xref: /linux/Documentation/admin-guide/pm/cpufreq.rst (revision 29dcbea92460e82181774b46f08b55a917615a97)
1.. SPDX-License-Identifier: GPL-2.0
2.. include:: <isonum.txt>
3
4.. |intel_pstate| replace:: :doc:`intel_pstate <intel_pstate>`
5
6=======================
7CPU Performance Scaling
8=======================
9
10:Copyright: |copy| 2017 Intel Corporation
11
12:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
13
14
15The Concept of CPU Performance Scaling
16======================================
17
18The majority of modern processors are capable of operating in a number of
19different clock frequency and voltage configurations, often referred to as
20Operating Performance Points or P-states (in ACPI terminology).  As a rule,
21the higher the clock frequency and the higher the voltage, the more instructions
22can be retired by the CPU over a unit of time, but also the higher the clock
23frequency and the higher the voltage, the more energy is consumed over a unit of
24time (or the more power is drawn) by the CPU in the given P-state.  Therefore
25there is a natural tradeoff between the CPU capacity (the number of instructions
26that can be executed over a unit of time) and the power drawn by the CPU.
27
28In some situations it is desirable or even necessary to run the program as fast
29as possible and then there is no reason to use any P-states different from the
30highest one (i.e. the highest-performance frequency/voltage configuration
31available).  In some other cases, however, it may not be necessary to execute
32instructions so quickly and maintaining the highest available CPU capacity for a
33relatively long time without utilizing it entirely may be regarded as wasteful.
34It also may not be physically possible to maintain maximum CPU capacity for too
35long for thermal or power supply capacity reasons or similar.  To cover those
36cases, there are hardware interfaces allowing CPUs to be switched between
37different frequency/voltage configurations or (in the ACPI terminology) to be
38put into different P-states.
39
40Typically, they are used along with algorithms to estimate the required CPU
41capacity, so as to decide which P-states to put the CPUs into.  Of course, since
42the utilization of the system generally changes over time, that has to be done
43repeatedly on a regular basis.  The activity by which this happens is referred
44to as CPU performance scaling or CPU frequency scaling (because it involves
45adjusting the CPU clock frequency).
46
47
48CPU Performance Scaling in Linux
49================================
50
51The Linux kernel supports CPU performance scaling by means of the ``CPUFreq``
52(CPU Frequency scaling) subsystem that consists of three layers of code: the
53core, scaling governors and scaling drivers.
54
55The ``CPUFreq`` core provides the common code infrastructure and user space
56interfaces for all platforms that support CPU performance scaling.  It defines
57the basic framework in which the other components operate.
58
59Scaling governors implement algorithms to estimate the required CPU capacity.
60As a rule, each governor implements one, possibly parametrized, scaling
61algorithm.
62
63Scaling drivers talk to the hardware.  They provide scaling governors with
64information on the available P-states (or P-state ranges in some cases) and
65access platform-specific hardware interfaces to change CPU P-states as requested
66by scaling governors.
67
68In principle, all available scaling governors can be used with every scaling
69driver.  That design is based on the observation that the information used by
70performance scaling algorithms for P-state selection can be represented in a
71platform-independent form in the majority of cases, so it should be possible
72to use the same performance scaling algorithm implemented in exactly the same
73way regardless of which scaling driver is used.  Consequently, the same set of
74scaling governors should be suitable for every supported platform.
75
76However, that observation may not hold for performance scaling algorithms
77based on information provided by the hardware itself, for example through
78feedback registers, as that information is typically specific to the hardware
79interface it comes from and may not be easily represented in an abstract,
80platform-independent way.  For this reason, ``CPUFreq`` allows scaling drivers
81to bypass the governor layer and implement their own performance scaling
82algorithms.  That is done by the |intel_pstate| scaling driver.
83
84
85``CPUFreq`` Policy Objects
86==========================
87
88In some cases the hardware interface for P-state control is shared by multiple
89CPUs.  That is, for example, the same register (or set of registers) is used to
90control the P-state of multiple CPUs at the same time and writing to it affects
91all of those CPUs simultaneously.
92
93Sets of CPUs sharing hardware P-state control interfaces are represented by
94``CPUFreq`` as struct cpufreq_policy objects.  For consistency,
95struct cpufreq_policy is also used when there is only one CPU in the given
96set.
97
98The ``CPUFreq`` core maintains a pointer to a struct cpufreq_policy object for
99every CPU in the system, including CPUs that are currently offline.  If multiple
100CPUs share the same hardware P-state control interface, all of the pointers
101corresponding to them point to the same struct cpufreq_policy object.
102
103``CPUFreq`` uses struct cpufreq_policy as its basic data type and the design
104of its user space interface is based on the policy concept.
105
106
107CPU Initialization
108==================
109
110First of all, a scaling driver has to be registered for ``CPUFreq`` to work.
111It is only possible to register one scaling driver at a time, so the scaling
112driver is expected to be able to handle all CPUs in the system.
113
114The scaling driver may be registered before or after CPU registration.  If
115CPUs are registered earlier, the driver core invokes the ``CPUFreq`` core to
116take a note of all of the already registered CPUs during the registration of the
117scaling driver.  In turn, if any CPUs are registered after the registration of
118the scaling driver, the ``CPUFreq`` core will be invoked to take note of them
119at their registration time.
120
121In any case, the ``CPUFreq`` core is invoked to take note of any logical CPU it
122has not seen so far as soon as it is ready to handle that CPU.  [Note that the
123logical CPU may be a physical single-core processor, or a single core in a
124multicore processor, or a hardware thread in a physical processor or processor
125core.  In what follows "CPU" always means "logical CPU" unless explicitly stated
126otherwise and the word "processor" is used to refer to the physical part
127possibly including multiple logical CPUs.]
128
129Once invoked, the ``CPUFreq`` core checks if the policy pointer is already set
130for the given CPU and if so, it skips the policy object creation.  Otherwise,
131a new policy object is created and initialized, which involves the creation of
132a new policy directory in ``sysfs``, and the policy pointer corresponding to
133the given CPU is set to the new policy object's address in memory.
134
135Next, the scaling driver's ``->init()`` callback is invoked with the policy
136pointer of the new CPU passed to it as the argument.  That callback is expected
137to initialize the performance scaling hardware interface for the given CPU (or,
138more precisely, for the set of CPUs sharing the hardware interface it belongs
139to, represented by its policy object) and, if the policy object it has been
140called for is new, to set parameters of the policy, like the minimum and maximum
141frequencies supported by the hardware, the table of available frequencies (if
142the set of supported P-states is not a continuous range), and the mask of CPUs
143that belong to the same policy (including both online and offline CPUs).  That
144mask is then used by the core to populate the policy pointers for all of the
145CPUs in it.
146
147The next major initialization step for a new policy object is to attach a
148scaling governor to it (to begin with, that is the default scaling governor
149determined by the kernel command line or configuration, but it may be changed
150later via ``sysfs``).  First, a pointer to the new policy object is passed to
151the governor's ``->init()`` callback which is expected to initialize all of the
152data structures necessary to handle the given policy and, possibly, to add
153a governor ``sysfs`` interface to it.  Next, the governor is started by
154invoking its ``->start()`` callback.
155
156That callback is expected to register per-CPU utilization update callbacks for
157all of the online CPUs belonging to the given policy with the CPU scheduler.
158The utilization update callbacks will be invoked by the CPU scheduler on
159important events, like task enqueue and dequeue, on every iteration of the
160scheduler tick or generally whenever the CPU utilization may change (from the
161scheduler's perspective).  They are expected to carry out computations needed
162to determine the P-state to use for the given policy going forward and to
163invoke the scaling driver to make changes to the hardware in accordance with
164the P-state selection.  The scaling driver may be invoked directly from
165scheduler context or asynchronously, via a kernel thread or workqueue, depending
166on the configuration and capabilities of the scaling driver and the governor.
167
168Similar steps are taken for policy objects that are not new, but were "inactive"
169previously, meaning that all of the CPUs belonging to them were offline.  The
170only practical difference in that case is that the ``CPUFreq`` core will attempt
171to use the scaling governor previously used with the policy that became
172"inactive" (and is re-initialized now) instead of the default governor.
173
174In turn, if a previously offline CPU is being brought back online, but some
175other CPUs sharing the policy object with it are online already, there is no
176need to re-initialize the policy object at all.  In that case, it only is
177necessary to restart the scaling governor so that it can take the new online CPU
178into account.  That is achieved by invoking the governor's ``->stop`` and
179``->start()`` callbacks, in this order, for the entire policy.
180
181As mentioned before, the |intel_pstate| scaling driver bypasses the scaling
182governor layer of ``CPUFreq`` and provides its own P-state selection algorithms.
183Consequently, if |intel_pstate| is used, scaling governors are not attached to
184new policy objects.  Instead, the driver's ``->setpolicy()`` callback is invoked
185to register per-CPU utilization update callbacks for each policy.  These
186callbacks are invoked by the CPU scheduler in the same way as for scaling
187governors, but in the |intel_pstate| case they both determine the P-state to
188use and change the hardware configuration accordingly in one go from scheduler
189context.
190
191The policy objects created during CPU initialization and other data structures
192associated with them are torn down when the scaling driver is unregistered
193(which happens when the kernel module containing it is unloaded, for example) or
194when the last CPU belonging to the given policy in unregistered.
195
196
197Policy Interface in ``sysfs``
198=============================
199
200During the initialization of the kernel, the ``CPUFreq`` core creates a
201``sysfs`` directory (kobject) called ``cpufreq`` under
202:file:`/sys/devices/system/cpu/`.
203
204That directory contains a ``policyX`` subdirectory (where ``X`` represents an
205integer number) for every policy object maintained by the ``CPUFreq`` core.
206Each ``policyX`` directory is pointed to by ``cpufreq`` symbolic links
207under :file:`/sys/devices/system/cpu/cpuY/` (where ``Y`` represents an integer
208that may be different from the one represented by ``X``) for all of the CPUs
209associated with (or belonging to) the given policy.  The ``policyX`` directories
210in :file:`/sys/devices/system/cpu/cpufreq` each contain policy-specific
211attributes (files) to control ``CPUFreq`` behavior for the corresponding policy
212objects (that is, for all of the CPUs associated with them).
213
214Some of those attributes are generic.  They are created by the ``CPUFreq`` core
215and their behavior generally does not depend on what scaling driver is in use
216and what scaling governor is attached to the given policy.  Some scaling drivers
217also add driver-specific attributes to the policy directories in ``sysfs`` to
218control policy-specific aspects of driver behavior.
219
220The generic attributes under :file:`/sys/devices/system/cpu/cpufreq/policyX/`
221are the following:
222
223``affected_cpus``
224	List of online CPUs belonging to this policy (i.e. sharing the hardware
225	performance scaling interface represented by the ``policyX`` policy
226	object).
227
228``bios_limit``
229	If the platform firmware (BIOS) tells the OS to apply an upper limit to
230	CPU frequencies, that limit will be reported through this attribute (if
231	present).
232
233	The existence of the limit may be a result of some (often unintentional)
234	BIOS settings, restrictions coming from a service processor or another
235	BIOS/HW-based mechanisms.
236
237	This does not cover ACPI thermal limitations which can be discovered
238	through a generic thermal driver.
239
240	This attribute is not present if the scaling driver in use does not
241	support it.
242
243``cpuinfo_cur_freq``
244	Current frequency of the CPUs belonging to this policy as obtained from
245	the hardware (in KHz).
246
247	This is expected to be the frequency the hardware actually runs at.
248	If that frequency cannot be determined, this attribute should not
249	be present.
250
251``cpuinfo_max_freq``
252	Maximum possible operating frequency the CPUs belonging to this policy
253	can run at (in kHz).
254
255``cpuinfo_min_freq``
256	Minimum possible operating frequency the CPUs belonging to this policy
257	can run at (in kHz).
258
259``cpuinfo_transition_latency``
260	The time it takes to switch the CPUs belonging to this policy from one
261	P-state to another, in nanoseconds.
262
263	If unknown or if known to be so high that the scaling driver does not
264	work with the `ondemand`_ governor, -1 (:c:macro:`CPUFREQ_ETERNAL`)
265	will be returned by reads from this attribute.
266
267``related_cpus``
268	List of all (online and offline) CPUs belonging to this policy.
269
270``scaling_available_frequencies``
271	List of available frequencies of the CPUs belonging to this policy
272	(in kHz).
273
274``scaling_available_governors``
275	List of ``CPUFreq`` scaling governors present in the kernel that can
276	be attached to this policy or (if the |intel_pstate| scaling driver is
277	in use) list of scaling algorithms provided by the driver that can be
278	applied to this policy.
279
280	[Note that some governors are modular and it may be necessary to load a
281	kernel module for the governor held by it to become available and be
282	listed by this attribute.]
283
284``scaling_cur_freq``
285	Current frequency of all of the CPUs belonging to this policy (in kHz).
286
287	In the majority of cases, this is the frequency of the last P-state
288	requested by the scaling driver from the hardware using the scaling
289	interface provided by it, which may or may not reflect the frequency
290	the CPU is actually running at (due to hardware design and other
291	limitations).
292
293	Some architectures (e.g. ``x86``) may attempt to provide information
294	more precisely reflecting the current CPU frequency through this
295	attribute, but that still may not be the exact current CPU frequency as
296	seen by the hardware at the moment.
297
298``scaling_driver``
299	The scaling driver currently in use.
300
301``scaling_governor``
302	The scaling governor currently attached to this policy or (if the
303	|intel_pstate| scaling driver is in use) the scaling algorithm
304	provided by the driver that is currently applied to this policy.
305
306	This attribute is read-write and writing to it will cause a new scaling
307	governor to be attached to this policy or a new scaling algorithm
308	provided by the scaling driver to be applied to it (in the
309	|intel_pstate| case), as indicated by the string written to this
310	attribute (which must be one of the names listed by the
311	``scaling_available_governors`` attribute described above).
312
313``scaling_max_freq``
314	Maximum frequency the CPUs belonging to this policy are allowed to be
315	running at (in kHz).
316
317	This attribute is read-write and writing a string representing an
318	integer to it will cause a new limit to be set (it must not be lower
319	than the value of the ``scaling_min_freq`` attribute).
320
321``scaling_min_freq``
322	Minimum frequency the CPUs belonging to this policy are allowed to be
323	running at (in kHz).
324
325	This attribute is read-write and writing a string representing a
326	non-negative integer to it will cause a new limit to be set (it must not
327	be higher than the value of the ``scaling_max_freq`` attribute).
328
329``scaling_setspeed``
330	This attribute is functional only if the `userspace`_ scaling governor
331	is attached to the given policy.
332
333	It returns the last frequency requested by the governor (in kHz) or can
334	be written to in order to set a new frequency for the policy.
335
336
337Generic Scaling Governors
338=========================
339
340``CPUFreq`` provides generic scaling governors that can be used with all
341scaling drivers.  As stated before, each of them implements a single, possibly
342parametrized, performance scaling algorithm.
343
344Scaling governors are attached to policy objects and different policy objects
345can be handled by different scaling governors at the same time (although that
346may lead to suboptimal results in some cases).
347
348The scaling governor for a given policy object can be changed at any time with
349the help of the ``scaling_governor`` policy attribute in ``sysfs``.
350
351Some governors expose ``sysfs`` attributes to control or fine-tune the scaling
352algorithms implemented by them.  Those attributes, referred to as governor
353tunables, can be either global (system-wide) or per-policy, depending on the
354scaling driver in use.  If the driver requires governor tunables to be
355per-policy, they are located in a subdirectory of each policy directory.
356Otherwise, they are located in a subdirectory under
357:file:`/sys/devices/system/cpu/cpufreq/`.  In either case the name of the
358subdirectory containing the governor tunables is the name of the governor
359providing them.
360
361``performance``
362---------------
363
364When attached to a policy object, this governor causes the highest frequency,
365within the ``scaling_max_freq`` policy limit, to be requested for that policy.
366
367The request is made once at that time the governor for the policy is set to
368``performance`` and whenever the ``scaling_max_freq`` or ``scaling_min_freq``
369policy limits change after that.
370
371``powersave``
372-------------
373
374When attached to a policy object, this governor causes the lowest frequency,
375within the ``scaling_min_freq`` policy limit, to be requested for that policy.
376
377The request is made once at that time the governor for the policy is set to
378``powersave`` and whenever the ``scaling_max_freq`` or ``scaling_min_freq``
379policy limits change after that.
380
381``userspace``
382-------------
383
384This governor does not do anything by itself.  Instead, it allows user space
385to set the CPU frequency for the policy it is attached to by writing to the
386``scaling_setspeed`` attribute of that policy.
387
388``schedutil``
389-------------
390
391This governor uses CPU utilization data available from the CPU scheduler.  It
392generally is regarded as a part of the CPU scheduler, so it can access the
393scheduler's internal data structures directly.
394
395It runs entirely in scheduler context, although in some cases it may need to
396invoke the scaling driver asynchronously when it decides that the CPU frequency
397should be changed for a given policy (that depends on whether or not the driver
398is capable of changing the CPU frequency from scheduler context).
399
400The actions of this governor for a particular CPU depend on the scheduling class
401invoking its utilization update callback for that CPU.  If it is invoked by the
402RT or deadline scheduling classes, the governor will increase the frequency to
403the allowed maximum (that is, the ``scaling_max_freq`` policy limit).  In turn,
404if it is invoked by the CFS scheduling class, the governor will use the
405Per-Entity Load Tracking (PELT) metric for the root control group of the
406given CPU as the CPU utilization estimate (see the *Per-entity load tracking*
407LWN.net article [1]_ for a description of the PELT mechanism).  Then, the new
408CPU frequency to apply is computed in accordance with the formula
409
410	f = 1.25 * ``f_0`` * ``util`` / ``max``
411
412where ``util`` is the PELT number, ``max`` is the theoretical maximum of
413``util``, and ``f_0`` is either the maximum possible CPU frequency for the given
414policy (if the PELT number is frequency-invariant), or the current CPU frequency
415(otherwise).
416
417This governor also employs a mechanism allowing it to temporarily bump up the
418CPU frequency for tasks that have been waiting on I/O most recently, called
419"IO-wait boosting".  That happens when the :c:macro:`SCHED_CPUFREQ_IOWAIT` flag
420is passed by the scheduler to the governor callback which causes the frequency
421to go up to the allowed maximum immediately and then draw back to the value
422returned by the above formula over time.
423
424This governor exposes only one tunable:
425
426``rate_limit_us``
427	Minimum time (in microseconds) that has to pass between two consecutive
428	runs of governor computations (default: 1.5 times the scaling driver's
429	transition latency or the maximum 2ms).
430
431	The purpose of this tunable is to reduce the scheduler context overhead
432	of the governor which might be excessive without it.
433
434This governor generally is regarded as a replacement for the older `ondemand`_
435and `conservative`_ governors (described below), as it is simpler and more
436tightly integrated with the CPU scheduler, its overhead in terms of CPU context
437switches and similar is less significant, and it uses the scheduler's own CPU
438utilization metric, so in principle its decisions should not contradict the
439decisions made by the other parts of the scheduler.
440
441``ondemand``
442------------
443
444This governor uses CPU load as a CPU frequency selection metric.
445
446In order to estimate the current CPU load, it measures the time elapsed between
447consecutive invocations of its worker routine and computes the fraction of that
448time in which the given CPU was not idle.  The ratio of the non-idle (active)
449time to the total CPU time is taken as an estimate of the load.
450
451If this governor is attached to a policy shared by multiple CPUs, the load is
452estimated for all of them and the greatest result is taken as the load estimate
453for the entire policy.
454
455The worker routine of this governor has to run in process context, so it is
456invoked asynchronously (via a workqueue) and CPU P-states are updated from
457there if necessary.  As a result, the scheduler context overhead from this
458governor is minimum, but it causes additional CPU context switches to happen
459relatively often and the CPU P-state updates triggered by it can be relatively
460irregular.  Also, it affects its own CPU load metric by running code that
461reduces the CPU idle time (even though the CPU idle time is only reduced very
462slightly by it).
463
464It generally selects CPU frequencies proportional to the estimated load, so that
465the value of the ``cpuinfo_max_freq`` policy attribute corresponds to the load of
4661 (or 100%), and the value of the ``cpuinfo_min_freq`` policy attribute
467corresponds to the load of 0, unless when the load exceeds a (configurable)
468speedup threshold, in which case it will go straight for the highest frequency
469it is allowed to use (the ``scaling_max_freq`` policy limit).
470
471This governor exposes the following tunables:
472
473``sampling_rate``
474	This is how often the governor's worker routine should run, in
475	microseconds.
476
477	Typically, it is set to values of the order of 2000 (2 ms).  Its
478	default value is to add a 50% breathing room
479	to ``cpuinfo_transition_latency`` on each policy this governor is
480	attached to. The minimum is typically the length of two scheduler
481	ticks.
482
483	If this tunable is per-policy, the following shell command sets the time
484	represented by it to be 1.5 times as high as the transition latency
485	(the default)::
486
487	# echo `$(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate
488
489``up_threshold``
490	If the estimated CPU load is above this value (in percent), the governor
491	will set the frequency to the maximum value allowed for the policy.
492	Otherwise, the selected frequency will be proportional to the estimated
493	CPU load.
494
495``ignore_nice_load``
496	If set to 1 (default 0), it will cause the CPU load estimation code to
497	treat the CPU time spent on executing tasks with "nice" levels greater
498	than 0 as CPU idle time.
499
500	This may be useful if there are tasks in the system that should not be
501	taken into account when deciding what frequency to run the CPUs at.
502	Then, to make that happen it is sufficient to increase the "nice" level
503	of those tasks above 0 and set this attribute to 1.
504
505``sampling_down_factor``
506	Temporary multiplier, between 1 (default) and 100 inclusive, to apply to
507	the ``sampling_rate`` value if the CPU load goes above ``up_threshold``.
508
509	This causes the next execution of the governor's worker routine (after
510	setting the frequency to the allowed maximum) to be delayed, so the
511	frequency stays at the maximum level for a longer time.
512
513	Frequency fluctuations in some bursty workloads may be avoided this way
514	at the cost of additional energy spent on maintaining the maximum CPU
515	capacity.
516
517``powersave_bias``
518	Reduction factor to apply to the original frequency target of the
519	governor (including the maximum value used when the ``up_threshold``
520	value is exceeded by the estimated CPU load) or sensitivity threshold
521	for the AMD frequency sensitivity powersave bias driver
522	(:file:`drivers/cpufreq/amd_freq_sensitivity.c`), between 0 and 1000
523	inclusive.
524
525	If the AMD frequency sensitivity powersave bias driver is not loaded,
526	the effective frequency to apply is given by
527
528		f * (1 - ``powersave_bias`` / 1000)
529
530	where f is the governor's original frequency target.  The default value
531	of this attribute is 0 in that case.
532
533	If the AMD frequency sensitivity powersave bias driver is loaded, the
534	value of this attribute is 400 by default and it is used in a different
535	way.
536
537	On Family 16h (and later) AMD processors there is a mechanism to get a
538	measured workload sensitivity, between 0 and 100% inclusive, from the
539	hardware.  That value can be used to estimate how the performance of the
540	workload running on a CPU will change in response to frequency changes.
541
542	The performance of a workload with the sensitivity of 0 (memory-bound or
543	IO-bound) is not expected to increase at all as a result of increasing
544	the CPU frequency, whereas workloads with the sensitivity of 100%
545	(CPU-bound) are expected to perform much better if the CPU frequency is
546	increased.
547
548	If the workload sensitivity is less than the threshold represented by
549	the ``powersave_bias`` value, the sensitivity powersave bias driver
550	will cause the governor to select a frequency lower than its original
551	target, so as to avoid over-provisioning workloads that will not benefit
552	from running at higher CPU frequencies.
553
554``conservative``
555----------------
556
557This governor uses CPU load as a CPU frequency selection metric.
558
559It estimates the CPU load in the same way as the `ondemand`_ governor described
560above, but the CPU frequency selection algorithm implemented by it is different.
561
562Namely, it avoids changing the frequency significantly over short time intervals
563which may not be suitable for systems with limited power supply capacity (e.g.
564battery-powered).  To achieve that, it changes the frequency in relatively
565small steps, one step at a time, up or down - depending on whether or not a
566(configurable) threshold has been exceeded by the estimated CPU load.
567
568This governor exposes the following tunables:
569
570``freq_step``
571	Frequency step in percent of the maximum frequency the governor is
572	allowed to set (the ``scaling_max_freq`` policy limit), between 0 and
573	100 (5 by default).
574
575	This is how much the frequency is allowed to change in one go.  Setting
576	it to 0 will cause the default frequency step (5 percent) to be used
577	and setting it to 100 effectively causes the governor to periodically
578	switch the frequency between the ``scaling_min_freq`` and
579	``scaling_max_freq`` policy limits.
580
581``down_threshold``
582	Threshold value (in percent, 20 by default) used to determine the
583	frequency change direction.
584
585	If the estimated CPU load is greater than this value, the frequency will
586	go up (by ``freq_step``).  If the load is less than this value (and the
587	``sampling_down_factor`` mechanism is not in effect), the frequency will
588	go down.  Otherwise, the frequency will not be changed.
589
590``sampling_down_factor``
591	Frequency decrease deferral factor, between 1 (default) and 10
592	inclusive.
593
594	It effectively causes the frequency to go down ``sampling_down_factor``
595	times slower than it ramps up.
596
597
598Frequency Boost Support
599=======================
600
601Background
602----------
603
604Some processors support a mechanism to raise the operating frequency of some
605cores in a multicore package temporarily (and above the sustainable frequency
606threshold for the whole package) under certain conditions, for example if the
607whole chip is not fully utilized and below its intended thermal or power budget.
608
609Different names are used by different vendors to refer to this functionality.
610For Intel processors it is referred to as "Turbo Boost", AMD calls it
611"Turbo-Core" or (in technical documentation) "Core Performance Boost" and so on.
612As a rule, it also is implemented differently by different vendors.  The simple
613term "frequency boost" is used here for brevity to refer to all of those
614implementations.
615
616The frequency boost mechanism may be either hardware-based or software-based.
617If it is hardware-based (e.g. on x86), the decision to trigger the boosting is
618made by the hardware (although in general it requires the hardware to be put
619into a special state in which it can control the CPU frequency within certain
620limits).  If it is software-based (e.g. on ARM), the scaling driver decides
621whether or not to trigger boosting and when to do that.
622
623The ``boost`` File in ``sysfs``
624-------------------------------
625
626This file is located under :file:`/sys/devices/system/cpu/cpufreq/` and controls
627the "boost" setting for the whole system.  It is not present if the underlying
628scaling driver does not support the frequency boost mechanism (or supports it,
629but provides a driver-specific interface for controlling it, like
630|intel_pstate|).
631
632If the value in this file is 1, the frequency boost mechanism is enabled.  This
633means that either the hardware can be put into states in which it is able to
634trigger boosting (in the hardware-based case), or the software is allowed to
635trigger boosting (in the software-based case).  It does not mean that boosting
636is actually in use at the moment on any CPUs in the system.  It only means a
637permission to use the frequency boost mechanism (which still may never be used
638for other reasons).
639
640If the value in this file is 0, the frequency boost mechanism is disabled and
641cannot be used at all.
642
643The only values that can be written to this file are 0 and 1.
644
645Rationale for Boost Control Knob
646--------------------------------
647
648The frequency boost mechanism is generally intended to help to achieve optimum
649CPU performance on time scales below software resolution (e.g. below the
650scheduler tick interval) and it is demonstrably suitable for many workloads, but
651it may lead to problems in certain situations.
652
653For this reason, many systems make it possible to disable the frequency boost
654mechanism in the platform firmware (BIOS) setup, but that requires the system to
655be restarted for the setting to be adjusted as desired, which may not be
656practical at least in some cases.  For example:
657
658  1. Boosting means overclocking the processor, although under controlled
659     conditions.  Generally, the processor's energy consumption increases
660     as a result of increasing its frequency and voltage, even temporarily.
661     That may not be desirable on systems that switch to power sources of
662     limited capacity, such as batteries, so the ability to disable the boost
663     mechanism while the system is running may help there (but that depends on
664     the workload too).
665
666  2. In some situations deterministic behavior is more important than
667     performance or energy consumption (or both) and the ability to disable
668     boosting while the system is running may be useful then.
669
670  3. To examine the impact of the frequency boost mechanism itself, it is useful
671     to be able to run tests with and without boosting, preferably without
672     restarting the system in the meantime.
673
674  4. Reproducible results are important when running benchmarks.  Since
675     the boosting functionality depends on the load of the whole package,
676     single-thread performance may vary because of it which may lead to
677     unreproducible results sometimes.  That can be avoided by disabling the
678     frequency boost mechanism before running benchmarks sensitive to that
679     issue.
680
681Legacy AMD ``cpb`` Knob
682-----------------------
683
684The AMD powernow-k8 scaling driver supports a ``sysfs`` knob very similar to
685the global ``boost`` one.  It is used for disabling/enabling the "Core
686Performance Boost" feature of some AMD processors.
687
688If present, that knob is located in every ``CPUFreq`` policy directory in
689``sysfs`` (:file:`/sys/devices/system/cpu/cpufreq/policyX/`) and is called
690``cpb``, which indicates a more fine grained control interface.  The actual
691implementation, however, works on the system-wide basis and setting that knob
692for one policy causes the same value of it to be set for all of the other
693policies at the same time.
694
695That knob is still supported on AMD processors that support its underlying
696hardware feature, but it may be configured out of the kernel (via the
697:c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option) and the global
698``boost`` knob is present regardless.  Thus it is always possible use the
699``boost`` knob instead of the ``cpb`` one which is highly recommended, as that
700is more consistent with what all of the other systems do (and the ``cpb`` knob
701may not be supported any more in the future).
702
703The ``cpb`` knob is never present for any processors without the underlying
704hardware feature (e.g. all Intel ones), even if the
705:c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option is set.
706
707
708References
709==========
710
711.. [1] Jonathan Corbet, *Per-entity load tracking*,
712       https://lwn.net/Articles/531853/
713