From mboxrd@z Thu Jan 1 00:00:00 1970 From: venkatesh.pallipadi@intel.com Subject: [patch 6/6] cpufreq: Add idle microaccounting in ondemand governor Date: Thu, 17 Jul 2008 13:56:00 -0700 Message-ID: <20080717205616.663052000@intel.com> References: <20080717205554.214645000@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline; filename=intro_idle_microaccounting.patch List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=m.gmane.org+glkc-cpufreq=m.gmane.org@lists.linux.org.uk To: cpufreq@www.linux.org.uk Cc: davej@redhat.com Use get_cpu_idle_time_us() to get micro-accounted idle information. This enables ondemand to get more accurate idle and busy timings than the jiffy based calculation. As a result, we can decrease the ondemand safety gaurd band from 80-10 to 95-3. Results in more aggressive power savings. Signed-off-by: Venkatesh Pallipadi --- drivers/cpufreq/cpufreq_ondemand.c | 46 ++++++++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-) Index: linux-2.6/drivers/cpufreq/cpufreq_ondemand.c =================================================================== --- linux-2.6.orig/drivers/cpufreq/cpufreq_ondemand.c 2008-07-17 13:19:08.000000000 -0700 +++ linux-2.6/drivers/cpufreq/cpufreq_ondemand.c 2008-07-17 13:27:33.000000000 -0700 @@ -18,6 +18,9 @@ #include #include #include +#include +#include +#include /* * dbs is used in this file as a shortform for demandbased switching @@ -26,6 +29,8 @@ #define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10) #define DEF_FREQUENCY_UP_THRESHOLD (80) +#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3) +#define MICRO_FREQUENCY_UP_THRESHOLD (95) #define MIN_FREQUENCY_UP_THRESHOLD (11) #define MAX_FREQUENCY_UP_THRESHOLD (100) @@ -58,6 +63,7 @@ enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE} struct cpu_dbs_info_s { cputime64_t prev_cpu_idle; cputime64_t prev_cpu_wall; + cputime64_t prev_cpu_nice; struct cpufreq_policy *cur_policy; struct delayed_work work; struct cpufreq_frequency_table *freq_table; @@ -97,7 +103,8 @@ static struct dbs_tuners { .powersave_bias = 0, }; -static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall) +static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu, + cputime64_t *wall) { cputime64_t idle_time; cputime64_t cur_wall_time; @@ -123,6 +130,33 @@ static inline cputime64_t get_cpu_idle_t return idle_time; } +static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall) +{ + u64 idle_time = get_cpu_idle_time_us(cpu, wall); + + if (idle_time == -1ULL) + return get_cpu_idle_time_jiffy(cpu, wall); + + if (dbs_tuners_ins.ignore_nice) { + cputime64_t cur_nice; + unsigned long cur_nice_jiffies; + struct cpu_dbs_info_s *dbs_info; + + dbs_info = &per_cpu(cpu_dbs_info, cpu); + cur_nice = cputime64_sub(kstat_cpu(cpu).cpustat.nice, + 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); + dbs_info->prev_cpu_nice = kstat_cpu(cpu).cpustat.nice; + return idle_time + jiffies_to_usecs(cur_nice_jiffies); + } + return idle_time; +} + /* * Find right freq to be set now with powersave_bias on. * Returns the freq_hi to be used right now and will set freq_hi_jiffies, @@ -602,6 +636,16 @@ EXPORT_SYMBOL(cpufreq_gov_ondemand); static int __init cpufreq_gov_dbs_init(void) { + cputime64_t wall; + u64 idle_time = get_cpu_idle_time_us(smp_processor_id(), &wall); + + if (idle_time != -1ULL) { + /* Idle micro accounting is supported. Use finer thresholds */ + dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD; + dbs_tuners_ins.down_differential = + MICRO_FREQUENCY_DOWN_DIFFERENTIAL; + } + kondemand_wq = create_workqueue("kondemand"); if (!kondemand_wq) { printk(KERN_ERR "Creation of kondemand failed\n"); --