CPU frequency and voltage scaling code in the Linux(TM) kernel L i n u x C P U F r e q C P U F r e q G o v e r n o r s - information for users and developers - Dominik Brodowski some additions and corrections by Nico Golde Clock scaling allows you to change the clock speed of the CPUs on the fly. This is a nice method to save battery power, because the lower the clock speed, the less power the CPU consumes. Contents: --------- 1. What is a CPUFreq Governor? 2. Governors In the Linux Kernel 2.1 Performance 2.2 Powersave 2.3 Userspace 2.4 Ondemand 2.5 Conservative 2.6 Interactive 3. The Governor Interface in the CPUfreq Core 1. What Is A CPUFreq Governor? ============================== Most cpufreq drivers (in fact, all except one, longrun) or even most cpu frequency scaling algorithms only offer the CPU to be set to one frequency. In order to offer dynamic frequency scaling, the cpufreq core must be able to tell these drivers of a "target frequency". So these specific drivers will be transformed to offer a "->target" call instead of the existing "->setpolicy" call. For "longrun", all stays the same, though. How to decide what frequency within the CPUfreq policy should be used? That's done using "cpufreq governors". Two are already in this patch -- they're the already existing "powersave" and "performance" which set the frequency statically to the lowest or highest frequency, respectively. At least two more such governors will be ready for addition in the near future, but likely many more as there are various different theories and models about dynamic frequency scaling around. Using such a generic interface as cpufreq offers to scaling governors, these can be tested extensively, and the best one can be selected for each specific use. Basically, it's the following flow graph: CPU can be set to switch independently | CPU can only be set within specific "limits" | to specific frequencies "CPUfreq policy" consists of frequency limits (policy->{min,max}) and CPUfreq governor to be used / \ / \ / the cpufreq governor decides / (dynamically or statically) / what target_freq to set within / the limits of policy->{min,max} / \ / \ Using the ->setpolicy call, Using the ->target call, the limits and the the frequency closest "policy" is set. to target_freq is set. It is assured that it is within policy->{min,max} 2. Governors In the Linux Kernel ================================ 2.1 Performance --------------- The CPUfreq governor "performance" sets the CPU statically to the highest frequency within the borders of scaling_min_freq and scaling_max_freq. 2.2 Powersave ------------- The CPUfreq governor "powersave" sets the CPU statically to the lowest frequency within the borders of scaling_min_freq and scaling_max_freq. 2.3 Userspace ------------- The CPUfreq governor "userspace" allows the user, or any userspace program running with UID "root", to set the CPU to a specific frequency by making a sysfs file "scaling_setspeed" available in the CPU-device directory. 2.4 Ondemand ------------ The CPUfreq governor "ondemand" sets the CPU depending on the current usage. To do this the CPU must have the capability to switch the frequency very quickly. There are a number of sysfs file accessible parameters: sampling_rate: measured in uS (10^-6 seconds), this is how often you want the kernel to look at the CPU usage and to make decisions on what to do about the frequency. Typically this is set to values of around '10000' or more. It's default value is (cmp. with users-guide.txt): transition_latency * 1000 Be aware that transition latency is in ns and sampling_rate is in us, so you get the same sysfs value by default. Sampling rate should always get adjusted considering the transition latency To set the sampling rate 750 times as high as the transition latency in the bash (as said, 1000 is default), do: echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \ >ondemand/sampling_rate sampling_rate_min: The sampling rate is limited by the HW transition latency: transition_latency * 100 Or by kernel restrictions: If CONFIG_NO_HZ is set, the limit is 10ms fixed. If CONFIG_NO_HZ is not set or nohz=off boot parameter is used, the limits depend on the CONFIG_HZ option: HZ=1000: min=20000us (20ms) HZ=250: min=80000us (80ms) HZ=100: min=200000us (200ms) The highest value of kernel and HW latency restrictions is shown and used as the minimum sampling rate. up_threshold: defines what the average CPU usage between the samplings of 'sampling_rate' needs to be for the kernel to make a decision on whether it should increase the frequency. For example when it is set to its default value of '95' it means that between the checking intervals the CPU needs to be on average more than 95% in use to then decide that the CPU frequency needs to be increased. ignore_nice_load: this parameter takes a value of '0' or '1'. When set to '0' (its default), all processes are counted towards the 'cpu utilisation' value. When set to '1', the processes that are run with a 'nice' value will not count (and thus be ignored) in the overall usage calculation. This is useful if you are running a CPU intensive calculation on your laptop that you do not care how long it takes to complete as you can 'nice' it and prevent it from taking part in the deciding process of whether to increase your CPU frequency. sampling_down_factor: this parameter controls the rate at which the kernel makes a decision on when to decrease the frequency while running at top speed. When set to 1 (the default) decisions to reevaluate load are made at the same interval regardless of current clock speed. But when 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. 2.5 Conservative ---------------- The CPUfreq governor "conservative", much like the "ondemand" governor, sets the CPU depending on the current usage. It differs in behaviour in that it gracefully increases and decreases the CPU speed rather than jumping to max speed the moment there is any load on the CPU. This behaviour more suitable in a battery powered environment. The governor is tweaked in the same manner as the "ondemand" governor through sysfs with the addition of: freq_step: this describes what percentage steps the cpu freq should be increased and decreased smoothly by. By default the cpu frequency will increase in 5% chunks of your maximum cpu frequency. You can change this value to anywhere between 0 and 100 where '0' will effectively lock your CPU at a speed regardless of its load whilst '100' will, in theory, make it behave identically to the "ondemand" governor. down_threshold: same as the 'up_threshold' found for the "ondemand" governor but for the opposite direction. For example when set to its default value of '20' it means that if the CPU usage needs to be below 20% between samples to have the frequency decreased. 2.6 Interactive --------------- The CPUfreq governor "interactive" is designed for latency-sensitive, interactive workloads. This governor sets the CPU speed depending on usage, similar to "ondemand" and "conservative" governors, but with a different set of configurable behaviors. The tuneable values for this governor are: target_loads: CPU load values used to adjust speed to influence the current CPU load toward that value. In general, the lower the target load, the more often the governor will raise CPU speeds to bring load below the target. The format is a single target load, optionally followed by pairs of CPU speeds and CPU loads to target at or above those speeds. Colons can be used between the speeds and associated target loads for readability. For example: 85 1000000:90 1700000:99 targets CPU load 85% below speed 1GHz, 90% at or above 1GHz, until 1.7GHz and above, at which load 99% is targeted. If speeds are specified these must appear in ascending order. Higher target load values are typically specified for higher speeds, that is, target load values also usually appear in an ascending order. The default is target load 90% for all speeds. min_sample_time: The minimum amount of time to spend at the current frequency before ramping down. Default is 80000 uS. hispeed_freq: An intermediate "hi speed" at which to initially ramp when CPU load hits the value specified in go_hispeed_load. If load stays high for the amount of time specified in above_hispeed_delay, then speed may be bumped higher. Default is the maximum speed allowed by the policy at governor initialization time. go_hispeed_load: The CPU load at which to ramp to hispeed_freq. Default is 99%. above_hispeed_delay: When speed is at or above hispeed_freq, wait for this long before raising speed in response to continued high load. The format is a single delay value, optionally followed by pairs of CPU speeds and the delay to use at or above those speeds. Colons can be used between the speeds and associated delays for readability. For example: 80000 1300000:200000 1500000:40000 uses delay 80000 uS until CPU speed 1.3 GHz, at which speed delay 200000 uS is used until speed 1.5 GHz, at which speed (and above) delay 40000 uS is used. If speeds are specified these must appear in ascending order. Default is 20000 uS. timer_rate: Sample rate for reevaluating CPU load when the CPU is not idle. A deferrable timer is used, such that the CPU will not be woken from idle to service this timer until something else needs to run. (The maximum time to allow deferring this timer when not running at minimum speed is configurable via timer_slack.) Default is 20000 uS. timer_slack: Maximum additional time to defer handling the governor sampling timer beyond timer_rate when running at speeds above the minimum. For platforms that consume additional power at idle when CPUs are running at speeds greater than minimum, this places an upper bound on how long the timer will be deferred prior to re-evaluating load and dropping speed. For example, if timer_rate is 20000uS and timer_slack is 10000uS then timers will be deferred for up to 30msec when not at lowest speed. A value of -1 means defer timers indefinitely at all speeds. Default is 80000 uS. boost: If non-zero, immediately boost speed of all CPUs to at least hispeed_freq until zero is written to this attribute. If zero, allow CPU speeds to drop below hispeed_freq according to load as usual. Default is zero. boostpulse: On each write, immediately boost speed of all CPUs to hispeed_freq for at least the period of time specified by boostpulse_duration, after which speeds are allowed to drop below hispeed_freq according to load as usual. boostpulse_duration: Length of time to hold CPU speed at hispeed_freq on a write to boostpulse, before allowing speed to drop according to load as usual. Default is 80000 uS. 3. The Governor Interface in the CPUfreq Core ============================================= A new governor must register itself with the CPUfreq core using "cpufreq_register_governor". The struct cpufreq_governor, which has to be passed to that function, must contain the following values: governor->name - A unique name for this governor governor->governor - The governor callback function governor->owner - .THIS_MODULE for the governor module (if appropriate) The governor->governor callback is called with the current (or to-be-set) cpufreq_policy struct for that CPU, and an unsigned int event. The following events are currently defined: CPUFREQ_GOV_START: This governor shall start its duty for the CPU policy->cpu CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU policy->cpu CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to policy->min and policy->max. If you need other "events" externally of your driver, _only_ use the cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the CPUfreq core to ensure proper locking. The CPUfreq governor may call the CPU processor driver using one of these two functions: int cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); target_freq must be within policy->min and policy->max, of course. What's the difference between these two functions? When your governor still is in a direct code path of a call to governor->governor, the per-CPU cpufreq lock is still held in the cpufreq core, and there's no need to lock it again (in fact, this would cause a deadlock). So use __cpufreq_driver_target only in these cases. In all other cases (for example, when there's a "daemonized" function that wakes up every second), use cpufreq_driver_target to lock the cpufreq per-CPU lock before the command is passed to the cpufreq processor driver.