1What: /sys/devices/system/cpu/ 2Date: pre-git history 3Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 4Description: 5 A collection of both global and individual CPU attributes 6 7 Individual CPU attributes are contained in subdirectories 8 named by the kernel's logical CPU number, e.g.: 9 10 /sys/devices/system/cpu/cpu#/ 11 12What: /sys/devices/system/cpu/kernel_max 13 /sys/devices/system/cpu/offline 14 /sys/devices/system/cpu/online 15 /sys/devices/system/cpu/possible 16 /sys/devices/system/cpu/present 17Date: December 2008 18Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 19Description: CPU topology files that describe kernel limits related to 20 hotplug. Briefly: 21 22 kernel_max: the maximum cpu index allowed by the kernel 23 configuration. 24 25 offline: cpus that are not online because they have been 26 HOTPLUGGED off or exceed the limit of cpus allowed by the 27 kernel configuration (kernel_max above). 28 29 online: cpus that are online and being scheduled. 30 31 possible: cpus that have been allocated resources and can be 32 brought online if they are present. 33 34 present: cpus that have been identified as being present in 35 the system. 36 37 See Documentation/cputopology.txt for more information. 38 39 40What: /sys/devices/system/cpu/probe 41 /sys/devices/system/cpu/release 42Date: November 2009 43Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 44Description: Dynamic addition and removal of CPU's. This is not hotplug 45 removal, this is meant complete removal/addition of the CPU 46 from the system. 47 48 probe: writes to this file will dynamically add a CPU to the 49 system. Information written to the file to add CPU's is 50 architecture specific. 51 52 release: writes to this file dynamically remove a CPU from 53 the system. Information writtento the file to remove CPU's 54 is architecture specific. 55 56What: /sys/devices/system/cpu/cpu#/node 57Date: October 2009 58Contact: Linux memory management mailing list <linux-mm@kvack.org> 59Description: Discover NUMA node a CPU belongs to 60 61 When CONFIG_NUMA is enabled, a symbolic link that points 62 to the corresponding NUMA node directory. 63 64 For example, the following symlink is created for cpu42 65 in NUMA node 2: 66 67 /sys/devices/system/cpu/cpu42/node2 -> ../../node/node2 68 69 70What: /sys/devices/system/cpu/cpu#/node 71Date: October 2009 72Contact: Linux memory management mailing list <linux-mm@kvack.org> 73Description: Discover NUMA node a CPU belongs to 74 75 When CONFIG_NUMA is enabled, a symbolic link that points 76 to the corresponding NUMA node directory. 77 78 For example, the following symlink is created for cpu42 79 in NUMA node 2: 80 81 /sys/devices/system/cpu/cpu42/node2 -> ../../node/node2 82 83 84What: /sys/devices/system/cpu/cpu#/topology/core_id 85 /sys/devices/system/cpu/cpu#/topology/core_siblings 86 /sys/devices/system/cpu/cpu#/topology/core_siblings_list 87 /sys/devices/system/cpu/cpu#/topology/physical_package_id 88 /sys/devices/system/cpu/cpu#/topology/thread_siblings 89 /sys/devices/system/cpu/cpu#/topology/thread_siblings_list 90Date: December 2008 91Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 92Description: CPU topology files that describe a logical CPU's relationship 93 to other cores and threads in the same physical package. 94 95 One cpu# directory is created per logical CPU in the system, 96 e.g. /sys/devices/system/cpu/cpu42/. 97 98 Briefly, the files above are: 99 100 core_id: the CPU core ID of cpu#. Typically it is the 101 hardware platform's identifier (rather than the kernel's). 102 The actual value is architecture and platform dependent. 103 104 core_siblings: internal kernel map of cpu#'s hardware threads 105 within the same physical_package_id. 106 107 core_siblings_list: human-readable list of the logical CPU 108 numbers within the same physical_package_id as cpu#. 109 110 physical_package_id: physical package id of cpu#. Typically 111 corresponds to a physical socket number, but the actual value 112 is architecture and platform dependent. 113 114 thread_siblings: internel kernel map of cpu#'s hardware 115 threads within the same core as cpu# 116 117 thread_siblings_list: human-readable list of cpu#'s hardware 118 threads within the same core as cpu# 119 120 See Documentation/cputopology.txt for more information. 121 122 123What: /sys/devices/system/cpu/cpuidle/current_driver 124 /sys/devices/system/cpu/cpuidle/current_governer_ro 125Date: September 2007 126Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 127Description: Discover cpuidle policy and mechanism 128 129 Various CPUs today support multiple idle levels that are 130 differentiated by varying exit latencies and power 131 consumption during idle. 132 133 Idle policy (governor) is differentiated from idle mechanism 134 (driver) 135 136 current_driver: displays current idle mechanism 137 138 current_governor_ro: displays current idle policy 139 140 See files in Documentation/cpuidle/ for more information. 141 142 143What: /sys/devices/system/cpu/cpu#/cpufreq/* 144Date: pre-git history 145Contact: cpufreq@vger.kernel.org 146Description: Discover and change clock speed of CPUs 147 148 Clock scaling allows you to change the clock speed of the 149 CPUs on the fly. This is a nice method to save battery 150 power, because the lower the clock speed, the less power 151 the CPU consumes. 152 153 There are many knobs to tweak in this directory. 154 155 See files in Documentation/cpu-freq/ for more information. 156 157 In particular, read Documentation/cpu-freq/user-guide.txt 158 to learn how to control the knobs. 159 160 161What: /sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1} 162Date: August 2008 163KernelVersion: 2.6.27 164Contact: discuss@x86-64.org 165Description: Disable L3 cache indices 166 167 These files exist in every CPU's cache/index3 directory. Each 168 cache_disable_{0,1} file corresponds to one disable slot which 169 can be used to disable a cache index. Reading from these files 170 on a processor with this functionality will return the currently 171 disabled index for that node. There is one L3 structure per 172 node, or per internal node on MCM machines. Writing a valid 173 index to one of these files will cause the specificed cache 174 index to be disabled. 175 176 All AMD processors with L3 caches provide this functionality. 177 For details, see BKDGs at 178 http://developer.amd.com/documentation/guides/Pages/default.aspx 179 180 181What: /sys/devices/system/cpu/cpufreq/boost 182Date: August 2012 183Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> 184Description: Processor frequency boosting control 185 186 This switch controls the boost setting for the whole system. 187 Boosting allows the CPU and the firmware to run at a frequency 188 beyound it's nominal limit. 189 More details can be found in Documentation/cpu-freq/boost.txt 190