1 .\" $NetBSD: systat.1,v 1.39 2009/10/21 21:12:07 rmind Exp $
3 .\" Copyright (c) 1985, 1990, 1993
4 .\" The Regents of the University of California. All rights reserved.
6 .\" Redistribution and use in source and binary forms, with or without
7 .\" modification, are permitted provided that the following conditions
9 .\" 1. Redistributions of source code must retain the above copyright
10 .\" notice, this list of conditions and the following disclaimer.
11 .\" 2. Redistributions in binary form must reproduce the above copyright
12 .\" notice, this list of conditions and the following disclaimer in the
13 .\" documentation and/or other materials provided with the distribution.
14 .\" 3. Neither the name of the University nor the names of its contributors
15 .\" may be used to endorse or promote products derived from this software
16 .\" without specific prior written permission.
18 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
19 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
22 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
23 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
24 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
25 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
26 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
27 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 .\" @(#)systat.1 8.2 (Berkeley) 12/30/93
37 .Nd display system statistics on a CRT
46 .Op Ar refresh-interval
49 displays various system statistics in a screen oriented fashion
50 using the curses screen display library,
55 is running the screen is usually divided into two windows (an exception
56 is the vmstat display which uses the entire screen).
57 The upper window depicts the current system load average.
58 The information displayed in the lower window may vary, depending on
60 The last line on the screen is reserved for user input and error messages.
64 displays the processes getting the largest percentage of the processor
66 Other displays show more detailed process information,
68 disk usage statistics (a la
74 virtual memory statistics (a la
76 network ``mbuf'' utilization, and network connections (a la
79 Input is interpreted at two different levels.
80 A ``global'' command interpreter processes all keyboard input.
81 If this command interpreter fails to recognize a command, the
82 input line is passed to a per-display command interpreter.
83 This allows each display to have certain display-specific commands.
86 .Bl -tag -width "refresh_interval"
88 Extract values associated with the name list from
90 instead of the default
93 Extract the name list from
95 instead of the default
98 Do not resolve IP addresses into string hostnames
102 It has the same effect as
108 .Ar refresh-interval .
110 How many refreshes to show each screen in 'all' display mode.
114 argument expects to be one of:
133 These displays can also be requested interactively and are described in
135 .It Ar refresh-interval
138 specifies the screen refresh time interval in seconds.
139 This is provided for backwards compatibility, and overrides the
146 Certain characters cause immediate action by
153 Print the name of the current ``display'' being shown in
154 the lower window and the refresh interval.
159 Print the names of the available displays on the command line.
161 Move the cursor to the command line and interpret the input
162 line typed as a command.
163 While entering a command the current character erase, word erase,
164 and line kill characters may be used.
167 The following commands are interpreted by the ``global''
171 Print the names of the available displays on the command line.
172 It will print long names as
181 Print the load average over the past 1, 5, and 15 minutes
184 Stop refreshing the screen.
185 .It Oo Ic start Oc Oo Ar number Oc
186 Start (continue) refreshing the screen.
187 If a second, numeric, argument is provided it is interpreted as a
188 refresh interval in seconds.
189 Supplying only a number will set the refresh interval to this
194 (This may be abbreviated to
198 The available displays are:
201 Cycle through all displays automatically.
202 At each display, wait some
203 refresh-turns, then switch to the next display.
204 Duration of one refresh-turn is adjustable with the
206 option, number of refresh-turns can be changed with the
210 Display, in the lower window, statistics about the file system buffers.
211 Statistics for each file system that has active buffers include the number
212 of buffers for that file system, the number of active kilobytes in those
213 buffers and the total size of the buffers for that file system.
215 Lists disk usage statistics for all filesystems,
216 including the available free space as well as a bar
217 graph indicating the used capacity.
219 The following commands are specific to the
223 .Bl -tag -width Fl -compact
225 Displays information for all filesystems, including
226 kernfs, procfs and null-mounts.
228 Suppress information about procfs, kernfs and null-mounts (default).
231 Display ICMP statistics.
233 Display IPv4 and UDP statistics.
235 Display TCP statistics.
237 Display statistics about the
241 Display IPv6 statistics.
243 Display IPsec statistics for both IPv4 and v6.
245 Display, in the lower window, statistics about processor use
247 Statistics on processor use appear as bar graphs of the amount of
248 time executing in user mode (``user''), in user mode running low
249 priority processes (``nice''), in system mode (``system''), and
251 Statistics on disk throughput show, for each drive, kilobytes of
252 data transferred, number of disk transactions performed, and time
253 spent in disk accesses in milliseconds.
254 This information may be displayed as bar graphs or as rows of
255 numbers which scroll downward.
256 Bar graphs are shown by default;
258 The following commands are specific to the
260 display; the minimum unambiguous prefix may be supplied.
262 .Bl -tag -width Fl -compact
266 statistics in numeric form.
268 displayed in numeric columns which scroll downward.
272 statistics in bar graph form (default).
274 Toggle the display of time in disk activity (the default is to
277 Show the read and write statistics combined (default).
279 Show the read and write statistics separately.
282 Display, in the lower window, the number of mbufs allocated
283 for particular uses, i.e. data, socket structures, etc.
285 Display, in the lower window, network connections.
286 By default, network servers awaiting requests are not displayed.
287 Each address is displayed in the format ``host.port'', with each
288 shown symbolically, when possible.
289 It is possible to have addresses displayed numerically,
290 limit the display to a set of ports, hosts, and/or protocols
291 (the minimum unambiguous prefix may be supplied):
293 .Bl -tag -width Ar -compact
295 Toggle the displaying of server processes awaiting requests (this
296 is the equivalent of the
301 Display network addresses numerically.
303 Display network addresses symbolically.
305 Display only network connections using the indicated protocol
306 (currently either ``tcp'' or ``udp'').
307 .It Cm ignore Op Ar items
308 Do not display information about connections associated with
309 the specified hosts or ports.
310 Hosts and ports may be specified by name (``vangogh'', ``ftp''),
312 Host addresses use the Internet dot notation (``128.32.0.9'').
313 Multiple items may be specified with a single command by separating
315 .It Cm display Op Ar items
316 Display information about the connections associated with the
317 specified hosts or ports.
321 may be names or numbers.
322 .It Cm show Op Ar ports\&|hosts
323 Show, on the command line, the currently selected protocols,
325 Hosts and ports which are being ignored are prefixed with a `!'.
330 is supplied as an argument to
332 then only the requested information will be displayed.
334 Reset the port, host, and protocol matching mechanisms to the default
335 (any protocol, port, or host).
338 Display, in the lower window, those processes which are getting the
339 largest portion of the processor (the default display).
340 When less than 100% of the
341 processor is scheduled to user processes, the remaining time
342 is accounted to the ``idle'' process.
344 Display, in the lower window, the same information provided
350 The following command is specific to the
352 display; the minimum unambiguous prefix may be supplied.
354 .Bl -tag -width Fl -compact
356 Limit the list of processes displayed to those owned by user
360 is specified as `+', processes owned by any user are displayed (default).
363 Show information about swap space usage on all the
364 swap areas configured with
366 The first column is the device name of the partition.
367 The next column is the total space available in the partition.
370 column indicates the total blocks used so far;
371 the graph shows the percentage of space in use on each partition.
372 If there are more than one swap partition in use,
373 a total line is also shown.
374 Areas known to the kernel, but not in use are shown as not available.
376 Show per system call statistics.
377 The display consists of several columns of system call name and counts.
379 In order to stop entries moving around the screen too much, an infinite
380 response filter is applied to the values before they are sorted.
382 The following commands are specific to the
386 .Bl -tag -width Ar -compact
388 Sort display by the syscall name (default).
390 Sort display by the count of calls or time spent in the calls.
391 .It Ic sort Ic syscall
392 Sort display be syscall number.
394 Show the number of times the system call has be called (default).
396 Show the average amount of time (in arbitrary units) spent in a call of
400 Take over the entire display and show a (rather crowded) compendium
401 of statistics related to virtual memory usage, process scheduling,
402 device interrupts, system name translation caching, disk
406 The upper left quadrant of the screen shows the number
407 of users logged in and the load average over the last one, five,
408 and fifteen minute intervals.
409 Below this is a list of the
410 average number of processes (over the last refresh interval)
411 that are runnable (`r'), in page wait (`p'),
412 in disk wait other than paging (`d'), sleeping (`s').
413 Below the queue length listing is a numerical listing and
414 a bar graph showing the amount of
415 system (shown as `='), user (shown as `\*[Gt]'),
416 nice (shown as `-'), and idle time (shown as ` ').
418 To the right of the process statistics is a column that
419 lists the average number of context switches (`Csw'),
420 traps (`Trp'; includes page faults), system calls (`Sys'), interrupts (`Int'),
421 network software interrupts (`Sof'),
424 Below this are statistics on memory utilization.
425 The first row of the table reports memory usage only among
426 active processes, that is processes that have run in the previous
428 The second row reports on memory usage of all processes.
429 The first column reports on the number of physical pages
430 claimed by processes.
431 The second column reports the number of pages of memory and swap.
432 The third column gives the number of pages of free memory and swap.
434 Below the memory display are statistics on name translations.
435 It lists the number of names translated in the previous interval,
436 the number and percentage of the translations that were
437 handled by the system wide name translation cache, and
438 the number and percentage of the translations that were
439 handled by the per process name translation cache.
441 At the bottom left is the disk usage display.
442 It reports the number of seeks, transfers, number
443 of kilobyte blocks transferred per second averaged over the
444 refresh period of the display (by default, five seconds), and
445 the time spent in disk accesses.
446 If there are more than five disks, and the terminal window has more
447 than 24 lines, the disks display will be flipped so that more
448 of the disk statistics are visible.
450 Under the date in the upper right hand quadrant are statistics
451 on paging and swapping activity.
452 The first two columns report the average number of pages
453 brought in and out per second over the last refresh interval
454 due to page faults and the paging daemon.
455 The third and fourth columns report the average number of pages
456 brought in and out per second over the last refresh interval
457 due to swap requests initiated by the scheduler.
458 The first row of the display shows the average
459 number of disk transfers per second over the last refresh interval;
460 the second row of the display shows the average
461 number of pages transferred per second over the last refresh interval.
463 Below the paging statistics is another columns of paging data.
464 From top to bottom, these represent average numbers of copy on write faults
465 (`cow'), object cache lookups (`objlk'), object cache hits (`objht'),
466 pages zero filled on demand (`zfodw'), number zfod's created (`nzfod'),
467 percentage of zfod's used (`%zfod'), number of kernel pages (`kern'),
468 number of wired pages (`wire'), number of active pages (`act'), number
469 of inactive pages (`inact'), number of free pages (`free'), pages freed
470 by daemon (`daefr'), pages freed by exiting processes (`prcfr'), number
471 of pages reactivated from freelist (`react'), scans in page out daemon
472 (`scan'), revolutions of the hand (`hdrev'), and in-transit blocking page
473 faults (`intrn'), per second over the refresh period.
474 Note that the `%zfod' percentage is usually less than 100%,
475 however it may exceed 100% if a large number of requests
476 are actually used long after they were set up during a
477 period when no new pages are being set up.
478 Thus this figure is most interesting when observed over
479 a long time period, such as from boot time
480 (see below on getting such a display).
482 To the left of the column of paging statistics is a breakdown
483 of the interrupts being handled by the system.
484 At the top of the list is the total interrupts per second
485 over the time interval.
486 The rest of the column breaks down the total on a device
488 Only devices that have interrupted at least once since boot time are shown.
491 Commands to switch between displays may be abbreviated to the
492 minimum unambiguous prefix; for example, ``io'' for ``iostat''.
493 Certain information may be discarded when the screen size is
494 insufficient for display.
495 For example, on a machine with 10 drives the
497 bar graph displays only 3 drives on a 24 line terminal.
498 When a bar graph would overflow the allotted screen space it is
499 truncated and the actual value is printed ``over top'' of the bar.
501 The following commands are common to each display which shows
502 information about disk drives.
503 These commands are used to select a set of drives to report on,
504 should your system have more drives configured than can normally
505 be displayed on the screen.
507 .Bl -tag -width Ar -compact
508 .It Cm display Op Ar drives
509 Display information about the drives indicated.
510 Multiple drives may be specified, separated by spaces.
511 .It Cm ignore Op Ar drives
512 Do not display information about the drives indicated.
513 Multiple drives may be specified, separated by spaces.
514 .It Cm drives Op Ar drives
515 With no arguments, display a list of available drives.
516 With arguments, replace the list of currently displayed drives
517 with the ones specified.
520 The following commands are specific to the
527 displays; the minimum unambiguous prefix may be supplied.
529 .Bl -tag -width Ar -compact
531 Display cumulative statistics since the system was booted.
533 Display statistics as a running total from the point this
536 Display statistics averaged over the refresh interval (the default).
538 Reset running statistics to zero.
541 .Bl -tag -width /etc/networks -compact
545 For information in main memory.
554 Much of the information that
557 uses is obtained from
558 .Cm struct vmmeter cnt .
573 Consumes CPU resources and thus may skew statistics.
575 Certain displays presume a minimum of 80 characters per line.
579 display looks out of place because it is (it was added in as
580 a separate display from what used to be a different program).