Re: [RFC/RFT][PATCH 1/2] cpufreq: schedutil: Use policy-dependent transition delays

From: Rafael J. Wysocki
Date: Fri Apr 14 2017 - 18:58:08 EST


On Tuesday, April 11, 2017 12:20:41 AM Rafael J. Wysocki wrote:
> From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
>
> Make the schedutil governor take the initial (default) value of the
> rate_limit_us sysfs attribute from the (new) transition_delay_us
> policy parameter (to be set by the scaling driver).
>
> That will allow scaling drivers to make schedutil use smaller default
> values of rate_limit_us and reduce the default average time interval
> between consecutive frequency changes.
>
> Make intel_pstate set transition_delay_us to 500.
>
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> ---
>
> This is a replacement for https://patchwork.kernel.org/patch/9671831/

Any concerns about this one?

>
> ---
> drivers/cpufreq/intel_pstate.c | 2 ++
> include/linux/cpufreq.h | 7 +++++++
> kernel/sched/cpufreq_schedutil.c | 15 ++++++++++-----
> 3 files changed, 19 insertions(+), 5 deletions(-)
>
> Index: linux-pm/include/linux/cpufreq.h
> ===================================================================
> --- linux-pm.orig/include/linux/cpufreq.h
> +++ linux-pm/include/linux/cpufreq.h
> @@ -120,6 +120,13 @@ struct cpufreq_policy {
> bool fast_switch_possible;
> bool fast_switch_enabled;
>
> + /*
> + * Preferred average time interval between consecutive invocations of
> + * the driver to set the frequency for this policy. To be set by the
> + * scaling driver (0, which is the default, means no preference).
> + */
> + unsigned int transition_delay_us;
> +
> /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
> unsigned int cached_target_freq;
> int cached_resolved_idx;
> Index: linux-pm/kernel/sched/cpufreq_schedutil.c
> ===================================================================
> --- linux-pm.orig/kernel/sched/cpufreq_schedutil.c
> +++ linux-pm/kernel/sched/cpufreq_schedutil.c
> @@ -491,7 +491,6 @@ static int sugov_init(struct cpufreq_pol
> {
> struct sugov_policy *sg_policy;
> struct sugov_tunables *tunables;
> - unsigned int lat;
> int ret = 0;
>
> /* State should be equivalent to EXIT */
> @@ -530,10 +529,16 @@ static int sugov_init(struct cpufreq_pol
> goto stop_kthread;
> }
>
> - tunables->rate_limit_us = LATENCY_MULTIPLIER;
> - lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
> - if (lat)
> - tunables->rate_limit_us *= lat;
> + if (policy->transition_delay_us) {
> + tunables->rate_limit_us = policy->transition_delay_us;
> + } else {
> + unsigned int lat;
> +
> + tunables->rate_limit_us = LATENCY_MULTIPLIER;
> + lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
> + if (lat)
> + tunables->rate_limit_us *= lat;
> + }
>
> policy->governor_data = sg_policy;
> sg_policy->tunables = tunables;
> Index: linux-pm/drivers/cpufreq/intel_pstate.c
> ===================================================================
> --- linux-pm.orig/drivers/cpufreq/intel_pstate.c
> +++ linux-pm/drivers/cpufreq/intel_pstate.c
> @@ -41,6 +41,7 @@
> #define INTEL_PSTATE_HWP_SAMPLING_INTERVAL (50 * NSEC_PER_MSEC)
>
> #define INTEL_CPUFREQ_TRANSITION_LATENCY 20000
> +#define INTEL_CPUFREQ_TRANSITION_DELAY 500
>
> #ifdef CONFIG_ACPI
> #include <acpi/processor.h>
> @@ -2237,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct
> return ret;
>
> policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
> + policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
> /* This reflects the intel_pstate_get_cpu_pstates() setting. */
> policy->cur = policy->cpuinfo.min_freq;
>
>