1IOSTAT(1) Linux User's Manual IOSTAT(1)
2
6 iostat - Report Central Processing Unit (CPU) statistics and input/out‐
7 put statistics for devices and partitions.
8
10 iostat [ -c ] [ -d ] [ -h ] [ -k | -m ] [ -N ] [ -s ] [ -t ] [ -V ] [
11 -x ] [ -y ] [ -z ] [ --dec={ 0 | 1 | 2 } ] [ -j { ID | LABEL | PATH |
12 UUID | ... } ] [ -o JSON ] [ [ -H ] -g group_name ] [ --human ] [ -p [
13 device [,...] | ALL ] ] [ device [...] | ALL ] [ interval [ count ] ]
14
16 The iostat command is used for monitoring system input/output device
17 loading by observing the time the devices are active in relation to
18 their average transfer rates. The iostat command generates reports that
19 can be used to change system configuration to better balance the
20 input/output load between physical disks.
21 The first report generated by the iostat command provides statistics
23 concerning the time since the system was booted, unless the -y option
24 is used (in this case, this first report is omitted). Each subsequent
25 report covers the time since the previous report. All statistics are
26 reported each time the iostat command is run. The report consists of a
27 CPU header row followed by a row of CPU statistics. On multiprocessor
28 systems, CPU statistics are calculated system-wide as averages among
29 all processors. A device header row is displayed followed by a line of
30 statistics for each device that is configured.
31 The interval parameter specifies the amount of time in seconds between
33 each report. The count parameter can be specified in conjunction with
34 the interval parameter. If the count parameter is specified, the value
35 of count determines the number of reports generated at interval seconds
36 apart. If the interval parameter is specified without the count parame‐
37 ter, the iostat command generates reports continuously.
38
41 The iostat command generates two types of reports, the CPU Utilization
42 report and the Device Utilization report.
43 CPU Utilization Report
45 The first report generated by the iostat command is the CPU Uti‐
46 lization Report. For multiprocessor systems, the CPU values are
47 global averages among all processors. The report has the fol‐
48 lowing format:
49 %user
51 Show the percentage of CPU utilization that occurred
52 while executing at the user level (application).
53 %nice
55 Show the percentage of CPU utilization that occurred
56 while executing at the user level with nice priority.
57 %system
59 Show the percentage of CPU utilization that occurred
60 while executing at the system level (kernel).
61 %iowait
63 Show the percentage of time that the CPU or CPUs were
64 idle during which the system had an outstanding disk I/O
65 request.
66 %steal
68 Show the percentage of time spent in involuntary wait by
69 the virtual CPU or CPUs while the hypervisor was servic‐
70 ing another virtual processor.
71 %idle
73 Show the percentage of time that the CPU or CPUs were
74 idle and the system did not have an outstanding disk I/O
75 request.
76 Device Utilization Report
78 The second report generated by the iostat command is the Device
79 Utilization Report. The device report provides statistics on a
80 per physical device or partition basis. Block devices and parti‐
81 tions for which statistics are to be displayed may be entered on
82 the command line. If no device nor partition is entered, then
83 statistics are displayed for every device used by the system,
84 and providing that the kernel maintains statistics for it. If
85 the ALL keyword is given on the command line, then statistics
86 are displayed for every device defined by the system, including
87 those that have never been used. Transfer rates are shown in 1K
88 blocks by default, unless the environment variable POSIXLY_COR‐
89 RECT is set, in which case 512-byte blocks are used. The report
90 may show the following fields, depending on the flags used:
91 Device:
93 This column gives the device (or partition) name as
94 listed in the /dev directory.
95 tps
97 Indicate the number of transfers per second that were
98 issued to the device. A transfer is an I/O request to the
99 device. Multiple logical requests can be combined into a
100 single I/O request to the device. A transfer is of inde‐
101 terminate size.
102 Blk_read/s (kB_read/s, MB_read/s)
104 Indicate the amount of data read from the device
105 expressed in a number of blocks (kilobytes, megabytes)
106 per second. Blocks are equivalent to sectors and there‐
107 fore have a size of 512 bytes.
108 Blk_wrtn/s (kB_wrtn/s, MB_wrtn/s)
110 Indicate the amount of data written to the device
111 expressed in a number of blocks (kilobytes, megabytes)
112 per second.
113 Blk_dscd/s (kB_dscd/s, MB_dscd/s)
115 Indicate the amount of data discarded for the device
116 expressed in a number of blocks (kilobytes, megabytes)
117 per second.
118 Blk_read (kB_read, MB_read)
120 The total number of blocks (kilobytes, megabytes) read.
121 Blk_wrtn (kB_wrtn, MB_wrtn)
123 The total number of blocks (kilobytes, megabytes) writ‐
124 ten.
125 Blk_dscd (kB_dscd, MB_dscd)
127 The total number of blocks (kilobytes, megabytes) dis‐
128 carded.
129 r/s
131 The number (after merges) of read requests completed per
132 second for the device.
133 w/s
135 The number (after merges) of write requests completed per
136 second for the device.
137 d/s
139 The number (after merges) of discard requests completed
140 per second for the device.
141 f/s
143 The number (after merges) of flush requests completed per
144 second for the device. This counts flush requests exe‐
145 cuted by disks. Flush requests are not tracked for parti‐
146 tions. Before being merged, flush operations are counted
147 as writes.
148 sec/s (kB/s, MB/s)
150 The number of sectors (kilobytes, megabytes) read from,
151 written to or discarded for the device per second.
152 rsec/s (rkB/s, rMB/s)
154 The number of sectors (kilobytes, megabytes) read from
155 the device per second.
156 wsec/s (wkB/s, wMB/s)
158 The number of sectors (kilobytes, megabytes) written to
159 the device per second.
160 dsec/s (dkB/s, dMB/s)
162 The number of sectors (kilobytes, megabytes) discarded
163 for the device per second.
164 rqm/s
166 The number of I/O requests merged per second that were
167 queued to the device.
168 rrqm/s
170 The number of read requests merged per second that were
171 queued to the device.
172 wrqm/s
174 The number of write requests merged per second that were
175 queued to the device.
176 drqm/s
178 The number of discard requests merged per second that
179 were queued to the device.
180 %rrqm
182 The percentage of read requests merged together before
183 being sent to the device.
184 %wrqm
186 The percentage of write requests merged together before
187 being sent to the device.
188 %drqm
190 The percentage of discard requests merged together before
191 being sent to the device.
192 areq-sz
194 The average size (in kilobytes) of the I/O requests that
195 were issued to the device.
196 Note: In previous versions, this field was known as
197 avgrq-sz and was expressed in sectors.
198 rareq-sz
200 The average size (in kilobytes) of the read requests that
201 were issued to the device.
202 wareq-sz
204 The average size (in kilobytes) of the write requests
205 that were issued to the device.
206 dareq-sz
208 The average size (in kilobytes) of the discard requests
209 that were issued to the device.
210 await
212 The average time (in milliseconds) for I/O requests
213 issued to the device to be served. This includes the time
214 spent by the requests in queue and the time spent servic‐
215 ing them.
216 r_await
218 The average time (in milliseconds) for read requests
219 issued to the device to be served. This includes the time
220 spent by the requests in queue and the time spent servic‐
221 ing them.
222 w_await
224 The average time (in milliseconds) for write requests
225 issued to the device to be served. This includes the time
226 spent by the requests in queue and the time spent servic‐
227 ing them.
228 d_await
230 The average time (in milliseconds) for discard requests
231 issued to the device to be served. This includes the time
232 spent by the requests in queue and the time spent servic‐
233 ing them.
234 f_await
236 The average time (in milliseconds) for flush requests
237 issued to the device to be served. The block layer com‐
238 bines flush requests and executes at most one at a time.
239 Thus flush operations could be twice as long: Wait for
240 current flush request, then execute it, then wait for the
241 next one.
242 aqu-sz
244 The average queue length of the requests that were issued
245 to the device.
246 Note: In previous versions, this field was known as
247 avgqu-sz.
248 %util
250 Percentage of elapsed time during which I/O requests were
251 issued to the device (bandwidth utilization for the
252 device). Device saturation occurs when this value is
253 close to 100% for devices serving requests serially. But
254 for devices serving requests in parallel, such as RAID
255 arrays and modern SSDs, this number does not reflect
256 their performance limits.
257
259 -c Display the CPU utilization report.
260 -d Display the device utilization report.
262 --dec={ 0 | 1 | 2 }
264 Specify the number of decimal places to use (0 to 2, default
265 value is 2).
266 -g group_name { device [...] | ALL }
268 Display statistics for a group of devices. The iostat command
269 reports statistics for each individual device in the list then a
270 line of global statistics for the group displayed as group_name
271 and made up of all the devices in the list. The ALL keyword
272 means that all the block devices defined by the system shall be
273 included in the group.
274 -H This option must be used with option -g and indicates that only
276 global statistics for the group are to be displayed, and not
277 statistics for individual devices in the group.
278 -h Make the Device Utilization Report easier to read by a human.
280 --human is enabled implicitly with this option.
281 --human
283 Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.)
284 The units displayed with this option supersede any other default
285 units (e.g. kilobytes, sectors...) associated with the metrics.
286 -j { ID | LABEL | PATH | UUID | ... } [ device [...] | ALL ]
288 Display persistent device names. Options ID, LABEL, etc. specify
289 the type of the persistent name. These options are not limited,
290 only prerequisite is that directory with required persistent
291 names is present in /dev/disk. Optionally, multiple devices can
292 be specified in the chosen persistent name type. Because per‐
293 sistent device names are usually long, option
294 -k Display statistics in kilobytes per second.
296 -m Display statistics in megabytes per second.
298 -N Display the registered device mapper names for any device mapper
300 devices. Useful for viewing LVM2 statistics.
301 -o JSON
303 Display the statistics in JSON (Javascript Object Notation) for‐
304 mat. JSON output field order is undefined, and new fields may
305 be added in the future.
306 -p [ { device [,...] | ALL } ]
308 The -p option displays statistics for block devices and all
309 their partitions that are used by the system. If a device name
310 is entered on the command line, then statistics for it and all
311 its partitions are displayed. Last, the ALL keyword indicates
312 that statistics have to be displayed for all the block devices
313 and partitions defined by the system, including those that have
314 never been used. If option -j is defined before this option,
315 devices entered on the command line can be specified with the
316 chosen persistent name type.
317 -s Display a short (narrow) version of the report that should fit
319 in 80 characters wide screens.
320 -t Print the time for each report displayed. The timestamp format
322 may depend on the value of the S_TIME_FORMAT environment vari‐
323 able (see below).
324 -V Print version number then exit.
326 -x Display extended statistics.
328 -y Omit first report with statistics since system boot, if display‐
330 ing multiple records at given interval.
331 -z Tell iostat to omit output for any devices for which there was
333 no activity during the sample period.
334
337 The iostat command takes into account the following environment vari‐
338 ables:
339 POSIXLY_CORRECT
342 When this variable is set, transfer rates are shown in 512-byte
343 blocks instead of the default 1K blocks.
344 S_COLORS
347 When this variable is set, display statistics in color on the
348 terminal. Possible values for this variable are never, always
349 or auto (the latter is the default).
350 Please note that the color (being red, yellow, or some other
352 color) used to display a value is not indicative of any kind of
353 issue simply because of the color. It only indicates different
354 ranges of values.
355 S_COLORS_SGR
358 Specify the colors and other attributes used to display statis‐
359 tics on the terminal. Its value is a colon-separated list of
360 capabilities that defaults to
361 H=31;1:I=32;22:M=35;1:N=34;1:Z=34;22. Supported capabilities
362 are:
363 H= SGR (Select Graphic Rendition) substring for percentage
366 values greater than or equal to 75%.
367 I= SGR substring for device names.
370 M= SGR substring for percentage values in the range from 50%
373 to 75%.
374 N= SGR substring for non-zero statistics values.
377 Z= SGR substring for zero values.
380 S_TIME_FORMAT
383 If this variable exists and its value is ISO then the current
384 locale will be ignored when printing the date in the report
385 header. The iostat command will use the ISO 8601 format (YYYY-
386 MM-DD) instead. The timestamp displayed with option -t will
387 also be compliant with ISO 8601 format.
388
391 iostat
392 Display a single history since boot report for all CPU and
393 Devices.
394 iostat -d 2
396 Display a continuous device report at two second intervals.
397 iostat -d 2 6
399 Display six reports at two second intervals for all devices.
400 iostat -x sda sdb 2 6
402 Display six reports of extended statistics at two second inter‐
403 vals for devices sda and sdb.
404 iostat -p sda 2 6
406 Display six reports at two second intervals for device sda and
407 all its partitions (sda1, etc.)
408
410 /proc filesystem must be mounted for iostat to work.
411 Kernels older than 2.6.x are no longer supported.
413
415 /proc/stat contains system statistics.
416 /proc/uptime contains system uptime.
418 /proc/diskstats contains disks statistics.
420 /sys contains statistics for block devices.
422 /proc/self/mountstats contains statistics for network filesystems.
424 /dev/disk contains persistent device names.
426
428 Sebastien Godard (sysstat <at> orange.fr)
429
431 sar(1), pidstat(1), mpstat(1), vmstat(8), tapestat(1), nfsiostat(1),
432 cifsiostat(1)
433 https://github.com/sysstat/sysstat
435 http://pagesperso-orange.fr/sebastien.godard/
437Linux DECEMBER 2019 IOSTAT(1)