info > pidstat(1)

man perldoc info pydoc3 ri search

Not found locally for pidstat. Try Google search

📋 NAME

pidstat - Report statistics for Linux tasks.

🚀 Quick Reference

Use Case	Command	Description
📊 Monitor CPU usage of all active tasks every 2 seconds, 5 reports	pidstat 2 5	Display five reports of CPU statistics for every active task at 2-second intervals.
🖥️ Memory & page faults for a specific PID	pidstat -r -p 1643 2 5	Display five reports of page faults and memory statistics for PID 1643.
🔍 Filter processes by name pattern	pidstat -C "fox|bird" -r -p ALL	Display global page faults and memory statistics for processes with command name containing "fox" or "bird".
👶 Monitor child processes of all tasks	pidstat -T CHILD -r 2 5	Display five reports of page faults statistics for child processes of all tasks.
⚡ Real-time continuous monitoring	pidstat -p ALL 1	Continuously report statistics for all tasks every second.
📋 I/O statistics	pidstat -d	Report I/O statistics (disk read/write per second).
🔄 Context switching	pidstat -w	Report voluntary and involuntary context switches per second.
🔢 Stack utilization	pidstat -s	Report stack size and referenced stack memory.

📖 SYNOPSIS

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

📝 DESCRIPTION

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 -p or for every task managed by the Linux kernel if option -p ALL has been used. Not selecting any tasks is equivalent to specifying -p ALL but only active tasks (tasks with non-zero statistics values) will appear in the report.

The pidstat command can also be used for monitoring the child processes of selected tasks. Read about option -T below.

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 count parameter can be specified in conjunction with the interval parameter if this one is not set to zero. The value of count determines the number of reports generated at interval seconds apart. If the interval parameter is specified without the count parameter, the pidstat command generates reports continuously.

You can select information about specific task activities using flags. Not specifying any flags selects only CPU activity.

⚙️ OPTIONS

🎯 -C comm

Display only tasks whose command name includes the string comm. This string can be a regular expression.

💾 -d — Report I/O statistics

Kernels 2.6.20 and later only. The following values may be displayed:

• UID — The real user identification number of the task being monitored.
• USER — The name of the real user owning the task.
• PID — The identification number of the task.
• kB_rd/s — Number of kilobytes the task has caused to be read from disk per second.
• kB_wr/s — Number of kilobytes the task has caused, or shall cause to be written to disk per second.
• kB_ccwr/s — Number of kilobytes whose writing to disk has been cancelled by the task (e.g., truncation of dirty pagecache).
• iodelay — Block I/O delay of the task, measured in clock ticks. Includes delays for sync block I/O completion and swapin block I/O completion.
• Command — The command name of the task.

🔢 --dec={ 0 | 1 | 2 }

Specify the number of decimal places to use (0 to 2, default is 2).

🚀 -e program args

Execute program with given arguments args and monitor it with pidstat. pidstat stops when program terminates.

🔍 -G process_name

Display only processes whose command name includes the string process_name. This string can be a regular expression. If option -t is used together with -G, then the threads belonging to that process are also displayed (even if their command name doesn't include the string).

⏱️ -H

Display timestamp in seconds since the epoch.

📊 -h

Display all activities horizontally on a single line, with no average statistics at the end. Intended for easier parsing by other programs.

👤 --human

Print sizes in human readable format (e.g., 1.0k, 1.2M, etc.). Units supersede any other default units (e.g., kilobytes, sectors).

🧮 -I

In an SMP environment, indicate that tasks CPU usage (as displayed by option -u) should be divided by the total number of processors.

📋 -l

Display the process command name and all its arguments.

🎯 -p { pid[,...] | SELF | ALL }

Select tasks (processes) for which statistics are to be reported. pid is the process identification number. SELF indicates statistics for the pidstat process itself. ALL indicates statistics for all tasks managed by the system.

⏲️ -R — Report realtime priority and scheduling policy

The following values may be displayed:

• UID — Real user identification number of the task.
• USER — Real user name owning the task.
• PID — Identification number of the task.
• prio — Realtime priority of the task.
• policy — Scheduling policy of the task.
• Command — Command name of the task.

🧠 -r — Report page faults and memory utilization

When reporting statistics for individual tasks, the following values may be displayed:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number.
• minflt/s — Total number of minor faults per second (no memory page loading from disk).
• majflt/s — Total number of major faults per second (memory page loading from disk).
• VSZ — Virtual Size: virtual memory usage of entire task in kilobytes.
• RSS — Resident Set Size: non-swapped physical memory used by the task in kilobytes.
• %MEM — Task's currently used share of available physical memory.
• Command — Command name of the task.

When reporting global statistics for tasks and all their children, the following values may be displayed:

• UID — Real user identification number of the task (together with children).
• USER — Real user name.
• PID — Identification number of the task.
• minflt-nr — Total number of minor faults made by the task and all its children during the interval.
• majflt-nr — Total number of major faults made by the task and all its children during the interval.
• Command — Command name of the task.

📦 -s — Report stack utilization

The following values may be displayed:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number.
• StkSize — Amount of memory in kilobytes reserved for the task as stack (not necessarily used).
• StkRef — Amount of memory in kilobytes used as stack, referenced by the task.
• Command — Command name of the task.

👶 -T { TASK | CHILD | ALL }

Specifies what to monitor. TASK (default) reports statistics for individual tasks. CHILD reports globally for selected tasks and all their children. ALL reports both individual and global statistics. Note: Global statistics for children are collected only when a child finishes or is killed.

🧵 -t — Also display statistics for threads

Adds the following values to reports:

• TGID — Identification number of the thread group leader.
• TID — Identification number of the thread being monitored.

👤 -U [ username ]

Display the real user name of the tasks instead of the UID. If username is specified, only tasks belonging to that user are displayed.

💻 -u — Report CPU utilization

When reporting for individual tasks:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number.
• %usr — Percentage of CPU used at user level (application), with or without nice priority. Does NOT include time running a virtual processor.
• %system — Percentage of CPU used at system level (kernel).
• %guest — Percentage of CPU spent in virtual machine (running a virtual processor).
• %wait — Percentage of CPU spent waiting to run.
• %CPU — Total percentage of CPU time used. In SMP, divided by total number of CPUs if -I is used.
• CPU — Processor number to which the task is attached.
• Command — Command name.

When reporting global statistics for tasks and children:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number of the task.
• usr-ms — Total milliseconds spent at user level (application) by task and children during the interval.
• system-ms — Total milliseconds spent at system level (kernel) by task and children during the interval.
• guest-ms — Total milliseconds spent in virtual machine by task and children during the interval.
• Command — Command name.

ℹ️ -V

Print version number then exit.

📏 -v — Report values of some kernel tables

The following values may be displayed:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number.
• threads — Number of threads associated with the current task.
• fd-nr — Number of file descriptors associated with the current task.
• Command — Command name.

🔄 -w — Report task switching activity

Kernels 2.6.23 and later only. The following values may be displayed:

• UID — Real user identification number.
• USER — Real user name.
• PID — Identification number.
• cswch/s — Total number of voluntary context switches per second (task blocks because it requires an unavailable resource).
• nvcswch/s — Total number of non-voluntary context switches per second (task executed for its time slice and forced to relinquish the processor).
• Command — Command name.

🌍 ENVIRONMENT

The pidstat command takes into account the following environment variables:

🎨 S_COLORS

By default statistics are displayed in color when output is connected to a terminal. Use this variable to change settings. Possible values: never, always, or auto (default). Note: The color used is not indicative of any issue; it only indicates different ranges of values.

🌈 S_COLORS_SGR

Specify colors and other attributes for terminal display. Value is a colon-separated list of capabilities, defaulting to H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22. Supported capabilities:

• H= — SGR substring for percentage values ≥ 75%.
• I= — SGR substring for item values like PID, UID, or CPU number.
• M= — SGR substring for percentage values in range 50% to 75%.
• N= — SGR substring for non-zero statistics values and task names.
• Z= — SGR substring for zero values and thread names.

⏰ S_TIME_FORMAT

If this variable exists and its value is ISO, the current locale will be ignored when printing the date in the report header. The pidstat command will use ISO 8601 format (YYYY-MM-DD) instead. The timestamp will also be compliant with ISO 8601 format.

💡 EXAMPLES

pidstat 2 5

Display five reports of CPU statistics for every active task in the system at two second intervals.

pidstat -r -p 1643 2 5

Display five reports of page faults and memory statistics for PID 1643 at two second intervals.

pidstat -C "fox|bird" -r -p ALL

Display global page faults and memory statistics for all processes whose command name includes the string "fox" or "bird".

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.

🐛 BUGS

/proc filesystem must be mounted for the pidstat command to work.

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.

📁 FILES

/proc contains various files with system statistics.

✍️ AUTHOR

Sebastien Godard (sysstat <at> orange.fr)

📚 SEE ALSO

sar(1), top(1), ps(1), mpstat(1), iostat(1), vmstat(8)

https://github.com/sysstat/sysstat
http://pagesperso-orange.fr/sebastien.godard/

📋 NAME 🚀 Quick Reference 📖 SYNOPSIS 📝 DESCRIPTION ⚙️ OPTIONS 🌍 ENVIRONMENT 💡 EXAMPLES 🐛 BUGS 📁 FILES ✍️ AUTHOR 📚 SEE ALSO