1PCP-MPSTAT(1) General Commands Manual PCP-MPSTAT(1)
2
3
4
6 pcp-mpstat - Report CPU and interrupt related statistics.
7
9 pcp [pcp options] mpstat [ -A ] [ -u ] [ -V ] [ -I { SUM | CPU | SCPU |
10 ALL } ] [ -P { cpu1,cpu2 [,...] | ON | ALL } ] [ -t interval ] [ -s
11 count ] [ -a archive ] [ -? ]
12
14 pcp-mpstat command writes to standard output activities for each avail‐
15 able processor, processor 0 being the first one. If no activity/option
16 has been selected, then the default report is the CPU utilization (-u)
17 report.
18
19 The interval parameter specifies the amount of time in seconds between
20 each report. The default is one second. The value of count parameter
21 determines the number of samples to be displayed. The default is con‐
22 tinous.
23
24 When invoked via the pcp(1) command, the -h/--host, -a/--archive,
25 -O/--origin, -s/--samples, -t/--interval, -Z/--timezone and several
26 other pcp options become indirectly available, see PCPIntro(1) for
27 their descriptions.
28
30 -A This option is equivalent to specifying -u -I ALL -P ALL
31
32 -I { SUM | CPU | SCPU | ALL }
33 Report interrupts statistics.
34 With the SUM keyword, the pcp-mpstat command reports the total
35 number of interrupts per processor. The following values are
36 displayed:
37
38 CPU
39 Processor number. The keyword all indicates that statis‐
40 tics are calculated as averages among all processors.
41
42 intr/s
43 Show the total number of interrupts received per second
44 by the CPU or CPUs.
45
46 With the CPU keyword, the number of each individual interrupt
47 received per second by the CPU or CPUs is displayed. Interrupts
48 are those under the kernel.percpu.interrupts metric tree.
49
50 With the SCPU keyword, the number of each individual software
51 interrupt received per second by the CPU or CPUs is displayed.
52 Software interrupts are those under the kernel.percpu.softirqs
53 tree
54
55 The ALL keyword is equivalent to specifying all the keywords
56 above and therefore all the interrupts statistics are displayed.
57
58 -P { cpu1,cpu2[,...] | ON | ALL }
59 Indicate the processor number for which statistics are to be
60 reported. cpu1 and cpu2 are the processor numbers. A list of
61 required processor numbers can be provided. Note that processor
62 0 is the first processor.
63
64 The ON keyword indicates that statistics are to be reported for
65 every online processor, whereas the ALL keyword indicates that
66 statistics are to be reported for all processors.
67
68 -u Report CPU utilization. The following values are displayed:
69
70 CPU
71 Processor number. The keyword ALL indicates that statis‐
72 tics are calculated as averages among all processors.
73
74 %usr
75 Show the percentage of CPU utilization that occurred
76 while executing at the user level (application).
77
78 %nice
79 Show the percentage of CPU utilization that occurred
80 while executing at the user level with nice priority.
81
82 %sys
83 Show the percentage of CPU utilization that occurred
84 while executing at the system level (kernel). Note that
85 this does not include time spent servicing hardware and
86 software interrupts.
87
88 %iowait
89 Show the percentage of time that the CPU or CPUs were
90 idle during which the system had an outstanding disk I/O
91 request.
92
93 %irq
94 Show the percentage of time spent by the CPU or CPUs to
95 service hardware interrupts.
96
97 %soft
98 Show the percentage of time spent by the CPU or CPUs to
99 service software interrupts.
100
101 %steal
102 Show the percentage of time spent in involuntary wait by
103 the virtual CPU or CPUs while the hypervisor was servic‐
104 ing another virtual processor.
105
106 %guest
107 Show the percentage of time spent by the CPU or CPUs to
108 run a virtual processor.
109
110 %gnice
111 Show the percentage of time spent by the CPU or CPUs to
112 run a niced guest.
113
114 %idle
115 Show the percentage of time that the CPU or CPUs were
116 idle and the system did not have an outstanding disk I/O
117 request.
118
119 Note: On SMP machines a processor that does not have any activ‐
120 ity at all is a disabled (offline) processor.
121
122
123 -s N , --samples = N
124 Set the number of samples to be displayed. Since the first sam‐
125 ple is used for the rate conversion of some of the metrics, the
126 total number of samples reported are one less that N. Default
127 is continous.
128
129
130 -t DELTA , --interval = DELTA
131 Set the interval between two samples. The default is one sec‐
132 ond.
133
134
135 -a FILE , --archive = FILE
136 Causes pcp-mpstat to use the specified archive than connecting
137 to PMCD. The argument to -a is a comma-separated list of names,
138 each of which may be the base name of an archive or the name of
139 a directory containing one or more archives.
140
141
142 -V , --version
143 Print version number then exit.
144
145
146 -? , --help
147 Print usage message then exit.
148
150 pcp-mpstat -t 2 -s 5
151 Display four reports of global statistics among all processors
152 at two second intervals.
153
154 pcp mpstat -P ALL -t 2 -s 5
155 Display four reports of statistics for all processors at two
156 second intervals.
157
159 pcp-mpstat is inspired by the mpstat(1) command and aims to be command
160 line and output compatible with it.
161
163 TZ and LC_TIME environment variables can be used to override the
164 default date display format for pcp-mpstat.
165
167 Environment variables with the prefix PCP_ are used to parameterize the
168 file and directory names used by PCP. On each installation, the file
169 /etc/pcp.conf contains the local values for these variables. The
170 $PCP_CONF variable may be used to specify an alternative configuration
171 file, as described in pcp.conf(5).
172
173 For environment variables affecting PCP tools, see pmGetOptions(3).
174
176 pcp(1), mpstat(1), PCPIntro(1), pmParseInterval(3) pmTraversePMNS(3)
177 and environ(7).
178
179
180
181Performance Co-Pilot PCP PCP-MPSTAT(1)