1.. SPDX-License-Identifier: BSD-3-Clause 2 Copyright(c) 2010-2014 Intel Corporation. 3 4Power Management 5================ 6 7The DPDK Power Management feature allows users space applications to save power 8by dynamically adjusting CPU frequency or entering into different C-States. 9 10* Adjusting the CPU frequency dynamically according to the utilization of RX queue. 11 12* Entering into different deeper C-States according to the adaptive algorithms to speculate 13 brief periods of time suspending the application if no packets are received. 14 15The interfaces for adjusting the operating CPU frequency are in the power management library. 16C-State control is implemented in applications according to the different use cases. 17 18CPU Frequency Scaling 19--------------------- 20 21The Linux kernel provides a cpufreq module for CPU frequency scaling for each lcore. 22For example, for cpuX, /sys/devices/system/cpu/cpuX/cpufreq/ has the following sys files for frequency scaling: 23 24* affected_cpus 25 26* bios_limit 27 28* cpuinfo_cur_freq 29 30* cpuinfo_max_freq 31 32* cpuinfo_min_freq 33 34* cpuinfo_transition_latency 35 36* related_cpus 37 38* scaling_available_frequencies 39 40* scaling_available_governors 41 42* scaling_cur_freq 43 44* scaling_driver 45 46* scaling_governor 47 48* scaling_max_freq 49 50* scaling_min_freq 51 52* scaling_setspeed 53 54In the DPDK, scaling_governor is configured in user space. 55Then, a user space application can prompt the kernel by writing scaling_setspeed to adjust the CPU frequency 56according to the strategies defined by the user space application. 57 58Core-load Throttling through C-States 59------------------------------------- 60 61Core state can be altered by speculative sleeps whenever the specified lcore has nothing to do. 62In the DPDK, if no packet is received after polling, 63speculative sleeps can be triggered according the strategies defined by the user space application. 64 65Per-core Turbo Boost 66-------------------- 67 68Individual cores can be allowed to enter a Turbo Boost state on a per-core 69basis. This is achieved by enabling Turbo Boost Technology in the BIOS, then 70looping through the relevant cores and enabling/disabling Turbo Boost on each 71core. 72 73Use of Power Library in a Hyper-Threaded Environment 74---------------------------------------------------- 75 76In the case where the power library is in use on a system with Hyper-Threading enabled, 77the frequency on the physical core is set to the highest frequency of the Hyper-Thread siblings. 78So even though an application may request a scale down, the core frequency will 79remain at the highest frequency until all Hyper-Threads on that core request a scale down. 80 81API Overview of the Power Library 82--------------------------------- 83 84The main methods exported by power library are for CPU frequency scaling and include the following: 85 86* **Freq up**: Prompt the kernel to scale up the frequency of the specific lcore. 87 88* **Freq down**: Prompt the kernel to scale down the frequency of the specific lcore. 89 90* **Freq max**: Prompt the kernel to scale up the frequency of the specific lcore to the maximum. 91 92* **Freq min**: Prompt the kernel to scale down the frequency of the specific lcore to the minimum. 93 94* **Get available freqs**: Read the available frequencies of the specific lcore from the sys file. 95 96* **Freq get**: Get the current frequency of the specific lcore. 97 98* **Freq set**: Prompt the kernel to set the frequency for the specific lcore. 99 100* **Enable turbo**: Prompt the kernel to enable Turbo Boost for the specific lcore. 101 102* **Disable turbo**: Prompt the kernel to disable Turbo Boost for the specific lcore. 103 104User Cases 105---------- 106 107The power management mechanism is used to save power when performing L3 forwarding. 108 109 110Ethernet PMD Power Management API 111--------------------------------- 112 113Abstract 114~~~~~~~~ 115 116Existing power management mechanisms require developers to change application 117design or change code to make use of it. The PMD power management API provides a 118convenient alternative by utilizing Ethernet PMD RX callbacks, and triggering 119power saving whenever empty poll count reaches a certain number. 120 121* Monitor 122 This power saving scheme will put the CPU into optimized power state and 123 monitor the Ethernet PMD RX descriptor address, waking the CPU up whenever 124 there's new traffic. Support for this scheme may not be available on all 125 platforms, and further limitations may apply (see below). 126 127* Pause 128 This power saving scheme will avoid busy polling by either entering 129 power-optimized sleep state with ``rte_power_pause()`` function, or, if it's 130 not supported by the underlying platform, use ``rte_pause()``. 131 132* Frequency scaling 133 This power saving scheme will use ``librte_power`` library functionality to 134 scale the core frequency up/down depending on traffic volume. 135 The reaction time of the frequency scaling mode is longer 136 than the pause and monitor mode. 137 138The "monitor" mode is only supported in the following configurations and scenarios: 139 140* On Linux* x86_64, `rte_power_monitor()` requires WAITPKG instruction set being 141 supported by the CPU, while `rte_power_monitor_multi()` requires WAITPKG and 142 RTM instruction sets being supported by the CPU. RTM instruction set may also 143 require booting the Linux with `tsx=on` command line parameter. Please refer 144 to your platform documentation for further information. 145 146* If ``rte_cpu_get_intrinsics_support()`` function indicates that 147 ``rte_power_monitor_multi()`` function is supported by the platform, then 148 monitoring multiple Ethernet Rx queues for traffic will be supported. 149 150* If ``rte_cpu_get_intrinsics_support()`` function indicates that only 151 ``rte_power_monitor()`` is supported by the platform, then monitoring will be 152 limited to a mapping of 1 core 1 queue (thus, each Rx queue will have to be 153 monitored from a different lcore). 154 155* If ``rte_cpu_get_intrinsics_support()`` function indicates that neither of the 156 two monitoring functions are supported, then monitor mode will not be supported. 157 158* Not all Ethernet drivers support monitoring, even if the underlying 159 platform may support the necessary CPU instructions. Please refer to 160 :doc:`../nics/overview` for more information. 161 162 163API Overview for Ethernet PMD Power Management 164~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 165 166* **Queue Enable**: Enable specific power scheme for certain queue/port/core. 167 168* **Queue Disable**: Disable power scheme for certain queue/port/core. 169 170* **Get Emptypoll Max**: Get the configured number of empty polls to wait before 171 entering sleep state. 172 173* **Set Emptypoll Max**: Set the number of empty polls to wait before entering 174 sleep state. 175 176* **Get Pause Duration**: Get the configured duration (microseconds) to be used 177 in the Pause callback. 178 179* **Set Pause Duration**: Set the duration of the pause (microseconds) used in 180 the Pause mode callback. 181 182* **Get Scaling Min Freq**: Get the configured minimum frequency (kHz) to be used 183 in Frequency Scaling mode. 184 185* **Set Scaling Min Freq**: Set the minimum frequency (kHz) to be used in Frequency 186 Scaling mode. 187 188* **Get Scaling Max Freq**: Get the configured maximum frequency (kHz) to be used 189 in Frequency Scaling mode. 190 191* **Set Scaling Max Freq**: Set the maximum frequency (kHz) to be used in Frequency 192 Scaling mode. 193 194Uncore API 195---------- 196 197Abstract 198~~~~~~~~ 199 200Uncore is a term used by Intel to describe the functions of a microprocessor 201that are not in the core, but which must be closely connected to the core 202to achieve high performance: L3 cache, on-die memory controller, etc. 203Significant power savings can be achieved by reducing the uncore frequency 204to its lowest value. 205 206Intel Uncore 207~~~~~~~~~~~~ 208 209The Linux kernel provides the driver "intel-uncore-frequency" 210to control the uncore frequency limits for x86 platform. 211The driver is available from kernel version 5.6 and above. 212Also CONFIG_INTEL_UNCORE_FREQ_CONTROL will need to be enabled in the kernel, 213which was added in 5.6. 214This manipulates the context of MSR 0x620, 215which sets min/max of the uncore for the SKU. 216 217AMD EPYC Uncore 218~~~~~~~~~~~~~~~ 219 220On AMD EPYC platforms, the Host System Management Port (HSMP) kernel module 221facilitates user-level access to HSMP mailboxes, 222which are implemented by the firmware in the System Management Unit (SMU). 223The AMD HSMP driver is available starting from kernel version 5.18. 224Please ensure that ``CONFIG_AMD_HSMP`` is enabled in your kernel configuration. 225 226Additionally, the EPYC System Management Interface In-band Library for Linux 227offers essential API, enabling user-space software 228to effectively manage system functions. 229 230Uncore API Overview 231~~~~~~~~~~~~~~~~~~~ 232 233Overview of each function in the Uncore API, 234with explanation of what they do. 235Each function should not be called in the fast path. 236 237Uncore Power Init 238 Initialize uncore power, populate frequency array 239 and record original min & max for die on pkg. 240 241Uncore Power Exit 242 Exit uncore power, restoring original min & max for die on pkg. 243 244Get Uncore Power Freq 245 Get current uncore freq index for die on pkg. 246 247Set Uncore Power Freq 248 Set min & max uncore freq index for die on pkg 249 to specified index value (min and max will be the same). 250 251Uncore Power Max 252 Set min & max uncore freq to maximum frequency index for die on pkg 253 (min and max will be the same). 254 255Uncore Power Min 256 Set min & max uncore freq to minimum frequency index for die on pkg 257 (min and max will be the same). 258 259Get Num Freqs 260 Get the number of frequencies in the index array. 261 262Get Num Pkgs 263 Get the number of packages (CPU's) on the system. 264 265Get Num Dies 266 Get the number of die's on a given package. 267 268References 269---------- 270 271* The :doc:`../sample_app_ug/l3_forward_power_man` 272 chapter in the :doc:`../sample_app_ug/index` section. 273 274* The :doc:`../sample_app_ug/vm_power_management` 275 chapter in the :doc:`../sample_app_ug/index` section. 276 277* The :doc:`../nics/overview` chapter in the :doc:`../nics/index` section 278