pmval - performance metrics value dumper
pmval [-dgrz] [-A align] [-a archive] [-f N] [-h host] [-i instances] [-K spec] [-n pmns-
file] [-O offset] [-p port] [-S starttime] [-s samples] [-T endtime] [-t interval] [-U ar-
chive] [-w width] [-Z timezone] metricname
pmval prints current or archived values for the nominated performance metric. The metric
of interest is named in the metricname argument, subject to instance qualification with
the -i flag as described below.
Unless directed to another host by the -h option, or to an archive by the -a or -U
options, pmval will contact the Performance Metrics Collector Daemon (PMCD) on the local
host to obtain the required information.
The metricname argument may also be given in the metric specification syntax, as described
in PCPIntro(1), where the source, metric and instance may all be included in the metric-
name, e.g. thathost:kernel.all.load["1 minute"]. When this format is used, none of the -h
or -a or -U options may be specified.
When using the metric specification syntax, the ``hostname'' @ is treated specially and
causes pmval to use a local context to collect metrics from PMDAs on the local host with-
out PMCD. Only some metrics are available in this mode.
When processing an archive, pmval may relinquish its own timing control, and operate as a
``slave'' of a pmtime(1) process that uses a GUI dialog to provide timing control. In
this case, either the -g option should be used to start pmval as the sole slave of a new
pmtime(1) instance, or -p should be used to attach pmval to an existing pmtime(1) instance
via the IPC channel identified by the port argument.
The -S, -T, -O and -A options may be used to define a time window to restrict the samples
retrieved, set an initial origin within the time window, or specify a ``natural'' align-
ment of the sample times; refer to PCPIntro(1) for a complete description of these
The other options which control the source, timing and layout of the information reported
by pmval are as follows:
-a Performance metric values are retrieved from the Performance Co-Pilot (PCP) archive
log file identified by the base name archive.
-d When replaying from an archive, this option requests that the prevailing real-time
delay be applied between samples (see -t) to effect a pause, rather than the default
behaviour of replaying at full speed.
-f Numbers are reported in ``fixed point'' notation, rather than the default scientific
notation. Each number will be up to the column width determined by the default
heuristics, else the -w option if specified, and include N digits after the decimal
point. So, the options -f 3 -w 8 would produce numbers of the form 9999.999. A
value of zero for N omits the decimal point and any fractional digits.
-g Start pmval as the slave of a new pmtime(1) process for replay of archived perfor-
mance data using the pmtime(1) graphical user interface.
-h Current performance metric values are retrieved from the nominated host machine.
-i instances is a list of one or more instance names for the nominated performance met-
ric - just these instances will be retrieved and reported (the default is to report
all instances). The list must be a single argument, with elements of the list sepa-
rated by commas and/or white space.
The instance name may be quoted with single (') or double (") quotes for those cases
where the instance name contains white space or commas.
Multiple -i options are allowed as an alternative way of specifying more than one
instance of interest.
As an example, the following are all equivalent:
$ pmval -i "'1 minute','5 minute'" kernel.all.load
$ pmval -i '"1 minute","5 minute"' kernel.all.load
$ pmval -i "'1 minute' '5 minute'" kernel.all.load
$ pmval -i "'1 minute'" -i "'5 minute'" kernel.all.load
$ pmval 'localhost:kernel.all.load["1 minute","5 minute"]'
-K When fetching metrics from a local context, the -K option may be used to control the
DSO PMDAs that should be made accessible. The spec argument conforms to the syntax
described in __pmSpecLocalPMDA(3). More than one -K option may be used.
-n Normally pmval operates on the default Performance Metrics Name Space (PMNS), however
if the -n option is specified an alternative namespace is loaded from the file pmns-
-p Attach pmval to an existing pmtime(1) time control process instance via the IPC chan-
nel identified by the port argument. This option is normally only used by other
tools, e.g. pmchart(1), when they launch pmval with synchronized time control.
-r Print raw values for cumulative counter metrics. Normally cumulative counter metrics
are converted to rates. For example, disk transfers are reported as number of disk
transfers per second during the preceding sample interval, rather than the raw value
of number of disk transfers since the machine was booted. If you specify this
option, the raw metric values are printed.
-s The argument samples defines the number of samples to be retrieved and reported. If
samples is 0 or -s is not specified, pmval will sample and report continuously (in
real time mode) or until the end of the PCP archive (in archive mode).
-t The default update interval may be set to something other than the default 1 second.
The interval argument follows the syntax described in PCPIntro(1), and in the sim-
plest form may be an unsigned integer (the implied units in this case are seconds).
-U Performance metric values are retrieved from the Performance Co-Pilot (PCP) archive
log file identified by the base name archive, although unlike -a every recorded value
in the archive for the selected metric and instances is reported (so no interpolation
mode, and the sample interval (-t option) is ignored.
At most one of the options -a and -U may be specified.
-w Set the width of each column of output to be width columns. If not specified columns
are wide enough to accommodate the largest value of the type being printed.
-Z By default, pmval reports the time of day according to the local timezone on the sys-
tem where pmval is run. The -Z option changes the timezone to timezone in the format
of the environment variable TZ as described in environ(5).
-z Change the reporting timezone to the local timezone at the host that is the source of
the performance metrics, as identified via either the metricname or the -h or -a or
The following symbols may occasionally appear, in place of a metric value, in pmval out-
put: A question mark symbol (?) indicates that a value is no longer available for that
metric instance. An exclamation mark (!) indicates that a 64-bit counter wrapped during
The output from pmval is directed to standard output.
default PMNS specification files
Environment variables with the prefix PCP_ are used to parameterize the file and directory
names used by PCP. On each installation, the file /etc/pcp.conf contains the local values
for these variables. The $PCP_CONF variable may be used to specify an alternative config-
uration file, as described in pcp.conf(5).
PCPIntro(1), pmcd(1), pmchart(1), pmdumplog(1), pminfo(1), pmlogger(1), pmtime(1),
PMAPI(3), __pmSpecLocalPMDA(3), pcp.conf(5) and pcp.env(5).
All are generated on standard error and are intended to be self-explanatory.
By default, pmval attempts to display non-integer numeric values in a way that does not
distort the inherent precision (rarely more than 4 significant digits), and tries to main-
tain a tabular format in the output. These goals are sometimes in conflict.
In the absence of the -f option (described above), the following table describes the for-
mats used for different ranges of numeric values for any metric that is of type
PM_TYPE_FLOAT or PM_TYPE_DOUBLE, or any metric that has the semantics of a counter (for
which pmval reports the rate converted value):
| Format | Value Range |
| ! | No values available |
|9.999E-99 | < 0.1 |
| 0.0 | 0 |
| 9.9999 | > 0 and <= 0.9999 |
| 9.999 | > 0.9999 and < 9.999 |
| 99.99 | > 9.999 and < 99.99 |
| 999.9 | > 99.99 and < 999.9 |
|9999. | > 999.9 and < 9999 |
|9.999E+99 | > 9999 |
Performance Co-Pilot PCP PMVAL(1)