blob: c7a2eb8450c226b50e55b28f8c6669c6041cc0e3 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001 CPU frequency and voltage scaling code in the Linux(TM) kernel
2
3
4 L i n u x C P U F r e q
5
6 C P U F r e q G o v e r n o r s
7
8 - information for users and developers -
9
10
11 Dominik Brodowski <linux@brodo.de>
Nico Golde594dd2c2005-06-25 14:58:33 -070012 some additions and corrections by Nico Golde <nico@ngolde.de>
Linus Torvalds1da177e2005-04-16 15:20:36 -070013
14
15
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.
19
20
21Contents:
22---------
231. What is a CPUFreq Governor?
24
252. Governors In the Linux Kernel
262.1 Performance
272.2 Powersave
282.3 Userspace
Nico Golde594dd2c2005-06-25 14:58:33 -0700292.4 Ondemand
Alexander Clouter537208c2005-12-01 01:09:23 -0800302.5 Conservative
Linus Torvalds1da177e2005-04-16 15:20:36 -070031
323. The Governor Interface in the CPUfreq Core
33
34
35
361. What Is A CPUFreq Governor?
37==============================
38
39Most cpufreq drivers (in fact, all except one, longrun) or even most
40cpu frequency scaling algorithms only offer the CPU to be set to one
41frequency. In order to offer dynamic frequency scaling, the cpufreq
42core must be able to tell these drivers of a "target frequency". So
43these specific drivers will be transformed to offer a "->target"
44call instead of the existing "->setpolicy" call. For "longrun", all
45stays the same, though.
46
47How to decide what frequency within the CPUfreq policy should be used?
48That's done using "cpufreq governors". Two are already in this patch
49-- they're the already existing "powersave" and "performance" which
50set the frequency statically to the lowest or highest frequency,
51respectively. At least two more such governors will be ready for
52addition in the near future, but likely many more as there are various
53different theories and models about dynamic frequency scaling
54around. Using such a generic interface as cpufreq offers to scaling
55governors, these can be tested extensively, and the best one can be
56selected for each specific use.
57
58Basically, it's the following flow graph:
59
Matt LaPlante2fe0ae72006-10-03 22:50:39 +020060CPU can be set to switch independently | CPU can only be set
Linus Torvalds1da177e2005-04-16 15:20:36 -070061 within specific "limits" | to specific frequencies
62
63 "CPUfreq policy"
64 consists of frequency limits (policy->{min,max})
65 and CPUfreq governor to be used
66 / \
67 / \
68 / the cpufreq governor decides
69 / (dynamically or statically)
70 / what target_freq to set within
71 / the limits of policy->{min,max}
72 / \
73 / \
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.
77 It is assured that it
78 is within policy->{min,max}
79
80
812. Governors In the Linux Kernel
82================================
83
842.1 Performance
85---------------
86
87The CPUfreq governor "performance" sets the CPU statically to the
88highest frequency within the borders of scaling_min_freq and
89scaling_max_freq.
90
91
Nico Golde594dd2c2005-06-25 14:58:33 -0700922.2 Powersave
Linus Torvalds1da177e2005-04-16 15:20:36 -070093-------------
94
95The CPUfreq governor "powersave" sets the CPU statically to the
96lowest frequency within the borders of scaling_min_freq and
97scaling_max_freq.
98
99
Nico Golde594dd2c2005-06-25 14:58:33 -07001002.3 Userspace
Linus Torvalds1da177e2005-04-16 15:20:36 -0700101-------------
102
103The CPUfreq governor "userspace" allows the user, or any userspace
104program running with UID "root", to set the CPU to a specific frequency
105by making a sysfs file "scaling_setspeed" available in the CPU-device
106directory.
107
108
Nico Golde594dd2c2005-06-25 14:58:33 -07001092.4 Ondemand
110------------
111
Matt LaPlantea2ffd272006-10-03 22:49:15 +0200112The CPUfreq governor "ondemand" sets the CPU depending on the
Nico Golde594dd2c2005-06-25 14:58:33 -0700113current usage. To do this the CPU must have the capability to
Alexander Clouter537208c2005-12-01 01:09:23 -0800114switch the frequency very quickly. There are a number of sysfs file
115accessible parameters:
116
117sampling_rate: measured in uS (10^-6 seconds), this is how often you
118want the kernel to look at the CPU usage and to make decisions on
119what to do about the frequency. Typically this is set to values of
Thomas Renninger112124a2009-02-04 11:55:12 +0100120around '10000' or more. It's default value is (cmp. with users-guide.txt):
121transition_latency * 1000
Thomas Renninger112124a2009-02-04 11:55:12 +0100122Be aware that transition latency is in ns and sampling_rate is in us, so you
123get the same sysfs value by default.
124Sampling rate should always get adjusted considering the transition latency
125To set the sampling rate 750 times as high as the transition latency
126in the bash (as said, 1000 is default), do:
127echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \
128 >ondemand/sampling_rate
Alexander Clouter537208c2005-12-01 01:09:23 -0800129
Paul Bollee7cbb5b2011-11-08 10:16:03 +0100130sampling_rate_min:
Thomas Renninger4f4d1ad2009-04-22 13:48:31 +0200131The sampling rate is limited by the HW transition latency:
132transition_latency * 100
133Or by kernel restrictions:
134If CONFIG_NO_HZ is set, the limit is 10ms fixed.
Paul Bollebd74b322011-08-06 14:33:43 +0200135If CONFIG_NO_HZ is not set or nohz=off boot parameter is used, the
Thomas Renninger4f4d1ad2009-04-22 13:48:31 +0200136limits depend on the CONFIG_HZ option:
137HZ=1000: min=20000us (20ms)
138HZ=250: min=80000us (80ms)
139HZ=100: min=200000us (200ms)
140The highest value of kernel and HW latency restrictions is shown and
141used as the minimum sampling rate.
142
Matt LaPlanted9195882008-07-25 19:45:33 -0700143up_threshold: defines what the average CPU usage between the samplings
Alexander Clouter537208c2005-12-01 01:09:23 -0800144of 'sampling_rate' needs to be for the kernel to make a decision on
145whether it should increase the frequency. For example when it is set
Mike Frysinger292e0042009-12-09 06:56:40 -0500146to its default value of '95' it means that between the checking
147intervals the CPU needs to be on average more than 95% in use to then
Alexander Clouter537208c2005-12-01 01:09:23 -0800148decide that the CPU frequency needs to be increased.
149
Matt LaPlante992caac2006-10-03 22:52:05 +0200150ignore_nice_load: this parameter takes a value of '0' or '1'. When
151set to '0' (its default), all processes are counted towards the
152'cpu utilisation' value. When set to '1', the processes that are
Alexander Clouter537208c2005-12-01 01:09:23 -0800153run with a 'nice' value will not count (and thus be ignored) in the
Matt LaPlante992caac2006-10-03 22:52:05 +0200154overall usage calculation. This is useful if you are running a CPU
Alexander Clouter537208c2005-12-01 01:09:23 -0800155intensive calculation on your laptop that you do not care how long it
156takes to complete as you can 'nice' it and prevent it from taking part
157in the deciding process of whether to increase your CPU frequency.
Nico Golde594dd2c2005-06-25 14:58:33 -0700158
Vishwanath BS5b953642011-01-25 20:12:41 +0530159sampling_down_factor: this parameter controls the rate at which the
160kernel makes a decision on when to decrease the frequency while running
161at top speed. When set to 1 (the default) decisions to reevaluate load
162are made at the same interval regardless of current clock speed. But
163when set to greater than 1 (e.g. 100) it acts as a multiplier for the
164scheduling interval for reevaluating load when the CPU is at its top
165speed due to high load. This improves performance by reducing the overhead
166of load evaluation and helping the CPU stay at its top speed when truly
167busy, rather than shifting back and forth in speed. This tunable has no
168effect on behavior at lower speeds/lower CPU loads.
169
Nico Golde594dd2c2005-06-25 14:58:33 -0700170
Alexander Clouter537208c2005-12-01 01:09:23 -08001712.5 Conservative
172----------------
173
174The CPUfreq governor "conservative", much like the "ondemand"
175governor, sets the CPU depending on the current usage. It differs in
176behaviour in that it gracefully increases and decreases the CPU speed
177rather than jumping to max speed the moment there is any load on the
178CPU. This behaviour more suitable in a battery powered environment.
179The governor is tweaked in the same manner as the "ondemand" governor
180through sysfs with the addition of:
181
182freq_step: this describes what percentage steps the cpu freq should be
183increased and decreased smoothly by. By default the cpu frequency will
184increase in 5% chunks of your maximum cpu frequency. You can change this
185value to anywhere between 0 and 100 where '0' will effectively lock your
186CPU at a speed regardless of its load whilst '100' will, in theory, make
187it behave identically to the "ondemand" governor.
188
189down_threshold: same as the 'up_threshold' found for the "ondemand"
190governor but for the opposite direction. For example when set to its
191default value of '20' it means that if the CPU usage needs to be below
19220% between samples to have the frequency decreased.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700193
1943. The Governor Interface in the CPUfreq Core
195=============================================
196
197A new governor must register itself with the CPUfreq core using
198"cpufreq_register_governor". The struct cpufreq_governor, which has to
199be passed to that function, must contain the following values:
200
201governor->name - A unique name for this governor
202governor->governor - The governor callback function
203governor->owner - .THIS_MODULE for the governor module (if
204 appropriate)
205
206The governor->governor callback is called with the current (or to-be-set)
207cpufreq_policy struct for that CPU, and an unsigned int event. The
208following events are currently defined:
209
210CPUFREQ_GOV_START: This governor shall start its duty for the CPU
211 policy->cpu
212CPUFREQ_GOV_STOP: This governor shall end its duty for the CPU
213 policy->cpu
214CPUFREQ_GOV_LIMITS: The limits for CPU policy->cpu have changed to
215 policy->min and policy->max.
216
217If you need other "events" externally of your driver, _only_ use the
218cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the
219CPUfreq core to ensure proper locking.
220
221
222The CPUfreq governor may call the CPU processor driver using one of
223these two functions:
224
225int cpufreq_driver_target(struct cpufreq_policy *policy,
226 unsigned int target_freq,
227 unsigned int relation);
228
229int __cpufreq_driver_target(struct cpufreq_policy *policy,
230 unsigned int target_freq,
231 unsigned int relation);
232
233target_freq must be within policy->min and policy->max, of course.
234What's the difference between these two functions? When your governor
235still is in a direct code path of a call to governor->governor, the
236per-CPU cpufreq lock is still held in the cpufreq core, and there's
237no need to lock it again (in fact, this would cause a deadlock). So
238use __cpufreq_driver_target only in these cases. In all other cases
239(for example, when there's a "daemonized" function that wakes up
240every second), use cpufreq_driver_target to lock the cpufreq per-CPU
241lock before the command is passed to the cpufreq processor driver.
242