1MPSTAT(1) Linux User's Manual MPSTAT(1)
2
3
4
6 mpstat - Report processors related statistics.
7
9 mpstat [ -A ] [ --dec={ 0 | 1 | 2 } ] [ -n ] [ -u ] [ -T ] [ -V ] [ -I
10 { keyword [,...] | ALL } ] [ -N { node_list | ALL } ] [ -o JSON ] [ -P
11 { cpu_list | ALL } ] [ interval [ count ] ]
12
14 The mpstat command writes to standard output activities for each avail‐
15 able processor, processor 0 being the first one. Global average activ‐
16 ities among all processors are also reported. The mpstat command can
17 be used both on SMP and UP machines, but in the latter, only global
18 average activities will be printed. If no activity has been selected,
19 then the default report is the CPU utilization report.
20
21 The interval parameter specifies the amount of time in seconds between
22 each report. A value of 0 (or no parameters at all) indicates that
23 processors statistics are to be reported for the time since system
24 startup (boot). The count parameter can be specified in conjunction
25 with the interval parameter if this one is not set to zero. The value
26 of count determines the number of reports generated at interval seconds
27 apart. If the interval parameter is specified without the count parame‐
28 ter, the mpstat command generates reports continuously.
29
30
32 -A This option is equivalent to specifying -n -u -I ALL. This
33 option also implies specifying -N ALL -P ALL unless these
34 options are explicitly set on the command line.
35
36 --dec={ 0 | 1 | 2 }
37 Specify the number of decimal places to use (0 to 2, default
38 value is 2).
39
40 -I { keyword [,...] | ALL }
41 Report interrupts statistics.
42
43 Possible keywords are CPU, SCPU, and SUM.
44
45 With the CPU keyword, the number of each individual interrupt
46 received per second by the CPU or CPUs is displayed. Interrupts
47 are those listed in /proc/interrupts file.
48
49 With the SCPU keyword, the number of each individual software
50 interrupt received per second by the CPU or CPUs is displayed.
51 This option works only with kernels 2.6.31 and later. Software
52 interrupts are those listed in /proc/softirqs file.
53
54 With the SUM keyword, the mpstat command reports the total num‐
55 ber of interrupts per processor. The following values are dis‐
56 played:
57
58 CPU
59 Processor number. The keyword all indicates that statis‐
60 tics are calculated as averages among all processors.
61
62 intr/s
63 Show the total number of interrupts received per second
64 by the CPU or CPUs.
65
66 The ALL keyword is equivalent to specifying all the keywords
67 above and therefore all the interrupts statistics are displayed.
68
69 -N { node_list | ALL }
70 Indicate the NUMA nodes for which statistics are to be reported.
71 node_list is a list of comma-separated values or range of values
72 (e.g., 0,2,4-7,12-). Note that node all is the global average
73 among all nodes. The ALL keyword indicates that statistics are
74 to be reported for all nodes.
75
76 -n Report summary CPU statistics based on NUMA node placement. The
77 following values are displayed:
78
79 NODE
80 Logical NUMA node number. The keyword all indicates that
81 statistics are calculated as averages among all nodes.
82
83 All the other fields are the same as those displayed with option
84 -u (see below).
85
86 -o JSON
87 Display the statistics in JSON (Javascript Object Notation) for‐
88 mat. JSON output field order is undefined, and new fields may
89 be added in the future.
90
91 -P { cpu_list | ALL }
92 Indicate the processors for which statistics are to be reported.
93 cpu_list is a list of comma-separated values or range of values
94 (e.g., 0,2,4-7,12-). Note that processor 0 is the first proces‐
95 sor, and processor all is the global average among all proces‐
96 sors. The ALL keyword indicates that statistics are to be
97 reported for all processors. Offline processors are not dis‐
98 played.
99
100 -T Display topology elements in the CPU report (see option -u
101 below). The following elements are displayed:
102
103 CORE
104 Logical core number.
105
106 SOCK
107 Logical socket number.
108
109 NODE
110 Logical NUMA node number.
111
112 -u Report CPU utilization. The following values are displayed:
113
114 CPU
115 Processor number. The keyword all indicates that statis‐
116 tics are calculated as averages among all processors.
117
118 %usr
119 Show the percentage of CPU utilization that occurred
120 while executing at the user level (application).
121
122 %nice
123 Show the percentage of CPU utilization that occurred
124 while executing at the user level with nice priority.
125
126 %sys
127 Show the percentage of CPU utilization that occurred
128 while executing at the system level (kernel). Note that
129 this does not include time spent servicing hardware and
130 software interrupts.
131
132 %iowait
133 Show the percentage of time that the CPU or CPUs were
134 idle during which the system had an outstanding disk I/O
135 request.
136
137 %irq
138 Show the percentage of time spent by the CPU or CPUs to
139 service hardware interrupts.
140
141 %soft
142 Show the percentage of time spent by the CPU or CPUs to
143 service software interrupts.
144
145 %steal
146 Show the percentage of time spent in involuntary wait by
147 the virtual CPU or CPUs while the hypervisor was servic‐
148 ing another virtual processor.
149
150 %guest
151 Show the percentage of time spent by the CPU or CPUs to
152 run a virtual processor.
153
154 %gnice
155 Show the percentage of time spent by the CPU or CPUs to
156 run a niced guest.
157
158 %idle
159 Show the percentage of time that the CPU or CPUs were
160 idle and the system did not have an outstanding disk I/O
161 request.
162
163 -V Print version number then exit.
164
165
167 The mpstat command takes into account the following environment vari‐
168 able:
169
170
171 S_COLORS
172 When this variable is set, display statistics in color on the
173 terminal. Possible values for this variable are never, always
174 or auto (the latter is the default).
175
176 Please note that the color (being red, yellow, or some other
177 color) used to display a value is not indicative of any kind of
178 issue simply because of the color. It only indicates different
179 ranges of values.
180
181
182 S_COLORS_SGR
183 Specify the colors and other attributes used to display statis‐
184 tics on the terminal. Its value is a colon-separated list of
185 capabilities that defaults to
186 H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22. Supported capabilities
187 are:
188
189
190 H= SGR (Select Graphic Rendition) substring for percentage
191 values greater than or equal to 75%.
192
193
194 I= SGR substring for CPU number.
195
196
197 M= SGR substring for percentage values in the range from 50%
198 to 75%.
199
200
201 N= SGR substring for non-zero statistics values.
202
203
204 Z= SGR substring for zero values.
205
206
207 S_TIME_FORMAT
208 If this variable exists and its value is ISO then the current
209 locale will be ignored when printing the date in the report
210 header. The mpstat command will use the ISO 8601 format (YYYY-
211 MM-DD) instead. The timestamp will also be compliant with ISO
212 8601 format.
213
214
216 mpstat 2 5
217 Display five reports of global statistics among all processors
218 at two second intervals.
219
220 mpstat -P ALL 2 5
221 Display five reports of statistics for all processors at two
222 second intervals.
223
224
226 /proc filesystem must be mounted for the mpstat command to work.
227
228
230 /proc contains various files with system statistics.
231
232
234 Sebastien Godard (sysstat <at> orange.fr)
235
237 sar(1), pidstat(1), iostat(1), vmstat(8)
238
239 https://github.com/sysstat/sysstat
240
241 http://pagesperso-orange.fr/sebastien.godard/
242
243
244
245Linux NOVEMBER 2019 MPSTAT(1)