1 .. SPDX-License-Identifier: GPL-2.0 2 .. include:: <isonum.txt> 3 4 .. |intel_pstate| replace:: :doc:`intel_pstate <intel_pstate>` 5 6 ======================= 7 CPU Performance Scaling 8 ======================= 9 10 :Copyright: |copy| 2017 Intel Corporation 11 12 :Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> 13 14 15 The Concept of CPU Performance Scaling 16 ====================================== 17 18 The majority of modern processors are capable of operating in a number of 19 different clock frequency and voltage configurations, often referred to as 20 Operating Performance Points or P-states (in ACPI terminology). As a rule, 21 the higher the clock frequency and the higher the voltage, the more instructions 22 can be retired by the CPU over a unit of time, but also the higher the clock 23 frequency and the higher the voltage, the more energy is consumed over a unit of 24 time (or the more power is drawn) by the CPU in the given P-state. Therefore 25 there is a natural tradeoff between the CPU capacity (the number of instructions 26 that can be executed over a unit of time) and the power drawn by the CPU. 27 28 In some situations it is desirable or even necessary to run the program as fast 29 as possible and then there is no reason to use any P-states different from the 30 highest one (i.e. the highest-performance frequency/voltage configuration 31 available). In some other cases, however, it may not be necessary to execute 32 instructions so quickly and maintaining the highest available CPU capacity for a 33 relatively long time without utilizing it entirely may be regarded as wasteful. 34 It also may not be physically possible to maintain maximum CPU capacity for too 35 long for thermal or power supply capacity reasons or similar. To cover those 36 cases, there are hardware interfaces allowing CPUs to be switched between 37 different frequency/voltage configurations or (in the ACPI terminology) to be 38 put into different P-states. 39 40 Typically, they are used along with algorithms to estimate the required CPU 41 capacity, so as to decide which P-states to put the CPUs into. Of course, since 42 the utilization of the system generally changes over time, that has to be done 43 repeatedly on a regular basis. The activity by which this happens is referred 44 to as CPU performance scaling or CPU frequency scaling (because it involves 45 adjusting the CPU clock frequency). 46 47 48 CPU Performance Scaling in Linux 49 ================================ 50 51 The Linux kernel supports CPU performance scaling by means of the ``CPUFreq`` 52 (CPU Frequency scaling) subsystem that consists of three layers of code: the 53 core, scaling governors and scaling drivers. 54 55 The ``CPUFreq`` core provides the common code infrastructure and user space 56 interfaces for all platforms that support CPU performance scaling. It defines 57 the basic framework in which the other components operate. 58 59 Scaling governors implement algorithms to estimate the required CPU capacity. 60 As a rule, each governor implements one, possibly parametrized, scaling 61 algorithm. 62 63 Scaling drivers talk to the hardware. They provide scaling governors with 64 information on the available P-states (or P-state ranges in some cases) and 65 access platform-specific hardware interfaces to change CPU P-states as requested 66 by scaling governors. 67 68 In principle, all available scaling governors can be used with every scaling 69 driver. That design is based on the observation that the information used by 70 performance scaling algorithms for P-state selection can be represented in a 71 platform-independent form in the majority of cases, so it should be possible 72 to use the same performance scaling algorithm implemented in exactly the same 73 way regardless of which scaling driver is used. Consequently, the same set of 74 scaling governors should be suitable for every supported platform. 75 76 However, that observation may not hold for performance scaling algorithms 77 based on information provided by the hardware itself, for example through 78 feedback registers, as that information is typically specific to the hardware 79 interface it comes from and may not be easily represented in an abstract, 80 platform-independent way. For this reason, ``CPUFreq`` allows scaling drivers 81 to bypass the governor layer and implement their own performance scaling 82 algorithms. That is done by the |intel_pstate| scaling driver. 83 84 85 ``CPUFreq`` Policy Objects 86 ========================== 87 88 In some cases the hardware interface for P-state control is shared by multiple 89 CPUs. That is, for example, the same register (or set of registers) is used to 90 control the P-state of multiple CPUs at the same time and writing to it affects 91 all of those CPUs simultaneously. 92 93 Sets of CPUs sharing hardware P-state control interfaces are represented by 94 ``CPUFreq`` as struct cpufreq_policy objects. For consistency, 95 struct cpufreq_policy is also used when there is only one CPU in the given 96 set. 97 98 The ``CPUFreq`` core maintains a pointer to a struct cpufreq_policy object for 99 every CPU in the system, including CPUs that are currently offline. If multiple 100 CPUs share the same hardware P-state control interface, all of the pointers 101 corresponding 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 104 of its user space interface is based on the policy concept. 105 106 107 CPU Initialization 108 ================== 109 110 First of all, a scaling driver has to be registered for ``CPUFreq`` to work. 111 It is only possible to register one scaling driver at a time, so the scaling 112 driver is expected to be able to handle all CPUs in the system. 113 114 The scaling driver may be registered before or after CPU registration. If 115 CPUs are registered earlier, the driver core invokes the ``CPUFreq`` core to 116 take a note of all of the already registered CPUs during the registration of the 117 scaling driver. In turn, if any CPUs are registered after the registration of 118 the scaling driver, the ``CPUFreq`` core will be invoked to take note of them 119 at their registration time. 120 121 In any case, the ``CPUFreq`` core is invoked to take note of any logical CPU it 122 has not seen so far as soon as it is ready to handle that CPU. [Note that the 123 logical CPU may be a physical single-core processor, or a single core in a 124 multicore processor, or a hardware thread in a physical processor or processor 125 core. In what follows "CPU" always means "logical CPU" unless explicitly stated 126 otherwise and the word "processor" is used to refer to the physical part 127 possibly including multiple logical CPUs.] 128 129 Once invoked, the ``CPUFreq`` core checks if the policy pointer is already set 130 for the given CPU and if so, it skips the policy object creation. Otherwise, 131 a new policy object is created and initialized, which involves the creation of 132 a new policy directory in ``sysfs``, and the policy pointer corresponding to 133 the given CPU is set to the new policy object's address in memory. 134 135 Next, the scaling driver's ``->init()`` callback is invoked with the policy 136 pointer of the new CPU passed to it as the argument. That callback is expected 137 to initialize the performance scaling hardware interface for the given CPU (or, 138 more precisely, for the set of CPUs sharing the hardware interface it belongs 139 to, represented by its policy object) and, if the policy object it has been 140 called for is new, to set parameters of the policy, like the minimum and maximum 141 frequencies supported by the hardware, the table of available frequencies (if 142 the set of supported P-states is not a continuous range), and the mask of CPUs 143 that belong to the same policy (including both online and offline CPUs). That 144 mask is then used by the core to populate the policy pointers for all of the 145 CPUs in it. 146 147 The next major initialization step for a new policy object is to attach a 148 scaling governor to it (to begin with, that is the default scaling governor 149 determined by the kernel command line or configuration, but it may be changed 150 later via ``sysfs``). First, a pointer to the new policy object is passed to 151 the governor's ``->init()`` callback which is expected to initialize all of the 152 data structures necessary to handle the given policy and, possibly, to add 153 a governor ``sysfs`` interface to it. Next, the governor is started by 154 invoking its ``->start()`` callback. 155 156 That callback is expected to register per-CPU utilization update callbacks for 157 all of the online CPUs belonging to the given policy with the CPU scheduler. 158 The utilization update callbacks will be invoked by the CPU scheduler on 159 important events, like task enqueue and dequeue, on every iteration of the 160 scheduler tick or generally whenever the CPU utilization may change (from the 161 scheduler's perspective). They are expected to carry out computations needed 162 to determine the P-state to use for the given policy going forward and to 163 invoke the scaling driver to make changes to the hardware in accordance with 164 the P-state selection. The scaling driver may be invoked directly from 165 scheduler context or asynchronously, via a kernel thread or workqueue, depending 166 on the configuration and capabilities of the scaling driver and the governor. 167 168 Similar steps are taken for policy objects that are not new, but were "inactive" 169 previously, meaning that all of the CPUs belonging to them were offline. The 170 only practical difference in that case is that the ``CPUFreq`` core will attempt 171 to use the scaling governor previously used with the policy that became 172 "inactive" (and is re-initialized now) instead of the default governor. 173 174 In turn, if a previously offline CPU is being brought back online, but some 175 other CPUs sharing the policy object with it are online already, there is no 176 need to re-initialize the policy object at all. In that case, it only is 177 necessary to restart the scaling governor so that it can take the new online CPU 178 into account. That is achieved by invoking the governor's ``->stop`` and 179 ``->start()`` callbacks, in this order, for the entire policy. 180 181 As mentioned before, the |intel_pstate| scaling driver bypasses the scaling 182 governor layer of ``CPUFreq`` and provides its own P-state selection algorithms. 183 Consequently, if |intel_pstate| is used, scaling governors are not attached to 184 new policy objects. Instead, the driver's ``->setpolicy()`` callback is invoked 185 to register per-CPU utilization update callbacks for each policy. These 186 callbacks are invoked by the CPU scheduler in the same way as for scaling 187 governors, but in the |intel_pstate| case they both determine the P-state to 188 use and change the hardware configuration accordingly in one go from scheduler 189 context. 190 191 The policy objects created during CPU initialization and other data structures 192 associated 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 194 when the last CPU belonging to the given policy in unregistered. 195 196 197 Policy Interface in ``sysfs`` 198 ============================= 199 200 During the initialization of the kernel, the ``CPUFreq`` core creates a 201 ``sysfs`` directory (kobject) called ``cpufreq`` under 202 :file:`/sys/devices/system/cpu/`. 203 204 That directory contains a ``policyX`` subdirectory (where ``X`` represents an 205 integer number) for every policy object maintained by the ``CPUFreq`` core. 206 Each ``policyX`` directory is pointed to by ``cpufreq`` symbolic links 207 under :file:`/sys/devices/system/cpu/cpuY/` (where ``Y`` represents an integer 208 that may be different from the one represented by ``X``) for all of the CPUs 209 associated with (or belonging to) the given policy. The ``policyX`` directories 210 in :file:`/sys/devices/system/cpu/cpufreq` each contain policy-specific 211 attributes (files) to control ``CPUFreq`` behavior for the corresponding policy 212 objects (that is, for all of the CPUs associated with them). 213 214 Some of those attributes are generic. They are created by the ``CPUFreq`` core 215 and their behavior generally does not depend on what scaling driver is in use 216 and what scaling governor is attached to the given policy. Some scaling drivers 217 also add driver-specific attributes to the policy directories in ``sysfs`` to 218 control policy-specific aspects of driver behavior. 219 220 The generic attributes under :file:`/sys/devices/system/cpu/cpufreq/policyX/` 221 are 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. 335 336 337 Generic Scaling Governors 338 ========================= 339 340 ``CPUFreq`` provides generic scaling governors that can be used with all 341 scaling drivers. As stated before, each of them implements a single, possibly 342 parametrized, performance scaling algorithm. 343 344 Scaling governors are attached to policy objects and different policy objects 345 can be handled by different scaling governors at the same time (although that 346 may lead to suboptimal results in some cases). 347 348 The scaling governor for a given policy object can be changed at any time with 349 the help of the ``scaling_governor`` policy attribute in ``sysfs``. 350 351 Some governors expose ``sysfs`` attributes to control or fine-tune the scaling 352 algorithms implemented by them. Those attributes, referred to as governor 353 tunables, can be either global (system-wide) or per-policy, depending on the 354 scaling driver in use. If the driver requires governor tunables to be 355 per-policy, they are located in a subdirectory of each policy directory. 356 Otherwise, they are located in a subdirectory under 357 :file:`/sys/devices/system/cpu/cpufreq/`. In either case the name of the 358 subdirectory containing the governor tunables is the name of the governor 359 providing them. 360 361 ``performance`` 362 --------------- 363 364 When attached to a policy object, this governor causes the highest frequency, 365 within the ``scaling_max_freq`` policy limit, to be requested for that policy. 366 367 The 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`` 369 policy limits change after that. 370 371 ``powersave`` 372 ------------- 373 374 When attached to a policy object, this governor causes the lowest frequency, 375 within the ``scaling_min_freq`` policy limit, to be requested for that policy. 376 377 The 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`` 379 policy limits change after that. 380 381 ``userspace`` 382 ------------- 383 384 This governor does not do anything by itself. Instead, it allows user space 385 to 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 ------------- 390 391 This governor uses CPU utilization data available from the CPU scheduler. It 392 generally is regarded as a part of the CPU scheduler, so it can access the 393 scheduler's internal data structures directly. 394 395 It runs entirely in scheduler context, although in some cases it may need to 396 invoke the scaling driver asynchronously when it decides that the CPU frequency 397 should be changed for a given policy (that depends on whether or not the driver 398 is capable of changing the CPU frequency from scheduler context). 399 400 The actions of this governor for a particular CPU depend on the scheduling class 401 invoking its utilization update callback for that CPU. If it is invoked by the 402 RT or deadline scheduling classes, the governor will increase the frequency to 403 the allowed maximum (that is, the ``scaling_max_freq`` policy limit). In turn, 404 if it is invoked by the CFS scheduling class, the governor will use the 405 Per-Entity Load Tracking (PELT) metric for the root control group of the 406 given CPU as the CPU utilization estimate (see the *Per-entity load tracking* 407 LWN.net article [1]_ for a description of the PELT mechanism). Then, the new 408 CPU frequency to apply is computed in accordance with the formula 409 410 f = 1.25 * ``f_0`` * ``util`` / ``max`` 411 412 where ``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 414 policy (if the PELT number is frequency-invariant), or the current CPU frequency 415 (otherwise). 416 417 This governor also employs a mechanism allowing it to temporarily bump up the 418 CPU 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 420 is passed by the scheduler to the governor callback which causes the frequency 421 to go up to the allowed maximum immediately and then draw back to the value 422 returned by the above formula over time. 423 424 This 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. 433 434 This governor generally is regarded as a replacement for the older `ondemand`_ 435 and `conservative`_ governors (described below), as it is simpler and more 436 tightly integrated with the CPU scheduler, its overhead in terms of CPU context 437 switches and similar is less significant, and it uses the scheduler's own CPU 438 utilization metric, so in principle its decisions should not contradict the 439 decisions made by the other parts of the scheduler. 440 441 ``ondemand`` 442 ------------ 443 444 This governor uses CPU load as a CPU frequency selection metric. 445 446 In order to estimate the current CPU load, it measures the time elapsed between 447 consecutive invocations of its worker routine and computes the fraction of that 448 time in which the given CPU was not idle. The ratio of the non-idle (active) 449 time to the total CPU time is taken as an estimate of the load. 450 451 If this governor is attached to a policy shared by multiple CPUs, the load is 452 estimated for all of them and the greatest result is taken as the load estimate 453 for the entire policy. 454 455 The worker routine of this governor has to run in process context, so it is 456 invoked asynchronously (via a workqueue) and CPU P-states are updated from 457 there if necessary. As a result, the scheduler context overhead from this 458 governor is minimum, but it causes additional CPU context switches to happen 459 relatively often and the CPU P-state updates triggered by it can be relatively 460 irregular. Also, it affects its own CPU load metric by running code that 461 reduces the CPU idle time (even though the CPU idle time is only reduced very 462 slightly by it). 463 464 It generally selects CPU frequencies proportional to the estimated load, so that 465 the value of the ``cpuinfo_max_freq`` policy attribute corresponds to the load of 466 1 (or 100%), and the value of the ``cpuinfo_min_freq`` policy attribute 467 corresponds to the load of 0, unless when the load exceeds a (configurable) 468 speedup threshold, in which case it will go straight for the highest frequency 469 it is allowed to use (the ``scaling_max_freq`` policy limit). 470 471 This 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 ---------------- 556 557 This governor uses CPU load as a CPU frequency selection metric. 558 559 It estimates the CPU load in the same way as the `ondemand`_ governor described 560 above, but the CPU frequency selection algorithm implemented by it is different. 561 562 Namely, it avoids changing the frequency significantly over short time intervals 563 which may not be suitable for systems with limited power supply capacity (e.g. 564 battery-powered). To achieve that, it changes the frequency in relatively 565 small 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. 567 568 This 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. 596 597 598 Frequency Boost Support 599 ======================= 600 601 Background 602 ---------- 603 604 Some processors support a mechanism to raise the operating frequency of some 605 cores in a multicore package temporarily (and above the sustainable frequency 606 threshold for the whole package) under certain conditions, for example if the 607 whole chip is not fully utilized and below its intended thermal or power budget. 608 609 Different names are used by different vendors to refer to this functionality. 610 For 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. 612 As a rule, it also is implemented differently by different vendors. The simple 613 term "frequency boost" is used here for brevity to refer to all of those 614 implementations. 615 616 The frequency boost mechanism may be either hardware-based or software-based. 617 If it is hardware-based (e.g. on x86), the decision to trigger the boosting is 618 made by the hardware (although in general it requires the hardware to be put 619 into a special state in which it can control the CPU frequency within certain 620 limits). If it is software-based (e.g. on ARM), the scaling driver decides 621 whether or not to trigger boosting and when to do that. 622 623 The ``boost`` File in ``sysfs`` 624 ------------------------------- 625 626 This file is located under :file:`/sys/devices/system/cpu/cpufreq/` and controls 627 the "boost" setting for the whole system. It is not present if the underlying 628 scaling driver does not support the frequency boost mechanism (or supports it, 629 but provides a driver-specific interface for controlling it, like 630 |intel_pstate|). 631 632 If the value in this file is 1, the frequency boost mechanism is enabled. This 633 means that either the hardware can be put into states in which it is able to 634 trigger boosting (in the hardware-based case), or the software is allowed to 635 trigger boosting (in the software-based case). It does not mean that boosting 636 is actually in use at the moment on any CPUs in the system. It only means a 637 permission to use the frequency boost mechanism (which still may never be used 638 for other reasons). 639 640 If the value in this file is 0, the frequency boost mechanism is disabled and 641 cannot be used at all. 642 643 The only values that can be written to this file are 0 and 1. 644 645 Rationale for Boost Control Knob 646 -------------------------------- 647 648 The frequency boost mechanism is generally intended to help to achieve optimum 649 CPU performance on time scales below software resolution (e.g. below the 650 scheduler tick interval) and it is demonstrably suitable for many workloads, but 651 it may lead to problems in certain situations. 652 653 For this reason, many systems make it possible to disable the frequency boost 654 mechanism in the platform firmware (BIOS) setup, but that requires the system to 655 be restarted for the setting to be adjusted as desired, which may not be 656 practical 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. 680 681 Legacy AMD ``cpb`` Knob 682 ----------------------- 683 684 The AMD powernow-k8 scaling driver supports a ``sysfs`` knob very similar to 685 the global ``boost`` one. It is used for disabling/enabling the "Core 686 Performance Boost" feature of some AMD processors. 687 688 If 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 691 implementation, however, works on the system-wide basis and setting that knob 692 for one policy causes the same value of it to be set for all of the other 693 policies at the same time. 694 695 That knob is still supported on AMD processors that support its underlying 696 hardware 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 700 is more consistent with what all of the other systems do (and the ``cpb`` knob 701 may not be supported any more in the future). 702 703 The ``cpb`` knob is never present for any processors without the underlying 704 hardware feature (e.g. all Intel ones), even if the 705 :c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option is set. 706 707 708 References 709 ========== 710 711 .. [1] Jonathan Corbet, *Per-entity load tracking*, 712 https://lwn.net/Articles/531853/
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.