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
		up(&dbs_sem);
		return count;
	}
	dbs_tuners_ins.ignore_nice = input;

	/* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *j_dbs_info;
		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
	}
	up(&dbs_sem);

	return count;
}

static ssize_t store_freq_step(struct cpufreq_policy *policy,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	ret = sscanf (buf, "%u", &input);

	if ( ret != 1 )
		return -EINVAL;

	if ( input > 100 )
		input = 100;
	
	/* no need to test here if freq_step is zero as the user might actually
	 * want this, they would be crazy though :) */
	down(&dbs_sem);
	dbs_tuners_ins.freq_step = input;
	up(&dbs_sem);

	return count;
}



#define define_one_rw(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)

define_one_rw(sampling_rate);
define_one_rw(sampling_down_factor);
define_one_rw(up_threshold);
define_one_rw(ignore_nice);
define_one_rw(freq_step);

static struct attribute * dbs_attributes[] = {
	&sampling_rate_max.attr,
	&sampling_rate_min.attr,
	&sampling_rate.attr,
	&sampling_down_factor.attr,
	&up_threshold.attr,
	&ignore_nice.attr,
	&freq_step.attr,
	NULL
};

static struct attribute_group dbs_attr_group = {
	.attrs = dbs_attributes,
	.name = "condemand",
};

/************************** sysfs end ************************/

static void dbs_check_cpu(int cpu)
{
	unsigned int idle_ticks, up_idle_ticks, total_ticks;
	unsigned int freq_next;
	unsigned int freq_step;
	unsigned int freq_down_sampling_rate;
	static int down_skip[NR_CPUS];
	struct cpu_dbs_info_s *this_dbs_info;

	struct cpufreq_policy *policy;
	unsigned int j;

	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
	if (!this_dbs_info->enable)
		return;

	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*sampling_down_factor, 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 
	 */

	/* Check for frequency increase */
	idle_ticks = UINT_MAX;
	for_each_cpu_mask(j, policy->cpus) {
		unsigned int tmp_idle_ticks, total_idle_ticks;
		struct cpu_dbs_info_s *j_dbs_info;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		total_idle_ticks = get_cpu_idle_time(j);
		tmp_idle_ticks = total_idle_ticks -
			j_dbs_info->prev_cpu_idle_up;
		j_dbs_info->prev_cpu_idle_up = total_idle_ticks;

		if (tmp_idle_ticks < idle_ticks)
			idle_ticks = tmp_idle_ticks;
	}

	/* Scale idle ticks by 100 and compare with up and down ticks */
	idle_ticks *= 100;
	up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
			usecs_to_jiffies(dbs_tuners_ins.sampling_rate);

	if (idle_ticks < up_idle_ticks) {
		down_skip[cpu] = 0;
		for_each_cpu_mask(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;

			j_dbs_info = &per_cpu(cpu_dbs_info, j);
			j_dbs_info->prev_cpu_idle_down = 
					j_dbs_info->prev_cpu_idle_up;
		}
		/* if we are already at full speed then break out early */
		if (policy->cur == policy->max)
			return;
		
                freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;

                /* max freq cannot be less than 100. Paranoid!
                if (unlikely(freq_step == 0))
	                        freq_step = 5;
		*/

                policy->cur += freq_step;
                if (policy->cur > policy->max)
	                        policy->cur = policy->max;

                __cpufreq_driver_target(policy, policy->cur,
		                        CPUFREQ_RELATION_H);
                return;
        }

	/* Check for frequency decrease */
	down_skip[cpu]++;
	if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor)
		return;

	idle_ticks = UINT_MAX;
	for_each_cpu_mask(j, policy->cpus) {
		unsigned int tmp_idle_ticks, total_idle_ticks;
		struct cpu_dbs_info_s *j_dbs_info;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		/* Check for frequency decrease */
		total_idle_ticks = j_dbs_info->prev_cpu_idle_up;
		tmp_idle_ticks = total_idle_ticks -
			j_dbs_info->prev_cpu_idle_down;
		j_dbs_info->prev_cpu_idle_down = total_idle_ticks;

		if (tmp_idle_ticks < idle_ticks)
			idle_ticks = tmp_idle_ticks;
	}

	down_skip[cpu] = 0;
	/* if we cannot reduce the frequency anymore, break out early */
	if (policy->cur == policy->min)
		return;

	/* Compute how many ticks there are between two measurements */
	freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
		dbs_tuners_ins.sampling_down_factor;
	total_ticks = usecs_to_jiffies(freq_down_sampling_rate);

	/*
	 * 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.
	 */
	freq_next = ((total_ticks - idle_ticks) * 100) / total_ticks;
	freq_next = (freq_next * policy->cur) / 
			(dbs_tuners_ins.up_threshold - 10);

	if (freq_next <= ((policy->cur * 95) / 100))
		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L);
}

static void do_dbs_timer(void *data)
{
	int i;
	down(&dbs_sem);
	for_each_online_cpu(i)
		dbs_check_cpu(i);
	schedule_delayed_work(&dbs_work, 
			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
	up(&dbs_sem);
}

static inline void dbs_timer_init(void)
{
	INIT_WORK(&dbs_work, do_dbs_timer, NULL);
	schedule_delayed_work(&dbs_work,
			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
	return;
}

static inline void dbs_timer_exit(void)
{
	cancel_delayed_work(&dbs_work);
	return;
}

static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
				   unsigned int event)
{
	unsigned int cpu = policy->cpu;
	struct cpu_dbs_info_s *this_dbs_info;
	unsigned int j;

	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);

	switch (event) {
	case CPUFREQ_GOV_START:
		if ((!cpu_online(cpu)) || 
		    (!policy->cur))
			return -EINVAL;

		if (policy->cpuinfo.transition_latency >
				(TRANSITION_LATENCY_LIMIT * 1000))
			return -EINVAL;
		if (this_dbs_info->enable) /* Already enabled */
			break;

		down(&dbs_sem);
		for_each_cpu_mask(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;
			j_dbs_info = &per_cpu(cpu_dbs_info, j);
			j_dbs_info->cur_policy = policy;

			j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
			j_dbs_info->prev_cpu_idle_down
				= j_dbs_info->prev_cpu_idle_up;
		}
		this_dbs_info->enable = 1;
		sysfs_create_group(&policy->kobj, &dbs_attr_group);
		dbs_enable++;
		/*
		 * Start the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 1) {
			unsigned int latency;
			/* policy latency is in nS. Convert it to uS first */

			latency = policy->cpuinfo.transition_latency;
			if (latency < 1000)
				latency = 1000;

			def_sampling_rate = (latency / 1000) *
					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
			dbs_tuners_ins.sampling_rate = def_sampling_rate;
			dbs_tuners_ins.ignore_nice = 0;
			dbs_tuners_ins.freq_step = 5;

			dbs_timer_init();
		}
		
		up(&dbs_sem);
		break;

	case CPUFREQ_GOV_STOP:
		down(&dbs_sem);
		this_dbs_info->enable = 0;
		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
		dbs_enable--;
		/*
		 * Stop the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 0)
			dbs_timer_exit();

		up(&dbs_sem);

		break;

	case CPUFREQ_GOV_LIMITS:
		down(&dbs_sem);
		if (policy->max < this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(
					this_dbs_info->cur_policy,
				       	policy->max, CPUFREQ_RELATION_H);
		else if (policy->min > this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(
					this_dbs_info->cur_policy,
				       	policy->min, CPUFREQ_RELATION_L);
		up(&dbs_sem);
		break;
	}
	return 0;
}

static struct cpufreq_governor cpufreq_gov_dbs = {
	.name		= "condemand",
	.governor	= cpufreq_governor_dbs,
	.owner		= THIS_MODULE,
};

static int __init cpufreq_gov_dbs_init(void)
{
	return cpufreq_register_governor(&cpufreq_gov_dbs);
}

static void __exit cpufreq_gov_dbs_exit(void)
{
	/* Make sure that the scheduled work is indeed not running */
	flush_scheduled_work();

	cpufreq_unregister_governor(&cpufreq_gov_dbs);
}


MODULE_AUTHOR ("Paolo Marchetti <natryum@gmail.com>");
MODULE_DESCRIPTION ("'cpufreq_condemand' - A dynamic cpufreq governor for "
		"Low Latency Frequency Transition capable processors "
		"fast scale down, gradual scale up");
MODULE_LICENSE ("GPL");

module_init(cpufreq_gov_dbs_init);
module_exit(cpufreq_gov_dbs_exit);

e quello di conservative:

/*
 *  drivers/cpufreq/cpufreq_conservative.c
 *
 *  Copyright (C)  2001 Russell King
 *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
 *                      Jun Nakajima <jun.nakajima@intel.com>
 *            (C)  2004 Alexander Clouter <alex-kernel@digriz.org.uk>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/ctype.h>
#include <linux/cpufreq.h>
#include <linux/sysctl.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/sched.h>
#include <linux/kmod.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.h>

/*
 * dbs is used in this file as a shortform for demandbased switching
 * It helps to keep variable names smaller, simpler
 */

#define DEF_FREQUENCY_UP_THRESHOLD		(80)
#define MIN_FREQUENCY_UP_THRESHOLD		(0)
#define MAX_FREQUENCY_UP_THRESHOLD		(100)

#define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
#define MIN_FREQUENCY_DOWN_THRESHOLD		(0)
#define MAX_FREQUENCY_DOWN_THRESHOLD		(100)

/* 
 * The polling frequency of this governor depends on the capability of 
 * the processor. Default polling frequency is 1000 times the transition
 * latency of the processor. The governor will work on any processor with 
 * transition latency <= 10mS, using appropriate sampling 
 * rate.
 * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
 * this governor will not work.
 * All times here are in uS.
 */
static unsigned int 				def_sampling_rate;
#define MIN_SAMPLING_RATE			(def_sampling_rate / 2)
#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(100000)
#define DEF_SAMPLING_DOWN_FACTOR		(5)
#define TRANSITION_LATENCY_LIMIT		(10 * 1000)

static void do_dbs_timer(void *data);

struct cpu_dbs_info_s {
	struct cpufreq_policy 	*cur_policy;
	unsigned int 		prev_cpu_idle_up;
	unsigned int 		prev_cpu_idle_down;
	unsigned int 		enable;
};
static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);

static unsigned int dbs_enable;	/* number of CPUs using this policy */

static DECLARE_MUTEX 	(dbs_sem);
static DECLARE_WORK	(dbs_work, do_dbs_timer, NULL);

struct dbs_tuners {
	unsigned int 		sampling_rate;
	unsigned int		sampling_down_factor;
	unsigned int		up_threshold;
	unsigned int		down_threshold;
	unsigned int		ignore_nice;
	unsigned int		freq_step;
};

static struct dbs_tuners dbs_tuners_ins = {
	.up_threshold 		= DEF_FREQUENCY_UP_THRESHOLD,
	.down_threshold 	= DEF_FREQUENCY_DOWN_THRESHOLD,
	.sampling_down_factor 	= DEF_SAMPLING_DOWN_FACTOR,
};

static inline unsigned int get_cpu_idle_time(unsigned int cpu)
{
	return	kstat_cpu(cpu).cpustat.idle +
		kstat_cpu(cpu).cpustat.iowait +
		( !dbs_tuners_ins.ignore_nice ? 
		  kstat_cpu(cpu).cpustat.nice :
		  0);
}

/************************** sysfs interface ************************/
static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
{
	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
}

static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
{
	return sprintf (buf, "%u\n", MIN_SAMPLING_RATE);
}

#define define_one_ro(_name) 					\
static struct freq_attr _name =  				\
__ATTR(_name, 0444, show_##_name, NULL)

define_one_ro(sampling_rate_max);
define_one_ro(sampling_rate_min);

/* cpufreq_conservative Governor Tunables */
#define show_one(file_name, object)					\
static ssize_t show_##file_name						\
(struct cpufreq_policy *unused, char *buf)				\
{									\
	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
}
show_one(sampling_rate, sampling_rate);
show_one(sampling_down_factor, sampling_down_factor);
show_one(up_threshold, up_threshold);
show_one(down_threshold, down_threshold);
show_one(ignore_nice, ignore_nice);
show_one(freq_step, freq_step);

static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, 
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);
	if (ret != 1 )
		return -EINVAL;

	down(&dbs_sem);
	dbs_tuners_ins.sampling_down_factor = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_sampling_rate(struct cpufreq_policy *unused, 
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);

	down(&dbs_sem);
	if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) {
		up(&dbs_sem);
		return -EINVAL;
	}

	dbs_tuners_ins.sampling_rate = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_up_threshold(struct cpufreq_policy *unused, 
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);

	down(&dbs_sem);
	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || 
			input < MIN_FREQUENCY_UP_THRESHOLD ||
			input <= dbs_tuners_ins.down_threshold) {
		up(&dbs_sem);
		return -EINVAL;
	}

	dbs_tuners_ins.up_threshold = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_down_threshold(struct cpufreq_policy *unused, 
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf (buf, "%u", &input);

	down(&dbs_sem);
	if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || 
			input < MIN_FREQUENCY_DOWN_THRESHOLD ||
			input >= dbs_tuners_ins.up_threshold) {
		up(&dbs_sem);
		return -EINVAL;
	}

	dbs_tuners_ins.down_threshold = input;
	up(&dbs_sem);

	return count;
}

static ssize_t store_ignore_nice(struct cpufreq_policy *policy,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	unsigned int j;
	
	ret = sscanf (buf, "%u", &input);
	if ( ret != 1 )
		return -EINVAL;

	if ( input > 1 )
		input = 1;
	
	down(&dbs_sem);
	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
		up(&dbs_sem);
		return count;
	}
	dbs_tuners_ins.ignore_nice = input;

	/* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *j_dbs_info;
		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
	}
	up(&dbs_sem);

	return count;
}

static ssize_t store_freq_step(struct cpufreq_policy *policy,
		const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	ret = sscanf (buf, "%u", &input);

	if ( ret != 1 )
		return -EINVAL;

	if ( input > 100 )
		input = 100;
	
	/* no need to test here if freq_step is zero as the user might actually
	 * want this, they would be crazy though :) */
	down(&dbs_sem);
	dbs_tuners_ins.freq_step = input;
	up(&dbs_sem);

	return count;
}

#define define_one_rw(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)

define_one_rw(sampling_rate);
define_one_rw(sampling_down_factor);
define_one_rw(up_threshold);
define_one_rw(down_threshold);
define_one_rw(ignore_nice);
define_one_rw(freq_step);

static struct attribute * dbs_attributes[] = {
	&sampling_rate_max.attr,
	&sampling_rate_min.attr,
	&sampling_rate.attr,
	&sampling_down_factor.attr,
	&up_threshold.attr,
	&down_threshold.attr,
	&ignore_nice.attr,
	&freq_step.attr,
	NULL
};

static struct attribute_group dbs_attr_group = {
	.attrs = dbs_attributes,
	.name = "conservative",
};

/************************** sysfs end ************************/

static void dbs_check_cpu(int cpu)
{
	unsigned int idle_ticks, up_idle_ticks, down_idle_ticks;
	unsigned int freq_step;
	unsigned int freq_down_sampling_rate;
	static int down_skip[NR_CPUS];
	static int requested_freq[NR_CPUS];
	static unsigned short init_flag = 0;
	struct cpu_dbs_info_s *this_dbs_info;
	struct cpu_dbs_info_s *dbs_info;

	struct cpufreq_policy *policy;
	unsigned int j;

	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
	if (!this_dbs_info->enable)
		return;

	policy = this_dbs_info->cur_policy;

	if ( init_flag == 0 ) {
		for ( /* NULL */; init_flag < NR_CPUS; init_flag++ ) {
			dbs_info = &per_cpu(cpu_dbs_info, init_flag);
			requested_freq[cpu] = dbs_info->cur_policy->cur;
		}
		init_flag = 1;
	}
	
	/* 
	 * The default safe range is 20% to 80% 
	 * Every sampling_rate, we check
	 * 	- If current idle time is less than 20%, then we try to 
	 * 	  increase frequency
	 * Every sampling_rate*sampling_down_factor, we check
	 * 	- If current idle time is more than 80%, then we try to
	 * 	  decrease frequency
	 *
	 * Any frequency increase takes it to the maximum frequency. 
	 * Frequency reduction happens at minimum steps of 
	 * 5% (default) of max_frequency 
	 */

	/* Check for frequency increase */

	idle_ticks = UINT_MAX;
	for_each_cpu_mask(j, policy->cpus) {
		unsigned int tmp_idle_ticks, total_idle_ticks;
		struct cpu_dbs_info_s *j_dbs_info;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		/* Check for frequency increase */
		total_idle_ticks = get_cpu_idle_time(j);
		tmp_idle_ticks = total_idle_ticks -
			j_dbs_info->prev_cpu_idle_up;
		j_dbs_info->prev_cpu_idle_up = total_idle_ticks;

		if (tmp_idle_ticks < idle_ticks)
			idle_ticks = tmp_idle_ticks;
	}

	/* Scale idle ticks by 100 and compare with up and down ticks */
	idle_ticks *= 100;
	up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
		usecs_to_jiffies(dbs_tuners_ins.sampling_rate);

	if (idle_ticks < up_idle_ticks) {
		down_skip[cpu] = 0;
		for_each_cpu_mask(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;

			j_dbs_info = &per_cpu(cpu_dbs_info, j);
			j_dbs_info->prev_cpu_idle_down =
					j_dbs_info->prev_cpu_idle_up;
		}
		/* if we are already at full speed then break out early */
		if (requested_freq[cpu] == policy->max)
			return;

		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;

		/* max freq cannot be less than 100. But who knows.... */
		if (unlikely(freq_step == 0))
			freq_step = 5;

		requested_freq[cpu] += freq_step;
		if (requested_freq[cpu] > policy->max)
			requested_freq[cpu] = policy->max;

		__cpufreq_driver_target(policy, requested_freq[cpu],
			CPUFREQ_RELATION_H);
		return;
	}

	/* Check for frequency decrease */
	down_skip[cpu]++;
	if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor)
		return;

	idle_ticks = UINT_MAX;
	for_each_cpu_mask(j, policy->cpus) {
		unsigned int tmp_idle_ticks, total_idle_ticks;
		struct cpu_dbs_info_s *j_dbs_info;

		j_dbs_info = &per_cpu(cpu_dbs_info, j);
		total_idle_ticks = j_dbs_info->prev_cpu_idle_up;
		tmp_idle_ticks = total_idle_ticks -
			j_dbs_info->prev_cpu_idle_down;
		j_dbs_info->prev_cpu_idle_down = total_idle_ticks;

		if (tmp_idle_ticks < idle_ticks)
			idle_ticks = tmp_idle_ticks;
	}

	/* Scale idle ticks by 100 and compare with up and down ticks */
	idle_ticks *= 100;
	down_skip[cpu] = 0;

	freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
		dbs_tuners_ins.sampling_down_factor;
	down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) *
			usecs_to_jiffies(freq_down_sampling_rate);

	if (idle_ticks > down_idle_ticks) {
		/* if we are already at the lowest speed then break out early
		 * or if we 'cannot' reduce the speed as the user might want
		 * freq_step to be zero */
		if (requested_freq[cpu] == policy->min
				|| dbs_tuners_ins.freq_step == 0)
			return;

		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;

		/* max freq cannot be less than 100. But who knows.... */
		if (unlikely(freq_step == 0))
			freq_step = 5;

		requested_freq[cpu] -= freq_step;
		if (requested_freq[cpu] < policy->min)
			requested_freq[cpu] = policy->min;

		__cpufreq_driver_target(policy,
			requested_freq[cpu],
			CPUFREQ_RELATION_H);
		return;
	}
}

static void do_dbs_timer(void *data)
{
	int i;
	down(&dbs_sem);
	for_each_online_cpu(i)
		dbs_check_cpu(i);
	schedule_delayed_work(&dbs_work,
			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
	up(&dbs_sem);
}

static inline void dbs_timer_init(void)
{
	INIT_WORK(&dbs_work, do_dbs_timer, NULL);
	schedule_delayed_work(&dbs_work,
			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
	return;
}

static inline void dbs_timer_exit(void)
{
	cancel_delayed_work(&dbs_work);
	return;
}

static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
				   unsigned int event)
{
	unsigned int cpu = policy->cpu;
	struct cpu_dbs_info_s *this_dbs_info;
	unsigned int j;

	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);

	switch (event) {
	case CPUFREQ_GOV_START:
		if ((!cpu_online(cpu)) ||
		    (!policy->cur))
			return -EINVAL;

		if (policy->cpuinfo.transition_latency >
				(TRANSITION_LATENCY_LIMIT * 1000))
			return -EINVAL;
		if (this_dbs_info->enable) /* Already enabled */
			break;
		 
		down(&dbs_sem);
		for_each_cpu_mask(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;
			j_dbs_info = &per_cpu(cpu_dbs_info, j);
			j_dbs_info->cur_policy = policy;
		
			j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
			j_dbs_info->prev_cpu_idle_down
				= j_dbs_info->prev_cpu_idle_up;
		}
		this_dbs_info->enable = 1;
		sysfs_create_group(&policy->kobj, &dbs_attr_group);
		dbs_enable++;
		/*
		 * Start the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 1) {
			unsigned int latency;
			/* policy latency is in nS. Convert it to uS first */

			latency = policy->cpuinfo.transition_latency;
			if (latency < 1000)
				latency = 1000;

			def_sampling_rate = (latency / 1000) *
					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
			dbs_tuners_ins.sampling_rate = def_sampling_rate;
			dbs_tuners_ins.ignore_nice = 0;
			dbs_tuners_ins.freq_step = 5;

			dbs_timer_init();
		}
		
		up(&dbs_sem);
		break;

	case CPUFREQ_GOV_STOP:
		down(&dbs_sem);
		this_dbs_info->enable = 0;
		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
		dbs_enable--;
		/*
		 * Stop the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 0) 
			dbs_timer_exit();
		
		up(&dbs_sem);

		break;

	case CPUFREQ_GOV_LIMITS:
		down(&dbs_sem);
		if (policy->max < this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(
					this_dbs_info->cur_policy,
				       	policy->max, CPUFREQ_RELATION_H);
		else if (policy->min > this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(
					this_dbs_info->cur_policy,
				       	policy->min, CPUFREQ_RELATION_L);
		up(&dbs_sem);
		break;
	}
	return 0;
}

static struct cpufreq_governor cpufreq_gov_dbs = {
	.name		= "conservative",
	.governor	= cpufreq_governor_dbs,
	.owner		= THIS_MODULE,
};

static int __init cpufreq_gov_dbs_init(void)
{
	return cpufreq_register_governor(&cpufreq_gov_dbs);
}

static void __exit cpufreq_gov_dbs_exit(void)
{
	/* Make sure that the scheduled work is indeed not running */
	flush_scheduled_work();

	cpufreq_unregister_governor(&cpufreq_gov_dbs);
}


MODULE_AUTHOR ("Alexander Clouter <alex-kernel@digriz.org.uk>");
MODULE_DESCRIPTION ("'cpufreq_conservative' - A dynamic cpufreq governor for "
		"Low Latency Frequency Transition capable processors "
		"optimised for use in a battery environment");
MODULE_LICENSE ("GPL");

module_init(cpufreq_gov_dbs_init);
module_exit(cpufreq_gov_dbs_exit);

Grazie Mille!!

[Andmart]

Posto qui alcuni semplici istruzioni per verificare l'effettivo scaling dinamico della frequenza con il demone Powernowd nel caso sia attivato il governor userspace nel kernel.

Un piccola nota: a partire dal kernel 2.6.10 questo demone diviene inutile. Infatti è sufficiente compilare il kernel in attivando l'opzione ondemand perché faccia tutto da solo senza bisogno d'aiuto....
Attenzione: dalla versione 2.6.12 del kernel è stato aggiunto un nuovo governor detto conservative.

Eseguite il comando

# cat /proc/cpuinfo

Otterrete un output simile a questo:

[andrea@KAOS andrea]$ cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 6
model           : 8
model name      : mobile AMD Athlon(tm) XP 1400+
stepping        : 0
cpu MHz         : 1200.559
cache size      : 256 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 mmx fxsr sse syscall mp mmxext 3dnowext 3dnow
bogomips        : 989.86

Come potete vedere l'indicazione della frequenza del processore è inevitabilmente sbagliata... Infatti il mio computer era a riposo.... Quindi la frequenza era molto più bassa... Ma quanto? Per saperlo diamo il comando che fornisce la frequenza in khz:

[andrea@KAOS andrea]$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed
500000

Ora annotiamo i due parametri che variranno durante il nostro test (sempre se il nostro demone non fa strani scherzi )
bogomips : 989.86
frequenza: 500Mhz

Assicuriamoci che Powernowd sia in esecuzione. Se non lo fosse diamo il comando da root:

[root@KAOS andrea]# powernowd
powernowd: PowerNow Daemon v0.96, (c) 2003-2005 John Clemens
powernowd: Found 1 cpu:  -- 1 thread (or core) per physical cpu
/sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies: No such file or directory
powernowd:   cpu0: 500Mhz - 1200Mhz (8 steps)

Ora procediamo con test: facciamo lavorare la cpu con il comando

[andrea@KAOS andrea]$ cat /dev/urandom > /dev/null

Ora eseguiamo i comandi:

[andrea@KAOS andrea]$ cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 6
model           : 8
model name      : mobile AMD Athlon(tm) XP 1400+
stepping        : 0
cpu MHz         : 1200.559
cache size      : 256 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 mmx fxsr sse syscall mp mmxext 3dnowext 3dnow
bogomips        : 2375.68

e

[andrea@KAOS andrea]$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed
1200000

Come potete vedere il demone riga dritto e lo scaling è avvenuto correttamente.

Interrompendo

[andrea@KAOS andrea]$ cat /dev/urandom > /dev/null

premendo ctrl+C sulla tastiera ed eseguendo di nuovo

[andrea@KAOS andrea]$ cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed
500000

cotrolliamo che la frequenza sia ritornata al suo posto.


Fra l'altro possiamo modificare -manualmente (provateci con Windows e fatemi sapere )-, all'occorrenza la frequenza, mediante:

# echo 700000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed

Spero che questo mini tutorial sia d'aiuto a chi ha problemi con lo scaling del processore....

Nel caso fosse attivato ondemand o conservative per verificare la frequenza della cpu si può usare il comando:

# cat /proc/cpuinfo

oppure

cat /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq

Per attivare ondemand andare i in /etc/rc.d/rc.local e
aggiugere questa riga:

echo ondemand > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor

Riavviare.

Per attivare conservative andare i in /etc/rc.d/rc.local e
aggiugere questa riga:

echo conservative > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor

Riavviare.

Per conservative e ondemand è necessario avere attivato sysfs nel kernel.

Ciao a tutti!

[Andmart]

Premessa dell'autore:

You can always use a userspace governer. I've attached the one I use.

Every five seconds (you can make it faster if you wish, but that seems
about right for my usage patterns), the program reads the load
average, and decides whether to adjust the CPU frequency. If the one
second load average is above $FASTTRESHHOLD, the frequency will be
stepped up by $FASTINC; otherwise if it's above $SLOWTHRESHHOLD, it's
incremented by $SLOWINC. If the 15-second load average is below
$DECTHRESSHOLD, the frequency is stepped downwards by $DEC. So you
get fast increases, and slow decreases, but becasue the time constant
for the decrease is long, you can get good response for a load spike,
then fairly rapid decrease. The aim is to keep the load average
around 0.9.

#!/bin/sh

# Seconds to sleep between adjustments
INTERVAL=5

# The controller increments the throttling state by FASTINC
# if the load average is over FASTTRHESHHOLD.
# Thresholds are in percentage points load average -- i.e., the one
# second load average of 1.0 corresponds to a threshold of 100.
FASTINC=3
FASTTHRESHOLD=100
# Slow increment
SLOWINC=1
SLOWTHRESHOLD=80
# Decrement
DEC=1
DECTHRESHOLD=500

cd /sys/devices/system/cpu/cpu0/cpufreq

# Do some parameter checks.
[ $FASTTHRESHOLD -le $SLOWTHRESHOLD ] && {
echo >&2 "Fast Threshold $FASTTHRESHOLD must be greater than the"
echo >&2 "slow threshold $SLOWTHRESHOLD"
exit 1
}

[ \( $SLOWINC -ge 1 \) -a \( $FASTINC -ge 1 \) -a \( $DEC -ge 1 \) ] || {
echo >&2 "Increments must all be small integers in the range 1 to 7"
exit 1
}

# convert a two dec place number to an int scaled by 100.
function to_int()
{
val=$1
OIFS="$IFS"
IFS="."
set $val
IFS="$OIFS"
expr $1 \* 100 + $2
}

# get load averages
function loadavg()
{
read onesec fivesec fifteensec rest < /proc/loadavg
onesec=`to_int $onesec`
fifteensec=`to_int $fifteensec`
}

function getspeeds()
{
echo userspace > scaling_governor
set `cat scaling_available_frequencies`
i=0
for j
do
i=`expr $i + 1`
eval speed$i=$j
done
nspeeds=$i
}

# Get current throttling factor.
# This can be changed automatically by the BIOS in response to power
# events (e.g., AC coming on line).
function throttle() {
< scaling_cur_freq read curfreq
i=1;
while [ $i -lt $nspeeds ]
do
eval [ \$speed$i -eq 0$curfreq ] && expr $nspeeds - $i
i=`expr $i + 1`
done
}

function set_speed() {
x=`expr $nspeeds - $1`
eval speed=\$speed$x
echo $speed > scaling_setspeed
}

# Increase the effective processor speed.
function up()
{
[ $current_throttle -eq 0 ] || {
current_throttle=`expr $current_throttle - $1`
[ $current_throttle -lt 0 ] && current_throttle=0
set_speed $current_throttle
}
}

# Decrease the effective processor speed.
function down()
{
[ $current_throttle -eq $nspeeds ] || {
current_throttle=`expr $current_throttle + $1`
[ $current_throttle -gt $nspeeds ] && current_throttle=$nspeeds
set_speed $current_throttle
}
}


getspeeds
current_throttle=`throttle`
while sleep $INTERVAL
do
loadavg

# Go up fast, then tail off.
#
if [ $onesec -gt $FASTTHRESHOLD ]
then
up $FASTINC
elif [ $onesec -gt $SLOWTHRESHOLD ]
then
up $SLOWINC
elif [ $fifteensec -lt $DECTHRESHOLD ]
then
down $DEC
fi
done

Quello che io voglio faccia:
--> aumenti la frequenza velocemente nel tempo ma con a passi molto piccoli indipendentemente dalla richiesta della CPU. Mi spiego. Ondemand e Powernowd aumentano velocemente nel tempo ma in base al carico di lavoro. Se vedono che la cpu lavora al 100% loro aumentano subito la frequenza (e qui mi sta bene) ma settano subito la frequenza massima. Io voglio che nel caso specificato la frequenza non sia cmq quella massima ma che l'aumento avvenga prontamente. Riassumendo: aumento pronto ma graduale.
--> appena cala la richiesta di potenza immediato abbassamento della cpu.

INTERESSANTE: http://n-dimensional.de/projects/cpufreq/algorithms.txt

[Andmart]

Originariamente inviato da ingeniere

posta amico, non ci tireremo certo indietro!

Quasi dimenticavo: la configurazione di cui parlavo era nel file cpufreqd.conf, direi più semplice ed immediata di quella che dici tu, che certamente funziona. Se facessero powernowd configurabile come cpufreqd per me sarebbe il massimo

Powernow, giusto per la cronaca è configurabile attraverso /etc/default/powernowd

[ingeniere]

Allora, questo fantomatico script?

[Andmart]

Ce l'hai sopra la testa... Anzi.. 2 post sopra!

[davide86]

ciao a tutti,
ho un acer ferrari 4000 e debian sid.
impostando la frequenza manualmente con:

# echo 700000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed

sembra effettivamente funzionare ma non funziona lo scaling automatico

PS: il file /etc/rc.d/rc.local non esiste.