Re: [PATCH 1/1] cpufreq: sampling_down_factor to improve ondemand performance
From: Venkatesh Pallipadi
Date: Wed Oct 06 2010 - 21:44:23 EST
On Wed, Oct 6, 2010 at 1:54 PM, David C Niemi <dniemi@xxxxxxxxxxxx> wrote:
> Adds a new global tunable, sampling_down_factor. Set to 1 it makes no
> changes from existing behavior, but set to greater than 1 (e.g. 100)
> it acts as a multiplier for the scheduling interval for reevaluating
> load when the CPU is at its top speed due to high load. This improves
> performance by reducing the overhead of load evaluation and helping
> the CPU stay at its top speed when truly busy, rather than shifting
> back and forth in speed. This tunable has no effect on behavior at
> lower speeds/lower CPU loads.
>
> This patch is against 2.6.36-rc6.
>
> This patch should help solve kernel bug 19672 "ondemand is slow".
>
> Signed-off-by: David Niemi <dniemi@xxxxxxxxxxxx>
> CC: Venkatesh Pallipadi <venki@xxxxxxxxxx>
> CC: Dave Jones <davej@xxxxxxxxxx>
> CC: Daniel Hollocher <danielhollocher@xxxxxxxxx>
> CC: <cpufreq-list@xxxxxxxxxxxxxxx>
> CC: <linux-kernel@xxxxxxxxxxxxxxx>
Acked-by: Venkatesh Pallipadi <venki@xxxxxxxxxx>
> ---
> cpufreq_ondemand.c | 42 +++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 41 insertions(+), 1 deletion(-)
>
> diff --git a/linux-2.6.36-rc6/drivers/cpufreq/cpufreq_ondemand.c.orig b/linux-2.6.36-rc6/drivers/cpufreq/cpufreq_ondemand.c
> index 7b50936..c631f27 100644
> --- a/linux-2.6.36-rc6/drivers/cpufreq/cpufreq_ondemand.c.orig
> +++ b/linux-2.6.36-rc6/drivers/cpufreq/cpufreq_ondemand.c
> @@ -30,6 +30,8 @@
>
> #define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10)
> #define DEF_FREQUENCY_UP_THRESHOLD (80)
> +#define DEF_SAMPLING_DOWN_FACTOR (1)
> +#define MAX_SAMPLING_DOWN_FACTOR (100000)
> #define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3)
> #define MICRO_FREQUENCY_UP_THRESHOLD (95)
> #define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000)
> @@ -82,6 +84,7 @@ struct cpu_dbs_info_s {
> unsigned int freq_lo;
> unsigned int freq_lo_jiffies;
> unsigned int freq_hi_jiffies;
> + unsigned int rate_mult;
> int cpu;
> unsigned int sample_type:1;
> /*
> @@ -108,10 +111,12 @@ static struct dbs_tuners {
> unsigned int up_threshold;
> unsigned int down_differential;
> unsigned int ignore_nice;
> + unsigned int sampling_down_factor;
> unsigned int powersave_bias;
> unsigned int io_is_busy;
> } dbs_tuners_ins = {
> .up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
> + .sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
> .down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
> .ignore_nice = 0,
> .powersave_bias = 0,
> @@ -259,6 +264,7 @@ static ssize_t show_##file_name \
> show_one(sampling_rate, sampling_rate);
> show_one(io_is_busy, io_is_busy);
> show_one(up_threshold, up_threshold);
> +show_one(sampling_down_factor, sampling_down_factor);
> show_one(ignore_nice_load, ignore_nice);
> show_one(powersave_bias, powersave_bias);
>
> @@ -340,6 +346,29 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
> return count;
> }
>
> +static ssize_t store_sampling_down_factor(struct kobject *a,
> + struct attribute *b, const char *buf, size_t count)
> +{
> + unsigned int input, j;
> + int ret;
> + ret = sscanf(buf, "%u", &input);
> +
> + if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
> + return -EINVAL;
> + mutex_lock(&dbs_mutex);
> + dbs_tuners_ins.sampling_down_factor = input;
> +
> + /* Reset down sampling multiplier in case it was active */
> + for_each_online_cpu(j) {
> + struct cpu_dbs_info_s *dbs_info;
> + dbs_info = &per_cpu(od_cpu_dbs_info, j);
> + dbs_info->rate_mult = 1;
> + }
> + mutex_unlock(&dbs_mutex);
> +
> + return count;
> +}
> +
> static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
> const char *buf, size_t count)
> {
> @@ -401,6 +430,7 @@ static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
> define_one_global_rw(sampling_rate);
> define_one_global_rw(io_is_busy);
> define_one_global_rw(up_threshold);
> +define_one_global_rw(sampling_down_factor);
> define_one_global_rw(ignore_nice_load);
> define_one_global_rw(powersave_bias);
>
> @@ -409,6 +439,7 @@ static struct attribute *dbs_attributes[] = {
> &sampling_rate_min.attr,
> &sampling_rate.attr,
> &up_threshold.attr,
> + &sampling_down_factor.attr,
> &ignore_nice_load.attr,
> &powersave_bias.attr,
> &io_is_busy.attr,
> @@ -562,6 +593,10 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
>
> /* 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)
> + this_dbs_info->rate_mult =
> + dbs_tuners_ins.sampling_down_factor;
> dbs_freq_increase(policy, policy->max);
> return;
> }
> @@ -584,6 +619,9 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
> (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;
>
> @@ -607,7 +645,8 @@ static void do_dbs_timer(struct work_struct *work)
> int sample_type = dbs_info->sample_type;
>
> /* We want all CPUs to do sampling nearly on same jiffy */
> - int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
> + int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate
> + * dbs_info->rate_mult);
>
> if (num_online_cpus() > 1)
> delay -= jiffies % delay;
> @@ -711,6 +750,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
> }
> }
> this_dbs_info->cpu = cpu;
> + this_dbs_info->rate_mult = 1;
> ondemand_powersave_bias_init_cpu(cpu);
> /*
> * Start the timerschedule work, when this governor
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/