1 CPU frequency and voltage scaling code in the Linux(TM) kernel
4 L i n u x C P U F r e q
6 C P U F r e q G o v e r n o r s
8 - information for users and developers -
11 Dominik Brodowski <linux@brodo.de>
12 some additions and corrections by Nico Golde <nico@ngolde.de>
16 Clock scaling allows you to change the clock speed of the CPUs on the
17 fly. This is a nice method to save battery power, because the lower
18 the clock speed, the less power the CPU consumes.
23 1. What is a CPUFreq Governor?
25 2. Governors In the Linux Kernel
32 3. The Governor Interface in the CPUfreq Core
36 1. What Is A CPUFreq Governor?
37 ==============================
39 Most cpufreq drivers (in fact, all except one, longrun) or even most
40 cpu frequency scaling algorithms only offer the CPU to be set to one
41 frequency. In order to offer dynamic frequency scaling, the cpufreq
42 core must be able to tell these drivers of a "target frequency". So
43 these specific drivers will be transformed to offer a "->target"
44 call instead of the existing "->setpolicy" call. For "longrun", all
45 stays the same, though.
47 How to decide what frequency within the CPUfreq policy should be used?
48 That's done using "cpufreq governors". Two are already in this patch
49 -- they're the already existing "powersave" and "performance" which
50 set the frequency statically to the lowest or highest frequency,
51 respectively. At least two more such governors will be ready for
52 addition in the near future, but likely many more as there are various
53 different theories and models about dynamic frequency scaling
54 around. Using such a generic interface as cpufreq offers to scaling
55 governors, these can be tested extensively, and the best one can be
56 selected for each specific use.
58 Basically, it's the following flow graph:
60 CPU can be set to switch independently | CPU can only be set
61 within specific "limits" | to specific frequencies
64 consists of frequency limits (policy->{min,max})
65 and CPUfreq governor to be used
68 / the cpufreq governor decides
69 / (dynamically or statically)
70 / what target_freq to set within
71 / the limits of policy->{min,max}
74 Using the ->setpolicy call, Using the ->target call,
75 the limits and the the frequency closest
76 "policy" is set. to target_freq is set.
78 is within policy->{min,max}
81 2. Governors In the Linux Kernel
82 ================================
87 The CPUfreq governor "performance" sets the CPU statically to the
88 highest frequency within the borders of scaling_min_freq and
95 The CPUfreq governor "powersave" sets the CPU statically to the
96 lowest frequency within the borders of scaling_min_freq and
103 The CPUfreq governor "userspace" allows the user, or any userspace
104 program running with UID "root", to set the CPU to a specific frequency
105 by making a sysfs file "scaling_setspeed" available in the CPU-device
112 The CPUfreq governor "ondemand" sets the CPU depending on the
113 current usage. To do this the CPU must have the capability to
114 switch the frequency very quickly. There are a number of sysfs file
115 accessible parameters:
117 sampling_rate: measured in uS (10^-6 seconds), this is how often you
118 want the kernel to look at the CPU usage and to make decisions on
119 what to do about the frequency. Typically this is set to values of
120 around '10000' or more. It's default value is (cmp. with users-guide.txt):
121 transition_latency * 1000
122 Be aware that transition latency is in ns and sampling_rate is in us, so you
123 get the same sysfs value by default.
124 Sampling rate should always get adjusted considering the transition latency
125 To set the sampling rate 750 times as high as the transition latency
126 in the bash (as said, 1000 is default), do:
127 echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \
128 >ondemand/sampling_rate
130 show_sampling_rate_min:
131 The sampling rate is limited by the HW transition latency:
132 transition_latency * 100
133 Or by kernel restrictions:
134 If CONFIG_NO_HZ is set, the limit is 10ms fixed.
135 If CONFIG_NO_HZ is not set or no_hz=off boot parameter is used, the
136 limits depend on the CONFIG_HZ option:
137 HZ=1000: min=20000us (20ms)
138 HZ=250: min=80000us (80ms)
139 HZ=100: min=200000us (200ms)
140 The highest value of kernel and HW latency restrictions is shown and
141 used as the minimum sampling rate.
143 show_sampling_rate_max: THIS INTERFACE IS DEPRECATED, DON'T USE IT.
145 up_threshold: defines what the average CPU usage between the samplings
146 of 'sampling_rate' needs to be for the kernel to make a decision on
147 whether it should increase the frequency. For example when it is set
148 to its default value of '95' it means that between the checking
149 intervals the CPU needs to be on average more than 95% in use to then
150 decide that the CPU frequency needs to be increased.
152 ignore_nice_load: this parameter takes a value of '0' or '1'. When
153 set to '0' (its default), all processes are counted towards the
154 'cpu utilisation' value. When set to '1', the processes that are
155 run with a 'nice' value will not count (and thus be ignored) in the
156 overall usage calculation. This is useful if you are running a CPU
157 intensive calculation on your laptop that you do not care how long it
158 takes to complete as you can 'nice' it and prevent it from taking part
159 in the deciding process of whether to increase your CPU frequency.
161 sampling_down_factor: this parameter controls the rate at which the
162 kernel makes a decision on when to decrease the frequency while running
163 at top speed. When set to 1 (the default) decisions to reevaluate load
164 are made at the same interval regardless of current clock speed. But
165 when set to greater than 1 (e.g. 100) it acts as a multiplier for the
166 scheduling interval for reevaluating load when the CPU is at its top
167 speed due to high load. This improves performance by reducing the overhead
168 of load evaluation and helping the CPU stay at its top speed when truly
169 busy, rather than shifting back and forth in speed. This tunable has no
170 effect on behavior at lower speeds/lower CPU loads.
176 The CPUfreq governor "conservative", much like the "ondemand"
177 governor, sets the CPU depending on the current usage. It differs in
178 behaviour in that it gracefully increases and decreases the CPU speed
179 rather than jumping to max speed the moment there is any load on the
180 CPU. This behaviour more suitable in a battery powered environment.
181 The governor is tweaked in the same manner as the "ondemand" governor
182 through sysfs with the addition of:
184 freq_step: this describes what percentage steps the cpu freq should be
185 increased and decreased smoothly by. By default the cpu frequency will
186 increase in 5% chunks of your maximum cpu frequency. You can change this
187 value to anywhere between 0 and 100 where '0' will effectively lock your
188 CPU at a speed regardless of its load whilst '100' will, in theory, make
189 it behave identically to the "ondemand" governor.
191 down_threshold: same as the 'up_threshold' found for the "ondemand"
192 governor but for the opposite direction. For example when set to its
193 default value of '20' it means that if the CPU usage needs to be below
194 20% between samples to have the frequency decreased.
196 3. The Governor Interface in the CPUfreq Core
197 =============================================
199 A new governor must register itself with the CPUfreq core using
200 "cpufreq_register_governor". The struct cpufreq_governor, which has to
201 be passed to that function, must contain the following values:
203 governor->name - A unique name for this governor
204 governor->governor - The governor callback function
205 governor->owner - .THIS_MODULE for the governor module (if
208 The governor->governor callback is called with the current (or to-be-set)
209 cpufreq_policy struct for that CPU, and an unsigned int event. The
210 following events are currently defined:
212 CPUFREQ_GOV_START: This governor shall start its duty for the CPU
214 CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU
216 CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to
217 policy->min and policy->max.
219 If you need other "events" externally of your driver, _only_ use the
220 cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the
221 CPUfreq core to ensure proper locking.
224 The CPUfreq governor may call the CPU processor driver using one of
227 int cpufreq_driver_target(struct cpufreq_policy *policy,
228 unsigned int target_freq,
229 unsigned int relation);
231 int __cpufreq_driver_target(struct cpufreq_policy *policy,
232 unsigned int target_freq,
233 unsigned int relation);
235 target_freq must be within policy->min and policy->max, of course.
236 What's the difference between these two functions? When your governor
237 still is in a direct code path of a call to governor->governor, the
238 per-CPU cpufreq lock is still held in the cpufreq core, and there's
239 no need to lock it again (in fact, this would cause a deadlock). So
240 use __cpufreq_driver_target only in these cases. In all other cases
241 (for example, when there's a "daemonized" function that wakes up
242 every second), use cpufreq_driver_target to lock the cpufreq per-CPU
243 lock before the command is passed to the cpufreq processor driver.