1PMVAL(1) General Commands Manual PMVAL(1)
2
6 pmval, pmevent - arbitrary performance metrics value dumper
7
9 pmval [-dgLrvVXz?] [-a archive] [-A align] [--container=name] [--de‐
10 rived=file] [-f N] [-h host] [-i instances] [-K spec] [-n pmnsfile] [-O
11 offset] [-p port] [-s samples] [-S starttime] [-t interval] [-T end‐
12 time] [-U archive] [-w width] [-x pattern] [-Z timezone] metricname
13 pmevent ...
15
17 pmval prints current or archived values for the nominated performance
18 metric. The metric of interest is named in the metricname argument,
19 subject to instance qualification with the -i flag as described below.
20 Unless directed to another host by the -h option, or to a set of ar‐
22 chives by the -a or -U options, pmval will contact the Performance Met‐
23 rics Collector Daemon (PMCD) on the local host to obtain the required
24 information.
25 The metricname argument may also be given in the metric specification
27 syntax, as described in PCPIntro(1), where the source, metric and in‐
28 stance may all be included in the metricname, e.g. thathost:ker‐
29 nel.all.load["1 minute"]. When this format is used, none of the -h or
30 -a or -U options may be specified.
31 When using the metric specification syntax, the ``hostname'' @ is
33 treated specially and causes pmval to use a local context to collect
34 metrics from PMDAs on the local host without PMCD. Only some metrics
35 are available in this mode.
36 When processing a set of archives, pmval may relinquish its own timing
38 control, and operate under the control of a a pmtime(1) process that
39 uses a GUI dialog to provide timing control. In this case, either the
40 -g option should be used to start pmval as the sole client of a new pm‐
41 time(1) instance, or -p should be used to attach pmval to an existing
42 pmtime(1) instance via the IPC channel identified by the port argument.
43 The -S, -T, -O and -A options may be used to define a time window to
45 restrict the samples retrieved, set an initial origin within the time
46 window, or specify a ``natural'' alignment of the sample times; refer
47 to PCPIntro(1) for a complete description of these options.
48 The output from pmval is directed to standard output. The following
50 symbols may occasionally appear, in place of a metric value, in pmval
51 output: A question mark symbol (?) indicates that a value is no longer
52 available for that metric instance. An exclamation mark (!) indicates
53 that a 64-bit counter wrapped during the sample.
54 pmevent is an alias for pmval.
56
58 The available command line options are:
59 -a archive, --archive=archive
61 Performance metric values are retrieved from the set of Perfor‐
62 mance Co-Pilot (PCP) archive log files identified by the archive
63 argument, which is a comma-separated list of names, each of which
64 may be the base name of an archive or the name of a directory con‐
65 taining one or more archives. See also -U.
66 -A align, --align=align
68 Force the initial sample to be aligned on the boundary of a natu‐
69 ral time unit align. Refer to PCPIntro(1) for a complete descrip‐
70 tion of the syntax for align.
71 --container=container
73 Specify an individual container to be queried.
74 -d, --delay
76 When replaying from an archive, this option requests that the pre‐
77 vailing real-time delay be applied between samples (see -t) to ef‐
78 fect a pause, rather than the default behaviour of replaying at
79 full speed.
80 --derived=file
82 Load derived metric definitions from file.
83 -f precision, --precision=precision
85 Numbers are reported in ``fixed point'' notation, rather than the
86 default scientific notation, using precision digits for precision.
87 Each number will be up to the column width determined by the de‐
88 fault heuristics, else the -w option if specified, and include
89 precision digits after the decimal point. So, the options -f 3 -w
90 8 would produce numbers of the form 9999.999. A value of zero for
91 precision omits the decimal point and any fractional digits.
92 -g, --guimode
94 Start pmval as the sole client of a new pmtime(1) server process
95 for replay of archived performance data using the pmtime(1) graph‐
96 ical user interface.
97 -h host, --host=host
99 Fetch performance metrics from pmcd(1) on host, rather than from
100 the default localhost.
101 -i instances, --instances=instances
103 Specify a list of one or more names of instances for the nominated
104 performance metric - just these instances will be retrieved and
105 reported (the default is to report all instances). The list must
106 be a single argument, with elements of the list separated by com‐
107 mas and/or white space.
108 The instance name may be quoted with single (') or double (")
110 quotes for those cases where the instance name contains white
111 space or commas.
112 Multiple -i options are allowed as an alternative way of specify‐
114 ing more than one instance of interest.
115 As an example, the following are all equivalent:
117 $ pmval -i "'1 minute','5 minute'" kernel.all.load
119 $ pmval -i '"1 minute","5 minute"' kernel.all.load
120 $ pmval -i "'1 minute' '5 minute'" kernel.all.load
121 $ pmval -i "'1 minute'" -i "'5 minute'" kernel.all.load
122 $ pmval 'localhost:kernel.all.load["1 minute","5 minute"]'
123 -K spec, --spec-local=spec
126 When fetching metrics from a local context (see -L), the -K option
127 may be used to control the DSO PMDAs that should be made accessi‐
128 ble. The spec argument conforms to the syntax described in pm‐
129 SpecLocalPMDA(3). More than one -K option may be used.
130 -L, --local-PMDA
132 Use a local context to collect metrics from DSO PMDAs on the local
133 host without PMCD. See also -K.
134 -n pmnsfile, --namespace=pmnsfile
136 Load an alternative Performance Metrics Name Space (PMNS(5)) from
137 the file pmnsfile.
138 -O origin, --origin=origin
140 When reporting archived metrics, start reporting at origin within
141 the time window (see -S and -T). Refer to PCPIntro(1) for a com‐
142 plete description of the syntax for origin.
143 -p port, --guiport=port
145 Attach pmval to an existing pmtime(1) time control process in‐
146 stance via the IPC channel identified by the port argument. This
147 option is normally only used by other tools, e.g. pmchart(1),
148 when they launch pmval with synchronized time control.
149 -r, --raw
151 Print raw values for cumulative counter metrics. Normally cumula‐
152 tive counter metrics are converted to rates. For example, disk
153 transfers are reported as number of disk transfers per second dur‐
154 ing the preceding sample interval, rather than the raw value of
155 number of disk transfers since the machine was booted. If you
156 specify this option, the raw metric values are printed.
157 -s samples, --samples=samples
159 The samples argument defines the number of samples to be retrieved
160 and reported. If samples is 0 or -s is not specified, pmval will
161 sample and report continuously (in real time mode) or until the
162 end of the set of PCP archives (in archive mode).
163 -S starttime, --start=starttime
165 When reporting archived metrics, the report will be restricted to
166 those records logged at or after starttime. Refer to PCPIntro(1)
167 for a complete description of the syntax for starttime.
168 -t interval, --interval=interval
170 Set the reporting interval to something other than the default 1
171 second. The interval argument follows the syntax described in
172 PCPIntro(1), and in the simplest form may be an unsigned integer
173 (the implied units in this case are seconds).
174 -T endtime, --finish=endtime
176 When reporting archived metrics, the report will be restricted to
177 those records logged before or at endtime. Refer to PCPIntro(1)
178 for a complete description of the syntax for endtime.
179 -U archive, --nointerp=archive
181 Performance metric values are retrieved from the Performance Co-
182 Pilot (PCP) archive. The argument is a comma-separated list of
183 names, each of which may be the base name of an archive or the
184 name of a directory containing one or more archives. However, un‐
185 like -a every recorded value in the archive for the selected met‐
186 ric and instances is reported (so no interpolation mode, and the
187 sample interval (-t option) is ignored. See also -a.
188 At most one of the options -a and -U may be specified.
190 -v, --verbose
192 Enable verbose mode.
193 -V, --version
195 Display version number and exit.
196 -w width, --width=width
198 Set the width of each column of output to be width columns. If
199 not specified columns are wide enough to accommodate the largest
200 value of the type being printed.
201 -x pattern, --filter=pattern
203 The given pattern is sent to the performance metric domain agent
204 for the requested metricname before any values are requested.
205 This serves two purposes. Firstly, it provides a mechanism for
206 server-side event filtering that is customisable for individual
207 event streams. In addition, some performance metrics domain
208 agents also use the PMCD store mechanism to provide a basic secu‐
209 rity model (e.g. for sensitive log files, only a client host with
210 pmStore(3) access would be able to access the event stream).
211 As pattern may be processed by regcomp(3) it should be a non-empty
213 string. Use . (dot) for a “match all” pattern.
214 -X, --timestamp
216 When replaying from an archive, this option requests that the
217 timestamp be reported with additional date information and mi‐
218 crosecond precision, for example Sat May 22 20:32:20.971633 2021
219 instead of the default format, for example 20:32:20.971.
220 -z, --hostzone
222 Use the local timezone of the host that is the source of the per‐
223 formance metrics, as identified by either the -h or the -a or the
224 -U options. The default is to use the timezone of the local host.
225 -Z timezone, --timezone=timezone
227 Use timezone for the date and time. Timezone is in the format of
228 the environment variable TZ as described in environ(7).
229 -?, --help
231 Display usage message and exit.
232
234 By default, pmval attempts to display non-integer numeric values in a
235 way that does not distort the inherent precision (rarely more than 4
236 significant digits), and tries to maintain a tabular format in the out‐
237 put. These goals are sometimes in conflict.
238 In the absence of the -f option (described above), the following table
240 describes the formats used for different ranges of numeric values for
241 any metric that is of type PM_TYPE_FLOAT or PM_TYPE_DOUBLE, or any met‐
242 ric that has the semantics of a counter (for which pmval reports the
243 rate converted value):
244 ┌──────────┬──────────────────────┐
246 │ Format │ Value Range │
247 ├──────────┼──────────────────────┤
248 │ ! │ No values available │
249 │9.999E-99 │ < 0.1 │
250 │ 0.0 │ 0 │
251 │ 9.9999 │ > 0 and <= 0.9999 │
252 │ 9.999 │ > 0.9999 and < 9.999 │
253 │ 99.99 │ > 9.999 and < 99.99 │
254 │ 999.9 │ > 99.99 and < 999.9 │
255 │9999. │ > 999.9 and < 9999 │
256 │9.999E+99 │ > 9999 │
257 └──────────┴──────────────────────┘
259 Environment variables with the prefix PCP_ are used to parameterize the
260 file and directory names used by PCP. On each installation, the file
261 /etc/pcp.conf contains the local values for these variables. The
262 $PCP_CONF variable may be used to specify an alternative configuration
263 file, as described in pcp.conf(5).
264 For environment variables affecting PCP tools, see pmGetOptions(3).
266
268 PCPIntro(1), pmcd(1), pmchart(1), pmdumplog(1), pmdumptext(1),
269 pminfo(1), pmlogger(1), pmrep(1), pmtime(1), PMAPI(3), pmStore(3), pm‐
270 SpecLocalPMDA(3), pcp.conf(5), pcp.env(5) and PMNS(5).
271Performance Co-Pilot PCP PMVAL(1)