1 .\" Copyright (c) 1985, 1990, 1993
2 .\" The Regents of the University of California. All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
7 .\" 1. Redistributions of source code must retain the above copyright
8 .\" notice, this list of conditions and the following disclaimer.
9 .\" 2. Redistributions in binary form must reproduce the above copyright
10 .\" notice, this list of conditions and the following disclaimer in the
11 .\" documentation and/or other materials provided with the distribution.
12 .\" 4. Neither the name of the University nor the names of its contributors
13 .\" may be used to endorse or promote products derived from this software
14 .\" without specific prior written permission.
16 .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
17 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
20 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
21 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
22 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
23 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
24 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
28 .\" @(#)systat.1 8.2 (Berkeley) 12/30/93
36 .Nd display system statistics
40 .Op Ar refresh-interval
44 utility displays various system statistics in a screen oriented fashion
45 using the curses screen display library,
50 is running the screen is usually divided into two windows (an exception
51 is the vmstat display which uses the entire screen).
53 upper window depicts the current system load average.
55 information displayed in the lower window may vary, depending on
57 The last line on the screen is reserved for user
58 input and error messages.
62 displays the processes getting the largest percentage of the processor
64 Other displays show swap space usage, disk
68 virtual memory statistics (a la
72 and network connections (a la
75 Input is interpreted at two different levels.
76 A ``global'' command interpreter processes all keyboard input.
77 If this command interpreter fails to recognize a command, the
78 input line is passed to a per-display command interpreter.
80 allows each display to have certain display-specific commands.
83 .Bl -tag -width "refresh_interval"
104 These displays can also be requested interactively (without the
108 .It Ar refresh-interval
111 specifies the screen refresh time interval in seconds.
112 Time interval can be fractional.
113 .It Ar display-commands
114 A list of commands specific to this display.
115 These commands can also be entered interactively and are described for
116 each display separately below.
117 If the command requires arguments, they can be specified as separate
118 command line arguments.
119 A command line argument
121 will finish display commands.
124 .Dl Nm Fl ifstat Fl match Ar bge0,em1 Fl pps
126 This will display statistics of packets per second for network interfaces
127 named as bge0 and em1.
129 .Dl Nm Fl iostat Fl numbers Fl - Ar 2.1
131 This will display all IO statistics in a numeric format and the information
132 will be refreshed each 2.1 seconds.
135 Certain characters cause immediate action by
142 Print the name of the current ``display'' being shown in
143 the lower window and the refresh interval.
145 Move the cursor to the command line and interpret the input
146 line typed as a command.
147 While entering a command the
148 current character erase, word erase, and line kill characters
152 The following commands are interpreted by the ``global''
156 Print the names of the available displays on the command line.
158 Print the load average over the past 1, 5, and 15 minutes
161 Stop refreshing the screen.
166 Start (continue) refreshing the screen.
167 If a second, numeric,
168 argument is provided it is interpreted as a refresh interval
170 Supplying only a number will set the refresh interval to this
175 (This may be abbreviated to
179 The available displays are:
182 Display, in the lower window, those processes resident in main
183 memory and getting the
184 largest portion of the processor (the default display).
185 When less than 100% of the
186 processor is scheduled to user processes, the remaining time
187 is accounted to the ``idle'' process.
189 Display, in the lower window, statistics about messages received and
190 transmitted by the Internet Control Message Protocol
192 The left half of the screen displays information about received
193 packets, and the right half displays information regarding transmitted
198 display understands two commands:
204 command is used to select one of four display modes, given as its argument:
205 .Bl -tag -width absoluteXX -compact
207 show the rate of change of each value in packets (the default)
210 show the rate of change of each value in packets per refresh interval
212 show the total change of each value since the display was last reset
214 show the absolute value of each statistic
219 command resets the baseline for
224 command with no argument will display the current mode in the command
227 This display is like the
230 but displays statistics for IPv6 ICMP.
232 Otherwise identical to the
234 display, except that it displays
243 except that it displays
261 Display, in the lower window, statistics about processor use
263 Statistics on processor use appear as
264 bar graphs of the amount of time executing in user mode (``user''),
265 in user mode running low priority processes (``nice''), in
266 system mode (``system''), in interrupt mode (``interrupt''),
269 on disk throughput show, for each drive, megabytes per second,
270 average number of disk transactions per second, and
271 average kilobytes of data per transaction.
272 This information may be
273 displayed as bar graphs or as rows of numbers which scroll downward.
275 graphs are shown by default.
277 The following commands are specific to the
279 display; the minimum unambiguous prefix may be supplied.
281 .Bl -tag -width Fl -compact
285 statistics in numeric form.
287 displayed in numeric columns which scroll downward.
291 statistics in bar graph form (default).
293 Toggle the display of kilobytes per transaction.
295 not display kilobytes per transaction).
298 Show information about swap space usage on all the
299 swap areas compiled into the kernel.
300 The first column is the device name of the partition.
301 The next column is the total space available in the partition.
304 column indicates the total blocks used so far;
305 the graph shows the percentage of space in use on each partition.
306 If there are more than one swap partition in use,
307 a total line is also shown.
308 Areas known to the kernel, but not in use are shown as not available.
310 Take over the entire display and show a (rather crowded) compendium
311 of statistics related to virtual memory usage, process scheduling,
312 device interrupts, system name translation caching, disk
316 The upper left quadrant of the screen shows the number
317 of users logged in and the load average over the last one, five,
318 and fifteen minute intervals.
319 Below this line are statistics on memory utilization.
320 The first row of the table reports memory usage only among
321 active processes, that is processes that have run in the previous
323 The second row reports on memory usage of all processes.
324 The first column reports on the number of kilobytes in physical pages
325 claimed by processes.
326 The second column reports the number of kilobytes in physical pages that
327 are devoted to read only text pages.
328 The third and fourth columns report the same two figures for
329 virtual pages, that is the number of kilobytes in pages that would be
330 needed if all processes had all of their pages.
331 Finally the last column shows the number of kilobytes in physical pages
334 Below the memory display is a list of the
335 average number of processes (over the last refresh interval)
336 that are runnable (`r'), in page wait (`p'),
337 in disk wait other than paging (`d'),
338 sleeping (`s'), and swapped out but desiring to run (`w').
339 The row also shows the average number of context switches
340 (`Csw'), traps (`Trp'; includes page faults), system calls (`Sys'),
341 interrupts (`Int'), network software interrupts (`Sof'), and page
344 Below the process queue length listing is a numerical listing and
345 a bar graph showing the amount of
346 system (shown as `='), interrupt (shown as `+'), user (shown as `>'),
347 nice (shown as `-'), and idle time (shown as ` ').
349 Below the process display are statistics on name translations.
350 It lists the number of names translated in the previous interval,
351 the number and percentage of the translations that were
352 handled by the system wide name translation cache, and
353 the number and percentage of the translations that were
354 handled by the per process name translation cache.
356 To the right of the name translations display are lines showing
357 the number of dirty buffers in the buffer cache (`dtbuf'),
358 desired maximum size of vnode cache (`desvn'),
359 number of vnodes actually allocated (`numvn'),
361 number of allocated vnodes that are free (`frevn').
363 At the bottom left is the disk usage display.
364 It reports the number of
365 kilobytes per transaction, transactions per second, megabytes
366 per second and the percentage of the time the disk was busy averaged
367 over the refresh period of the display (by default, five seconds).
368 The system keeps statistics on most every storage device.
370 to seven devices are displayed.
371 The devices displayed by default are the
372 first devices in the kernel's device list.
377 for details on the devstat system.
379 Under the date in the upper right hand quadrant are statistics
380 on paging and swapping activity.
381 The first two columns report the average number of pages
382 brought in and out per second over the last refresh interval
383 due to page faults and the paging daemon.
384 The third and fourth columns report the average number of pages
385 brought in and out per second over the last refresh interval
386 due to swap requests initiated by the scheduler.
387 The first row of the display shows the average
388 number of disk transfers per second over the last refresh interval;
389 the second row of the display shows the average
390 number of pages transferred per second over the last refresh interval.
392 Below the paging statistics is a column of lines regarding the virtual
394 The first few lines describe,
395 in units (except as noted below)
396 of pages per second averaged over the sampling interval,
397 pages copied on write (`cow'),
398 pages zero filled on demand (`zfod'),
399 pages optimally zero filled on demand (`ozfod'),
400 the ratio of the (average) ozfod / zfod as a percentage (`%ozfod'),
401 pages freed by the page daemon (`daefr'),
402 pages freed by exiting processes (`prcfr'),
403 total pages freed (`totfr'),
404 pages reactivated from the free list (`react'),
405 the average number of
406 times per second that the page daemon was awakened (`pdwak'),
407 pages analyzed by the page daemon (`pdpgs'),
409 in-transit blocking page faults (`intrn').
410 Note that the units are special for `%ozfod' and `pdwak'.
411 The next few lines describe,
412 as amounts of memory in kilobytes,
413 pages wired down (`wire'),
414 active pages (`act'),
415 inactive pages (`inact'),
416 pages on the cache queue (`cache'),
419 Note that the values displayed are the current transient ones;
420 they are not averages.
422 At the bottom of this column is a line showing the
423 amount of virtual memory, in kilobytes, mapped into the buffer cache (`buf').
424 This statistic is not useful.
425 It exists only as a placeholder for the corresponding useful statistic
426 (the amount of real memory used to cache disks).
427 The most important component of the latter (the amount of real memory
428 used by the vm system to cache disks) is not available,
429 but can be guessed from the `inact' amount under some system loads.
431 Running down the right hand side of the display is a breakdown
432 of the interrupts being handled by the system.
433 At the top of the list is the total interrupts per second
434 over the time interval.
435 The rest of the column breaks down the total on a device
437 Only devices that have interrupted at least once since boot time are shown.
439 The following commands are specific to the
441 display; the minimum unambiguous prefix may be supplied.
443 .Bl -tag -width Ar -compact
445 Display cumulative statistics since the system was booted.
447 Display statistics as a running total from the point this
450 Display statistics averaged over the refresh interval (the default).
452 Reset running statistics to zero.
455 display arc cache usage and hit/miss statistics.
457 Display, in the lower window, network connections.
459 network servers awaiting requests are not displayed.
461 is displayed in the format ``host.port'', with each shown symbolically,
463 It is possible to have addresses displayed numerically,
464 limit the display to a set of ports, hosts, and/or protocols
465 (the minimum unambiguous prefix may be supplied):
467 .Bl -tag -width Ar -compact
469 Toggle the displaying of server processes awaiting requests (this
470 is the equivalent of the
475 Display network addresses numerically.
477 Display network addresses symbolically.
478 .It Cm proto Ar protocol
479 Display only network connections using the indicated
481 Supported protocols are ``tcp'', ``udp'', and ``all''.
482 .It Cm ignore Op Ar items
483 Do not display information about connections associated with
484 the specified hosts or ports.
485 Hosts and ports may be specified
486 by name (``vangogh'', ``ftp''), or numerically.
488 use the Internet dot notation (``128.32.0.9'').
490 may be specified with a single command by separating them with
492 .It Cm display Op Ar items
493 Display information about the connections associated with the
494 specified hosts or ports.
498 may be names or numbers.
499 .It Cm show Op Ar ports\&|hosts
500 Show, on the command line, the currently selected protocols,
502 Hosts and ports which are being ignored
503 are prefixed with a `!'.
508 is supplied as an argument to
510 then only the requested information will be displayed.
512 Reset the port, host, and protocol matching mechanisms to the default
513 (any protocol, port, or host).
516 Display the network traffic going through active interfaces on the
518 Idle interfaces will not be displayed until they receive some
521 For each interface being displayed, the current, peak and total
522 statistics are displayed for incoming and outgoing traffic.
526 display will automatically scale the units being used so that they are
527 in a human-readable format.
528 The scaling units used for the current and
530 traffic columns can be altered by the
533 .Bl -tag -width ".Cm scale Op Ar units"
534 .It Cm scale Op Ar units
535 Modify the scale used to display the current and peak traffic over all
537 The following units are recognised: kbit, kbyte, mbit,
538 mbyte, gbit, gbyte and auto.
540 Show statistics in packets per second instead of bytes/bits per second.
543 switches this mode off.
544 .It Cm match Op Ar patterns
545 Display only interfaces that match pattern provided as an argument.
546 Patterns should be in shell syntax separated by whitespaces or commas.
547 If this command is called without arguments then all interfaces are displayed.
552 This will display em0 and bge1 interfaces.
554 .Dl match em*, bge*, lo0
556 This will display all
560 interfaces and the loopback interface.
564 Commands to switch between displays may be abbreviated to the
565 minimum unambiguous prefix; for example, ``io'' for ``iostat''.
566 Certain information may be discarded when the screen size is
567 insufficient for display.
568 For example, on a machine with 10
571 bar graph displays only 3 drives on a 24 line terminal.
573 a bar graph would overflow the allotted screen space it is
574 truncated and the actual value is printed ``over top'' of the bar.
576 The following commands are common to each display which shows
577 information about disk drives.
578 These commands are used to
579 select a set of drives to report on, should your system have
580 more drives configured than can normally be displayed on the
583 .Bl -tag -width Ar -compact
584 .It Cm ignore Op Ar drives
585 Do not display information about the drives indicated.
587 drives may be specified, separated by spaces.
588 .It Cm display Op Ar drives
589 Display information about the drives indicated.
591 may be specified, separated by spaces.
592 .It Cm only Op Ar drives
593 Display only the specified drives.
594 Multiple drives may be specified,
597 Display a list of available devices.
599 .Ar type , Ns Ar if , Ns Ar pass
602 Display devices matching the given pattern.
604 expressions are the same as those used in
607 Instead of specifying multiple
609 arguments which are then ORed together, the user instead specifies multiple
610 matching expressions joined by the pipe
614 separated arguments within each matching expression are ANDed together, and
615 then the pipe separated matching expressions are ORed together.
617 device matching the combined expression will be displayed, if there is room
621 .Dl match da,scsi | cd,ide
623 This will display all SCSI Direct Access devices and all IDE CDROM devices.
625 .Dl match da | sa | cd,pass
627 This will display all Direct Access devices, all Sequential Access devices,
628 and all passthrough devices that provide access to CDROM drives.
631 .Bl -tag -width /boot/kernel/kernel -compact
632 .It Pa /boot/kernel/kernel
635 For information in main memory.
667 the notion of having different display modes for the
673 statistics was stolen from the
681 Certain displays presume a minimum of 80 characters per line.
684 display looks out of place because it is (it was added in as
685 a separate display rather than created as a new program).