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 .\" 3. 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 display-commands
41 .Op Ar refresh-interval
45 utility displays various system statistics in a screen oriented fashion
46 using the curses screen display library,
51 is running the screen is usually divided into two windows (an exception
52 is the vmstat display which uses the entire screen).
54 upper window depicts the current system load average.
56 information displayed in the lower window may vary, depending on
58 The last line on the screen is reserved for user
59 input and error messages.
63 displays the processes getting the largest percentage of the processor
65 Other displays show swap space usage, disk
69 virtual memory statistics (a la
73 and network connections (a la
76 Input is interpreted at two different levels.
77 A ``global'' command interpreter processes all keyboard input.
78 If this command interpreter fails to recognize a command, the
79 input line is passed to a per-display command interpreter.
81 allows each display to have certain display-specific commands.
84 .Bl -tag -width "refresh_interval"
105 These displays can also be requested interactively (without the
109 .It Ar refresh-interval
112 specifies the screen refresh time interval in seconds.
113 Time interval can be fractional.
114 .It Ar display-commands
115 A list of commands specific to this display.
116 These commands can also be entered interactively and are described for
117 each display separately below.
118 If the command requires arguments, they can be specified as separate
119 command line arguments.
120 A command line argument
122 will finish display commands.
125 .Dl Nm Fl ifstat Fl match Ar bge0,em1 Fl pps
127 This will display statistics of packets per second for network interfaces
128 named as bge0 and em1.
130 .Dl Nm Fl iostat Fl numbers Fl - Ar 2.1
132 This will display all IO statistics in a numeric format and the information
133 will be refreshed each 2.1 seconds.
136 Certain characters cause immediate action by
143 Print the name of the current ``display'' being shown in
144 the lower window and the refresh interval.
146 Move the cursor to the command line and interpret the input
147 line typed as a command.
148 While entering a command the
149 current character erase, word erase, and line kill characters
153 The following commands are interpreted by the ``global''
157 Print the names of the available displays on the command line.
159 Print the load average over the past 1, 5, and 15 minutes
162 Stop refreshing the screen.
167 Start (continue) refreshing the screen.
168 If a second, numeric,
169 argument is provided it is interpreted as a refresh interval
171 Supplying only a number will set the refresh interval to this
176 (This may be abbreviated to
180 The available displays are:
183 Display, in the lower window, those processes resident in main
184 memory and getting the
185 largest portion of the processor (the default display).
186 When less than 100% of the
187 processor is scheduled to user processes, the remaining time
188 is accounted to the ``idle'' process.
190 Display, in the lower window, statistics about messages received and
191 transmitted by the Internet Control Message Protocol
193 The left half of the screen displays information about received
194 packets, and the right half displays information regarding transmitted
199 display understands two commands:
205 command is used to select one of four display modes, given as its argument:
206 .Bl -tag -width absoluteXX -compact
208 show the rate of change of each value in packets (the default)
211 show the rate of change of each value in packets per refresh interval
213 show the total change of each value since the display was last reset
215 show the absolute value of each statistic
220 command resets the baseline for
225 command with no argument will display the current mode in the command
228 This display is like the
231 but displays statistics for IPv6 ICMP.
233 Otherwise identical to the
235 display, except that it displays
244 except that it displays
262 Display, in the lower window, statistics about processor use
264 Statistics on processor use appear as
265 bar graphs of the amount of time executing in user mode (``user''),
266 in user mode running low priority processes (``nice''), in
267 system mode (``system''), in interrupt mode (``interrupt''),
270 on disk throughput show, for each drive, megabytes per second,
271 average number of disk transactions per second, and
272 average kilobytes of data per transaction.
273 This information may be
274 displayed as bar graphs or as rows of numbers which scroll downward.
276 graphs are shown by default.
278 The following commands are specific to the
280 display; the minimum unambiguous prefix may be supplied.
282 .Bl -tag -width Fl -compact
286 statistics in numeric form.
288 displayed in numeric columns which scroll downward.
292 statistics in bar graph form (default).
294 Toggle the display of kilobytes per transaction.
296 not display kilobytes per transaction).
299 Show information about swap space usage on all the
300 swap areas compiled into the kernel.
301 The first column is the device name of the partition.
302 The next column is the total space available in the partition.
305 column indicates the total blocks used so far;
306 the graph shows the percentage of space in use on each partition.
307 If there are more than one swap partition in use,
308 a total line is also shown.
309 Areas known to the kernel, but not in use are shown as not available.
311 Take over the entire display and show a (rather crowded) compendium
312 of statistics related to virtual memory usage, process scheduling,
313 device interrupts, system name translation caching, disk
317 The upper left quadrant of the screen shows the number
318 of users logged in and the load average over the last one, five,
319 and fifteen minute intervals.
320 Below this line are statistics on memory utilization.
321 The first row of the table reports memory usage only among
322 active processes, that is processes that have run in the previous
324 The second row reports on memory usage of all processes.
325 The first column reports on the number of kilobytes in physical pages
326 claimed by processes.
327 The second column reports the number of kilobytes in physical pages that
328 are devoted to read only text pages.
329 The third and fourth columns report the same two figures for
330 virtual pages, that is the number of kilobytes in pages that would be
331 needed if all processes had all of their pages.
332 Finally the last column shows the number of kilobytes in physical pages
335 Below the memory display is a list of the
336 average number of processes (over the last refresh interval)
337 that are runnable (`r'), in page wait (`p'),
338 in disk wait other than paging (`d'),
339 sleeping (`s'), and swapped out but desiring to run (`w').
340 The row also shows the average number of context switches
341 (`Csw'), traps (`Trp'; includes page faults), system calls (`Sys'),
342 interrupts (`Int'), network software interrupts (`Sof'), and page
345 Below the process queue length listing is a numerical listing and
346 a bar graph showing the amount of
347 system (shown as `='), interrupt (shown as `+'), user (shown as `>'),
348 nice (shown as `-'), and idle time (shown as ` ').
350 Below the process display are statistics on name translations.
351 It lists the number of names translated in the previous interval,
352 the number and percentage of the translations that were
353 handled by the system wide name translation cache, and
354 the number and percentage of the translations that were
355 handled by the per process name translation cache.
357 To the right of the name translations display are lines showing
358 the number of dirty buffers in the buffer cache (`dtbuf'),
359 desired maximum size of vnode cache (`desvn'),
360 number of vnodes actually allocated (`numvn'),
362 number of allocated vnodes that are free (`frevn').
364 At the bottom left is the disk usage display.
365 It reports the number of
366 kilobytes per transaction, transactions per second, megabytes
367 per second and the percentage of the time the disk was busy averaged
368 over the refresh period of the display (by default, five seconds).
369 The system keeps statistics on most every storage device.
371 to seven devices are displayed.
372 The devices displayed by default are the
373 first devices in the kernel's device list.
378 for details on the devstat system.
380 Under the date in the upper right hand quadrant are statistics
381 on paging and swapping activity.
382 The first two columns report the average number of pages
383 brought in and out per second over the last refresh interval
384 due to page faults and the paging daemon.
385 The third and fourth columns report the average number of pages
386 brought in and out per second over the last refresh interval
387 due to swap requests initiated by the scheduler.
388 The first row of the display shows the average
389 number of disk transfers per second over the last refresh interval;
390 the second row of the display shows the average
391 number of pages transferred per second over the last refresh interval.
393 Below the paging statistics is a column of lines regarding the virtual
395 The first few lines describe,
396 in units (except as noted below)
397 of pages per second averaged over the sampling interval,
398 pages copied on write (`cow'),
399 pages zero filled on demand (`zfod'),
400 pages optimally zero filled on demand (`ozfod'),
401 the ratio of the (average) ozfod / zfod as a percentage (`%ozfod'),
402 pages freed by the page daemon (`daefr'),
403 pages freed by exiting processes (`prcfr'),
404 total pages freed (`totfr'),
405 pages reactivated from the free list (`react'),
406 the average number of
407 times per second that the page daemon was awakened (`pdwak'),
408 pages analyzed by the page daemon (`pdpgs'),
410 in-transit blocking page faults (`intrn').
411 Note that the units are special for `%ozfod' and `pdwak'.
412 The next few lines describe,
413 as amounts of memory in kilobytes,
414 pages wired down (`wire'),
415 active pages (`act'),
416 inactive pages (`inact'),
417 dirty pages queued for laundering (`laund'),
420 Note that the values displayed are the current transient ones;
421 they are not averages.
423 At the bottom of this column is a line showing the
424 amount of virtual memory, in kilobytes, mapped into the buffer cache (`buf').
425 This statistic is not useful.
426 It exists only as a placeholder for the corresponding useful statistic
427 (the amount of real memory used to cache disks).
428 The most important component of the latter (the amount of real memory
429 used by the vm system to cache disks) is not available,
430 but can be guessed from the `inact' amount under some system loads.
432 Running down the right hand side of the display is a breakdown
433 of the interrupts being handled by the system.
434 At the top of the list is the total interrupts per second
435 over the time interval.
436 The rest of the column breaks down the total on a device
438 Only devices that have interrupted at least once since boot time are shown.
440 The following commands are specific to the
442 display; the minimum unambiguous prefix may be supplied.
444 .Bl -tag -width Ar -compact
446 Display cumulative statistics since the system was booted.
448 Display statistics as a running total from the point this
451 Display statistics averaged over the refresh interval (the default).
453 Reset running statistics to zero.
456 display arc cache usage and hit/miss statistics.
458 Display, in the lower window, network connections.
460 network servers awaiting requests are not displayed.
462 is displayed in the format ``host.port'', with each shown symbolically,
464 It is possible to have addresses displayed numerically,
465 limit the display to a set of ports, hosts, and/or protocols
466 (the minimum unambiguous prefix may be supplied):
468 .Bl -tag -width Ar -compact
470 Toggle the displaying of server processes awaiting requests (this
471 is the equivalent of the
476 Display network addresses numerically.
478 Display network addresses symbolically.
479 .It Cm proto Ar protocol
480 Display only network connections using the indicated
482 Supported protocols are ``tcp'', ``udp'', and ``all''.
483 .It Cm ignore Op Ar items
484 Do not display information about connections associated with
485 the specified hosts or ports.
486 Hosts and ports may be specified
487 by name (``vangogh'', ``ftp''), or numerically.
489 use the Internet dot notation (``128.32.0.9'').
491 may be specified with a single command by separating them with
493 .It Cm display Op Ar items
494 Display information about the connections associated with the
495 specified hosts or ports.
499 may be names or numbers.
500 .It Cm show Op Ar ports\&|hosts
501 Show, on the command line, the currently selected protocols,
503 Hosts and ports which are being ignored
504 are prefixed with a `!'.
509 is supplied as an argument to
511 then only the requested information will be displayed.
513 Reset the port, host, and protocol matching mechanisms to the default
514 (any protocol, port, or host).
517 Display the network traffic going through active interfaces on the
519 Idle interfaces will not be displayed until they receive some
522 For each interface being displayed, the current, peak and total
523 statistics are displayed for incoming and outgoing traffic.
527 display will automatically scale the units being used so that they are
528 in a human-readable format.
529 The scaling units used for the current and
531 traffic columns can be altered by the
534 .Bl -tag -width ".Cm scale Op Ar units"
535 .It Cm scale Op Ar units
536 Modify the scale used to display the current and peak traffic over all
538 The following units are recognised: kbit, kbyte, mbit,
539 mbyte, gbit, gbyte and auto.
541 Show statistics in packets per second instead of bytes/bits per second.
544 switches this mode off.
545 .It Cm match Op Ar patterns
546 Display only interfaces that match pattern provided as an argument.
547 Patterns should be in shell syntax separated by whitespaces or commas.
548 If this command is called without arguments then all interfaces are displayed.
553 This will display em0 and bge1 interfaces.
555 .Dl match em*, bge*, lo0
557 This will display all
561 interfaces and the loopback interface.
565 Commands to switch between displays may be abbreviated to the
566 minimum unambiguous prefix; for example, ``io'' for ``iostat''.
567 Certain information may be discarded when the screen size is
568 insufficient for display.
569 For example, on a machine with 10
572 bar graph displays only 3 drives on a 24 line terminal.
574 a bar graph would overflow the allotted screen space it is
575 truncated and the actual value is printed ``over top'' of the bar.
577 The following commands are common to each display which shows
578 information about disk drives.
579 These commands are used to
580 select a set of drives to report on, should your system have
581 more drives configured than can normally be displayed on the
584 .Bl -tag -width Ar -compact
585 .It Cm ignore Op Ar drives
586 Do not display information about the drives indicated.
588 drives may be specified, separated by spaces.
589 .It Cm display Op Ar drives
590 Display information about the drives indicated.
592 may be specified, separated by spaces.
593 .It Cm only Op Ar drives
594 Display only the specified drives.
595 Multiple drives may be specified,
598 Display a list of available devices.
600 .Ar type , Ns Ar if , Ns Ar pass
603 Display devices matching the given pattern.
605 expressions are the same as those used in
608 Instead of specifying multiple
610 arguments which are then ORed together, the user instead specifies multiple
611 matching expressions joined by the pipe
615 separated arguments within each matching expression are ANDed together, and
616 then the pipe separated matching expressions are ORed together.
618 device matching the combined expression will be displayed, if there is room
622 .Dl match da,scsi | cd,ide
624 This will display all SCSI Direct Access devices and all IDE CDROM devices.
626 .Dl match da | sa | cd,pass
628 This will display all Direct Access devices, all Sequential Access devices,
629 and all passthrough devices that provide access to CDROM drives.
632 .Bl -tag -width /boot/kernel/kernel -compact
633 .It Pa /boot/kernel/kernel
636 For information in main memory.
668 the notion of having different display modes for the
674 statistics was stolen from the
682 Certain displays presume a minimum of 80 characters per line.
683 Ifstat does not detect new interfaces.
686 display looks out of place because it is (it was added in as
687 a separate display rather than created as a new program).