Intel P-State driver -------------------- This driver provides an interface to control the P-State selection for the SandyBridge+ Intel processors. The following document explains P-States: http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf As stated in the document, P-State doesn’t exactly mean a frequency. However, for the sake of the relationship with cpufreq, P-State and frequency are used interchangeably. Understanding the cpufreq core governors and policies are important before discussing more details about the Intel P-State driver. Based on what callbacks a cpufreq driver provides to the cpufreq core, it can support two types of drivers: - with target_index() callback: In this mode, the drivers using cpufreq core simply provide the minimum and maximum frequency limits and an additional interface target_index() to set the current frequency. The cpufreq subsystem has a number of scaling governors ("performance", "powersave", "ondemand", etc.). Depending on which governor is in use, cpufreq core will call for transitions to a specific frequency using target_index() callback. - setpolicy() callback: In this mode, drivers do not provide target_index() callback, so cpufreq core can't request a transition to a specific frequency. The driver provides minimum and maximum frequency limits and callbacks to set a policy. The policy in cpufreq sysfs is referred to as the "scaling governor". The cpufreq core can request the driver to operate in any of the two policies: "performance: and "powersave". The driver decides which frequency to use based on the above policy selection considering minimum and maximum frequency limits. The Intel P-State driver falls under the latter category, which implements the setpolicy() callback. This driver decides what P-State to use based on the requested policy from the cpufreq core. If the processor is capable of selecting its next P-State internally, then the driver will offload this responsibility to the processor (aka HWP: Hardware P-States). If not, the driver implements algorithms to select the next P-State. Since these policies are implemented in the driver, they are not same as the cpufreq scaling governors implementation, even if they have the same name in the cpufreq sysfs (scaling_governors). For example the "performance" policy is similar to cpufreq’s "performance" governor, but "powersave" is completely different than the cpufreq "powersave" governor. The strategy here is similar to cpufreq "ondemand", where the requested P-State is related to the system load. Sysfs Interface In addition to the frequency-controlling interfaces provided by the cpufreq core, the driver provides its own sysfs files to control the P-State selection. These files have been added to /sys/devices/system/cpu/intel_pstate/. Any changes made to these files are applicable to all CPUs (even in a multi-package system). max_perf_pct: Limits the maximum P-State that will be requested by the driver. It states it as a percentage of the available performance. The available (P-State) performance may be reduced by the no_turbo setting described below. min_perf_pct: Limits the minimum P-State that will be requested by the driver. It states it as a percentage of the max (non-turbo) performance level. no_turbo: Limits the driver to selecting P-State below the turbo frequency range. turbo_pct: Displays the percentage of the total performance that is supported by hardware that is in the turbo range. This number is independent of whether turbo has been disabled or not. num_pstates: Displays the number of P-States that are supported by hardware. This number is independent of whether turbo has been disabled or not. For example, if a system has these parameters: Max 1 core turbo ratio: 0x21 (Max 1 core ratio is the maximum P-State) Max non turbo ratio: 0x17 Minimum ratio : 0x08 (Here the ratio is called max efficiency ratio) Sysfs will show : max_perf_pct:100, which corresponds to 1 core ratio min_perf_pct:24, max_efficiency_ratio / max 1 Core ratio no_turbo:0, turbo is not disabled num_pstates:26 = (max 1 Core ratio - Max Efficiency Ratio + 1) turbo_pct:39 = (max 1 core ratio - max non turbo ratio) / num_pstates Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide" to understand ratios. cpufreq sysfs for Intel P-State Since this driver registers with cpufreq, cpufreq sysfs is also presented. There are some important differences, which need to be considered. scaling_cur_freq: This displays the real frequency which was used during the last sample period instead of what is requested. Some other cpufreq driver, like acpi-cpufreq, displays what is requested (Some changes are on the way to fix this for acpi-cpufreq driver). The same is true for frequencies displayed at /proc/cpuinfo. scaling_governor: This displays current active policy. Since each CPU has a cpufreq sysfs, it is possible to set a scaling governor to each CPU. But this is not possible with Intel P-States, as there is one common policy for all CPUs. Here, the last requested policy will be applicable to all CPUs. It is suggested that one use the cpupower utility to change policy to all CPUs at the same time. scaling_setspeed: This attribute can never be used with Intel P-State. scaling_max_freq/scaling_min_freq: This interface can be used similarly to the max_perf_pct/min_perf_pct of Intel P-State sysfs. However since frequencies are converted to nearest possible P-State, this is prone to rounding errors. This method is not preferred to limit performance. affected_cpus: Not used related_cpus: Not used For contemporary Intel processors, the frequency is controlled by the processor itself and the P-State exposed to software is related to performance levels. The idea that frequency can be set to a single frequency is fictional for Intel Core processors. Even if the scaling driver selects a single P-State, the actual frequency the processor will run at is selected by the processor itself. Tuning Intel P-State driver When HWP mode is not used, debugfs files have also been added to allow the tuning of the internal governor algorithm. These files are located at /sys/kernel/debug/pstate_snb/. The algorithm uses a PID (Proportional Integral Derivative) controller. The PID tunable parameters are: deadband d_gain_pct i_gain_pct p_gain_pct sample_rate_ms setpoint To adjust these parameters, some understanding of driver implementation is necessary. There are some tweeks described here, but be very careful. Adjusting them requires expert level understanding of power and performance relationship. These limits are only useful when the "powersave" policy is active. -To make the system more responsive to load changes, sample_rate_ms can be adjusted (current default is 10ms). -To make the system use higher performance, even if the load is lower, setpoint can be adjusted to a lower number. This will also lead to faster ramp up time to reach the maximum P-State. If there are no derivative and integral coefficients, The next P-State will be equal to: current P-State - ((setpoint - current cpu load) * p_gain_pct) For example, if the current PID parameters are (Which are defaults for the core processors like SandyBridge): deadband = 0 d_gain_pct = 0 i_gain_pct = 0 p_gain_pct = 20 sample_rate_ms = 10 setpoint = 97 If the current P-State = 0x08 and current load = 100, this will result in the next P-State = 0x08 - ((97 - 100) * 0.2) = 8.6 (rounded to 9). Here the P-State goes up by only 1. If during next sample interval the current load doesn't change and still 100, then P-State goes up by one again. This process will continue as long as the load is more than the setpoint until the maximum P-State is reached. For the same load at setpoint = 60, this will result in the next P-State = 0x08 - ((60 - 100) * 0.2) = 16 So by changing the setpoint from 97 to 60, there is an increase of the next P-State from 9 to 16. So this will make processor execute at higher P-State for the same CPU load. If the load continues to be more than the setpoint during next sample intervals, then P-State will go up again till the maximum P-State is reached. But the ramp up time to reach the maximum P-State will be much faster when the setpoint is 60 compared to 97. Debugging Intel P-State driver Event tracing To debug P-State transition, the Linux event tracing interface can be used. There are two specific events, which can be enabled (Provided the kernel configs related to event tracing are enabled). # cd /sys/kernel/debug/tracing/ # echo 1 > events/power/pstate_sample/enable # echo 1 > events/power/cpu_frequency/enable # cat trace gnome-terminal--4510 [001] ..s. 1177.680733: pstate_sample: core_busy=107 scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618 freq=2474476 cat-5235 [002] ..s. 1177.681723: cpu_frequency: state=2900000 cpu_id=2 Using ftrace If function level tracing is required, the Linux ftrace interface can be used. For example if we want to check how often a function to set a P-State is called, we can set ftrace filter to intel_pstate_set_pstate. # cd /sys/kernel/debug/tracing/ # cat available_filter_functions | grep -i pstate intel_pstate_set_pstate intel_pstate_cpu_init ... # echo intel_pstate_set_pstate > set_ftrace_filter # echo function > current_tracer # cat trace | head -15 # tracer: function # # entries-in-buffer/entries-written: 80/80 #P:4 # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | Xorg-3129 [000] ..s. 2537.644844: intel_pstate_set_pstate <-intel_pstate_timer_func gnome-terminal--4510 [002] ..s. 2537.649844: intel_pstate_set_pstate <-intel_pstate_timer_func gnome-shell-3409 [001] ..s. 2537.650850: intel_pstate_set_pstate <-intel_pstate_timer_func -0 [000] ..s. 2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func