sysstat/man/pidstat.1

.\" pidstat manual page - (C) 2007-2020 Sebastien Godard (sysstat <at> orange.fr)
.TH PIDSTAT 1 "JULY 2020" Linux "Linux User's Manual" -*- nroff -*-
.SH NAME
pidstat \- Report statistics for Linux tasks.

.SH SYNOPSIS
.B pidstat [ -d ] [ -H ] [ -h ] [ -I ] [ -l ] [ -R ] [ -r ] [ -s ] [ -t ] [ -U [
.IB "username " "] ] [ -u ] [ -V ] [ -v ] [ -w ] [ -C " "comm " "] [ -G " "process_name"
.BI "] [ --dec={ 0 | 1 | 2 } ] [ --human ] [ -p { " "pid" "[,...]"
.B | SELF | ALL } ] [ -T { TASK | CHILD | ALL } ] [
.IB "interval " "[ " "count " "] ] [ -e " "program"
.IB "args " "]"

.SH DESCRIPTION
.RB "The " "pidstat"
command is used for monitoring individual tasks currently being managed
by the Linux kernel.
It writes to standard output activities for every task selected with option
.B -p
or for every task managed by the Linux kernel if option
.B -p ALL
has been used. Not selecting any tasks is equivalent to specifying
.B -p ALL
but only active tasks (tasks with non-zero statistics values)
will appear in the report.
.PP
.RB "The " "pidstat"
command can also be used for monitoring the child processes of selected tasks.
Read about option
.BR "-T " "below."
.PP
.RI "The " "interval"
parameter specifies the amount of time in seconds between each report.
A value of 0 (or no parameters at all) indicates that tasks statistics are
to be reported for the time since system startup (boot). The
.IR "count " "parameter can be specified in conjunction with the"
.IR "interval " "parameter if this one is not set to zero. The value of"
.IR "count " "determines the number of reports generated at"
.IR "interval " "seconds apart. If the " "interval " "parameter is specified without the " "count"
parameter, the
.B pidstat
command generates reports continuously.
.PP
You can select information about specific task activities using flags.
Not specifying any flags selects only CPU activity.

.SH OPTIONS
.TP
.BI "-C " "comm"
Display only tasks whose command name includes the string
.IR "comm" ". This string can be a regular expression."
.TP
.B -d
Report I/O statistics (kernels 2.6.20 and later only).
The following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP kB_rd/s
Number of kilobytes the task has caused to be read from disk per second.
.IP kB_wr/s
Number of kilobytes the task has caused, or shall cause to be
written to disk per second.
.IP kB_ccwr/s
Number of kilobytes whose writing to disk has been cancelled by
the task. This may occur when the task truncates some
dirty pagecache. In this case, some IO which another task has
been accounted for will not be happening.
.IP iodelay
Block I/O delay of the task being monitored,
measured in clock ticks. This metric includes the delays spent
waiting for sync block I/O completion and for swapin block I/O
completion.
.IP Command
The command name of the task.
.RE
.TP
.B --dec={ 0 | 1 | 2 }
Specify the number of decimal places to use (0 to 2, default value is 2).
.TP
.BI "-e " "program args"
Execute
.I program
with given arguments
.I args
and monitor it with
.BR "pidstat" "."
.BR "pidstat " "stops when"
.IR "program " "terminates."
.TP
.BI "-G " "process_name"
Display only processes whose command name includes the string
.IR "process_name" "."
This string can be a regular expression. If option
.BR "-t " "is used together with option " "-G"
then the threads belonging to that process are also displayed
(even if their command name doesn't include the string
.IR "process_name" ")."
.TP
.B -H
Display timestamp in seconds since the epoch.
.TP
.B -h
Display all activities horizontally on a single line, with no
average statistics at the end of the report. This is
intended to make it easier to be parsed by other programs.
.TP
.B --human
Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
The units displayed with this option supersede any other default units (e.g.
kilobytes, sectors...) associated with the metrics.
.TP
.B -I
In an SMP environment, indicate that tasks CPU usage
.RB "(as displayed by option " "-u" ")"
should be divided by the total number of processors.
.TP
.B -l
Display the process command name and all its arguments.
.TP
.BI "-p { " "pid" "[,...] | SELF | ALL }"
Select tasks (processes) for which statistics are to be reported.
.I pid
is the process identification number. The
.B SELF
keyword indicates that statistics are to be reported for the
.BR "pidstat " "process itself, whereas the " "ALL"
keyword indicates that statistics are to be reported for all the
tasks managed by the system.
.TP
.B -R
Report realtime priority and scheduling policy information.
The following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP prio
The realtime priority of the task being monitored.
.IP policy
The scheduling policy of the task being monitored.
.IP Command
The command name of the task.
.RE
.TP
.B -r
Report page faults and memory utilization.

When reporting statistics for individual tasks,
the following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP minflt/s
Total number of minor faults the task has made per second, those
which have not required loading a memory page from disk.
.IP majflt/s
Total number of major faults the task has made per second, those
which have required loading a memory page from disk.
.IP VSZ
Virtual Size: The virtual memory usage of entire task in kilobytes.
.IP RSS
Resident Set Size: The non-swapped physical memory
used by the task in kilobytes.
.IP %MEM
The tasks's currently used share of available physical memory.
.IP Command
The command name of the task.
.RE
.IP
When reporting global statistics for tasks and all their children,
the following values may be displayed:
.RS
.IP UID
The real user identification number of the task which is being monitored
together with its children.
.IP USER
The name of the real user owning the task which is being monitored
together with its children.
.IP PID
The identification number of the task which is being monitored
together with its children.
.IP minflt-nr
Total number of minor faults made by the task and all its children,
and collected during the interval of time.
.IP majflt-nr
Total number of major faults made by the task and all its children,
and collected during the interval of time.
.IP Command
The command name of the task which is being monitored
together with its children.
.RE
.TP
.B -s
Report stack utilization.
The following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP StkSize
The amount of memory in kilobytes reserved for the task as stack,
but not necessarily used.
.IP StkRef
The amount of memory in kilobytes used as stack, referenced by the task.
.IP Command
The command name of the task.
.RE
.TP
.B -T { TASK | CHILD | ALL }
This option specifies what has to be monitored by the
.BR "pidstat " "command. The " "TASK"
keyword indicates that statistics are to be reported for individual tasks
(this is the default option) whereas the
.B CHILD
keyword indicates that statistics are to be globally reported for the
selected tasks and all their children. The
.B ALL
keyword indicates that statistics are to be reported for
individual tasks and globally for the selected
tasks and their children.

Note: Global statistics for tasks and all their children are not available
for all options of
.B pidstat.
Also these statistics are not necessarily relevant to current time interval:
The statistics of a child process are collected only when it finishes or
it is killed.
.TP
.B -t
Also display statistics for threads associated with selected tasks.

This option adds the following values to the reports:
.RS
.IP TGID
The identification number of the thread group leader.
.IP TID
The identification number of the thread being monitored.
.RE
.TP
.BI "-U [ " "username " "]"
Display the real user name of the tasks being monitored instead of the UID.
.RI "If " "username"
is specified, then only tasks belonging to the specified user are displayed.
.TP
.B -u
Report CPU utilization.

When reporting statistics for individual tasks,
the following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP %usr
Percentage of CPU used by the task while executing at the user level
(application), with or without nice priority. Note that this field
does NOT include time spent running a virtual processor.
.IP %system
Percentage of CPU used by the task while executing at the system level (kernel).
.IP %guest
Percentage of CPU spent by the task in virtual machine (running a virtual processor).
.IP %wait
Percentage of CPU spent by the task while waiting to run.
.IP %CPU
Total percentage of CPU time used by the task. In an SMP environment,
the task's CPU usage will be divided by the total number of CPU's if option
.B -I
has been entered on the command line.
.IP CPU
Processor number to which the task is attached.
.IP Command
The command name of the task.
.RE
.IP
When reporting global statistics for tasks and all their children,
the following values may be displayed:
.RS
.IP UID
The real user identification number of the task which is being monitored
together with its children.
.IP USER
The name of the real user owning the task which is being monitored
together with its children.
.IP PID
The identification number of the task which is being monitored
together with its children.
.IP usr-ms
Total number of milliseconds spent
by the task and all its children while executing at the
user level (application), with or without nice priority, and
collected during the interval of time. Note that this field does
NOT include time spent running a virtual processor.
.IP system-ms
Total number of milliseconds spent
by the task and all its children while executing at the
system level (kernel), and collected during the interval of time.
.IP guest-ms
Total number of milliseconds spent
by the task and all its children in virtual machine (running a virtual processor).
.IP Command
The command name of the task which is being monitored
together with its children.
.RE
.TP
.B -V
Print version number then exit.
.TP
.B -v
Report values of some kernel tables. The following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP threads
Number of threads associated with current task.
.IP fd-nr
Number of file descriptors associated with current task.
.IP Command
The command name of the task.
.RE
.TP
.B -w
Report task switching activity (kernels 2.6.23 and later only).
The following values may be displayed:
.RS
.IP UID
The real user identification number of the task being monitored.
.IP USER
The name of the real user owning the task being monitored.
.IP PID
The identification number of the task being monitored.
.IP cswch/s
Total number of voluntary context switches the task made per second.
A voluntary context switch occurs when a task blocks because it
requires a resource that is unavailable.
.IP nvcswch/s
Total number of non voluntary context switches the task made per second.
An involuntary context switch takes place when a task executes
for the duration of its time slice and then is forced to relinquish the
processor.
.IP Command
The command name of the task.
.RE

.SH ENVIRONMENT
The
.B pidstat
command takes into account the following environment variables:
.TP
.B S_COLORS
By default statistics are displayed in color when the output is connected to a terminal.
Use this variable to change the settings. Possible values for this variable are
.IR "never" ", " "always " "or " "auto"
(the latter is equivalent to the default settings).
.br
Please note that the color (being red, yellow, or some other color) used to display a value
is not indicative of any kind of issue simply because of the color. It only indicates different
ranges of values.
.TP
.B S_COLORS_SGR
Specify the colors and other attributes used to display statistics on the terminal.
Its value is a colon-separated list of capabilities that defaults to
.BR "H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22" "."
Supported capabilities are:
.RS
.TP
.B H=
SGR (Select Graphic Rendition) substring for percentage values greater than or equal to 75%.
.TP
.B I=
SGR substring for item values like PID, UID or CPU number.
.TP
.B M=
SGR substring for percentage values in the range from 50% to 75%.
.TP
.B N=
SGR substring for non-zero statistics values and for tasks names.
.TP
.B Z=
SGR substring for zero values and for threads names.
.RE
.TP
.B S_TIME_FORMAT
If this variable exists and its value is
.BR ISO
then the current locale will be ignored when printing the date in the report header. The
.B pidstat
command will use the ISO 8601 format (YYYY-MM-DD) instead.
The timestamp will also be compliant with ISO 8601 format.

.SH EXAMPLES
.TP
.B pidstat 2 5
Display five reports of CPU statistics for every active task in the system
at two second intervals.
.TP
.B pidstat -r -p 1643 2 5
Display five reports of page faults and memory statistics for
PID 1643 at two second intervals.
.TP
.B pidstat -C """fox|bird"" -r -p ALL
Display global page faults and memory statistics for all the
processes whose command name includes the string "fox" or "bird".
.TP
.B pidstat -T CHILD -r 2 5
Display five reports of page faults statistics at two second intervals
for the child processes of all tasks in the system. Only child processes
with non-zero statistics values are displayed.

.SH BUGS
.IR "/proc " "filesystem must be mounted for the"
.BR "pidstat " "command to work."
.PP
.RB "Although " "pidstat"
speaks of kilobytes (kB), megabytes (MB)..., it actually uses kibibytes (kiB), mebibytes (MiB)...
A kibibyte is equal to 1024 bytes, and a mebibyte is equal to 1024 kibibytes.

.SH FILES
.IR "/proc " "contains various files with system statistics."

.SH AUTHOR
Sebastien Godard (sysstat <at> orange.fr)

.SH SEE ALSO
.BR "sar" "(1), " "top" "(1), " "ps" "(1), " "mpstat" "(1), " "iostat" "(1), " "vmstat" "(8)"
.PP
.I https://github.com/sysstat/sysstat
.br
.I http://pagesperso-orange.fr/sebastien.godard/