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. All advertising materials mentioning features or use of this software 42.\" must display the following acknowledgement: 43.\" This product includes software developed by the University of 44.\" California, Berkeley and its contributors. 45.\" 4. Neither the name of the University nor the names of its contributors 46.\" may be used to endorse or promote products derived from this software 47.\" without specific prior written permission. 48.\" 49.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 50.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 51.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 52.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 53.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 54.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 55.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 56.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 57.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 58.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 59.\" SUCH DAMAGE. 60.\" 61.\" @(#)iostat.8 8.1 (Berkeley) 6/6/93 62.\" 63.Dd December 22, 1997 64.Dt IOSTAT 8 65.Os 66.Sh NAME 67.Nm iostat 68.Nd report 69.Tn I/O 70statistics 71.Sh SYNOPSIS 72.Nm 73.Op Fl CdhKIoT?\& 74.Op Fl c Ar count 75.Op Fl M Ar core 76.Op Fl n Ar devs 77.Op Fl N Ar system 78.Oo 79.Fl t 80.Sm off 81.Ar type , if , pass 82.Sm on 83.Oc 84.Op Fl w Ar wait 85.Op Ar drives 86.Sh DESCRIPTION 87The 88.Nm 89utility displays kernel 90.Tn I/O 91statistics on terminal, device and cpu operations. 92The first statistics that are printed are averaged over the system uptime. 93To get information about the current activity, a suitable wait time should 94be specified, so that the subsequent sets of printed statistics will be 95averaged over that time. 96.Pp 97The options are as follows: 98.Bl -tag -width flag 99.It Fl c 100Repeat the display 101.Ar count 102times. 103If no 104.Ar wait 105interval is specified, the default is 1 second. 106.It Fl C 107Display CPU statistics. 108This is on by default, unless 109.Fl d 110is specified. 111.It Fl d 112Display only device statistics. 113If this flag is turned on, only device statistics will be displayed, unless 114.Fl C 115or 116.Fl T 117is also specfied to enable the display of CPU or TTY statistics. 118.It Fl h 119Put 120.Nm 121in 122.Sq top 123mode. 124In this mode, 125.Nm 126will show devices in order from highest to lowest bytes 127per measurement cycle. 128.It Fl I 129Display total statstics for a given time period, rather than average 130statistics for each second during that time period. 131.It Fl K 132In the blocks transfered display (-o), display block count in kilobytes rather 133then the device native block size. 134.It Fl M 135Extract values associated with the name list from the specified core 136instead of the default 137.Dq Pa /dev/kmem . 138.It Fl n 139Display up to 140.Ar devs 141number of devices. 142The 143.Nm 144utility will display fewer devices if there aren't 145.Ar devs 146devices present. 147.It Fl N 148Extract the name list from the specified system instead of the default 149.Dq Pa /boot/kernel/kernel . 150.It Fl o 151Display old-style 152.Nm 153device statistics. 154Sectors per second, transfers per second, and miliseconds per seek are 155displayed. 156If 157.Fl I 158is specified, total blocks/sectors, total transfers, and 159miliseconds per seek are displayed. 160.It Fl t 161Specify which types of devices to display. 162There are three different categories of devices: 163.Pp 164.Bl -tag -width indent -compact 165.It device type: 166.Bl -tag -width 9n -compact 167.It da 168Direct Access devices 169.It sa 170Sequential Access devices 171.It printer 172Printers 173.It proc 174Processor devices 175.It worm 176Write Once Read Multiple devices 177.It cd 178CD devices 179.It scanner 180Scanner devices 181.It optical 182Optical Memory devices 183.It changer 184Medium Changer devices 185.It comm 186Communication devices 187.It array 188Storage Array devices 189.It enclosure 190Enclosure Services devices 191.It floppy 192Floppy devices 193.El 194.Pp 195.It interface: 196.Bl -tag -width 9n -compact 197.It IDE 198Integrated Drive Electronics devices 199.It SCSI 200Small Computer System Interface devices 201.It other 202Any other device interface 203.El 204.Pp 205.It passthrough: 206.Bl -tag -width 9n -compact 207.It pass 208Passthrough devices 209.El 210.El 211.Pp 212The user must specify at least one device type, and may specify at most 213one device type from each category. 214Multiple device types in a single device type statement must be separated by 215commas. 216.Pp 217Any number of 218.Fl t 219arguments may be specified on the command line. 220All 221.Fl t 222arguments are ORed together to form a matching expression against which 223all devices in the system are compared. 224Any device that fully matches any 225.Fl t 226argument will be included in the 227.Nm 228output, up to the number of devices that can be displayed in 22980 columns, or the maximum number of devices specified by the user. 230.It Fl T 231Display TTY statistics. 232This is on by default, unless 233.Fl d 234is specified. 235.It Fl w 236Pause 237.Ar wait 238seconds between each display. 239If no repeat 240.Ar count 241is specified, the default is infinity. 242.It Fl ?\& 243Display a usage statement and exit. 244.El 245.Pp 246The 247.Nm 248utility displays its information in the following format: 249.Bl -tag -width flag 250.It tty 251.Bl -tag -width indent -compact 252.It tin 253characters read from terminals 254.It tout 255characters written to terminals 256.El 257.It devices 258Device operations. 259The header of the field is the device name and unit number. 260The 261.Nm 262utility 263will display as many devices as will fit in a standard 80 column screen, or 264the maximum number of devices in the system, whichever is smaller. 265If 266.Fl n 267is specified on the command line, 268.Nm 269will display the smaller of the 270requested number of devices, and the maximum number of devices in the system. 271To force 272.Nm 273to display specific drives, their names may be supplied on the command 274line. 275The 276.Nm 277utility 278will not display more devices than will fit in an 80 column screen, unless 279the 280.Fl n 281argument is given on the command line to specify a maximum number of 282devices to display. 283If fewer devices are specified on the command line than will fit in an 80 284column screen, 285.Nm 286will show only the specified devices. 287.Pp 288The standard 289.Nm 290device display shows the following statistics: 291.Pp 292.Bl -tag -width indent -compact 293.It KB/t 294kilobytes per transfer 295.It tps 296transfers per second 297.It MB/s 298megabytes per second 299.El 300.Pp 301The standard 302.Nm 303device display, with the 304.Fl I 305flag specified, shows the following statistics: 306.Pp 307.Bl -tag -width indent -compact 308.It KB/t 309kilobytes per transfer 310.It xfrs 311total number of transfers 312.It MB 313total number of megabytes transferred 314.El 315.Pp 316The old-style 317.Nm 318display (using 319.Fl o ) 320shows the following statistics: 321.Pp 322.Bl -tag -width indent -compact 323.It sps 324sectors transferred per second 325.It tps 326transfers per second 327.It msps 328average milliseconds per transaction 329.El 330.Pp 331The old-style 332.Nm 333display, with the 334.Fl I 335flag specified, shows the following statistics: 336.Pp 337.Bl -tag -width indent -compact 338.It blk 339total blocks/sectors transferred 340.It xfr 341total transfers 342.It msps 343average milliseconds per transaction 344.El 345.It cpu 346.Bl -tag -width indent -compact 347.It \&us 348% of cpu time in user mode 349.It \&ni 350% of cpu time in user mode running niced processes 351.It \&sy 352% of cpu time in system mode 353.It \&in 354% of cpu time in interrupt mode 355.It \&id 356% of cpu time in idle mode 357.El 358.El 359.Sh FILES 360.Bl -tag -width /boot/kernel/kernel -compact 361.It Pa /boot/kernel/kernel 362Default kernel namelist. 363.It Pa /dev/kmem 364Default memory file. 365.El 366.Sh EXAMPLES 367.Dl iostat -w 1 da0 da1 cd0 368.Pp 369Display statistics for the first two Direct Access devices and the first 370CDROM device every second ad infinitum. 371.Pp 372.Dl iostat -c 2 373.Pp 374Display the statistics for the first four devices in the system twice, with 375a one second display interval. 376.Pp 377.Dl iostat -t da -t cd -w 1 378.Pp 379Display statistics for all CDROM and Direct Access devices every second 380ad infinitum. 381.Pp 382.Dl iostat -t da,scsi,pass -t cd,scsi,pass 383.Pp 384Display statistics once for all SCSI passthrough devices that provide access 385to either Direct Access or CDROM devices. 386.Pp 387.Dl iostat -h -n 8 -w 1 388.Pp 389Display up to 8 devices with the most I/O every second ad infinitum. 390.Pp 391.Dl iostat -dh -t da -w 1 392.Pp 393Omit the TTY and CPU displays, show devices in order of performance and 394show only Direct Access devices every second ad infinitum. 395.Pp 396.Dl iostat -Iw 3 397.Pp 398Display total statistics every three seconds ad infinitum. 399.Pp 400.Dl iostat -odICTw 2 -c 9 401.Pp 402Display total statistics using the old-style output format 9 times, with 403a two second interval between each measurement/display. 404The 405.Fl d 406flag generally disables the TTY and CPU displays, but since the 407.Fl T 408and 409.Fl C 410flags are given, the TTY and CPU displays will be displayed. 411.Sh SEE ALSO 412.Xr fstat 1 , 413.Xr netstat 1 , 414.Xr nfsstat 1 , 415.Xr ps 1 , 416.Xr systat 1 , 417.Xr pstat 8 , 418.Xr vmstat 8 419.Pp 420The sections starting with ``Interpreting system activity'' in 421.%T "Installing and Operating 4.3BSD" . 422.Sh HISTORY 423This version of 424.Nm 425first appeared in 426.Fx 3.0 . 427.Sh BUGS 428The use of 429.Nm 430as a debugging tool for crash dumps is probably limited because there is 431currently no way to get statistics that only cover the time immediately before 432the crash. 433.Sh AUTHORS 434.An Kenneth Merry Aq ken@FreeBSD.org 435