xref: /freebsd/usr.sbin/iostat/iostat.8 (revision c697fb7f)
1.\"
2.\" Copyright (c) 1997 Kenneth D. Merry.
3.\" All rights reserved.
4.\"
5.\" Redistribution and use in source and binary forms, with or without
6.\" modification, are permitted provided that the following conditions
7.\" are met:
8.\" 1. Redistributions of source code must retain the above copyright
9.\"    notice, this list of conditions and the following disclaimer.
10.\" 2. Redistributions in binary form must reproduce the above copyright
11.\"    notice, this list of conditions and the following disclaimer in the
12.\"    documentation and/or other materials provided with the distribution.
13.\" 3. The name of the author may not be used to endorse or promote products
14.\"    derived from this software without specific prior written permission.
15.\"
16.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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
26.\" SUCH DAMAGE.
27.\"
28.\" $FreeBSD$
29.\"
30.\" Copyright (c) 1985, 1991, 1993
31.\"	The Regents of the University of California.  All rights reserved.
32.\"
33.\" Redistribution and use in source and binary forms, with or without
34.\" modification, are permitted provided that the following conditions
35.\" are met:
36.\" 1. Redistributions of source code must retain the above copyright
37.\"    notice, this list of conditions and the following disclaimer.
38.\" 2. Redistributions in binary form must reproduce the above copyright
39.\"    notice, this list of conditions and the following disclaimer in the
40.\"    documentation and/or other materials provided with the distribution.
41.\" 3. Neither the name of the University nor the names of its contributors
42.\"    may be used to endorse or promote products derived from this software
43.\"    without specific prior written permission.
44.\"
45.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
46.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
47.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
48.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
49.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
50.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
51.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
52.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
53.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
54.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
55.\" SUCH DAMAGE.
56.\"
57.\"	@(#)iostat.8	8.1 (Berkeley) 6/6/93
58.\"
59.Dd May 22, 2015
60.Dt IOSTAT 8
61.Os
62.Sh NAME
63.Nm iostat
64.Nd report
65.Tn I/O
66statistics
67.Sh SYNOPSIS
68.Nm
69.Op Fl CdhIKoTxz?\&
70.Op Fl c Ar count
71.Op Fl M Ar core
72.Op Fl n Ar devs
73.Op Fl N Ar system
74.Oo
75.Fl t
76.Sm off
77.Ar type , if , pass
78.Sm on
79.Oc
80.Op Fl w Ar wait
81.Op Ar drives
82.Sh DESCRIPTION
83The
84.Nm
85utility displays kernel
86.Tn I/O
87statistics on terminal, device and cpu operations.
88The first statistics that are printed are averaged over the system uptime.
89To get information about the current activity, a suitable wait time should
90be specified, so that the subsequent sets of printed statistics will be
91averaged over that time.
92.Pp
93The options are as follows:
94.Bl -tag -width flag
95.It Fl c
96Repeat the display
97.Ar count
98times.
99If no repeat
100.Ar count
101is specified, the default depends on whether
102.Fl w
103is specified.
104With
105.Fl w
106the default repeat count is infinity, otherwise it is 1.
107.It Fl C
108Display CPU statistics.
109This is on by default, unless
110.Fl d
111or
112.Fl x
113is specified.
114.It Fl d
115Display only device statistics.
116If this flag is turned on, only device statistics will be displayed, unless
117.Fl C
118or
119.Fl T
120is also specified to enable the display of CPU or TTY statistics.
121.It Fl h
122Put
123.Nm
124in
125.Sq top
126mode.
127In this mode,
128.Nm
129will show devices in order from highest to lowest bytes
130per measurement cycle.
131.It Fl I
132Display total statistics for a given time period, rather than average
133statistics for each second during that time period.
134.It Fl K
135In the blocks transferred display (-o), display block count in kilobytes rather
136then the device native block size.
137.It Fl M
138Extract values associated with the name list from the specified core
139instead of the default
140.Dq Pa /dev/kmem .
141.It Fl n
142Display up to
143.Ar devs
144number of devices.
145The
146.Nm
147utility will display fewer devices if there are not
148.Ar devs
149devices present.
150.It Fl N
151Extract the name list from the specified system instead of the default
152.Dq Pa /boot/kernel/kernel .
153.It Fl o
154Display old-style
155.Nm
156device statistics.
157Sectors per second, transfers per second, and milliseconds per seek are
158displayed.
159If
160.Fl I
161is specified, total blocks/sectors, total transfers, and
162milliseconds per seek are displayed.
163.It Fl t
164Specify which types of devices to display.
165There are three different categories of devices:
166.Pp
167.Bl -tag -width indent -compact
168.It device type:
169.Bl -tag -width 9n -compact
170.It da
171Direct Access devices
172.It sa
173Sequential Access devices
174.It printer
175Printers
176.It proc
177Processor devices
178.It worm
179Write Once Read Multiple devices
180.It cd
181CD devices
182.It scanner
183Scanner devices
184.It optical
185Optical Memory devices
186.It changer
187Medium Changer devices
188.It comm
189Communication devices
190.It array
191Storage Array devices
192.It enclosure
193Enclosure Services devices
194.It floppy
195Floppy devices
196.El
197.Pp
198.It interface:
199.Bl -tag -width 9n -compact
200.It IDE
201Integrated Drive Electronics devices
202.It SCSI
203Small Computer System Interface devices
204.It other
205Any other device interface
206.El
207.Pp
208.It passthrough:
209.Bl -tag -width 9n -compact
210.It pass
211Passthrough devices
212.El
213.El
214.Pp
215The user must specify at least one device type, and may specify at most
216one device type from each category.
217Multiple device types in a single device type statement must be separated by
218commas.
219.Pp
220Any number of
221.Fl t
222arguments may be specified on the command line.
223All
224.Fl t
225arguments are ORed together to form a matching expression against which
226all devices in the system are compared.
227Any device that fully matches any
228.Fl t
229argument will be included in the
230.Nm
231output, up to the number of devices that can be displayed in
23280 columns, or the maximum number of devices specified by the user.
233.It Fl T
234Display TTY statistics.
235This is on by default, unless
236.Fl d
237or
238.Fl x
239is specified.
240.It Fl w
241Pause
242.Ar wait
243seconds between each display.
244If no
245.Ar wait
246interval is specified, the default is 1 second.
247.Pp
248The
249.Nm
250command will accept and honor a non-integer number of seconds.
251Note that the interval only has millisecond granularity.
252Finer values will be truncated.
253E.g.,
254.Dq Li -w1.0001
255is the same as
256.Dq Li -w1.000 .
257The interval will also suffer from modifications to
258.Va kern.hz
259so your mileage may vary.
260.It Fl x
261Show extended disk statistics.
262Each disk is displayed on a line of its own with all available statistics.
263If this flag is turned on, only disk statistics will be displayed, unless
264.Fl C
265or
266.Fl T
267is also specified to enable the display of CPU or TTY statistics.
268.It Fl z
269If
270.Fl x
271is specified, omit lines for devices with no activity.
272.It Fl ?\&
273Display a usage statement and exit.
274.El
275.Pp
276The
277.Nm
278utility displays its information in the following format:
279.Bl -tag -width flag
280.It tty
281.Bl -tag -width indent -compact
282.It tin
283characters read from terminals
284.It tout
285characters written to terminals
286.El
287.It devices
288Device operations.
289The header of the field is the device name and unit number.
290The
291.Nm
292utility
293will display as many devices as will fit in a standard 80 column screen, or
294the maximum number of devices in the system, whichever is smaller.
295If
296.Fl n
297is specified on the command line,
298.Nm
299will display the smaller of the
300requested number of devices, and the maximum number of devices in the system.
301To force
302.Nm
303to display specific drives, their names may be supplied on the command
304line.
305The
306.Nm
307utility
308will not display more devices than will fit in an 80 column screen, unless
309the
310.Fl n
311argument is given on the command line to specify a maximum number of
312devices to display.
313If fewer devices are specified on the command line than will fit in an 80
314column screen,
315.Nm
316will show only the specified devices.
317.Pp
318The standard
319.Nm
320device display shows the following statistics:
321.Pp
322.Bl -tag -width indent -compact
323.It KB/t
324kilobytes per transfer
325.It tps
326transfers per second
327.It MB/s
328megabytes per second
329.El
330.Pp
331The standard
332.Nm
333device display, with the
334.Fl I
335flag specified, shows the following statistics:
336.Pp
337.Bl -tag -width indent -compact
338.It KB/t
339kilobytes per transfer
340.It xfrs
341total number of transfers
342.It MB
343total number of megabytes transferred
344.El
345.Pp
346The extended
347.Nm
348device display, with the
349.Fl x
350flag specified, shows the following statistics:
351.Pp
352.Bl -tag -width indent -compact
353.It r/s
354read operations per second
355.It w/s
356write operations per second
357.It kr/s
358kilobytes read per second
359.It kw/s
360kilobytes write per second
361.It qlen
362transactions queue length
363.It ms/r
364average duration of read transactions, in milliseconds
365.It ms/w
366average duration of write transactions, in milliseconds
367.It ms/o
368average duration of all other transactions, in milliseconds
369.It ms/t
370average duration of all transactions, in milliseconds
371.It %b
372% of time the device had one or more outstanding transactions
373.El
374.Pp
375The extended
376.Nm
377device display, with the
378.Fl x
379and
380.Fl I
381flags specified, shows the following statistics:
382.Pp
383.Bl -tag -width indent -compact
384.It r/i
385read operations per time period
386.It w/i
387write operations per time period
388.It kr/i
389kilobytes read per time period
390.It kw/i
391kilobytes write per time period
392.It qlen
393transactions queue length
394.It tsvc_t/i
395total duration of transactions per time period, in seconds
396.It sb/i
397total time the device had one or more outstanding transactions per
398time period, in seconds
399.El
400.Pp
401The old-style
402.Nm
403display (using
404.Fl o )
405shows the following statistics:
406.Pp
407.Bl -tag -width indent -compact
408.It sps
409sectors transferred per second
410.It tps
411transfers per second
412.It msps
413average milliseconds per transaction
414.El
415.Pp
416The old-style
417.Nm
418display, with the
419.Fl I
420flag specified, shows the following statistics:
421.Pp
422.Bl -tag -width indent -compact
423.It blk
424total blocks/sectors transferred
425.It xfr
426total transfers
427.It msps
428average milliseconds per transaction
429.El
430.It cpu
431.Bl -tag -width indent -compact
432.It \&us
433% of cpu time in user mode
434.It \&ni
435% of cpu time in user mode running niced processes
436.It \&sy
437% of cpu time in system mode
438.It \&in
439% of cpu time in interrupt mode
440.It \&id
441% of cpu time in idle mode
442.El
443.El
444.Sh FILES
445.Bl -tag -width /boot/kernel/kernel -compact
446.It Pa /boot/kernel/kernel
447Default kernel namelist.
448.It Pa /dev/kmem
449Default memory file.
450.El
451.Sh EXAMPLES
452.Dl iostat -w 1 da0 da1 cd0
453.Pp
454Display statistics for the first two Direct Access devices and the first
455CDROM device every second ad infinitum.
456.Pp
457.Dl iostat -c 2
458.Pp
459Display the statistics for the first four devices in the system twice, with
460a one second display interval.
461.Pp
462.Dl iostat -t da -t cd -w 1
463.Pp
464Display statistics for all CDROM and Direct Access devices every second
465ad infinitum.
466.Pp
467.Dl iostat -t da,scsi,pass -t cd,scsi,pass
468.Pp
469Display statistics once for all SCSI passthrough devices that provide access
470to either Direct Access or CDROM devices.
471.Pp
472.Dl iostat -h -n 8 -w 1
473.Pp
474Display up to 8 devices with the most I/O every second ad infinitum.
475.Pp
476.Dl iostat -dh -t da -w 1
477.Pp
478Omit the TTY and CPU displays, show devices in order of performance and
479show only Direct Access devices every second ad infinitum.
480.Pp
481.Dl iostat -Iw 3
482.Pp
483Display total statistics every three seconds ad infinitum.
484.Pp
485.Dl iostat -odICTw 2 -c 9
486.Pp
487Display total statistics using the old-style output format 9 times, with
488a two second interval between each measurement/display.
489The
490.Fl d
491flag generally disables the TTY and CPU displays, but since the
492.Fl T
493and
494.Fl C
495flags are given, the TTY and CPU displays will be displayed.
496.Sh SEE ALSO
497.Xr fstat 1 ,
498.Xr netstat 1 ,
499.Xr nfsstat 1 ,
500.Xr ps 1 ,
501.Xr systat 1 ,
502.Xr devstat 3 ,
503.Xr ctlstat 8 ,
504.Xr gstat 8 ,
505.Xr pstat 8 ,
506.Xr vmstat 8
507.Pp
508The sections starting with ``Interpreting system activity'' in
509.%T "Installing and Operating 4.3BSD" .
510.Sh HISTORY
511This version of
512.Nm
513first appeared in
514.Fx 3.0 .
515.Sh AUTHORS
516.An Kenneth Merry Aq Mt ken@FreeBSD.org
517.Sh BUGS
518The use of
519.Nm
520as a debugging tool for crash dumps is probably limited because there is
521currently no way to get statistics that only cover the time immediately before
522the crash.
523