1 .TH CPUPOWER\-MONITOR "1" "22/02/2011" "" "cpupower Manual" 2 .SH NAME 3 cpupower\-monitor \- Report processor frequency and idle statistics 4 .SH SYNOPSIS 5 .ft B 6 .B cpupower monitor 7 .RB "\-l" 8 9 .B cpupower monitor 10 .RB [ -c ] [ "\-m <mon1>," [ "<mon2>,..." ] ] 11 .RB [ "\-i seconds" ] 12 .br 13 .B cpupower monitor 14 .RB [ -c ][ "\-m <mon1>," [ "<mon2>,..." ] ] 15 .RB command 16 .br 17 .SH DESCRIPTION 18 \fBcpupower-monitor \fP reports processor topology, frequency and idle power 19 state statistics. Either \fBcommand\fP is forked and 20 statistics are printed upon its completion, or statistics are printed periodically. 21 22 \fBcpupower-monitor \fP implements independent processor sleep state and 23 frequency counters. Some are retrieved from kernel statistics, some are 24 directly reading out hardware registers. Use \-l to get an overview which are 25 supported on your system. 26 27 .SH Options 28 .PP 29 \-l 30 .RS 4 31 List available monitors on your system. Additional details about each monitor 32 are shown: 33 .RS 2 34 .IP \(bu 35 The name in quotation marks which can be passed to the \-m parameter. 36 .IP \(bu 37 The number of different counters the monitor supports in brackets. 38 .IP \(bu 39 The amount of time in seconds the counters might overflow, due to 40 implementation constraints. 41 .IP \(bu 42 The name and a description of each counter and its processor hierarchy level 43 coverage in square brackets: 44 .RS 4 45 .IP \(bu 46 [T] \-> Thread 47 .IP \(bu 48 [C] \-> Core 49 .IP \(bu 50 [P] \-> Processor Package (Socket) 51 .IP \(bu 52 [M] \-> Machine/Platform wide counter 53 .RE 54 .RE 55 .RE 56 .PP 57 \-m <mon1>,<mon2>,... 58 .RS 4 59 Only display specific monitors. Use the monitor string(s) provided by \-l option. 60 .RE 61 .PP 62 \-i seconds 63 .RS 4 64 Measure interval. 65 .RE 66 .PP 67 \-c 68 .RS 4 69 Schedule the process on every core before starting and ending measuring. 70 This could be needed for the Idle_Stats monitor when no other MSR based 71 monitor (has to be run on the core that is measured) is run in parallel. 72 This is to wake up the processors from deeper sleep states and let the 73 kernel re 74 -account its cpuidle (C-state) information before reading the 75 cpuidle timings from sysfs. 76 .RE 77 .PP 78 command 79 .RS 4 80 Measure idle and frequency characteristics of an arbitrary command/workload. 81 The executable \fBcommand\fP is forked and upon its exit, statistics gathered since it was 82 forked are displayed. 83 .RE 84 85 .SH MONITOR DESCRIPTIONS 86 .SS "Idle_Stats" 87 Shows statistics of the cpuidle kernel subsystem. Values are retrieved from 88 /sys/devices/system/cpu/cpu*/cpuidle/state*/. 89 The kernel updates these values every time an idle state is entered or 90 left. Therefore there can be some inaccuracy when cores are in an idle 91 state for some time when the measure starts or ends. In worst case it can happen 92 that one core stayed in an idle state for the whole measure time and the idle 93 state usage time as exported by the kernel did not get updated. In this case 94 a state residency of 0 percent is shown while it was 100. 95 96 .SS "Mperf" 97 The name comes from the aperf/mperf (average and maximum) MSR registers used 98 which are available on recent X86 processors. It shows the average frequency 99 (including boost frequencies). 100 The fact that on all recent hardware the mperf timer stops ticking in any idle 101 state it is also used to show C0 (processor is active) and Cx (processor is in 102 any sleep state) times. These counters do not have the inaccuracy restrictions 103 the "Idle_Stats" counters may show. 104 May work poorly on Linux-2.6.20 through 2.6.29, as the \fBacpi-cpufreq \fP 105 kernel frequency driver periodically cleared aperf/mperf registers in those 106 kernels. 107 108 .SS "Nehalem" "SandyBridge" "HaswellExtended" 109 Intel Core and Package sleep state counters. 110 Threads (hyperthreaded cores) may not be able to enter deeper core states if 111 its sibling is utilized. 112 Deepest package sleep states may in reality show up as machine/platform wide 113 sleep states and can only be entered if all cores are idle. Look up Intel 114 manuals (some are provided in the References section) for further details. 115 The monitors are named after the CPU family where the sleep state capabilities 116 got introduced and may not match exactly the CPU name of the platform. 117 For example an IvyBridge processor has sleep state capabilities which got 118 introduced in Nehalem and SandyBridge processor families. 119 Thus on an IvyBridge processor one will get Nehalem and SandyBridge sleep 120 state monitors. 121 HaswellExtended extra package sleep state capabilities are available only in a 122 specific Haswell (family 0x45) and probably also other future processors. 123 124 .SS "Fam_12h" "Fam_14h" 125 AMD laptop and desktop processor (family 12h and 14h) sleep state counters. 126 The registers are accessed via PCI and therefore can still be read out while 127 cores have been offlined. 128 129 There is one special counter: NBP1 (North Bridge P1). 130 This one always returns 0 or 1, depending on whether the North Bridge P1 131 power state got entered at least once during measure time. 132 Being able to enter NBP1 state also depends on graphics power management. 133 Therefore this counter can be used to verify whether the graphics' driver 134 power management is working as expected. 135 136 .SH EXAMPLES 137 138 cpupower monitor -l" may show: 139 .RS 4 140 Monitor "Mperf" (3 states) \- Might overflow after 922000000 s 141 142 ... 143 144 Monitor "Idle_Stats" (3 states) \- Might overflow after 4294967295 s 145 146 ... 147 148 .RE 149 cpupower monitor \-m "Idle_Stats,Mperf" scp /tmp/test /nfs/tmp 150 151 Monitor the scp command, show both Mperf and Idle_Stats states counter 152 statistics, but in exchanged order. 153 154 155 156 .RE 157 Be careful that the typical command to fully utilize one CPU by doing: 158 159 cpupower monitor cat /dev/zero >/dev/null 160 161 Does not work as expected, because the measured output is redirected to 162 /dev/null. This could get workarounded by putting the line into an own, tiny 163 shell script. Hit CTRL\-c to terminate the command and get the measure output 164 displayed. 165 166 .SH REFERENCES 167 "BIOS and Kernel Developer’s Guide (BKDG) for AMD Family 14h Processors" 168 https://support.amd.com/us/Processor_TechDocs/43170.pdf 169 170 "What Is Intel® Turbo Boost Technology?" 171 https://www.intel.com/content/www/us/en/gaming/resources/turbo-boost.html 172 173 "Power Management - Technology Overview" 174 https://cdrdv2.intel.com/v1/dl/getContent/637748 175 176 "Intel® 64 and IA-32 Architectures Software Developer's Manual 177 Volume 3B: System Programming Guide" 178 https://www.intel.com/products/processor/manuals 179 180 .SH FILES 181 .ta 182 .nf 183 /dev/cpu/*/msr 184 /sys/devices/system/cpu/cpu*/cpuidle/state*/. 185 .fi 186 187 .SH "SEE ALSO" 188 powertop(8), msr(4), vmstat(8) 189 .PP 190 .SH AUTHORS 191 .nf 192 Written by Thomas Renninger <trenn@suse.de> 193 194 Nehalem, SandyBridge monitors and command passing 195 based on turbostat.8 from Len Brown <len.brown@intel.com>
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.