Commit | Line | Data |
---|---|---|
9040e236 | 1 | .TH fio 1 "March 2017" "User Manual" |
d60e92d1 AC |
2 | .SH NAME |
3 | fio \- flexible I/O tester | |
4 | .SH SYNOPSIS | |
5 | .B fio | |
6 | [\fIoptions\fR] [\fIjobfile\fR]... | |
7 | .SH DESCRIPTION | |
8 | .B fio | |
9 | is a tool that will spawn a number of threads or processes doing a | |
10 | particular type of I/O action as specified by the user. | |
11 | The typical use of fio is to write a job file matching the I/O load | |
12 | one wants to simulate. | |
13 | .SH OPTIONS | |
14 | .TP | |
49da1240 JA |
15 | .BI \-\-debug \fR=\fPtype |
16 | Enable verbose tracing of various fio actions. May be `all' for all types | |
17 | or individual types separated by a comma (eg \-\-debug=io,file). `help' will | |
18 | list all available tracing options. | |
19 | .TP | |
d60e92d1 AC |
20 | .BI \-\-output \fR=\fPfilename |
21 | Write output to \fIfilename\fR. | |
22 | .TP | |
e28ee21d | 23 | .BI \-\-output-format \fR=\fPformat |
513e37ee VF |
24 | Set the reporting format to \fInormal\fR, \fIterse\fR, \fIjson\fR, or |
25 | \fIjson+\fR. Multiple formats can be selected, separate by a comma. \fIterse\fR | |
26 | is a CSV based format. \fIjson+\fR is like \fIjson\fR, except it adds a full | |
27 | dump of the latency buckets. | |
e28ee21d | 28 | .TP |
b2cecdc2 | 29 | .BI \-\-runtime \fR=\fPruntime |
30 | Limit run time to \fIruntime\fR seconds. | |
d60e92d1 | 31 | .TP |
d60e92d1 | 32 | .B \-\-bandwidth\-log |
d23ae827 | 33 | Generate aggregate bandwidth logs. |
d60e92d1 AC |
34 | .TP |
35 | .B \-\-minimal | |
d1429b5c | 36 | Print statistics in a terse, semicolon-delimited format. |
d60e92d1 | 37 | .TP |
f6a7df53 JA |
38 | .B \-\-append-terse |
39 | Print statistics in selected mode AND terse, semicolon-delimited format. | |
40 | Deprecated, use \-\-output-format instead to select multiple formats. | |
41 | .TP | |
49da1240 JA |
42 | .B \-\-version |
43 | Display version information and exit. | |
44 | .TP | |
065248bf | 45 | .BI \-\-terse\-version \fR=\fPversion |
4d658652 | 46 | Set terse version output format (Current version 3, or older version 2). |
49da1240 JA |
47 | .TP |
48 | .B \-\-help | |
49 | Display usage information and exit. | |
50 | .TP | |
fec0f21c JA |
51 | .B \-\-cpuclock-test |
52 | Perform test and validation of internal CPU clock | |
53 | .TP | |
54 | .BI \-\-crctest[\fR=\fPtest] | |
55 | Test the speed of the builtin checksumming functions. If no argument is given, | |
56 | all of them are tested. Or a comma separated list can be passed, in which | |
57 | case the given ones are tested. | |
58 | .TP | |
49da1240 JA |
59 | .BI \-\-cmdhelp \fR=\fPcommand |
60 | Print help information for \fIcommand\fR. May be `all' for all commands. | |
61 | .TP | |
de890a1e SL |
62 | .BI \-\-enghelp \fR=\fPioengine[,command] |
63 | List all commands defined by \fIioengine\fR, or print help for \fIcommand\fR defined by \fIioengine\fR. | |
64 | .TP | |
d60e92d1 AC |
65 | .BI \-\-showcmd \fR=\fPjobfile |
66 | Convert \fIjobfile\fR to a set of command-line options. | |
67 | .TP | |
d60e92d1 AC |
68 | .BI \-\-eta \fR=\fPwhen |
69 | Specifies when real-time ETA estimate should be printed. \fIwhen\fR may | |
70 | be one of `always', `never' or `auto'. | |
71 | .TP | |
30b5d57f JA |
72 | .BI \-\-eta\-newline \fR=\fPtime |
73 | Force an ETA newline for every `time` period passed. | |
74 | .TP | |
75 | .BI \-\-status\-interval \fR=\fPtime | |
76 | Report full output status every `time` period passed. | |
77 | .TP | |
49da1240 JA |
78 | .BI \-\-readonly |
79 | Turn on safety read-only checks, preventing any attempted write. | |
80 | .TP | |
c0a5d35e | 81 | .BI \-\-section \fR=\fPsec |
cf145d90 | 82 | Only run section \fIsec\fR from job file. This option can be used multiple times to add more sections to run. |
c0a5d35e | 83 | .TP |
49da1240 JA |
84 | .BI \-\-alloc\-size \fR=\fPkb |
85 | Set the internal smalloc pool size to \fIkb\fP kilobytes. | |
d60e92d1 | 86 | .TP |
49da1240 JA |
87 | .BI \-\-warnings\-fatal |
88 | All fio parser warnings are fatal, causing fio to exit with an error. | |
9183788d | 89 | .TP |
49da1240 | 90 | .BI \-\-max\-jobs \fR=\fPnr |
57e118a2 | 91 | Set the maximum allowed number of jobs (threads/processes) to support. |
d60e92d1 | 92 | .TP |
49da1240 JA |
93 | .BI \-\-server \fR=\fPargs |
94 | Start a backend server, with \fIargs\fP specifying what to listen to. See client/server section. | |
f57a9c59 | 95 | .TP |
49da1240 JA |
96 | .BI \-\-daemonize \fR=\fPpidfile |
97 | Background a fio server, writing the pid to the given pid file. | |
98 | .TP | |
99 | .BI \-\-client \fR=\fPhost | |
39b5f61e | 100 | Instead of running the jobs locally, send and run them on the given host or set of hosts. See client/server section. |
f2a2ce0e HL |
101 | .TP |
102 | .BI \-\-idle\-prof \fR=\fPoption | |
103 | Report cpu idleness on a system or percpu basis (\fIoption\fP=system,percpu) or run unit work calibration only (\fIoption\fP=calibrate). | |
d60e92d1 AC |
104 | .SH "JOB FILE FORMAT" |
105 | Job files are in `ini' format. They consist of one or more | |
106 | job definitions, which begin with a job name in square brackets and | |
107 | extend to the next job name. The job name can be any ASCII string | |
108 | except `global', which has a special meaning. Following the job name is | |
109 | a sequence of zero or more parameters, one per line, that define the | |
110 | behavior of the job. Any line starting with a `;' or `#' character is | |
d1429b5c | 111 | considered a comment and ignored. |
d9956b64 AC |
112 | .P |
113 | If \fIjobfile\fR is specified as `-', the job file will be read from | |
114 | standard input. | |
d60e92d1 AC |
115 | .SS "Global Section" |
116 | The global section contains default parameters for jobs specified in the | |
117 | job file. A job is only affected by global sections residing above it, | |
118 | and there may be any number of global sections. Specific job definitions | |
119 | may override any parameter set in global sections. | |
120 | .SH "JOB PARAMETERS" | |
121 | .SS Types | |
b470a02c SC |
122 | Some parameters may take arguments of a specific type. |
123 | Anywhere a numeric value is required, an arithmetic expression may be used, | |
d59aa780 JA |
124 | provided it is surrounded by parentheses. Supported operators are: |
125 | .RS | |
126 | .RS | |
127 | .TP | |
128 | .B addition (+) | |
129 | .TP | |
130 | .B subtraction (-) | |
131 | .TP | |
132 | .B multiplication (*) | |
133 | .TP | |
134 | .B division (/) | |
135 | .TP | |
136 | .B modulus (%) | |
137 | .TP | |
138 | .B exponentiation (^) | |
139 | .RE | |
140 | .RE | |
141 | .P | |
142 | For time values in expressions, units are microseconds by default. This is | |
143 | different than for time values not in expressions (not enclosed in | |
144 | parentheses). The types used are: | |
d60e92d1 AC |
145 | .TP |
146 | .I str | |
147 | String: a sequence of alphanumeric characters. | |
148 | .TP | |
149 | .I int | |
6d500c2e RE |
150 | Integer. A whole number value, which may contain an integer prefix |
151 | and an integer suffix. | |
152 | ||
153 | [integer prefix]number[integer suffix] | |
154 | ||
155 | The optional integer prefix specifies the number's base. The default | |
156 | is decimal. 0x specifies hexadecimal. | |
157 | ||
158 | The optional integer suffix specifies the number's units, and includes | |
159 | an optional unit prefix and an optional unit. For quantities | |
160 | of data, the default unit is bytes. For quantities of time, | |
161 | the default unit is seconds. | |
162 | ||
163 | With \fBkb_base=1000\fR, fio follows international standards for unit prefixes. | |
164 | To specify power-of-10 decimal values defined in the International | |
165 | System of Units (SI): | |
166 | .nf | |
167 | ki means kilo (K) or 1000 | |
168 | mi means mega (M) or 1000**2 | |
169 | gi means giga (G) or 1000**3 | |
170 | ti means tera (T) or 1000**4 | |
171 | pi means peta (P) or 1000**5 | |
172 | .fi | |
173 | ||
174 | To specify power-of-2 binary values defined in IEC 80000-13: | |
175 | .nf | |
176 | k means kibi (Ki) or 1024 | |
177 | m means mebi (Mi) or 1024**2 | |
178 | g means gibi (Gi) or 1024**3 | |
179 | t means tebi (Ti) or 1024**4 | |
180 | p means pebi (Pi) or 1024**5 | |
181 | .fi | |
182 | ||
183 | With \fBkb_base=1024\fR (the default), the unit prefixes are opposite from | |
184 | those specified in the SI and IEC 80000-13 standards to provide | |
185 | compatibility with old scripts. For example, 4k means 4096. | |
186 | ||
187 | .nf | |
188 | Examples with \fBkb_base=1000\fR: | |
189 | 4 KiB: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB | |
190 | 1 MiB: 1048576, 1m, 1024k | |
191 | 1 MB: 1000000, 1mi, 1000ki | |
192 | 1 TiB: 1073741824, 1t, 1024m, 1048576k | |
193 | 1 TB: 1000000000, 1ti, 1000mi, 1000000ki | |
194 | .fi | |
195 | ||
196 | .nf | |
197 | Examples with \fBkb_base=1024\fR (default): | |
198 | 4 KiB: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB | |
199 | 1 MiB: 1048576, 1m, 1024k | |
200 | 1 MB: 1000000, 1mi, 1000ki | |
201 | 1 TiB: 1073741824, 1t, 1024m, 1048576k | |
202 | 1 TB: 1000000000, 1ti, 1000mi, 1000000ki | |
203 | .fi | |
204 | ||
205 | For quantities of data, an optional unit of 'B' may be included | |
206 | (e.g., 'kb' is the same as 'k'). | |
207 | ||
208 | The integer suffix is not case sensitive (e.g., m/mi mean mebi/mega, | |
209 | not milli). 'b' and 'B' both mean byte, not bit. | |
210 | ||
211 | To specify times (units are not case sensitive): | |
212 | .nf | |
213 | D means days | |
214 | H means hours | |
215 | M mean minutes | |
216 | s or sec means seconds (default) | |
217 | ms or msec means milliseconds | |
218 | us or usec means microseconds | |
219 | .fi | |
220 | ||
d60e92d1 AC |
221 | .TP |
222 | .I bool | |
223 | Boolean: a true or false value. `0' denotes false, `1' denotes true. | |
224 | .TP | |
225 | .I irange | |
226 | Integer range: a range of integers specified in the format | |
d1429b5c AC |
227 | \fIlower\fR:\fIupper\fR or \fIlower\fR\-\fIupper\fR. \fIlower\fR and |
228 | \fIupper\fR may contain a suffix as described above. If an option allows two | |
229 | sets of ranges, they are separated with a `,' or `/' character. For example: | |
230 | `8\-8k/8M\-4G'. | |
83349190 YH |
231 | .TP |
232 | .I float_list | |
233 | List of floating numbers: A list of floating numbers, separated by | |
cecbfd47 | 234 | a ':' character. |
d60e92d1 AC |
235 | .SS "Parameter List" |
236 | .TP | |
237 | .BI name \fR=\fPstr | |
d9956b64 | 238 | May be used to override the job name. On the command line, this parameter |
d60e92d1 AC |
239 | has the special purpose of signalling the start of a new job. |
240 | .TP | |
9cc8cb91 AK |
241 | .BI wait_for \fR=\fPstr |
242 | Specifies the name of the already defined job to wait for. Single waitee name | |
243 | only may be specified. If set, the job won't be started until all workers of | |
244 | the waitee job are done. Wait_for operates on the job name basis, so there are | |
245 | a few limitations. First, the waitee must be defined prior to the waiter job | |
246 | (meaning no forward references). Second, if a job is being referenced as a | |
247 | waitee, it must have a unique name (no duplicate waitees). | |
248 | .TP | |
d60e92d1 AC |
249 | .BI description \fR=\fPstr |
250 | Human-readable description of the job. It is printed when the job is run, but | |
251 | otherwise has no special purpose. | |
252 | .TP | |
253 | .BI directory \fR=\fPstr | |
254 | Prefix filenames with this directory. Used to place files in a location other | |
255 | than `./'. | |
bcbfeefa CE |
256 | You can specify a number of directories by separating the names with a ':' |
257 | character. These directories will be assigned equally distributed to job clones | |
258 | creates with \fInumjobs\fR as long as they are using generated filenames. | |
259 | If specific \fIfilename(s)\fR are set fio will use the first listed directory, | |
260 | and thereby matching the \fIfilename\fR semantic which generates a file each | |
67445b63 JA |
261 | clone if not specified, but let all clones use the same if set. See |
262 | \fIfilename\fR for considerations regarding escaping certain characters on | |
263 | some platforms. | |
d60e92d1 AC |
264 | .TP |
265 | .BI filename \fR=\fPstr | |
266 | .B fio | |
267 | normally makes up a file name based on the job name, thread number, and file | |
d1429b5c | 268 | number. If you want to share files between threads in a job or several jobs, |
de890a1e SL |
269 | specify a \fIfilename\fR for each of them to override the default. |
270 | If the I/O engine is file-based, you can specify | |
d1429b5c AC |
271 | a number of files by separating the names with a `:' character. `\-' is a |
272 | reserved name, meaning stdin or stdout, depending on the read/write direction | |
67445b63 JA |
273 | set. On Windows, disk devices are accessed as \\.\PhysicalDrive0 for the first |
274 | device, \\.\PhysicalDrive1 for the second etc. Note: Windows and FreeBSD | |
275 | prevent write access to areas of the disk containing in-use data | |
276 | (e.g. filesystems). If the wanted filename does need to include a colon, then | |
4904acd5 JM |
277 | escape that with a '\\' character. For instance, if the filename is |
278 | "/dev/dsk/foo@3,0:c", then you would use filename="/dev/dsk/foo@3,0\\:c". | |
d60e92d1 | 279 | .TP |
de98bd30 | 280 | .BI filename_format \fR=\fPstr |
ce594fbe | 281 | If sharing multiple files between jobs, it is usually necessary to have |
de98bd30 JA |
282 | fio generate the exact names that you want. By default, fio will name a file |
283 | based on the default file format specification of | |
284 | \fBjobname.jobnumber.filenumber\fP. With this option, that can be | |
285 | customized. Fio will recognize and replace the following keywords in this | |
286 | string: | |
287 | .RS | |
288 | .RS | |
289 | .TP | |
290 | .B $jobname | |
291 | The name of the worker thread or process. | |
292 | .TP | |
293 | .B $jobnum | |
294 | The incremental number of the worker thread or process. | |
295 | .TP | |
296 | .B $filenum | |
297 | The incremental number of the file for that worker thread or process. | |
298 | .RE | |
299 | .P | |
300 | To have dependent jobs share a set of files, this option can be set to | |
301 | have fio generate filenames that are shared between the two. For instance, | |
302 | if \fBtestfiles.$filenum\fR is specified, file number 4 for any job will | |
303 | be named \fBtestfiles.4\fR. The default of \fB$jobname.$jobnum.$filenum\fR | |
304 | will be used if no other format specifier is given. | |
305 | .RE | |
306 | .P | |
307 | .TP | |
922a5be8 JA |
308 | .BI unique_filename \fR=\fPbool |
309 | To avoid collisions between networked clients, fio defaults to prefixing | |
310 | any generated filenames (with a directory specified) with the source of | |
311 | the client connecting. To disable this behavior, set this option to 0. | |
312 | .TP | |
3ce9dcaf JA |
313 | .BI lockfile \fR=\fPstr |
314 | Fio defaults to not locking any files before it does IO to them. If a file or | |
315 | file descriptor is shared, fio can serialize IO to that file to make the end | |
316 | result consistent. This is usual for emulating real workloads that share files. | |
317 | The lock modes are: | |
318 | .RS | |
319 | .RS | |
320 | .TP | |
321 | .B none | |
322 | No locking. This is the default. | |
323 | .TP | |
324 | .B exclusive | |
cf145d90 | 325 | Only one thread or process may do IO at a time, excluding all others. |
3ce9dcaf JA |
326 | .TP |
327 | .B readwrite | |
328 | Read-write locking on the file. Many readers may access the file at the same | |
329 | time, but writes get exclusive access. | |
330 | .RE | |
ce594fbe | 331 | .RE |
3ce9dcaf | 332 | .P |
d60e92d1 AC |
333 | .BI opendir \fR=\fPstr |
334 | Recursively open any files below directory \fIstr\fR. | |
335 | .TP | |
336 | .BI readwrite \fR=\fPstr "\fR,\fP rw" \fR=\fPstr | |
337 | Type of I/O pattern. Accepted values are: | |
338 | .RS | |
339 | .RS | |
340 | .TP | |
341 | .B read | |
d1429b5c | 342 | Sequential reads. |
d60e92d1 AC |
343 | .TP |
344 | .B write | |
d1429b5c | 345 | Sequential writes. |
d60e92d1 | 346 | .TP |
fa769d44 | 347 | .B trim |
169c098d | 348 | Sequential trims (Linux block devices only). |
fa769d44 | 349 | .TP |
d60e92d1 | 350 | .B randread |
d1429b5c | 351 | Random reads. |
d60e92d1 AC |
352 | .TP |
353 | .B randwrite | |
d1429b5c | 354 | Random writes. |
d60e92d1 | 355 | .TP |
fa769d44 | 356 | .B randtrim |
169c098d | 357 | Random trims (Linux block devices only). |
fa769d44 | 358 | .TP |
10b023db | 359 | .B rw, readwrite |
d1429b5c | 360 | Mixed sequential reads and writes. |
d60e92d1 | 361 | .TP |
ff6bb260 | 362 | .B randrw |
d1429b5c | 363 | Mixed random reads and writes. |
82a90686 JA |
364 | .TP |
365 | .B trimwrite | |
169c098d RE |
366 | Sequential trim and write mixed workload. Blocks will be trimmed first, then |
367 | the same blocks will be written to. | |
d60e92d1 AC |
368 | .RE |
369 | .P | |
38f8c318 | 370 | Fio defaults to read if the option is not specified. |
38dad62d JA |
371 | For mixed I/O, the default split is 50/50. For certain types of io the result |
372 | may still be skewed a bit, since the speed may be different. It is possible to | |
3b7fa9ec | 373 | specify a number of IO's to do before getting a new offset, this is done by |
38dad62d JA |
374 | appending a `:\fI<nr>\fR to the end of the string given. For a random read, it |
375 | would look like \fBrw=randread:8\fR for passing in an offset modifier with a | |
059b0802 JA |
376 | value of 8. If the postfix is used with a sequential IO pattern, then the value |
377 | specified will be added to the generated offset for each IO. For instance, | |
378 | using \fBrw=write:4k\fR will skip 4k for every write. It turns sequential IO | |
379 | into sequential IO with holes. See the \fBrw_sequencer\fR option. | |
d60e92d1 AC |
380 | .RE |
381 | .TP | |
38dad62d JA |
382 | .BI rw_sequencer \fR=\fPstr |
383 | If an offset modifier is given by appending a number to the \fBrw=<str>\fR line, | |
384 | then this option controls how that number modifies the IO offset being | |
385 | generated. Accepted values are: | |
386 | .RS | |
387 | .RS | |
388 | .TP | |
389 | .B sequential | |
390 | Generate sequential offset | |
391 | .TP | |
392 | .B identical | |
393 | Generate the same offset | |
394 | .RE | |
395 | .P | |
396 | \fBsequential\fR is only useful for random IO, where fio would normally | |
397 | generate a new random offset for every IO. If you append eg 8 to randread, you | |
398 | would get a new random offset for every 8 IO's. The result would be a seek for | |
399 | only every 8 IO's, instead of for every IO. Use \fBrw=randread:8\fR to specify | |
400 | that. As sequential IO is already sequential, setting \fBsequential\fR for that | |
401 | would not result in any differences. \fBidentical\fR behaves in a similar | |
402 | fashion, except it sends the same offset 8 number of times before generating a | |
403 | new offset. | |
404 | .RE | |
405 | .P | |
406 | .TP | |
90fef2d1 JA |
407 | .BI kb_base \fR=\fPint |
408 | The base unit for a kilobyte. The defacto base is 2^10, 1024. Storage | |
409 | manufacturers like to use 10^3 or 1000 as a base ten unit instead, for obvious | |
5c9323fb | 410 | reasons. Allowed values are 1024 or 1000, with 1024 being the default. |
90fef2d1 | 411 | .TP |
771e58be JA |
412 | .BI unified_rw_reporting \fR=\fPbool |
413 | Fio normally reports statistics on a per data direction basis, meaning that | |
169c098d | 414 | reads, writes, and trims are accounted and reported separately. If this option is |
cf145d90 | 415 | set fio sums the results and reports them as "mixed" instead. |
771e58be | 416 | .TP |
d60e92d1 | 417 | .BI randrepeat \fR=\fPbool |
56e2a5fc CE |
418 | Seed the random number generator used for random I/O patterns in a predictable |
419 | way so the pattern is repeatable across runs. Default: true. | |
420 | .TP | |
421 | .BI allrandrepeat \fR=\fPbool | |
422 | Seed all random number generators in a predictable way so results are | |
423 | repeatable across runs. Default: false. | |
d60e92d1 | 424 | .TP |
04778baf JA |
425 | .BI randseed \fR=\fPint |
426 | Seed the random number generators based on this seed value, to be able to | |
427 | control what sequence of output is being generated. If not set, the random | |
428 | sequence depends on the \fBrandrepeat\fR setting. | |
429 | .TP | |
a596f047 EG |
430 | .BI fallocate \fR=\fPstr |
431 | Whether pre-allocation is performed when laying down files. Accepted values | |
432 | are: | |
433 | .RS | |
434 | .RS | |
435 | .TP | |
436 | .B none | |
437 | Do not pre-allocate space. | |
438 | .TP | |
439 | .B posix | |
ccc2b328 | 440 | Pre-allocate via \fBposix_fallocate\fR\|(3). |
a596f047 EG |
441 | .TP |
442 | .B keep | |
ccc2b328 | 443 | Pre-allocate via \fBfallocate\fR\|(2) with FALLOC_FL_KEEP_SIZE set. |
a596f047 EG |
444 | .TP |
445 | .B 0 | |
446 | Backward-compatible alias for 'none'. | |
447 | .TP | |
448 | .B 1 | |
449 | Backward-compatible alias for 'posix'. | |
450 | .RE | |
451 | .P | |
452 | May not be available on all supported platforms. 'keep' is only | |
453 | available on Linux. If using ZFS on Solaris this must be set to 'none' | |
454 | because ZFS doesn't support it. Default: 'posix'. | |
455 | .RE | |
7bc8c2cf | 456 | .TP |
ecb2083d | 457 | .BI fadvise_hint \fR=\fPstr |
cf145d90 | 458 | Use \fBposix_fadvise\fR\|(2) to advise the kernel what I/O patterns |
ecb2083d JA |
459 | are likely to be issued. Accepted values are: |
460 | .RS | |
461 | .RS | |
462 | .TP | |
463 | .B 0 | |
464 | Backwards compatible hint for "no hint". | |
465 | .TP | |
466 | .B 1 | |
467 | Backwards compatible hint for "advise with fio workload type". This | |
468 | uses \fBFADV_RANDOM\fR for a random workload, and \fBFADV_SEQUENTIAL\fR | |
469 | for a sequential workload. | |
470 | .TP | |
471 | .B sequential | |
472 | Advise using \fBFADV_SEQUENTIAL\fR | |
473 | .TP | |
474 | .B random | |
475 | Advise using \fBFADV_RANDOM\fR | |
476 | .RE | |
477 | .RE | |
d60e92d1 | 478 | .TP |
37659335 JA |
479 | .BI fadvise_stream \fR=\fPint |
480 | Use \fBposix_fadvise\fR\|(2) to advise the kernel what stream ID the | |
481 | writes issued belong to. Only supported on Linux. Note, this option | |
482 | may change going forward. | |
483 | .TP | |
f7fa2653 | 484 | .BI size \fR=\fPint |
d60e92d1 | 485 | Total size of I/O for this job. \fBfio\fR will run until this many bytes have |
a4d3b4db JA |
486 | been transferred, unless limited by other options (\fBruntime\fR, for instance, |
487 | or increased/descreased by \fBio_size\fR). Unless \fBnrfiles\fR and | |
488 | \fBfilesize\fR options are given, this amount will be divided between the | |
489 | available files for the job. If not set, fio will use the full size of the | |
490 | given files or devices. If the files do not exist, size must be given. It is | |
491 | also possible to give size as a percentage between 1 and 100. If size=20% is | |
492 | given, fio will use 20% of the full size of the given files or devices. | |
493 | .TP | |
494 | .BI io_size \fR=\fPint "\fR,\fB io_limit \fR=\fPint | |
77731b29 JA |
495 | Normally fio operates within the region set by \fBsize\fR, which means that |
496 | the \fBsize\fR option sets both the region and size of IO to be performed. | |
497 | Sometimes that is not what you want. With this option, it is possible to | |
498 | define just the amount of IO that fio should do. For instance, if \fBsize\fR | |
499 | is set to 20G and \fBio_limit\fR is set to 5G, fio will perform IO within | |
a4d3b4db JA |
500 | the first 20G but exit when 5G have been done. The opposite is also |
501 | possible - if \fBsize\fR is set to 20G, and \fBio_size\fR is set to 40G, then | |
502 | fio will do 40G of IO within the 0..20G region. | |
d60e92d1 | 503 | .TP |
74586c1e | 504 | .BI fill_device \fR=\fPbool "\fR,\fB fill_fs" \fR=\fPbool |
3ce9dcaf JA |
505 | Sets size to something really large and waits for ENOSPC (no space left on |
506 | device) as the terminating condition. Only makes sense with sequential write. | |
507 | For a read workload, the mount point will be filled first then IO started on | |
4f12432e JA |
508 | the result. This option doesn't make sense if operating on a raw device node, |
509 | since the size of that is already known by the file system. Additionally, | |
510 | writing beyond end-of-device will not return ENOSPC there. | |
3ce9dcaf | 511 | .TP |
d60e92d1 AC |
512 | .BI filesize \fR=\fPirange |
513 | Individual file sizes. May be a range, in which case \fBfio\fR will select sizes | |
d1429b5c AC |
514 | for files at random within the given range, limited to \fBsize\fR in total (if |
515 | that is given). If \fBfilesize\fR is not specified, each created file is the | |
516 | same size. | |
d60e92d1 | 517 | .TP |
bedc9dc2 JA |
518 | .BI file_append \fR=\fPbool |
519 | Perform IO after the end of the file. Normally fio will operate within the | |
520 | size of a file. If this option is set, then fio will append to the file | |
521 | instead. This has identical behavior to setting \fRoffset\fP to the size | |
0aae4ce7 | 522 | of a file. This option is ignored on non-regular files. |
bedc9dc2 | 523 | .TP |
6d500c2e RE |
524 | .BI blocksize \fR=\fPint[,int][,int] "\fR,\fB bs" \fR=\fPint[,int][,int] |
525 | The block size in bytes for I/O units. Default: 4096. | |
526 | A single value applies to reads, writes, and trims. | |
527 | Comma-separated values may be specified for reads, writes, and trims. | |
528 | Empty values separated by commas use the default value. A value not | |
529 | terminated in a comma applies to subsequent types. | |
530 | .nf | |
531 | Examples: | |
532 | bs=256k means 256k for reads, writes and trims | |
533 | bs=8k,32k means 8k for reads, 32k for writes and trims | |
534 | bs=8k,32k, means 8k for reads, 32k for writes, and default for trims | |
535 | bs=,8k means default for reads, 8k for writes and trims | |
536 | bs=,8k, means default for reads, 8k for writes, and default for writes | |
537 | .fi | |
538 | .TP | |
539 | .BI blocksize_range \fR=\fPirange[,irange][,irange] "\fR,\fB bsrange" \fR=\fPirange[,irange][,irange] | |
540 | A range of block sizes in bytes for I/O units. | |
541 | The issued I/O unit will always be a multiple of the minimum size, unless | |
542 | \fBblocksize_unaligned\fR is set. | |
543 | Comma-separated ranges may be specified for reads, writes, and trims | |
544 | as described in \fBblocksize\fR. | |
545 | .nf | |
546 | Example: bsrange=1k-4k,2k-8k. | |
547 | .fi | |
548 | .TP | |
549 | .BI bssplit \fR=\fPstr[,str][,str] | |
9183788d JA |
550 | This option allows even finer grained control of the block sizes issued, |
551 | not just even splits between them. With this option, you can weight various | |
552 | block sizes for exact control of the issued IO for a job that has mixed | |
553 | block sizes. The format of the option is bssplit=blocksize/percentage, | |
5982a925 | 554 | optionally adding as many definitions as needed separated by a colon. |
9183788d | 555 | Example: bssplit=4k/10:64k/50:32k/40 would issue 50% 64k blocks, 10% 4k |
c83cdd3e | 556 | blocks and 40% 32k blocks. \fBbssplit\fR also supports giving separate |
6d500c2e RE |
557 | splits to reads, writes, and trims. |
558 | Comma-separated values may be specified for reads, writes, and trims | |
559 | as described in \fBblocksize\fR. | |
d60e92d1 | 560 | .TP |
6d500c2e RE |
561 | .B blocksize_unaligned\fR,\fB bs_unaligned |
562 | If set, fio will issue I/O units with any size within \fBblocksize_range\fR, | |
563 | not just multiples of the minimum size. This typically won't | |
d1429b5c | 564 | work with direct I/O, as that normally requires sector alignment. |
d60e92d1 | 565 | .TP |
6aca9b3d JA |
566 | .BI bs_is_seq_rand \fR=\fPbool |
567 | If this option is set, fio will use the normal read,write blocksize settings as | |
6d500c2e RE |
568 | sequential,random blocksize settings instead. Any random read or write will |
569 | use the WRITE blocksize settings, and any sequential read or write will use | |
570 | the READ blocksize settings. | |
571 | .TP | |
572 | .BI blockalign \fR=\fPint[,int][,int] "\fR,\fB ba" \fR=\fPint[,int][,int] | |
573 | Boundary to which fio will align random I/O units. Default: \fBblocksize\fR. | |
574 | Minimum alignment is typically 512b for using direct IO, though it usually | |
575 | depends on the hardware block size. This option is mutually exclusive with | |
576 | using a random map for files, so it will turn off that option. | |
577 | Comma-separated values may be specified for reads, writes, and trims | |
578 | as described in \fBblocksize\fR. | |
6aca9b3d | 579 | .TP |
d60e92d1 | 580 | .B zero_buffers |
cf145d90 | 581 | Initialize buffers with all zeros. Default: fill buffers with random data. |
d60e92d1 | 582 | .TP |
901bb994 JA |
583 | .B refill_buffers |
584 | If this option is given, fio will refill the IO buffers on every submit. The | |
585 | default is to only fill it at init time and reuse that data. Only makes sense | |
586 | if zero_buffers isn't specified, naturally. If data verification is enabled, | |
587 | refill_buffers is also automatically enabled. | |
588 | .TP | |
fd68418e JA |
589 | .BI scramble_buffers \fR=\fPbool |
590 | If \fBrefill_buffers\fR is too costly and the target is using data | |
591 | deduplication, then setting this option will slightly modify the IO buffer | |
592 | contents to defeat normal de-dupe attempts. This is not enough to defeat | |
593 | more clever block compression attempts, but it will stop naive dedupe | |
594 | of blocks. Default: true. | |
595 | .TP | |
c5751c62 JA |
596 | .BI buffer_compress_percentage \fR=\fPint |
597 | If this is set, then fio will attempt to provide IO buffer content (on WRITEs) | |
598 | that compress to the specified level. Fio does this by providing a mix of | |
d1af2894 JA |
599 | random data and a fixed pattern. The fixed pattern is either zeroes, or the |
600 | pattern specified by \fBbuffer_pattern\fR. If the pattern option is used, it | |
601 | might skew the compression ratio slightly. Note that this is per block size | |
602 | unit, for file/disk wide compression level that matches this setting. Note | |
603 | that this is per block size unit, for file/disk wide compression level that | |
604 | matches this setting, you'll also want to set refill_buffers. | |
c5751c62 JA |
605 | .TP |
606 | .BI buffer_compress_chunk \fR=\fPint | |
607 | See \fBbuffer_compress_percentage\fR. This setting allows fio to manage how | |
608 | big the ranges of random data and zeroed data is. Without this set, fio will | |
609 | provide \fBbuffer_compress_percentage\fR of blocksize random data, followed by | |
610 | the remaining zeroed. With this set to some chunk size smaller than the block | |
611 | size, fio can alternate random and zeroed data throughout the IO buffer. | |
612 | .TP | |
ce35b1ec | 613 | .BI buffer_pattern \fR=\fPstr |
cf145d90 CVB |
614 | If set, fio will fill the IO buffers with this pattern. If not set, the contents |
615 | of IO buffers is defined by the other options related to buffer contents. The | |
ce35b1ec | 616 | setting can be any pattern of bytes, and can be prefixed with 0x for hex |
02975b64 | 617 | values. It may also be a string, where the string must then be wrapped with |
2fa5a241 RP |
618 | "", e.g.: |
619 | .RS | |
620 | .RS | |
621 | \fBbuffer_pattern\fR="abcd" | |
622 | .RS | |
623 | or | |
624 | .RE | |
625 | \fBbuffer_pattern\fR=-12 | |
626 | .RS | |
627 | or | |
628 | .RE | |
629 | \fBbuffer_pattern\fR=0xdeadface | |
630 | .RE | |
631 | .LP | |
632 | Also you can combine everything together in any order: | |
633 | .LP | |
634 | .RS | |
635 | \fBbuffer_pattern\fR=0xdeadface"abcd"-12 | |
636 | .RE | |
637 | .RE | |
ce35b1ec | 638 | .TP |
5c94b008 JA |
639 | .BI dedupe_percentage \fR=\fPint |
640 | If set, fio will generate this percentage of identical buffers when writing. | |
641 | These buffers will be naturally dedupable. The contents of the buffers depend | |
642 | on what other buffer compression settings have been set. It's possible to have | |
643 | the individual buffers either fully compressible, or not at all. This option | |
644 | only controls the distribution of unique buffers. | |
645 | .TP | |
d60e92d1 AC |
646 | .BI nrfiles \fR=\fPint |
647 | Number of files to use for this job. Default: 1. | |
648 | .TP | |
649 | .BI openfiles \fR=\fPint | |
650 | Number of files to keep open at the same time. Default: \fBnrfiles\fR. | |
651 | .TP | |
652 | .BI file_service_type \fR=\fPstr | |
653 | Defines how files to service are selected. The following types are defined: | |
654 | .RS | |
655 | .RS | |
656 | .TP | |
657 | .B random | |
5c9323fb | 658 | Choose a file at random. |
d60e92d1 AC |
659 | .TP |
660 | .B roundrobin | |
cf145d90 | 661 | Round robin over opened files (default). |
5c9323fb | 662 | .TP |
6b7f6851 JA |
663 | .B sequential |
664 | Do each file in the set sequentially. | |
8c07860d JA |
665 | .TP |
666 | .B zipf | |
667 | Use a zipfian distribution to decide what file to access. | |
668 | .TP | |
669 | .B pareto | |
670 | Use a pareto distribution to decide what file to access. | |
671 | .TP | |
672 | .B gauss | |
673 | Use a gaussian (normal) distribution to decide what file to access. | |
d60e92d1 AC |
674 | .RE |
675 | .P | |
8c07860d JA |
676 | For \fBrandom\fR, \fBroundrobin\fR, and \fBsequential\fR, a postfix can be |
677 | appended to tell fio how many I/Os to issue before switching to a new file. | |
678 | For example, specifying \fBfile_service_type=random:8\fR would cause fio to | |
679 | issue \fI8\fR I/Os before selecting a new file at random. For the non-uniform | |
680 | distributions, a floating point postfix can be given to influence how the | |
681 | distribution is skewed. See \fBrandom_distribution\fR for a description of how | |
682 | that would work. | |
d60e92d1 AC |
683 | .RE |
684 | .TP | |
685 | .BI ioengine \fR=\fPstr | |
686 | Defines how the job issues I/O. The following types are defined: | |
687 | .RS | |
688 | .RS | |
689 | .TP | |
690 | .B sync | |
ccc2b328 | 691 | Basic \fBread\fR\|(2) or \fBwrite\fR\|(2) I/O. \fBfseek\fR\|(2) is used to |
d60e92d1 AC |
692 | position the I/O location. |
693 | .TP | |
a31041ea | 694 | .B psync |
ccc2b328 | 695 | Basic \fBpread\fR\|(2) or \fBpwrite\fR\|(2) I/O. |
38f8c318 | 696 | Default on all supported operating systems except for Windows. |
a31041ea | 697 | .TP |
9183788d | 698 | .B vsync |
ccc2b328 | 699 | Basic \fBreadv\fR\|(2) or \fBwritev\fR\|(2) I/O. Will emulate queuing by |
cecbfd47 | 700 | coalescing adjacent IOs into a single submission. |
9183788d | 701 | .TP |
a46c5e01 | 702 | .B pvsync |
ccc2b328 | 703 | Basic \fBpreadv\fR\|(2) or \fBpwritev\fR\|(2) I/O. |
a46c5e01 | 704 | .TP |
2cafffbe JA |
705 | .B pvsync2 |
706 | Basic \fBpreadv2\fR\|(2) or \fBpwritev2\fR\|(2) I/O. | |
707 | .TP | |
d60e92d1 | 708 | .B libaio |
de890a1e | 709 | Linux native asynchronous I/O. This ioengine defines engine specific options. |
d60e92d1 AC |
710 | .TP |
711 | .B posixaio | |
ccc2b328 | 712 | POSIX asynchronous I/O using \fBaio_read\fR\|(3) and \fBaio_write\fR\|(3). |
03e20d68 BC |
713 | .TP |
714 | .B solarisaio | |
715 | Solaris native asynchronous I/O. | |
716 | .TP | |
717 | .B windowsaio | |
38f8c318 | 718 | Windows native asynchronous I/O. Default on Windows. |
d60e92d1 AC |
719 | .TP |
720 | .B mmap | |
ccc2b328 SW |
721 | File is memory mapped with \fBmmap\fR\|(2) and data copied using |
722 | \fBmemcpy\fR\|(3). | |
d60e92d1 AC |
723 | .TP |
724 | .B splice | |
ccc2b328 | 725 | \fBsplice\fR\|(2) is used to transfer the data and \fBvmsplice\fR\|(2) to |
d1429b5c | 726 | transfer data from user-space to the kernel. |
d60e92d1 | 727 | .TP |
d60e92d1 AC |
728 | .B sg |
729 | SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if | |
ccc2b328 SW |
730 | the target is an sg character device, we use \fBread\fR\|(2) and |
731 | \fBwrite\fR\|(2) for asynchronous I/O. | |
d60e92d1 AC |
732 | .TP |
733 | .B null | |
734 | Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR | |
735 | itself and for debugging and testing purposes. | |
736 | .TP | |
737 | .B net | |
de890a1e SL |
738 | Transfer over the network. The protocol to be used can be defined with the |
739 | \fBprotocol\fR parameter. Depending on the protocol, \fBfilename\fR, | |
740 | \fBhostname\fR, \fBport\fR, or \fBlisten\fR must be specified. | |
741 | This ioengine defines engine specific options. | |
d60e92d1 AC |
742 | .TP |
743 | .B netsplice | |
ccc2b328 | 744 | Like \fBnet\fR, but uses \fBsplice\fR\|(2) and \fBvmsplice\fR\|(2) to map data |
de890a1e | 745 | and send/receive. This ioengine defines engine specific options. |
d60e92d1 | 746 | .TP |
53aec0a4 | 747 | .B cpuio |
d60e92d1 | 748 | Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and |
3e93fc25 TK |
749 | \fBcpuchunks\fR parameters. A job never finishes unless there is at least one |
750 | non-cpuio job. | |
d60e92d1 AC |
751 | .TP |
752 | .B guasi | |
753 | The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface | |
cecbfd47 | 754 | approach to asynchronous I/O. |
d1429b5c AC |
755 | .br |
756 | See <http://www.xmailserver.org/guasi\-lib.html>. | |
d60e92d1 | 757 | .TP |
21b8aee8 | 758 | .B rdma |
85286c5c BVA |
759 | The RDMA I/O engine supports both RDMA memory semantics (RDMA_WRITE/RDMA_READ) |
760 | and channel semantics (Send/Recv) for the InfiniBand, RoCE and iWARP protocols. | |
21b8aee8 | 761 | .TP |
d60e92d1 AC |
762 | .B external |
763 | Loads an external I/O engine object file. Append the engine filename as | |
764 | `:\fIenginepath\fR'. | |
d54fce84 DM |
765 | .TP |
766 | .B falloc | |
cecbfd47 | 767 | IO engine that does regular linux native fallocate call to simulate data |
d54fce84 DM |
768 | transfer as fio ioengine |
769 | .br | |
770 | DDIR_READ does fallocate(,mode = FALLOC_FL_KEEP_SIZE,) | |
771 | .br | |
0981fd71 | 772 | DIR_WRITE does fallocate(,mode = 0) |
d54fce84 DM |
773 | .br |
774 | DDIR_TRIM does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE) | |
775 | .TP | |
776 | .B e4defrag | |
777 | IO engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate defragment activity | |
778 | request to DDIR_WRITE event | |
0d978694 DAG |
779 | .TP |
780 | .B rbd | |
ff6bb260 SL |
781 | IO engine supporting direct access to Ceph Rados Block Devices (RBD) via librbd |
782 | without the need to use the kernel rbd driver. This ioengine defines engine specific | |
0d978694 | 783 | options. |
a7c386f4 | 784 | .TP |
785 | .B gfapi | |
cc47f094 | 786 | Using Glusterfs libgfapi sync interface to direct access to Glusterfs volumes without |
787 | having to go through FUSE. This ioengine defines engine specific | |
788 | options. | |
789 | .TP | |
790 | .B gfapi_async | |
791 | Using Glusterfs libgfapi async interface to direct access to Glusterfs volumes without | |
a7c386f4 | 792 | having to go through FUSE. This ioengine defines engine specific |
793 | options. | |
1b10477b | 794 | .TP |
b74e419e MM |
795 | .B libhdfs |
796 | Read and write through Hadoop (HDFS). The \fBfilename\fR option is used to | |
797 | specify host,port of the hdfs name-node to connect. This engine interprets | |
798 | offsets a little differently. In HDFS, files once created cannot be modified. | |
799 | So random writes are not possible. To imitate this, libhdfs engine expects | |
800 | bunch of small files to be created over HDFS, and engine will randomly pick a | |
801 | file out of those files based on the offset generated by fio backend. (see the | |
802 | example job file to create such files, use rw=write option). Please note, you | |
803 | might want to set necessary environment variables to work with hdfs/libhdfs | |
804 | properly. | |
65fa28ca DE |
805 | .TP |
806 | .B mtd | |
807 | Read, write and erase an MTD character device (e.g., /dev/mtd0). Discards are | |
808 | treated as erases. Depending on the underlying device type, the I/O may have | |
809 | to go in a certain pattern, e.g., on NAND, writing sequentially to erase blocks | |
169c098d | 810 | and discarding before overwriting. The trimwrite mode works well for this |
65fa28ca | 811 | constraint. |
5c4ef02e JA |
812 | .TP |
813 | .B pmemblk | |
a12fc8b2 RE |
814 | Read and write using filesystem DAX to a file on a filesystem mounted with |
815 | DAX on a persistent memory device through the NVML libpmemblk library. | |
104ee4de DJ |
816 | .TP |
817 | .B dev-dax | |
a12fc8b2 RE |
818 | Read and write using device DAX to a persistent memory device |
819 | (e.g., /dev/dax0.0) through the NVML libpmem library. | |
d60e92d1 | 820 | .RE |
595e1734 | 821 | .P |
d60e92d1 AC |
822 | .RE |
823 | .TP | |
824 | .BI iodepth \fR=\fPint | |
8489dae4 SK |
825 | Number of I/O units to keep in flight against the file. Note that increasing |
826 | iodepth beyond 1 will not affect synchronous ioengines (except for small | |
cf145d90 | 827 | degress when verify_async is in use). Even async engines may impose OS |
ee72ca09 JA |
828 | restrictions causing the desired depth not to be achieved. This may happen on |
829 | Linux when using libaio and not setting \fBdirect\fR=1, since buffered IO is | |
830 | not async on that OS. Keep an eye on the IO depth distribution in the | |
831 | fio output to verify that the achieved depth is as expected. Default: 1. | |
d60e92d1 | 832 | .TP |
e63a0b2f RP |
833 | .BI iodepth_batch \fR=\fPint "\fR,\fP iodepth_batch_submit" \fR=\fPint |
834 | This defines how many pieces of IO to submit at once. It defaults to 1 | |
835 | which means that we submit each IO as soon as it is available, but can | |
836 | be raised to submit bigger batches of IO at the time. If it is set to 0 | |
837 | the \fBiodepth\fR value will be used. | |
d60e92d1 | 838 | .TP |
82407585 | 839 | .BI iodepth_batch_complete_min \fR=\fPint "\fR,\fP iodepth_batch_complete" \fR=\fPint |
3ce9dcaf JA |
840 | This defines how many pieces of IO to retrieve at once. It defaults to 1 which |
841 | means that we'll ask for a minimum of 1 IO in the retrieval process from the | |
842 | kernel. The IO retrieval will go on until we hit the limit set by | |
843 | \fBiodepth_low\fR. If this variable is set to 0, then fio will always check for | |
844 | completed events before queuing more IO. This helps reduce IO latency, at the | |
845 | cost of more retrieval system calls. | |
846 | .TP | |
82407585 RP |
847 | .BI iodepth_batch_complete_max \fR=\fPint |
848 | This defines maximum pieces of IO to | |
849 | retrieve at once. This variable should be used along with | |
850 | \fBiodepth_batch_complete_min\fR=int variable, specifying the range | |
851 | of min and max amount of IO which should be retrieved. By default | |
852 | it is equal to \fBiodepth_batch_complete_min\fR value. | |
853 | ||
854 | Example #1: | |
855 | .RS | |
856 | .RS | |
857 | \fBiodepth_batch_complete_min\fR=1 | |
858 | .LP | |
859 | \fBiodepth_batch_complete_max\fR=<iodepth> | |
860 | .RE | |
861 | ||
4e7a8814 | 862 | which means that we will retrieve at least 1 IO and up to the |
82407585 RP |
863 | whole submitted queue depth. If none of IO has been completed |
864 | yet, we will wait. | |
865 | ||
866 | Example #2: | |
867 | .RS | |
868 | \fBiodepth_batch_complete_min\fR=0 | |
869 | .LP | |
870 | \fBiodepth_batch_complete_max\fR=<iodepth> | |
871 | .RE | |
872 | ||
873 | which means that we can retrieve up to the whole submitted | |
874 | queue depth, but if none of IO has been completed yet, we will | |
875 | NOT wait and immediately exit the system call. In this example | |
876 | we simply do polling. | |
877 | .RE | |
878 | .TP | |
d60e92d1 AC |
879 | .BI iodepth_low \fR=\fPint |
880 | Low watermark indicating when to start filling the queue again. Default: | |
ff6bb260 | 881 | \fBiodepth\fR. |
d60e92d1 | 882 | .TP |
1ad01bd1 JA |
883 | .BI io_submit_mode \fR=\fPstr |
884 | This option controls how fio submits the IO to the IO engine. The default is | |
885 | \fBinline\fR, which means that the fio job threads submit and reap IO directly. | |
886 | If set to \fBoffload\fR, the job threads will offload IO submission to a | |
887 | dedicated pool of IO threads. This requires some coordination and thus has a | |
888 | bit of extra overhead, especially for lower queue depth IO where it can | |
889 | increase latencies. The benefit is that fio can manage submission rates | |
890 | independently of the device completion rates. This avoids skewed latency | |
891 | reporting if IO gets back up on the device side (the coordinated omission | |
892 | problem). | |
893 | .TP | |
d60e92d1 AC |
894 | .BI direct \fR=\fPbool |
895 | If true, use non-buffered I/O (usually O_DIRECT). Default: false. | |
896 | .TP | |
d01612f3 CM |
897 | .BI atomic \fR=\fPbool |
898 | If value is true, attempt to use atomic direct IO. Atomic writes are guaranteed | |
899 | to be stable once acknowledged by the operating system. Only Linux supports | |
900 | O_ATOMIC right now. | |
901 | .TP | |
d60e92d1 AC |
902 | .BI buffered \fR=\fPbool |
903 | If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter. | |
904 | Default: true. | |
905 | .TP | |
f7fa2653 | 906 | .BI offset \fR=\fPint |
d60e92d1 AC |
907 | Offset in the file to start I/O. Data before the offset will not be touched. |
908 | .TP | |
591e9e06 JA |
909 | .BI offset_increment \fR=\fPint |
910 | If this is provided, then the real offset becomes the | |
69bdd6ba JH |
911 | offset + offset_increment * thread_number, where the thread number is a |
912 | counter that starts at 0 and is incremented for each sub-job (i.e. when | |
913 | numjobs option is specified). This option is useful if there are several jobs | |
914 | which are intended to operate on a file in parallel disjoint segments, with | |
915 | even spacing between the starting points. | |
591e9e06 | 916 | .TP |
ddf24e42 JA |
917 | .BI number_ios \fR=\fPint |
918 | Fio will normally perform IOs until it has exhausted the size of the region | |
919 | set by \fBsize\fR, or if it exhaust the allocated time (or hits an error | |
920 | condition). With this setting, the range/size can be set independently of | |
921 | the number of IOs to perform. When fio reaches this number, it will exit | |
be3fec7d JA |
922 | normally and report status. Note that this does not extend the amount |
923 | of IO that will be done, it will only stop fio if this condition is met | |
924 | before other end-of-job criteria. | |
ddf24e42 | 925 | .TP |
d60e92d1 | 926 | .BI fsync \fR=\fPint |
d1429b5c AC |
927 | How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If |
928 | 0, don't sync. Default: 0. | |
d60e92d1 | 929 | .TP |
5f9099ea JA |
930 | .BI fdatasync \fR=\fPint |
931 | Like \fBfsync\fR, but uses \fBfdatasync\fR\|(2) instead to only sync the | |
932 | data parts of the file. Default: 0. | |
933 | .TP | |
fa769d44 SW |
934 | .BI write_barrier \fR=\fPint |
935 | Make every Nth write a barrier write. | |
936 | .TP | |
e76b1da4 | 937 | .BI sync_file_range \fR=\fPstr:int |
ccc2b328 SW |
938 | Use \fBsync_file_range\fR\|(2) for every \fRval\fP number of write operations. Fio will |
939 | track range of writes that have happened since the last \fBsync_file_range\fR\|(2) call. | |
e76b1da4 JA |
940 | \fRstr\fP can currently be one or more of: |
941 | .RS | |
942 | .TP | |
943 | .B wait_before | |
944 | SYNC_FILE_RANGE_WAIT_BEFORE | |
945 | .TP | |
946 | .B write | |
947 | SYNC_FILE_RANGE_WRITE | |
948 | .TP | |
949 | .B wait_after | |
950 | SYNC_FILE_RANGE_WRITE | |
951 | .TP | |
952 | .RE | |
953 | .P | |
954 | So if you do sync_file_range=wait_before,write:8, fio would use | |
955 | \fBSYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE\fP for every 8 writes. | |
ccc2b328 | 956 | Also see the \fBsync_file_range\fR\|(2) man page. This option is Linux specific. |
e76b1da4 | 957 | .TP |
d60e92d1 | 958 | .BI overwrite \fR=\fPbool |
d1429b5c | 959 | If writing, setup the file first and do overwrites. Default: false. |
d60e92d1 AC |
960 | .TP |
961 | .BI end_fsync \fR=\fPbool | |
dbd11ead | 962 | Sync file contents when a write stage has completed. Default: false. |
d60e92d1 AC |
963 | .TP |
964 | .BI fsync_on_close \fR=\fPbool | |
965 | If true, sync file contents on close. This differs from \fBend_fsync\fR in that | |
d1429b5c | 966 | it will happen on every close, not just at the end of the job. Default: false. |
d60e92d1 | 967 | .TP |
d60e92d1 AC |
968 | .BI rwmixread \fR=\fPint |
969 | Percentage of a mixed workload that should be reads. Default: 50. | |
970 | .TP | |
971 | .BI rwmixwrite \fR=\fPint | |
d1429b5c | 972 | Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and |
c35dd7a6 JA |
973 | \fBrwmixwrite\fR are given and do not sum to 100%, the latter of the two |
974 | overrides the first. This may interfere with a given rate setting, if fio is | |
975 | asked to limit reads or writes to a certain rate. If that is the case, then | |
976 | the distribution may be skewed. Default: 50. | |
d60e92d1 | 977 | .TP |
92d42d69 JA |
978 | .BI random_distribution \fR=\fPstr:float |
979 | By default, fio will use a completely uniform random distribution when asked | |
980 | to perform random IO. Sometimes it is useful to skew the distribution in | |
981 | specific ways, ensuring that some parts of the data is more hot than others. | |
982 | Fio includes the following distribution models: | |
983 | .RS | |
984 | .TP | |
985 | .B random | |
986 | Uniform random distribution | |
987 | .TP | |
988 | .B zipf | |
989 | Zipf distribution | |
990 | .TP | |
991 | .B pareto | |
992 | Pareto distribution | |
993 | .TP | |
8116fd24 JA |
994 | .B gauss |
995 | Normal (gaussian) distribution | |
996 | .TP | |
e0a04ac1 JA |
997 | .B zoned |
998 | Zoned random distribution | |
999 | .TP | |
92d42d69 | 1000 | .RE |
8116fd24 JA |
1001 | When using a \fBzipf\fR or \fBpareto\fR distribution, an input value is also |
1002 | needed to define the access pattern. For \fBzipf\fR, this is the zipf theta. | |
1003 | For \fBpareto\fR, it's the pareto power. Fio includes a test program, genzipf, | |
1004 | that can be used visualize what the given input values will yield in terms of | |
1005 | hit rates. If you wanted to use \fBzipf\fR with a theta of 1.2, you would use | |
92d42d69 | 1006 | random_distribution=zipf:1.2 as the option. If a non-uniform model is used, |
8116fd24 JA |
1007 | fio will disable use of the random map. For the \fBgauss\fR distribution, a |
1008 | normal deviation is supplied as a value between 0 and 100. | |
e0a04ac1 JA |
1009 | .P |
1010 | .RS | |
1011 | For a \fBzoned\fR distribution, fio supports specifying percentages of IO | |
1012 | access that should fall within what range of the file or device. For example, | |
1013 | given a criteria of: | |
1014 | .P | |
1015 | .RS | |
1016 | 60% of accesses should be to the first 10% | |
1017 | .RE | |
1018 | .RS | |
1019 | 30% of accesses should be to the next 20% | |
1020 | .RE | |
1021 | .RS | |
1022 | 8% of accesses should be to to the next 30% | |
1023 | .RE | |
1024 | .RS | |
1025 | 2% of accesses should be to the next 40% | |
1026 | .RE | |
1027 | .P | |
1028 | we can define that through zoning of the random accesses. For the above | |
1029 | example, the user would do: | |
1030 | .P | |
1031 | .RS | |
1032 | .B random_distribution=zoned:60/10:30/20:8/30:2/40 | |
1033 | .RE | |
1034 | .P | |
1035 | similarly to how \fBbssplit\fR works for setting ranges and percentages of block | |
1036 | sizes. Like \fBbssplit\fR, it's possible to specify separate zones for reads, | |
1037 | writes, and trims. If just one set is given, it'll apply to all of them. | |
1038 | .RE | |
92d42d69 | 1039 | .TP |
6d500c2e | 1040 | .BI percentage_random \fR=\fPint[,int][,int] |
211c9b89 JA |
1041 | For a random workload, set how big a percentage should be random. This defaults |
1042 | to 100%, in which case the workload is fully random. It can be set from | |
1043 | anywhere from 0 to 100. Setting it to 0 would make the workload fully | |
d9472271 JA |
1044 | sequential. It is possible to set different values for reads, writes, and |
1045 | trim. To do so, simply use a comma separated list. See \fBblocksize\fR. | |
211c9b89 | 1046 | .TP |
d60e92d1 AC |
1047 | .B norandommap |
1048 | Normally \fBfio\fR will cover every block of the file when doing random I/O. If | |
1049 | this parameter is given, a new offset will be chosen without looking at past | |
1050 | I/O history. This parameter is mutually exclusive with \fBverify\fR. | |
1051 | .TP | |
744492c9 | 1052 | .BI softrandommap \fR=\fPbool |
3ce9dcaf JA |
1053 | See \fBnorandommap\fR. If fio runs with the random block map enabled and it |
1054 | fails to allocate the map, if this option is set it will continue without a | |
1055 | random block map. As coverage will not be as complete as with random maps, this | |
1056 | option is disabled by default. | |
1057 | .TP | |
e8b1961d JA |
1058 | .BI random_generator \fR=\fPstr |
1059 | Fio supports the following engines for generating IO offsets for random IO: | |
1060 | .RS | |
1061 | .TP | |
1062 | .B tausworthe | |
1063 | Strong 2^88 cycle random number generator | |
1064 | .TP | |
1065 | .B lfsr | |
1066 | Linear feedback shift register generator | |
1067 | .TP | |
c3546b53 JA |
1068 | .B tausworthe64 |
1069 | Strong 64-bit 2^258 cycle random number generator | |
1070 | .TP | |
e8b1961d JA |
1071 | .RE |
1072 | .P | |
1073 | Tausworthe is a strong random number generator, but it requires tracking on the | |
1074 | side if we want to ensure that blocks are only read or written once. LFSR | |
1075 | guarantees that we never generate the same offset twice, and it's also less | |
1076 | computationally expensive. It's not a true random generator, however, though | |
1077 | for IO purposes it's typically good enough. LFSR only works with single block | |
1078 | sizes, not with workloads that use multiple block sizes. If used with such a | |
3bb85e84 JA |
1079 | workload, fio may read or write some blocks multiple times. The default |
1080 | value is tausworthe, unless the required space exceeds 2^32 blocks. If it does, | |
1081 | then tausworthe64 is selected automatically. | |
e8b1961d | 1082 | .TP |
d60e92d1 | 1083 | .BI nice \fR=\fPint |
ccc2b328 | 1084 | Run job with given nice value. See \fBnice\fR\|(2). |
d60e92d1 AC |
1085 | .TP |
1086 | .BI prio \fR=\fPint | |
1087 | Set I/O priority value of this job between 0 (highest) and 7 (lowest). See | |
ccc2b328 | 1088 | \fBionice\fR\|(1). |
d60e92d1 AC |
1089 | .TP |
1090 | .BI prioclass \fR=\fPint | |
ccc2b328 | 1091 | Set I/O priority class. See \fBionice\fR\|(1). |
d60e92d1 AC |
1092 | .TP |
1093 | .BI thinktime \fR=\fPint | |
1094 | Stall job for given number of microseconds between issuing I/Os. | |
1095 | .TP | |
1096 | .BI thinktime_spin \fR=\fPint | |
1097 | Pretend to spend CPU time for given number of microseconds, sleeping the rest | |
1098 | of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set. | |
1099 | .TP | |
1100 | .BI thinktime_blocks \fR=\fPint | |
4d01ece6 JA |
1101 | Only valid if thinktime is set - control how many blocks to issue, before |
1102 | waiting \fBthinktime\fR microseconds. If not set, defaults to 1 which will | |
1103 | make fio wait \fBthinktime\fR microseconds after every block. This | |
1104 | effectively makes any queue depth setting redundant, since no more than 1 IO | |
1105 | will be queued before we have to complete it and do our thinktime. In other | |
1106 | words, this setting effectively caps the queue depth if the latter is larger. | |
d60e92d1 AC |
1107 | Default: 1. |
1108 | .TP | |
6d500c2e | 1109 | .BI rate \fR=\fPint[,int][,int] |
c35dd7a6 JA |
1110 | Cap bandwidth used by this job. The number is in bytes/sec, the normal postfix |
1111 | rules apply. You can use \fBrate\fR=500k to limit reads and writes to 500k each, | |
6d500c2e RE |
1112 | or you can specify reads, write, and trim limits separately. |
1113 | Using \fBrate\fR=1m,500k would | |
1114 | limit reads to 1MiB/sec and writes to 500KiB/sec. Capping only reads or writes | |
c35dd7a6 | 1115 | can be done with \fBrate\fR=,500k or \fBrate\fR=500k,. The former will only |
6d500c2e | 1116 | limit writes (to 500KiB/sec), the latter will only limit reads. |
d60e92d1 | 1117 | .TP |
6d500c2e | 1118 | .BI rate_min \fR=\fPint[,int][,int] |
d60e92d1 | 1119 | Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth. |
c35dd7a6 | 1120 | Failing to meet this requirement will cause the job to exit. The same format |
6d500c2e | 1121 | as \fBrate\fR is used for read vs write vs trim separation. |
d60e92d1 | 1122 | .TP |
6d500c2e | 1123 | .BI rate_iops \fR=\fPint[,int][,int] |
c35dd7a6 JA |
1124 | Cap the bandwidth to this number of IOPS. Basically the same as rate, just |
1125 | specified independently of bandwidth. The same format as \fBrate\fR is used for | |
6d500c2e | 1126 | read vs write vs trim separation. If \fBblocksize\fR is a range, the smallest block |
c35dd7a6 | 1127 | size is used as the metric. |
d60e92d1 | 1128 | .TP |
6d500c2e | 1129 | .BI rate_iops_min \fR=\fPint[,int][,int] |
c35dd7a6 | 1130 | If this rate of I/O is not met, the job will exit. The same format as \fBrate\fR |
6d500c2e | 1131 | is used for read vs write vs trim separation. |
d60e92d1 | 1132 | .TP |
6de65959 JA |
1133 | .BI rate_process \fR=\fPstr |
1134 | This option controls how fio manages rated IO submissions. The default is | |
1135 | \fBlinear\fR, which submits IO in a linear fashion with fixed delays between | |
1136 | IOs that gets adjusted based on IO completion rates. If this is set to | |
1137 | \fBpoisson\fR, fio will submit IO based on a more real world random request | |
1138 | flow, known as the Poisson process | |
5d02b083 JA |
1139 | (https://en.wikipedia.org/wiki/Poisson_process). The lambda will be |
1140 | 10^6 / IOPS for the given workload. | |
ff6bb260 | 1141 | .TP |
6d428bcd JA |
1142 | .BI rate_cycle \fR=\fPint |
1143 | Average bandwidth for \fBrate\fR and \fBrate_min\fR over this number of | |
d60e92d1 AC |
1144 | milliseconds. Default: 1000ms. |
1145 | .TP | |
3e260a46 JA |
1146 | .BI latency_target \fR=\fPint |
1147 | If set, fio will attempt to find the max performance point that the given | |
1148 | workload will run at while maintaining a latency below this target. The | |
1149 | values is given in microseconds. See \fBlatency_window\fR and | |
1150 | \fBlatency_percentile\fR. | |
1151 | .TP | |
1152 | .BI latency_window \fR=\fPint | |
1153 | Used with \fBlatency_target\fR to specify the sample window that the job | |
1154 | is run at varying queue depths to test the performance. The value is given | |
1155 | in microseconds. | |
1156 | .TP | |
1157 | .BI latency_percentile \fR=\fPfloat | |
1158 | The percentage of IOs that must fall within the criteria specified by | |
1159 | \fBlatency_target\fR and \fBlatency_window\fR. If not set, this defaults | |
1160 | to 100.0, meaning that all IOs must be equal or below to the value set | |
1161 | by \fBlatency_target\fR. | |
1162 | .TP | |
15501535 JA |
1163 | .BI max_latency \fR=\fPint |
1164 | If set, fio will exit the job if it exceeds this maximum latency. It will exit | |
1165 | with an ETIME error. | |
1166 | .TP | |
d60e92d1 AC |
1167 | .BI cpumask \fR=\fPint |
1168 | Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job | |
1169 | may run on. See \fBsched_setaffinity\fR\|(2). | |
1170 | .TP | |
1171 | .BI cpus_allowed \fR=\fPstr | |
1172 | Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers. | |
1173 | .TP | |
c2acfbac JA |
1174 | .BI cpus_allowed_policy \fR=\fPstr |
1175 | Set the policy of how fio distributes the CPUs specified by \fBcpus_allowed\fR | |
1176 | or \fBcpumask\fR. Two policies are supported: | |
1177 | .RS | |
1178 | .RS | |
1179 | .TP | |
1180 | .B shared | |
1181 | All jobs will share the CPU set specified. | |
1182 | .TP | |
1183 | .B split | |
1184 | Each job will get a unique CPU from the CPU set. | |
1185 | .RE | |
1186 | .P | |
1187 | \fBshared\fR is the default behaviour, if the option isn't specified. If | |
ada083cd JA |
1188 | \fBsplit\fR is specified, then fio will assign one cpu per job. If not enough |
1189 | CPUs are given for the jobs listed, then fio will roundrobin the CPUs in | |
1190 | the set. | |
c2acfbac JA |
1191 | .RE |
1192 | .P | |
1193 | .TP | |
d0b937ed | 1194 | .BI numa_cpu_nodes \fR=\fPstr |
cecbfd47 | 1195 | Set this job running on specified NUMA nodes' CPUs. The arguments allow |
d0b937ed YR |
1196 | comma delimited list of cpu numbers, A-B ranges, or 'all'. |
1197 | .TP | |
1198 | .BI numa_mem_policy \fR=\fPstr | |
1199 | Set this job's memory policy and corresponding NUMA nodes. Format of | |
cecbfd47 | 1200 | the arguments: |
d0b937ed YR |
1201 | .RS |
1202 | .TP | |
1203 | .B <mode>[:<nodelist>] | |
1204 | .TP | |
1205 | .B mode | |
1206 | is one of the following memory policy: | |
1207 | .TP | |
1208 | .B default, prefer, bind, interleave, local | |
1209 | .TP | |
1210 | .RE | |
1211 | For \fBdefault\fR and \fBlocal\fR memory policy, no \fBnodelist\fR is | |
1212 | needed to be specified. For \fBprefer\fR, only one node is | |
1213 | allowed. For \fBbind\fR and \fBinterleave\fR, \fBnodelist\fR allows | |
1214 | comma delimited list of numbers, A-B ranges, or 'all'. | |
1215 | .TP | |
23ed19b0 CE |
1216 | .BI startdelay \fR=\fPirange |
1217 | Delay start of job for the specified number of seconds. Supports all time | |
1218 | suffixes to allow specification of hours, minutes, seconds and | |
bd66aa2c | 1219 | milliseconds - seconds are the default if a unit is omitted. |
23ed19b0 CE |
1220 | Can be given as a range which causes each thread to choose randomly out of the |
1221 | range. | |
d60e92d1 AC |
1222 | .TP |
1223 | .BI runtime \fR=\fPint | |
1224 | Terminate processing after the specified number of seconds. | |
1225 | .TP | |
1226 | .B time_based | |
1227 | If given, run for the specified \fBruntime\fR duration even if the files are | |
1228 | completely read or written. The same workload will be repeated as many times | |
1229 | as \fBruntime\fR allows. | |
1230 | .TP | |
901bb994 JA |
1231 | .BI ramp_time \fR=\fPint |
1232 | If set, fio will run the specified workload for this amount of time before | |
1233 | logging any performance numbers. Useful for letting performance settle before | |
1234 | logging results, thus minimizing the runtime required for stable results. Note | |
c35dd7a6 JA |
1235 | that the \fBramp_time\fR is considered lead in time for a job, thus it will |
1236 | increase the total runtime if a special timeout or runtime is specified. | |
901bb994 | 1237 | .TP |
39c7a2ca VF |
1238 | .BI steadystate \fR=\fPstr:float "\fR,\fP ss" \fR=\fPstr:float |
1239 | Define the criterion and limit for assessing steady state performance. The | |
1240 | first parameter designates the criterion whereas the second parameter sets the | |
1241 | threshold. When the criterion falls below the threshold for the specified | |
1242 | duration, the job will stop. For example, iops_slope:0.1% will direct fio | |
1243 | to terminate the job when the least squares regression slope falls below 0.1% | |
1244 | of the mean IOPS. If group_reporting is enabled this will apply to all jobs in | |
1245 | the group. All assessments are carried out using only data from the rolling | |
1246 | collection window. Threshold limits can be expressed as a fixed value or as a | |
1247 | percentage of the mean in the collection window. Below are the available steady | |
1248 | state assessment criteria. | |
1249 | .RS | |
1250 | .RS | |
1251 | .TP | |
1252 | .B iops | |
1253 | Collect IOPS data. Stop the job if all individual IOPS measurements are within | |
1254 | the specified limit of the mean IOPS (e.g., iops:2 means that all individual | |
1255 | IOPS values must be within 2 of the mean, whereas iops:0.2% means that all | |
1256 | individual IOPS values must be within 0.2% of the mean IOPS to terminate the | |
1257 | job). | |
1258 | .TP | |
1259 | .B iops_slope | |
1260 | Collect IOPS data and calculate the least squares regression slope. Stop the | |
1261 | job if the slope falls below the specified limit. | |
1262 | .TP | |
1263 | .B bw | |
1264 | Collect bandwidth data. Stop the job if all individual bandwidth measurements | |
1265 | are within the specified limit of the mean bandwidth. | |
1266 | .TP | |
1267 | .B bw_slope | |
1268 | Collect bandwidth data and calculate the least squares regression slope. Stop | |
1269 | the job if the slope falls below the specified limit. | |
1270 | .RE | |
1271 | .RE | |
1272 | .TP | |
1273 | .BI steadystate_duration \fR=\fPtime "\fR,\fP ss_dur" \fR=\fPtime | |
1274 | A rolling window of this duration will be used to judge whether steady state | |
1275 | has been reached. Data will be collected once per second. The default is 0 | |
1276 | which disables steady state detection. | |
1277 | .TP | |
1278 | .BI steadystate_ramp_time \fR=\fPtime "\fR,\fP ss_ramp" \fR=\fPtime | |
1279 | Allow the job to run for the specified duration before beginning data collection | |
1280 | for checking the steady state job termination criterion. The default is 0. | |
1281 | .TP | |
d60e92d1 AC |
1282 | .BI invalidate \fR=\fPbool |
1283 | Invalidate buffer-cache for the file prior to starting I/O. Default: true. | |
1284 | .TP | |
1285 | .BI sync \fR=\fPbool | |
1286 | Use synchronous I/O for buffered writes. For the majority of I/O engines, | |
d1429b5c | 1287 | this means using O_SYNC. Default: false. |
d60e92d1 AC |
1288 | .TP |
1289 | .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr | |
1290 | Allocation method for I/O unit buffer. Allowed values are: | |
1291 | .RS | |
1292 | .RS | |
1293 | .TP | |
1294 | .B malloc | |
38f8c318 | 1295 | Allocate memory with \fBmalloc\fR\|(3). Default memory type. |
d60e92d1 AC |
1296 | .TP |
1297 | .B shm | |
ccc2b328 | 1298 | Use shared memory buffers allocated through \fBshmget\fR\|(2). |
d60e92d1 AC |
1299 | .TP |
1300 | .B shmhuge | |
1301 | Same as \fBshm\fR, but use huge pages as backing. | |
1302 | .TP | |
1303 | .B mmap | |
ccc2b328 | 1304 | Use \fBmmap\fR\|(2) for allocation. Uses anonymous memory unless a filename |
d60e92d1 AC |
1305 | is given after the option in the format `:\fIfile\fR'. |
1306 | .TP | |
1307 | .B mmaphuge | |
1308 | Same as \fBmmap\fR, but use huge files as backing. | |
09c782bb JA |
1309 | .TP |
1310 | .B mmapshared | |
1311 | Same as \fBmmap\fR, but use a MMAP_SHARED mapping. | |
03553853 YR |
1312 | .TP |
1313 | .B cudamalloc | |
1314 | Use GPU memory as the buffers for GPUDirect RDMA benchmark. The ioengine must be \fBrdma\fR. | |
d60e92d1 AC |
1315 | .RE |
1316 | .P | |
1317 | The amount of memory allocated is the maximum allowed \fBblocksize\fR for the | |
1318 | job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work, | |
1319 | the system must have free huge pages allocated. \fBmmaphuge\fR also needs to | |
2e266ba6 JA |
1320 | have hugetlbfs mounted, and \fIfile\fR must point there. At least on Linux, |
1321 | huge pages must be manually allocated. See \fB/proc/sys/vm/nr_hugehages\fR | |
1322 | and the documentation for that. Normally you just need to echo an appropriate | |
1323 | number, eg echoing 8 will ensure that the OS has 8 huge pages ready for | |
1324 | use. | |
d60e92d1 AC |
1325 | .RE |
1326 | .TP | |
d392365e | 1327 | .BI iomem_align \fR=\fPint "\fR,\fP mem_align" \fR=\fPint |
cecbfd47 | 1328 | This indicates the memory alignment of the IO memory buffers. Note that the |
d529ee19 JA |
1329 | given alignment is applied to the first IO unit buffer, if using \fBiodepth\fR |
1330 | the alignment of the following buffers are given by the \fBbs\fR used. In | |
1331 | other words, if using a \fBbs\fR that is a multiple of the page sized in the | |
1332 | system, all buffers will be aligned to this value. If using a \fBbs\fR that | |
1333 | is not page aligned, the alignment of subsequent IO memory buffers is the | |
1334 | sum of the \fBiomem_align\fR and \fBbs\fR used. | |
1335 | .TP | |
f7fa2653 | 1336 | .BI hugepage\-size \fR=\fPint |
d60e92d1 | 1337 | Defines the size of a huge page. Must be at least equal to the system setting. |
6d500c2e | 1338 | Should be a multiple of 1MiB. Default: 4MiB. |
d60e92d1 AC |
1339 | .TP |
1340 | .B exitall | |
1341 | Terminate all jobs when one finishes. Default: wait for each job to finish. | |
1342 | .TP | |
f9cafb12 JA |
1343 | .B exitall_on_error \fR=\fPbool |
1344 | Terminate all jobs if one job finishes in error. Default: wait for each job | |
1345 | to finish. | |
1346 | .TP | |
d60e92d1 | 1347 | .BI bwavgtime \fR=\fPint |
a47591e4 JA |
1348 | Average bandwidth calculations over the given time in milliseconds. If the job |
1349 | also does bandwidth logging through \fBwrite_bw_log\fR, then the minimum of | |
1350 | this option and \fBlog_avg_msec\fR will be used. Default: 500ms. | |
d60e92d1 | 1351 | .TP |
c8eeb9df | 1352 | .BI iopsavgtime \fR=\fPint |
a47591e4 JA |
1353 | Average IOPS calculations over the given time in milliseconds. If the job |
1354 | also does IOPS logging through \fBwrite_iops_log\fR, then the minimum of | |
1355 | this option and \fBlog_avg_msec\fR will be used. Default: 500ms. | |
c8eeb9df | 1356 | .TP |
d60e92d1 | 1357 | .BI create_serialize \fR=\fPbool |
d1429b5c | 1358 | If true, serialize file creation for the jobs. Default: true. |
d60e92d1 AC |
1359 | .TP |
1360 | .BI create_fsync \fR=\fPbool | |
ccc2b328 | 1361 | \fBfsync\fR\|(2) data file after creation. Default: true. |
d60e92d1 | 1362 | .TP |
6b7f6851 JA |
1363 | .BI create_on_open \fR=\fPbool |
1364 | If true, the files are not created until they are opened for IO by the job. | |
1365 | .TP | |
25460cf6 JA |
1366 | .BI create_only \fR=\fPbool |
1367 | If true, fio will only run the setup phase of the job. If files need to be | |
1368 | laid out or updated on disk, only that will be done. The actual job contents | |
1369 | are not executed. | |
1370 | .TP | |
2378826d JA |
1371 | .BI allow_file_create \fR=\fPbool |
1372 | If true, fio is permitted to create files as part of its workload. This is | |
1373 | the default behavior. If this option is false, then fio will error out if the | |
1374 | files it needs to use don't already exist. Default: true. | |
1375 | .TP | |
e81ecca3 JA |
1376 | .BI allow_mounted_write \fR=\fPbool |
1377 | If this isn't set, fio will abort jobs that are destructive (eg that write) | |
1378 | to what appears to be a mounted device or partition. This should help catch | |
1379 | creating inadvertently destructive tests, not realizing that the test will | |
1380 | destroy data on the mounted file system. Default: false. | |
1381 | .TP | |
e9f48479 JA |
1382 | .BI pre_read \fR=\fPbool |
1383 | If this is given, files will be pre-read into memory before starting the given | |
1384 | IO operation. This will also clear the \fR \fBinvalidate\fR flag, since it is | |
9c0d2241 JA |
1385 | pointless to pre-read and then drop the cache. This will only work for IO |
1386 | engines that are seekable, since they allow you to read the same data | |
1387 | multiple times. Thus it will not work on eg network or splice IO. | |
e9f48479 | 1388 | .TP |
d60e92d1 AC |
1389 | .BI unlink \fR=\fPbool |
1390 | Unlink job files when done. Default: false. | |
1391 | .TP | |
39c1c323 | 1392 | .BI unlink_each_loop \fR=\fPbool |
1393 | Unlink job files after each iteration or loop. Default: false. | |
1394 | .TP | |
d60e92d1 AC |
1395 | .BI loops \fR=\fPint |
1396 | Specifies the number of iterations (runs of the same workload) of this job. | |
1397 | Default: 1. | |
1398 | .TP | |
5e4c7118 JA |
1399 | .BI verify_only \fR=\fPbool |
1400 | Do not perform the specified workload, only verify data still matches previous | |
1401 | invocation of this workload. This option allows one to check data multiple | |
1402 | times at a later date without overwriting it. This option makes sense only for | |
1403 | workloads that write data, and does not support workloads with the | |
1404 | \fBtime_based\fR option set. | |
1405 | .TP | |
d60e92d1 AC |
1406 | .BI do_verify \fR=\fPbool |
1407 | Run the verify phase after a write phase. Only valid if \fBverify\fR is set. | |
1408 | Default: true. | |
1409 | .TP | |
1410 | .BI verify \fR=\fPstr | |
b638d82f RP |
1411 | Method of verifying file contents after each iteration of the job. Each |
1412 | verification method also implies verification of special header, which is | |
1413 | written to the beginning of each block. This header also includes meta | |
1414 | information, like offset of the block, block number, timestamp when block | |
1415 | was written, etc. \fBverify\fR=str can be combined with \fBverify_pattern\fR=str | |
1416 | option. The allowed values are: | |
d60e92d1 AC |
1417 | .RS |
1418 | .RS | |
1419 | .TP | |
ae3a5acc | 1420 | .B md5 crc16 crc32 crc32c crc32c-intel crc64 crc7 sha256 sha512 sha1 sha3-224 sha3-256 sha3-384 sha3-512 xxhash |
0539d758 JA |
1421 | Store appropriate checksum in the header of each block. crc32c-intel is |
1422 | hardware accelerated SSE4.2 driven, falls back to regular crc32c if | |
1423 | not supported by the system. | |
d60e92d1 AC |
1424 | .TP |
1425 | .B meta | |
b638d82f RP |
1426 | This option is deprecated, since now meta information is included in generic |
1427 | verification header and meta verification happens by default. For detailed | |
1428 | information see the description of the \fBverify\fR=str setting. This option | |
1429 | is kept because of compatibility's sake with old configurations. Do not use it. | |
d60e92d1 | 1430 | .TP |
59245381 JA |
1431 | .B pattern |
1432 | Verify a strict pattern. Normally fio includes a header with some basic | |
1433 | information and checksumming, but if this option is set, only the | |
1434 | specific pattern set with \fBverify_pattern\fR is verified. | |
1435 | .TP | |
d60e92d1 AC |
1436 | .B null |
1437 | Pretend to verify. Used for testing internals. | |
1438 | .RE | |
b892dc08 JA |
1439 | |
1440 | This option can be used for repeated burn-in tests of a system to make sure | |
1441 | that the written data is also correctly read back. If the data direction given | |
1442 | is a read or random read, fio will assume that it should verify a previously | |
1443 | written file. If the data direction includes any form of write, the verify will | |
1444 | be of the newly written data. | |
d60e92d1 AC |
1445 | .RE |
1446 | .TP | |
5c9323fb | 1447 | .BI verifysort \fR=\fPbool |
d60e92d1 AC |
1448 | If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to |
1449 | read them back in a sorted manner. Default: true. | |
1450 | .TP | |
fa769d44 SW |
1451 | .BI verifysort_nr \fR=\fPint |
1452 | Pre-load and sort verify blocks for a read workload. | |
1453 | .TP | |
f7fa2653 | 1454 | .BI verify_offset \fR=\fPint |
d60e92d1 | 1455 | Swap the verification header with data somewhere else in the block before |
d1429b5c | 1456 | writing. It is swapped back before verifying. |
d60e92d1 | 1457 | .TP |
f7fa2653 | 1458 | .BI verify_interval \fR=\fPint |
d60e92d1 AC |
1459 | Write the verification header for this number of bytes, which should divide |
1460 | \fBblocksize\fR. Default: \fBblocksize\fR. | |
1461 | .TP | |
996093bb JA |
1462 | .BI verify_pattern \fR=\fPstr |
1463 | If set, fio will fill the io buffers with this pattern. Fio defaults to filling | |
1464 | with totally random bytes, but sometimes it's interesting to fill with a known | |
1465 | pattern for io verification purposes. Depending on the width of the pattern, | |
1466 | fio will fill 1/2/3/4 bytes of the buffer at the time(it can be either a | |
1467 | decimal or a hex number). The verify_pattern if larger than a 32-bit quantity | |
1468 | has to be a hex number that starts with either "0x" or "0X". Use with | |
b638d82f | 1469 | \fBverify\fP=str. Also, verify_pattern supports %o format, which means that for |
4e7a8814 | 1470 | each block offset will be written and then verified back, e.g.: |
2fa5a241 RP |
1471 | .RS |
1472 | .RS | |
1473 | \fBverify_pattern\fR=%o | |
1474 | .RE | |
1475 | Or use combination of everything: | |
1476 | .LP | |
1477 | .RS | |
1478 | \fBverify_pattern\fR=0xff%o"abcd"-21 | |
1479 | .RE | |
1480 | .RE | |
996093bb | 1481 | .TP |
d60e92d1 AC |
1482 | .BI verify_fatal \fR=\fPbool |
1483 | If true, exit the job on the first observed verification failure. Default: | |
1484 | false. | |
1485 | .TP | |
b463e936 JA |
1486 | .BI verify_dump \fR=\fPbool |
1487 | If set, dump the contents of both the original data block and the data block we | |
1488 | read off disk to files. This allows later analysis to inspect just what kind of | |
ef71e317 | 1489 | data corruption occurred. Off by default. |
b463e936 | 1490 | .TP |
e8462bd8 JA |
1491 | .BI verify_async \fR=\fPint |
1492 | Fio will normally verify IO inline from the submitting thread. This option | |
1493 | takes an integer describing how many async offload threads to create for IO | |
1494 | verification instead, causing fio to offload the duty of verifying IO contents | |
c85c324c JA |
1495 | to one or more separate threads. If using this offload option, even sync IO |
1496 | engines can benefit from using an \fBiodepth\fR setting higher than 1, as it | |
1497 | allows them to have IO in flight while verifies are running. | |
e8462bd8 JA |
1498 | .TP |
1499 | .BI verify_async_cpus \fR=\fPstr | |
1500 | Tell fio to set the given CPU affinity on the async IO verification threads. | |
1501 | See \fBcpus_allowed\fP for the format used. | |
1502 | .TP | |
6f87418f JA |
1503 | .BI verify_backlog \fR=\fPint |
1504 | Fio will normally verify the written contents of a job that utilizes verify | |
1505 | once that job has completed. In other words, everything is written then | |
1506 | everything is read back and verified. You may want to verify continually | |
1507 | instead for a variety of reasons. Fio stores the meta data associated with an | |
1508 | IO block in memory, so for large verify workloads, quite a bit of memory would | |
092f707f DN |
1509 | be used up holding this meta data. If this option is enabled, fio will write |
1510 | only N blocks before verifying these blocks. | |
6f87418f JA |
1511 | .TP |
1512 | .BI verify_backlog_batch \fR=\fPint | |
1513 | Control how many blocks fio will verify if verify_backlog is set. If not set, | |
1514 | will default to the value of \fBverify_backlog\fR (meaning the entire queue is | |
ff6bb260 SL |
1515 | read back and verified). If \fBverify_backlog_batch\fR is less than |
1516 | \fBverify_backlog\fR then not all blocks will be verified, if | |
092f707f DN |
1517 | \fBverify_backlog_batch\fR is larger than \fBverify_backlog\fR, some blocks |
1518 | will be verified more than once. | |
6f87418f | 1519 | .TP |
fa769d44 SW |
1520 | .BI trim_percentage \fR=\fPint |
1521 | Number of verify blocks to discard/trim. | |
1522 | .TP | |
1523 | .BI trim_verify_zero \fR=\fPbool | |
1524 | Verify that trim/discarded blocks are returned as zeroes. | |
1525 | .TP | |
1526 | .BI trim_backlog \fR=\fPint | |
1527 | Trim after this number of blocks are written. | |
1528 | .TP | |
1529 | .BI trim_backlog_batch \fR=\fPint | |
1530 | Trim this number of IO blocks. | |
1531 | .TP | |
1532 | .BI experimental_verify \fR=\fPbool | |
1533 | Enable experimental verification. | |
1534 | .TP | |
ca09be4b JA |
1535 | .BI verify_state_save \fR=\fPbool |
1536 | When a job exits during the write phase of a verify workload, save its | |
1537 | current state. This allows fio to replay up until that point, if the | |
1538 | verify state is loaded for the verify read phase. | |
1539 | .TP | |
1540 | .BI verify_state_load \fR=\fPbool | |
1541 | If a verify termination trigger was used, fio stores the current write | |
1542 | state of each thread. This can be used at verification time so that fio | |
1543 | knows how far it should verify. Without this information, fio will run | |
1544 | a full verification pass, according to the settings in the job file used. | |
1545 | .TP | |
d392365e | 1546 | .B stonewall "\fR,\fP wait_for_previous" |
5982a925 | 1547 | Wait for preceding jobs in the job file to exit before starting this one. |
d60e92d1 AC |
1548 | \fBstonewall\fR implies \fBnew_group\fR. |
1549 | .TP | |
1550 | .B new_group | |
1551 | Start a new reporting group. If not given, all jobs in a file will be part | |
1552 | of the same reporting group, unless separated by a stonewall. | |
1553 | .TP | |
8243be59 JA |
1554 | .BI stats \fR=\fPbool |
1555 | By default, fio collects and shows final output results for all jobs that run. | |
1556 | If this option is set to 0, then fio will ignore it in the final stat output. | |
1557 | .TP | |
d60e92d1 | 1558 | .BI numjobs \fR=\fPint |
ff6bb260 | 1559 | Number of clones (processes/threads performing the same workload) of this job. |
d60e92d1 AC |
1560 | Default: 1. |
1561 | .TP | |
1562 | .B group_reporting | |
1563 | If set, display per-group reports instead of per-job when \fBnumjobs\fR is | |
1564 | specified. | |
1565 | .TP | |
1566 | .B thread | |
1567 | Use threads created with \fBpthread_create\fR\|(3) instead of processes created | |
1568 | with \fBfork\fR\|(2). | |
1569 | .TP | |
f7fa2653 | 1570 | .BI zonesize \fR=\fPint |
d60e92d1 AC |
1571 | Divide file into zones of the specified size in bytes. See \fBzoneskip\fR. |
1572 | .TP | |
fa769d44 SW |
1573 | .BI zonerange \fR=\fPint |
1574 | Give size of an IO zone. See \fBzoneskip\fR. | |
1575 | .TP | |
f7fa2653 | 1576 | .BI zoneskip \fR=\fPint |
d1429b5c | 1577 | Skip the specified number of bytes when \fBzonesize\fR bytes of data have been |
d60e92d1 AC |
1578 | read. |
1579 | .TP | |
1580 | .BI write_iolog \fR=\fPstr | |
5b42a488 SH |
1581 | Write the issued I/O patterns to the specified file. Specify a separate file |
1582 | for each job, otherwise the iologs will be interspersed and the file may be | |
1583 | corrupt. | |
d60e92d1 AC |
1584 | .TP |
1585 | .BI read_iolog \fR=\fPstr | |
1586 | Replay the I/O patterns contained in the specified file generated by | |
1587 | \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file. | |
1588 | .TP | |
64bbb865 DN |
1589 | .BI replay_no_stall \fR=\fPint |
1590 | While replaying I/O patterns using \fBread_iolog\fR the default behavior | |
1591 | attempts to respect timing information between I/Os. Enabling | |
1592 | \fBreplay_no_stall\fR causes I/Os to be replayed as fast as possible while | |
1593 | still respecting ordering. | |
1594 | .TP | |
d1c46c04 DN |
1595 | .BI replay_redirect \fR=\fPstr |
1596 | While replaying I/O patterns using \fBread_iolog\fR the default behavior | |
1597 | is to replay the IOPS onto the major/minor device that each IOP was recorded | |
1598 | from. Setting \fBreplay_redirect\fR causes all IOPS to be replayed onto the | |
1599 | single specified device regardless of the device it was recorded from. | |
1600 | .TP | |
0c63576e JA |
1601 | .BI replay_align \fR=\fPint |
1602 | Force alignment of IO offsets and lengths in a trace to this power of 2 value. | |
1603 | .TP | |
1604 | .BI replay_scale \fR=\fPint | |
1605 | Scale sector offsets down by this factor when replaying traces. | |
1606 | .TP | |
3a5db920 JA |
1607 | .BI per_job_logs \fR=\fPbool |
1608 | If set, this generates bw/clat/iops log with per file private filenames. If | |
1609 | not set, jobs with identical names will share the log filename. Default: true. | |
1610 | .TP | |
836bad52 | 1611 | .BI write_bw_log \fR=\fPstr |
d23ae827 OS |
1612 | If given, write a bandwidth log for this job. Can be used to store data of the |
1613 | bandwidth of the jobs in their lifetime. The included fio_generate_plots script | |
1614 | uses gnuplot to turn these text files into nice graphs. See \fBwrite_lat_log\fR | |
1615 | for behaviour of given filename. For this option, the postfix is _bw.x.log, | |
1616 | where x is the index of the job (1..N, where N is the number of jobs). If | |
1617 | \fBper_job_logs\fR is false, then the filename will not include the job index. | |
1618 | See the \fBLOG FILE FORMATS\fR | |
a3ae5b05 | 1619 | section. |
d60e92d1 | 1620 | .TP |
836bad52 | 1621 | .BI write_lat_log \fR=\fPstr |
901bb994 | 1622 | Same as \fBwrite_bw_log\fR, but writes I/O completion latencies. If no |
8ad3b3dd JA |
1623 | filename is given with this option, the default filename of |
1624 | "jobname_type.x.log" is used, where x is the index of the job (1..N, where | |
1625 | N is the number of jobs). Even if the filename is given, fio will still | |
3a5db920 | 1626 | append the type of log. If \fBper_job_logs\fR is false, then the filename will |
a3ae5b05 | 1627 | not include the job index. See the \fBLOG FILE FORMATS\fR section. |
901bb994 | 1628 | .TP |
1e613c9c KC |
1629 | .BI write_hist_log \fR=\fPstr |
1630 | Same as \fBwrite_lat_log\fR, but writes I/O completion latency histograms. If | |
1631 | no filename is given with this option, the default filename of | |
1632 | "jobname_clat_hist.x.log" is used, where x is the index of the job (1..N, where | |
1633 | N is the number of jobs). Even if the filename is given, fio will still append | |
1634 | the type of log. If \fBper_job_logs\fR is false, then the filename will not | |
1635 | include the job index. See the \fBLOG FILE FORMATS\fR section. | |
1636 | .TP | |
c8eeb9df JA |
1637 | .BI write_iops_log \fR=\fPstr |
1638 | Same as \fBwrite_bw_log\fR, but writes IOPS. If no filename is given with this | |
8ad3b3dd JA |
1639 | option, the default filename of "jobname_type.x.log" is used, where x is the |
1640 | index of the job (1..N, where N is the number of jobs). Even if the filename | |
3a5db920 | 1641 | is given, fio will still append the type of log. If \fBper_job_logs\fR is false, |
a3ae5b05 JA |
1642 | then the filename will not include the job index. See the \fBLOG FILE FORMATS\fR |
1643 | section. | |
c8eeb9df | 1644 | .TP |
b8bc8cba JA |
1645 | .BI log_avg_msec \fR=\fPint |
1646 | By default, fio will log an entry in the iops, latency, or bw log for every | |
1647 | IO that completes. When writing to the disk log, that can quickly grow to a | |
1648 | very large size. Setting this option makes fio average the each log entry | |
e6989e10 | 1649 | over the specified period of time, reducing the resolution of the log. See |
4b1ddb7a | 1650 | \fBlog_max_value\fR as well. Defaults to 0, logging all entries. |
e6989e10 | 1651 | .TP |
4b1ddb7a | 1652 | .BI log_max_value \fR=\fPbool |
e6989e10 JA |
1653 | If \fBlog_avg_msec\fR is set, fio logs the average over that window. If you |
1654 | instead want to log the maximum value, set this option to 1. Defaults to | |
1655 | 0, meaning that averaged values are logged. | |
b8bc8cba | 1656 | .TP |
1e613c9c KC |
1657 | .BI log_hist_msec \fR=\fPint |
1658 | Same as \fBlog_avg_msec\fR, but logs entries for completion latency histograms. | |
1659 | Computing latency percentiles from averages of intervals using \fBlog_avg_msec\fR | |
1660 | is innacurate. Setting this option makes fio log histogram entries over the | |
1661 | specified period of time, reducing log sizes for high IOPS devices while | |
1662 | retaining percentile accuracy. See \fBlog_hist_coarseness\fR as well. Defaults | |
1663 | to 0, meaning histogram logging is disabled. | |
1664 | .TP | |
1665 | .BI log_hist_coarseness \fR=\fPint | |
1666 | Integer ranging from 0 to 6, defining the coarseness of the resolution of the | |
1667 | histogram logs enabled with \fBlog_hist_msec\fR. For each increment in | |
1668 | coarseness, fio outputs half as many bins. Defaults to 0, for which histogram | |
1669 | logs contain 1216 latency bins. See the \fBLOG FILE FORMATS\fR section. | |
1670 | .TP | |
ae588852 JA |
1671 | .BI log_offset \fR=\fPbool |
1672 | If this is set, the iolog options will include the byte offset for the IO | |
1673 | entry as well as the other data values. | |
1674 | .TP | |
aee2ab67 JA |
1675 | .BI log_compression \fR=\fPint |
1676 | If this is set, fio will compress the IO logs as it goes, to keep the memory | |
1677 | footprint lower. When a log reaches the specified size, that chunk is removed | |
1678 | and compressed in the background. Given that IO logs are fairly highly | |
1679 | compressible, this yields a nice memory savings for longer runs. The downside | |
1680 | is that the compression will consume some background CPU cycles, so it may | |
1681 | impact the run. This, however, is also true if the logging ends up consuming | |
1682 | most of the system memory. So pick your poison. The IO logs are saved | |
1683 | normally at the end of a run, by decompressing the chunks and storing them | |
1684 | in the specified log file. This feature depends on the availability of zlib. | |
1685 | .TP | |
c08f9fe2 JA |
1686 | .BI log_compression_cpus \fR=\fPstr |
1687 | Define the set of CPUs that are allowed to handle online log compression | |
1688 | for the IO jobs. This can provide better isolation between performance | |
1689 | sensitive jobs, and background compression work. | |
1690 | .TP | |
b26317c9 | 1691 | .BI log_store_compressed \fR=\fPbool |
c08f9fe2 JA |
1692 | If set, fio will store the log files in a compressed format. They can be |
1693 | decompressed with fio, using the \fB\-\-inflate-log\fR command line parameter. | |
1694 | The files will be stored with a \fB\.fz\fR suffix. | |
b26317c9 | 1695 | .TP |
3aea75b1 KC |
1696 | .BI log_unix_epoch \fR=\fPbool |
1697 | If set, fio will log Unix timestamps to the log files produced by enabling | |
1698 | \fBwrite_type_log\fR for each log type, instead of the default zero-based | |
1699 | timestamps. | |
1700 | .TP | |
66347cfa DE |
1701 | .BI block_error_percentiles \fR=\fPbool |
1702 | If set, record errors in trim block-sized units from writes and trims and output | |
1703 | a histogram of how many trims it took to get to errors, and what kind of error | |
1704 | was encountered. | |
1705 | .TP | |
836bad52 | 1706 | .BI disable_lat \fR=\fPbool |
02af0988 | 1707 | Disable measurements of total latency numbers. Useful only for cutting |
ccc2b328 | 1708 | back the number of calls to \fBgettimeofday\fR\|(2), as that does impact performance at |
901bb994 JA |
1709 | really high IOPS rates. Note that to really get rid of a large amount of these |
1710 | calls, this option must be used with disable_slat and disable_bw as well. | |
1711 | .TP | |
836bad52 | 1712 | .BI disable_clat \fR=\fPbool |
c95f9daf | 1713 | Disable measurements of completion latency numbers. See \fBdisable_lat\fR. |
02af0988 | 1714 | .TP |
836bad52 | 1715 | .BI disable_slat \fR=\fPbool |
02af0988 | 1716 | Disable measurements of submission latency numbers. See \fBdisable_lat\fR. |
901bb994 | 1717 | .TP |
836bad52 | 1718 | .BI disable_bw_measurement \fR=\fPbool |
02af0988 | 1719 | Disable measurements of throughput/bandwidth numbers. See \fBdisable_lat\fR. |
d60e92d1 | 1720 | .TP |
f7fa2653 | 1721 | .BI lockmem \fR=\fPint |
d60e92d1 | 1722 | Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to |
81c6b6cd | 1723 | simulate a smaller amount of memory. The amount specified is per worker. |
d60e92d1 AC |
1724 | .TP |
1725 | .BI exec_prerun \fR=\fPstr | |
1726 | Before running the job, execute the specified command with \fBsystem\fR\|(3). | |
ce486495 EV |
1727 | .RS |
1728 | Output is redirected in a file called \fBjobname.prerun.txt\fR | |
1729 | .RE | |
d60e92d1 AC |
1730 | .TP |
1731 | .BI exec_postrun \fR=\fPstr | |
1732 | Same as \fBexec_prerun\fR, but the command is executed after the job completes. | |
ce486495 EV |
1733 | .RS |
1734 | Output is redirected in a file called \fBjobname.postrun.txt\fR | |
1735 | .RE | |
d60e92d1 AC |
1736 | .TP |
1737 | .BI ioscheduler \fR=\fPstr | |
1738 | Attempt to switch the device hosting the file to the specified I/O scheduler. | |
1739 | .TP | |
d60e92d1 | 1740 | .BI disk_util \fR=\fPbool |
d1429b5c | 1741 | Generate disk utilization statistics if the platform supports it. Default: true. |
901bb994 | 1742 | .TP |
23893646 JA |
1743 | .BI clocksource \fR=\fPstr |
1744 | Use the given clocksource as the base of timing. The supported options are: | |
1745 | .RS | |
1746 | .TP | |
1747 | .B gettimeofday | |
ccc2b328 | 1748 | \fBgettimeofday\fR\|(2) |
23893646 JA |
1749 | .TP |
1750 | .B clock_gettime | |
ccc2b328 | 1751 | \fBclock_gettime\fR\|(2) |
23893646 JA |
1752 | .TP |
1753 | .B cpu | |
1754 | Internal CPU clock source | |
1755 | .TP | |
1756 | .RE | |
1757 | .P | |
1758 | \fBcpu\fR is the preferred clocksource if it is reliable, as it is very fast | |
1759 | (and fio is heavy on time calls). Fio will automatically use this clocksource | |
1760 | if it's supported and considered reliable on the system it is running on, | |
1761 | unless another clocksource is specifically set. For x86/x86-64 CPUs, this | |
1762 | means supporting TSC Invariant. | |
1763 | .TP | |
901bb994 | 1764 | .BI gtod_reduce \fR=\fPbool |
ccc2b328 | 1765 | Enable all of the \fBgettimeofday\fR\|(2) reducing options (disable_clat, disable_slat, |
901bb994 | 1766 | disable_bw) plus reduce precision of the timeout somewhat to really shrink the |
ccc2b328 | 1767 | \fBgettimeofday\fR\|(2) call count. With this option enabled, we only do about 0.4% of |
901bb994 JA |
1768 | the gtod() calls we would have done if all time keeping was enabled. |
1769 | .TP | |
1770 | .BI gtod_cpu \fR=\fPint | |
1771 | Sometimes it's cheaper to dedicate a single thread of execution to just getting | |
1772 | the current time. Fio (and databases, for instance) are very intensive on | |
ccc2b328 | 1773 | \fBgettimeofday\fR\|(2) calls. With this option, you can set one CPU aside for doing |
901bb994 JA |
1774 | nothing but logging current time to a shared memory location. Then the other |
1775 | threads/processes that run IO workloads need only copy that segment, instead of | |
ccc2b328 | 1776 | entering the kernel with a \fBgettimeofday\fR\|(2) call. The CPU set aside for doing |
901bb994 JA |
1777 | these time calls will be excluded from other uses. Fio will manually clear it |
1778 | from the CPU mask of other jobs. | |
f2bba182 | 1779 | .TP |
8b28bd41 DM |
1780 | .BI ignore_error \fR=\fPstr |
1781 | Sometimes you want to ignore some errors during test in that case you can specify | |
1782 | error list for each error type. | |
1783 | .br | |
1784 | ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST | |
1785 | .br | |
1786 | errors for given error type is separated with ':'. | |
1787 | Error may be symbol ('ENOSPC', 'ENOMEM') or an integer. | |
1788 | .br | |
1789 | Example: ignore_error=EAGAIN,ENOSPC:122 . | |
ff6bb260 SL |
1790 | .br |
1791 | This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from WRITE. | |
8b28bd41 DM |
1792 | .TP |
1793 | .BI error_dump \fR=\fPbool | |
1794 | If set dump every error even if it is non fatal, true by default. If disabled | |
1795 | only fatal error will be dumped | |
1796 | .TP | |
fa769d44 SW |
1797 | .BI profile \fR=\fPstr |
1798 | Select a specific builtin performance test. | |
1799 | .TP | |
a696fa2a JA |
1800 | .BI cgroup \fR=\fPstr |
1801 | Add job to this control group. If it doesn't exist, it will be created. | |
6adb38a1 JA |
1802 | The system must have a mounted cgroup blkio mount point for this to work. If |
1803 | your system doesn't have it mounted, you can do so with: | |
1804 | ||
5982a925 | 1805 | # mount \-t cgroup \-o blkio none /cgroup |
a696fa2a JA |
1806 | .TP |
1807 | .BI cgroup_weight \fR=\fPint | |
1808 | Set the weight of the cgroup to this value. See the documentation that comes | |
1809 | with the kernel, allowed values are in the range of 100..1000. | |
e0b0d892 | 1810 | .TP |
7de87099 VG |
1811 | .BI cgroup_nodelete \fR=\fPbool |
1812 | Normally fio will delete the cgroups it has created after the job completion. | |
1813 | To override this behavior and to leave cgroups around after the job completion, | |
1814 | set cgroup_nodelete=1. This can be useful if one wants to inspect various | |
1815 | cgroup files after job completion. Default: false | |
1816 | .TP | |
e0b0d892 JA |
1817 | .BI uid \fR=\fPint |
1818 | Instead of running as the invoking user, set the user ID to this value before | |
1819 | the thread/process does any work. | |
1820 | .TP | |
1821 | .BI gid \fR=\fPint | |
1822 | Set group ID, see \fBuid\fR. | |
83349190 | 1823 | .TP |
fa769d44 SW |
1824 | .BI unit_base \fR=\fPint |
1825 | Base unit for reporting. Allowed values are: | |
1826 | .RS | |
1827 | .TP | |
1828 | .B 0 | |
1829 | Use auto-detection (default). | |
1830 | .TP | |
1831 | .B 8 | |
1832 | Byte based. | |
1833 | .TP | |
1834 | .B 1 | |
1835 | Bit based. | |
1836 | .RE | |
1837 | .P | |
1838 | .TP | |
9e684a49 DE |
1839 | .BI flow_id \fR=\fPint |
1840 | The ID of the flow. If not specified, it defaults to being a global flow. See | |
1841 | \fBflow\fR. | |
1842 | .TP | |
1843 | .BI flow \fR=\fPint | |
1844 | Weight in token-based flow control. If this value is used, then there is a | |
1845 | \fBflow counter\fR which is used to regulate the proportion of activity between | |
1846 | two or more jobs. fio attempts to keep this flow counter near zero. The | |
1847 | \fBflow\fR parameter stands for how much should be added or subtracted to the | |
1848 | flow counter on each iteration of the main I/O loop. That is, if one job has | |
1849 | \fBflow=8\fR and another job has \fBflow=-1\fR, then there will be a roughly | |
1850 | 1:8 ratio in how much one runs vs the other. | |
1851 | .TP | |
1852 | .BI flow_watermark \fR=\fPint | |
1853 | The maximum value that the absolute value of the flow counter is allowed to | |
1854 | reach before the job must wait for a lower value of the counter. | |
1855 | .TP | |
1856 | .BI flow_sleep \fR=\fPint | |
1857 | The period of time, in microseconds, to wait after the flow watermark has been | |
1858 | exceeded before retrying operations | |
1859 | .TP | |
83349190 YH |
1860 | .BI clat_percentiles \fR=\fPbool |
1861 | Enable the reporting of percentiles of completion latencies. | |
1862 | .TP | |
1863 | .BI percentile_list \fR=\fPfloat_list | |
66347cfa DE |
1864 | Overwrite the default list of percentiles for completion latencies and the |
1865 | block error histogram. Each number is a floating number in the range (0,100], | |
1866 | and the maximum length of the list is 20. Use ':' to separate the | |
3eb07285 | 1867 | numbers. For example, \-\-percentile_list=99.5:99.9 will cause fio to |
83349190 YH |
1868 | report the values of completion latency below which 99.5% and 99.9% of |
1869 | the observed latencies fell, respectively. | |
de890a1e SL |
1870 | .SS "Ioengine Parameters List" |
1871 | Some parameters are only valid when a specific ioengine is in use. These are | |
1872 | used identically to normal parameters, with the caveat that when used on the | |
cf145d90 | 1873 | command line, they must come after the ioengine. |
de890a1e | 1874 | .TP |
2403767a | 1875 | .BI (cpuio)cpuload \fR=\fPint |
e4585935 JA |
1876 | Attempt to use the specified percentage of CPU cycles. |
1877 | .TP | |
2403767a | 1878 | .BI (cpuio)cpuchunks \fR=\fPint |
e4585935 JA |
1879 | Split the load into cycles of the given time. In microseconds. |
1880 | .TP | |
2403767a | 1881 | .BI (cpuio)exit_on_io_done \fR=\fPbool |
046395d7 JA |
1882 | Detect when IO threads are done, then exit. |
1883 | .TP | |
de890a1e SL |
1884 | .BI (libaio)userspace_reap |
1885 | Normally, with the libaio engine in use, fio will use | |
1886 | the io_getevents system call to reap newly returned events. | |
1887 | With this flag turned on, the AIO ring will be read directly | |
1888 | from user-space to reap events. The reaping mode is only | |
1889 | enabled when polling for a minimum of 0 events (eg when | |
1890 | iodepth_batch_complete=0). | |
1891 | .TP | |
82e65aec | 1892 | .BI (pvsync2)hipri |
2cafffbe JA |
1893 | Set RWF_HIPRI on IO, indicating to the kernel that it's of |
1894 | higher priority than normal. | |
1895 | .TP | |
de890a1e SL |
1896 | .BI (net,netsplice)hostname \fR=\fPstr |
1897 | The host name or IP address to use for TCP or UDP based IO. | |
1898 | If the job is a TCP listener or UDP reader, the hostname is not | |
b511c9aa | 1899 | used and must be omitted unless it is a valid UDP multicast address. |
de890a1e SL |
1900 | .TP |
1901 | .BI (net,netsplice)port \fR=\fPint | |
6315af9d JA |
1902 | The TCP or UDP port to bind to or connect to. If this is used with |
1903 | \fBnumjobs\fR to spawn multiple instances of the same job type, then | |
1904 | this will be the starting port number since fio will use a range of ports. | |
de890a1e | 1905 | .TP |
b93b6a2e SB |
1906 | .BI (net,netsplice)interface \fR=\fPstr |
1907 | The IP address of the network interface used to send or receive UDP multicast | |
1908 | packets. | |
1909 | .TP | |
d3a623de SB |
1910 | .BI (net,netsplice)ttl \fR=\fPint |
1911 | Time-to-live value for outgoing UDP multicast packets. Default: 1 | |
1912 | .TP | |
1d360ffb JA |
1913 | .BI (net,netsplice)nodelay \fR=\fPbool |
1914 | Set TCP_NODELAY on TCP connections. | |
1915 | .TP | |
de890a1e SL |
1916 | .BI (net,netsplice)protocol \fR=\fPstr "\fR,\fP proto" \fR=\fPstr |
1917 | The network protocol to use. Accepted values are: | |
1918 | .RS | |
1919 | .RS | |
1920 | .TP | |
1921 | .B tcp | |
1922 | Transmission control protocol | |
1923 | .TP | |
49ccb8c1 JA |
1924 | .B tcpv6 |
1925 | Transmission control protocol V6 | |
1926 | .TP | |
de890a1e | 1927 | .B udp |
f5cc3d0e | 1928 | User datagram protocol |
de890a1e | 1929 | .TP |
49ccb8c1 JA |
1930 | .B udpv6 |
1931 | User datagram protocol V6 | |
1932 | .TP | |
de890a1e SL |
1933 | .B unix |
1934 | UNIX domain socket | |
1935 | .RE | |
1936 | .P | |
1937 | When the protocol is TCP or UDP, the port must also be given, | |
1938 | as well as the hostname if the job is a TCP listener or UDP | |
1939 | reader. For unix sockets, the normal filename option should be | |
1940 | used and the port is invalid. | |
1941 | .RE | |
1942 | .TP | |
1943 | .BI (net,netsplice)listen | |
1944 | For TCP network connections, tell fio to listen for incoming | |
1945 | connections rather than initiating an outgoing connection. The | |
1946 | hostname must be omitted if this option is used. | |
d54fce84 | 1947 | .TP |
7aeb1e94 | 1948 | .BI (net, pingpong) \fR=\fPbool |
cecbfd47 | 1949 | Normally a network writer will just continue writing data, and a network reader |
cf145d90 | 1950 | will just consume packets. If pingpong=1 is set, a writer will send its normal |
7aeb1e94 JA |
1951 | payload to the reader, then wait for the reader to send the same payload back. |
1952 | This allows fio to measure network latencies. The submission and completion | |
1953 | latencies then measure local time spent sending or receiving, and the | |
1954 | completion latency measures how long it took for the other end to receive and | |
b511c9aa SB |
1955 | send back. For UDP multicast traffic pingpong=1 should only be set for a single |
1956 | reader when multiple readers are listening to the same address. | |
7aeb1e94 | 1957 | .TP |
1008602c JA |
1958 | .BI (net, window_size) \fR=\fPint |
1959 | Set the desired socket buffer size for the connection. | |
1960 | .TP | |
e5f34d95 JA |
1961 | .BI (net, mss) \fR=\fPint |
1962 | Set the TCP maximum segment size (TCP_MAXSEG). | |
1963 | .TP | |
d54fce84 DM |
1964 | .BI (e4defrag,donorname) \fR=\fPstr |
1965 | File will be used as a block donor (swap extents between files) | |
1966 | .TP | |
1967 | .BI (e4defrag,inplace) \fR=\fPint | |
ff6bb260 | 1968 | Configure donor file block allocation strategy |
d54fce84 DM |
1969 | .RS |
1970 | .BI 0(default) : | |
1971 | Preallocate donor's file on init | |
1972 | .TP | |
1973 | .BI 1: | |
cecbfd47 | 1974 | allocate space immediately inside defragment event, and free right after event |
d54fce84 | 1975 | .RE |
6d500c2e | 1976 | .TP |
6e20c6e7 T |
1977 | .BI (rbd)clustername \fR=\fPstr |
1978 | Specifies the name of the ceph cluster. | |
0d978694 DAG |
1979 | .TP |
1980 | .BI (rbd)rbdname \fR=\fPstr | |
1981 | Specifies the name of the RBD. | |
1982 | .TP | |
1983 | .BI (rbd)pool \fR=\fPstr | |
1984 | Specifies the name of the Ceph pool containing the RBD. | |
1985 | .TP | |
1986 | .BI (rbd)clientname \fR=\fPstr | |
6e20c6e7 | 1987 | Specifies the username (without the 'client.' prefix) used to access the Ceph |
08a2cbf6 JA |
1988 | cluster. If the clustername is specified, the clientname shall be the full |
1989 | type.id string. If no type. prefix is given, fio will add 'client.' by default. | |
65fa28ca DE |
1990 | .TP |
1991 | .BI (mtd)skipbad \fR=\fPbool | |
1992 | Skip operations against known bad blocks. | |
d60e92d1 | 1993 | .SH OUTPUT |
d1429b5c AC |
1994 | While running, \fBfio\fR will display the status of the created jobs. For |
1995 | example: | |
d60e92d1 | 1996 | .RS |
d1429b5c | 1997 | .P |
6d500c2e | 1998 | Jobs: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s] |
d60e92d1 AC |
1999 | .RE |
2000 | .P | |
d1429b5c AC |
2001 | The characters in the first set of brackets denote the current status of each |
2002 | threads. The possible values are: | |
2003 | .P | |
2004 | .PD 0 | |
d60e92d1 AC |
2005 | .RS |
2006 | .TP | |
2007 | .B P | |
2008 | Setup but not started. | |
2009 | .TP | |
2010 | .B C | |
2011 | Thread created. | |
2012 | .TP | |
2013 | .B I | |
2014 | Initialized, waiting. | |
2015 | .TP | |
2016 | .B R | |
2017 | Running, doing sequential reads. | |
2018 | .TP | |
2019 | .B r | |
2020 | Running, doing random reads. | |
2021 | .TP | |
2022 | .B W | |
2023 | Running, doing sequential writes. | |
2024 | .TP | |
2025 | .B w | |
2026 | Running, doing random writes. | |
2027 | .TP | |
2028 | .B M | |
2029 | Running, doing mixed sequential reads/writes. | |
2030 | .TP | |
2031 | .B m | |
2032 | Running, doing mixed random reads/writes. | |
2033 | .TP | |
2034 | .B F | |
2035 | Running, currently waiting for \fBfsync\fR\|(2). | |
2036 | .TP | |
2037 | .B V | |
2038 | Running, verifying written data. | |
2039 | .TP | |
2040 | .B E | |
2041 | Exited, not reaped by main thread. | |
2042 | .TP | |
2043 | .B \- | |
2044 | Exited, thread reaped. | |
2045 | .RE | |
d1429b5c | 2046 | .PD |
d60e92d1 AC |
2047 | .P |
2048 | The second set of brackets shows the estimated completion percentage of | |
2049 | the current group. The third set shows the read and write I/O rate, | |
2050 | respectively. Finally, the estimated run time of the job is displayed. | |
2051 | .P | |
2052 | When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data | |
2053 | for each thread, each group of threads, and each disk, in that order. | |
2054 | .P | |
2055 | Per-thread statistics first show the threads client number, group-id, and | |
2056 | error code. The remaining figures are as follows: | |
2057 | .RS | |
d60e92d1 AC |
2058 | .TP |
2059 | .B io | |
2060 | Number of megabytes of I/O performed. | |
2061 | .TP | |
2062 | .B bw | |
2063 | Average data rate (bandwidth). | |
2064 | .TP | |
2065 | .B runt | |
2066 | Threads run time. | |
2067 | .TP | |
2068 | .B slat | |
2069 | Submission latency minimum, maximum, average and standard deviation. This is | |
2070 | the time it took to submit the I/O. | |
2071 | .TP | |
2072 | .B clat | |
2073 | Completion latency minimum, maximum, average and standard deviation. This | |
2074 | is the time between submission and completion. | |
2075 | .TP | |
2076 | .B bw | |
2077 | Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average | |
2078 | and standard deviation. | |
2079 | .TP | |
2080 | .B cpu | |
2081 | CPU usage statistics. Includes user and system time, number of context switches | |
23a8e176 JA |
2082 | this thread went through and number of major and minor page faults. The CPU |
2083 | utilization numbers are averages for the jobs in that reporting group, while | |
2084 | the context and fault counters are summed. | |
d60e92d1 AC |
2085 | .TP |
2086 | .B IO depths | |
2087 | Distribution of I/O depths. Each depth includes everything less than (or equal) | |
2088 | to it, but greater than the previous depth. | |
2089 | .TP | |
2090 | .B IO issued | |
2091 | Number of read/write requests issued, and number of short read/write requests. | |
2092 | .TP | |
2093 | .B IO latencies | |
2094 | Distribution of I/O completion latencies. The numbers follow the same pattern | |
2095 | as \fBIO depths\fR. | |
2096 | .RE | |
d60e92d1 AC |
2097 | .P |
2098 | The group statistics show: | |
d1429b5c | 2099 | .PD 0 |
d60e92d1 AC |
2100 | .RS |
2101 | .TP | |
2102 | .B io | |
2103 | Number of megabytes I/O performed. | |
2104 | .TP | |
2105 | .B aggrb | |
2106 | Aggregate bandwidth of threads in the group. | |
2107 | .TP | |
2108 | .B minb | |
2109 | Minimum average bandwidth a thread saw. | |
2110 | .TP | |
2111 | .B maxb | |
2112 | Maximum average bandwidth a thread saw. | |
2113 | .TP | |
2114 | .B mint | |
d1429b5c | 2115 | Shortest runtime of threads in the group. |
d60e92d1 AC |
2116 | .TP |
2117 | .B maxt | |
2118 | Longest runtime of threads in the group. | |
2119 | .RE | |
d1429b5c | 2120 | .PD |
d60e92d1 AC |
2121 | .P |
2122 | Finally, disk statistics are printed with reads first: | |
d1429b5c | 2123 | .PD 0 |
d60e92d1 AC |
2124 | .RS |
2125 | .TP | |
2126 | .B ios | |
2127 | Number of I/Os performed by all groups. | |
2128 | .TP | |
2129 | .B merge | |
2130 | Number of merges in the I/O scheduler. | |
2131 | .TP | |
2132 | .B ticks | |
2133 | Number of ticks we kept the disk busy. | |
2134 | .TP | |
2135 | .B io_queue | |
2136 | Total time spent in the disk queue. | |
2137 | .TP | |
2138 | .B util | |
2139 | Disk utilization. | |
2140 | .RE | |
d1429b5c | 2141 | .PD |
8423bd11 JA |
2142 | .P |
2143 | It is also possible to get fio to dump the current output while it is | |
2144 | running, without terminating the job. To do that, send fio the \fBUSR1\fR | |
2145 | signal. | |
d60e92d1 | 2146 | .SH TERSE OUTPUT |
2b8c71b0 CE |
2147 | If the \fB\-\-minimal\fR / \fB\-\-append-terse\fR options are given, the |
2148 | results will be printed/appended in a semicolon-delimited format suitable for | |
2149 | scripted use. | |
2150 | A job description (if provided) follows on a new line. Note that the first | |
525c2bfa JA |
2151 | number in the line is the version number. If the output has to be changed |
2152 | for some reason, this number will be incremented by 1 to signify that | |
2153 | change. The fields are: | |
d60e92d1 AC |
2154 | .P |
2155 | .RS | |
5e726d0a | 2156 | .B terse version, fio version, jobname, groupid, error |
d60e92d1 AC |
2157 | .P |
2158 | Read status: | |
2159 | .RS | |
6d500c2e | 2160 | .B Total I/O \fR(KiB)\fP, bandwidth \fR(KiB/s)\fP, IOPS, runtime \fR(ms)\fP |
d60e92d1 AC |
2161 | .P |
2162 | Submission latency: | |
2163 | .RS | |
2164 | .B min, max, mean, standard deviation | |
2165 | .RE | |
2166 | Completion latency: | |
2167 | .RS | |
2168 | .B min, max, mean, standard deviation | |
2169 | .RE | |
1db92cb6 JA |
2170 | Completion latency percentiles (20 fields): |
2171 | .RS | |
2172 | .B Xth percentile=usec | |
2173 | .RE | |
525c2bfa JA |
2174 | Total latency: |
2175 | .RS | |
2176 | .B min, max, mean, standard deviation | |
2177 | .RE | |
d60e92d1 AC |
2178 | Bandwidth: |
2179 | .RS | |
2180 | .B min, max, aggregate percentage of total, mean, standard deviation | |
2181 | .RE | |
2182 | .RE | |
2183 | .P | |
2184 | Write status: | |
2185 | .RS | |
6d500c2e | 2186 | .B Total I/O \fR(KiB)\fP, bandwidth \fR(KiB/s)\fP, IOPS, runtime \fR(ms)\fP |
d60e92d1 AC |
2187 | .P |
2188 | Submission latency: | |
2189 | .RS | |
2190 | .B min, max, mean, standard deviation | |
2191 | .RE | |
2192 | Completion latency: | |
2193 | .RS | |
2194 | .B min, max, mean, standard deviation | |
2195 | .RE | |
1db92cb6 JA |
2196 | Completion latency percentiles (20 fields): |
2197 | .RS | |
2198 | .B Xth percentile=usec | |
2199 | .RE | |
525c2bfa JA |
2200 | Total latency: |
2201 | .RS | |
2202 | .B min, max, mean, standard deviation | |
2203 | .RE | |
d60e92d1 AC |
2204 | Bandwidth: |
2205 | .RS | |
2206 | .B min, max, aggregate percentage of total, mean, standard deviation | |
2207 | .RE | |
2208 | .RE | |
2209 | .P | |
d1429b5c | 2210 | CPU usage: |
d60e92d1 | 2211 | .RS |
bd2626f0 | 2212 | .B user, system, context switches, major page faults, minor page faults |
d60e92d1 AC |
2213 | .RE |
2214 | .P | |
2215 | IO depth distribution: | |
2216 | .RS | |
2217 | .B <=1, 2, 4, 8, 16, 32, >=64 | |
2218 | .RE | |
2219 | .P | |
562c2d2f | 2220 | IO latency distribution: |
d60e92d1 | 2221 | .RS |
562c2d2f DN |
2222 | Microseconds: |
2223 | .RS | |
2224 | .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000 | |
2225 | .RE | |
2226 | Milliseconds: | |
2227 | .RS | |
2228 | .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000 | |
2229 | .RE | |
2230 | .RE | |
2231 | .P | |
f2f788dd JA |
2232 | Disk utilization (1 for each disk used): |
2233 | .RS | |
2234 | .B name, read ios, write ios, read merges, write merges, read ticks, write ticks, read in-queue time, write in-queue time, disk utilization percentage | |
2235 | .RE | |
2236 | .P | |
5982a925 | 2237 | Error Info (dependent on continue_on_error, default off): |
562c2d2f | 2238 | .RS |
ff6bb260 | 2239 | .B total # errors, first error code |
d60e92d1 AC |
2240 | .RE |
2241 | .P | |
562c2d2f | 2242 | .B text description (if provided in config - appears on newline) |
d60e92d1 | 2243 | .RE |
29dbd1e5 JA |
2244 | .SH TRACE FILE FORMAT |
2245 | There are two trace file format that you can encounter. The older (v1) format | |
2246 | is unsupported since version 1.20-rc3 (March 2008). It will still be described | |
2247 | below in case that you get an old trace and want to understand it. | |
2248 | ||
2249 | In any case the trace is a simple text file with a single action per line. | |
2250 | ||
2251 | .P | |
2252 | .B Trace file format v1 | |
2253 | .RS | |
2254 | Each line represents a single io action in the following format: | |
2255 | ||
2256 | rw, offset, length | |
2257 | ||
2258 | where rw=0/1 for read/write, and the offset and length entries being in bytes. | |
2259 | ||
2260 | This format is not supported in Fio versions => 1.20-rc3. | |
2261 | ||
2262 | .RE | |
2263 | .P | |
2264 | .B Trace file format v2 | |
2265 | .RS | |
2266 | The second version of the trace file format was added in Fio version 1.17. | |
8fb5444d | 2267 | It allows one to access more then one file per trace and has a bigger set of |
29dbd1e5 JA |
2268 | possible file actions. |
2269 | ||
2270 | The first line of the trace file has to be: | |
2271 | ||
2272 | \fBfio version 2 iolog\fR | |
2273 | ||
2274 | Following this can be lines in two different formats, which are described below. | |
2275 | The file management format: | |
2276 | ||
2277 | \fBfilename action\fR | |
2278 | ||
2279 | The filename is given as an absolute path. The action can be one of these: | |
2280 | ||
2281 | .P | |
2282 | .PD 0 | |
2283 | .RS | |
2284 | .TP | |
2285 | .B add | |
2286 | Add the given filename to the trace | |
2287 | .TP | |
2288 | .B open | |
2289 | Open the file with the given filename. The filename has to have been previously | |
2290 | added with the \fBadd\fR action. | |
2291 | .TP | |
2292 | .B close | |
2293 | Close the file with the given filename. The file must have previously been | |
2294 | opened. | |
2295 | .RE | |
2296 | .PD | |
2297 | .P | |
2298 | ||
2299 | The file io action format: | |
2300 | ||
2301 | \fBfilename action offset length\fR | |
2302 | ||
2303 | The filename is given as an absolute path, and has to have been added and opened | |
2304 | before it can be used with this format. The offset and length are given in | |
2305 | bytes. The action can be one of these: | |
2306 | ||
2307 | .P | |
2308 | .PD 0 | |
2309 | .RS | |
2310 | .TP | |
2311 | .B wait | |
2312 | Wait for 'offset' microseconds. Everything below 100 is discarded. The time is | |
2313 | relative to the previous wait statement. | |
2314 | .TP | |
2315 | .B read | |
2316 | Read \fBlength\fR bytes beginning from \fBoffset\fR | |
2317 | .TP | |
2318 | .B write | |
2319 | Write \fBlength\fR bytes beginning from \fBoffset\fR | |
2320 | .TP | |
2321 | .B sync | |
2322 | fsync() the file | |
2323 | .TP | |
2324 | .B datasync | |
2325 | fdatasync() the file | |
2326 | .TP | |
2327 | .B trim | |
2328 | trim the given file from the given \fBoffset\fR for \fBlength\fR bytes | |
2329 | .RE | |
2330 | .PD | |
2331 | .P | |
2332 | ||
2333 | .SH CPU IDLENESS PROFILING | |
2334 | In some cases, we want to understand CPU overhead in a test. For example, | |
2335 | we test patches for the specific goodness of whether they reduce CPU usage. | |
2336 | fio implements a balloon approach to create a thread per CPU that runs at | |
2337 | idle priority, meaning that it only runs when nobody else needs the cpu. | |
2338 | By measuring the amount of work completed by the thread, idleness of each | |
2339 | CPU can be derived accordingly. | |
2340 | ||
2341 | An unit work is defined as touching a full page of unsigned characters. Mean | |
2342 | and standard deviation of time to complete an unit work is reported in "unit | |
2343 | work" section. Options can be chosen to report detailed percpu idleness or | |
2344 | overall system idleness by aggregating percpu stats. | |
2345 | ||
2346 | .SH VERIFICATION AND TRIGGERS | |
2347 | Fio is usually run in one of two ways, when data verification is done. The | |
2348 | first is a normal write job of some sort with verify enabled. When the | |
2349 | write phase has completed, fio switches to reads and verifies everything | |
2350 | it wrote. The second model is running just the write phase, and then later | |
2351 | on running the same job (but with reads instead of writes) to repeat the | |
2352 | same IO patterns and verify the contents. Both of these methods depend | |
2353 | on the write phase being completed, as fio otherwise has no idea how much | |
2354 | data was written. | |
2355 | ||
2356 | With verification triggers, fio supports dumping the current write state | |
2357 | to local files. Then a subsequent read verify workload can load this state | |
2358 | and know exactly where to stop. This is useful for testing cases where | |
2359 | power is cut to a server in a managed fashion, for instance. | |
2360 | ||
2361 | A verification trigger consists of two things: | |
2362 | ||
2363 | .RS | |
2364 | Storing the write state of each job | |
2365 | .LP | |
2366 | Executing a trigger command | |
2367 | .RE | |
2368 | ||
2369 | The write state is relatively small, on the order of hundreds of bytes | |
2370 | to single kilobytes. It contains information on the number of completions | |
2371 | done, the last X completions, etc. | |
2372 | ||
2373 | A trigger is invoked either through creation (\fBtouch\fR) of a specified | |
2374 | file in the system, or through a timeout setting. If fio is run with | |
2375 | \fB\-\-trigger\-file=/tmp/trigger-file\fR, then it will continually check for | |
2376 | the existence of /tmp/trigger-file. When it sees this file, it will | |
2377 | fire off the trigger (thus saving state, and executing the trigger | |
2378 | command). | |
2379 | ||
2380 | For client/server runs, there's both a local and remote trigger. If | |
2381 | fio is running as a server backend, it will send the job states back | |
2382 | to the client for safe storage, then execute the remote trigger, if | |
2383 | specified. If a local trigger is specified, the server will still send | |
2384 | back the write state, but the client will then execute the trigger. | |
2385 | ||
2386 | .RE | |
2387 | .P | |
2388 | .B Verification trigger example | |
2389 | .RS | |
2390 | ||
2391 | Lets say we want to run a powercut test on the remote machine 'server'. | |
2392 | Our write workload is in write-test.fio. We want to cut power to 'server' | |
2393 | at some point during the run, and we'll run this test from the safety | |
2394 | or our local machine, 'localbox'. On the server, we'll start the fio | |
2395 | backend normally: | |
2396 | ||
2397 | server# \fBfio \-\-server\fR | |
2398 | ||
2399 | and on the client, we'll fire off the workload: | |
2400 | ||
e0ee7a8b | 2401 | localbox$ \fBfio \-\-client=server \-\-trigger\-file=/tmp/my\-trigger \-\-trigger-remote="bash \-c "echo b > /proc/sysrq-triger""\fR |
29dbd1e5 JA |
2402 | |
2403 | We set \fB/tmp/my-trigger\fR as the trigger file, and we tell fio to execute | |
2404 | ||
2405 | \fBecho b > /proc/sysrq-trigger\fR | |
2406 | ||
2407 | on the server once it has received the trigger and sent us the write | |
2408 | state. This will work, but it's not \fIreally\fR cutting power to the server, | |
2409 | it's merely abruptly rebooting it. If we have a remote way of cutting | |
2410 | power to the server through IPMI or similar, we could do that through | |
2411 | a local trigger command instead. Lets assume we have a script that does | |
2412 | IPMI reboot of a given hostname, ipmi-reboot. On localbox, we could | |
2413 | then have run fio with a local trigger instead: | |
2414 | ||
2415 | localbox$ \fBfio \-\-client=server \-\-trigger\-file=/tmp/my\-trigger \-\-trigger="ipmi-reboot server"\fR | |
2416 | ||
2417 | For this case, fio would wait for the server to send us the write state, | |
2418 | then execute 'ipmi-reboot server' when that happened. | |
2419 | ||
2420 | .RE | |
2421 | .P | |
2422 | .B Loading verify state | |
2423 | .RS | |
2424 | To load store write state, read verification job file must contain | |
2425 | the verify_state_load option. If that is set, fio will load the previously | |
2426 | stored state. For a local fio run this is done by loading the files directly, | |
2427 | and on a client/server run, the server backend will ask the client to send | |
2428 | the files over and load them from there. | |
2429 | ||
2430 | .RE | |
2431 | ||
a3ae5b05 JA |
2432 | .SH LOG FILE FORMATS |
2433 | ||
2434 | Fio supports a variety of log file formats, for logging latencies, bandwidth, | |
2435 | and IOPS. The logs share a common format, which looks like this: | |
2436 | ||
2437 | .B time (msec), value, data direction, offset | |
2438 | ||
2439 | Time for the log entry is always in milliseconds. The value logged depends | |
2440 | on the type of log, it will be one of the following: | |
2441 | ||
2442 | .P | |
2443 | .PD 0 | |
2444 | .TP | |
2445 | .B Latency log | |
2446 | Value is in latency in usecs | |
2447 | .TP | |
2448 | .B Bandwidth log | |
6d500c2e | 2449 | Value is in KiB/sec |
a3ae5b05 JA |
2450 | .TP |
2451 | .B IOPS log | |
2452 | Value is in IOPS | |
2453 | .PD | |
2454 | .P | |
2455 | ||
2456 | Data direction is one of the following: | |
2457 | ||
2458 | .P | |
2459 | .PD 0 | |
2460 | .TP | |
2461 | .B 0 | |
2462 | IO is a READ | |
2463 | .TP | |
2464 | .B 1 | |
2465 | IO is a WRITE | |
2466 | .TP | |
2467 | .B 2 | |
2468 | IO is a TRIM | |
2469 | .PD | |
2470 | .P | |
2471 | ||
2472 | The \fIoffset\fR is the offset, in bytes, from the start of the file, for that | |
2473 | particular IO. The logging of the offset can be toggled with \fBlog_offset\fR. | |
2474 | ||
4e7a8814 | 2475 | If windowed logging is enabled through \fBlog_avg_msec\fR, then fio doesn't log |
a3ae5b05 JA |
2476 | individual IOs. Instead of logs the average values over the specified |
2477 | period of time. Since \fIdata direction\fR and \fIoffset\fR are per-IO values, | |
2478 | they aren't applicable if windowed logging is enabled. If windowed logging | |
2479 | is enabled and \fBlog_max_value\fR is set, then fio logs maximum values in | |
2480 | that window instead of averages. | |
2481 | ||
1e613c9c KC |
2482 | For histogram logging the logs look like this: |
2483 | ||
2484 | .B time (msec), data direction, block-size, bin 0, bin 1, ..., bin 1215 | |
2485 | ||
2486 | Where 'bin i' gives the frequency of IO requests with a latency falling in | |
2487 | the i-th bin. See \fBlog_hist_coarseness\fR for logging fewer bins. | |
2488 | ||
a3ae5b05 JA |
2489 | .RE |
2490 | ||
49da1240 JA |
2491 | .SH CLIENT / SERVER |
2492 | Normally you would run fio as a stand-alone application on the machine | |
2493 | where the IO workload should be generated. However, it is also possible to | |
2494 | run the frontend and backend of fio separately. This makes it possible to | |
2495 | have a fio server running on the machine(s) where the IO workload should | |
2496 | be running, while controlling it from another machine. | |
2497 | ||
2498 | To start the server, you would do: | |
2499 | ||
2500 | \fBfio \-\-server=args\fR | |
2501 | ||
2502 | on that machine, where args defines what fio listens to. The arguments | |
811826be | 2503 | are of the form 'type:hostname or IP:port'. 'type' is either 'ip' (or ip4) |
20c67f10 MS |
2504 | for TCP/IP v4, 'ip6' for TCP/IP v6, or 'sock' for a local unix domain |
2505 | socket. 'hostname' is either a hostname or IP address, and 'port' is the port to | |
811826be | 2506 | listen to (only valid for TCP/IP, not a local socket). Some examples: |
49da1240 | 2507 | |
e0ee7a8b | 2508 | 1) \fBfio \-\-server\fR |
49da1240 JA |
2509 | |
2510 | Start a fio server, listening on all interfaces on the default port (8765). | |
2511 | ||
e0ee7a8b | 2512 | 2) \fBfio \-\-server=ip:hostname,4444\fR |
49da1240 JA |
2513 | |
2514 | Start a fio server, listening on IP belonging to hostname and on port 4444. | |
2515 | ||
e0ee7a8b | 2516 | 3) \fBfio \-\-server=ip6:::1,4444\fR |
811826be JA |
2517 | |
2518 | Start a fio server, listening on IPv6 localhost ::1 and on port 4444. | |
2519 | ||
e0ee7a8b | 2520 | 4) \fBfio \-\-server=,4444\fR |
49da1240 JA |
2521 | |
2522 | Start a fio server, listening on all interfaces on port 4444. | |
2523 | ||
e0ee7a8b | 2524 | 5) \fBfio \-\-server=1.2.3.4\fR |
49da1240 JA |
2525 | |
2526 | Start a fio server, listening on IP 1.2.3.4 on the default port. | |
2527 | ||
e0ee7a8b | 2528 | 6) \fBfio \-\-server=sock:/tmp/fio.sock\fR |
49da1240 JA |
2529 | |
2530 | Start a fio server, listening on the local socket /tmp/fio.sock. | |
2531 | ||
2532 | When a server is running, you can connect to it from a client. The client | |
2533 | is run with: | |
2534 | ||
e0ee7a8b | 2535 | \fBfio \-\-local-args \-\-client=server \-\-remote-args <job file(s)>\fR |
49da1240 | 2536 | |
e01e9745 MS |
2537 | where \-\-local-args are arguments that are local to the client where it is |
2538 | running, 'server' is the connect string, and \-\-remote-args and <job file(s)> | |
49da1240 JA |
2539 | are sent to the server. The 'server' string follows the same format as it |
2540 | does on the server side, to allow IP/hostname/socket and port strings. | |
2541 | You can connect to multiple clients as well, to do that you could run: | |
2542 | ||
e0ee7a8b | 2543 | \fBfio \-\-client=server2 \-\-client=server2 <job file(s)>\fR |
323255cc JA |
2544 | |
2545 | If the job file is located on the fio server, then you can tell the server | |
2546 | to load a local file as well. This is done by using \-\-remote-config: | |
2547 | ||
e0ee7a8b | 2548 | \fBfio \-\-client=server \-\-remote-config /path/to/file.fio\fR |
323255cc | 2549 | |
39b5f61e | 2550 | Then fio will open this local (to the server) job file instead |
323255cc | 2551 | of being passed one from the client. |
39b5f61e | 2552 | |
ff6bb260 | 2553 | If you have many servers (example: 100 VMs/containers), you can input a pathname |
39b5f61e BE |
2554 | of a file containing host IPs/names as the parameter value for the \-\-client option. |
2555 | For example, here is an example "host.list" file containing 2 hostnames: | |
2556 | ||
2557 | host1.your.dns.domain | |
2558 | .br | |
2559 | host2.your.dns.domain | |
2560 | ||
2561 | The fio command would then be: | |
2562 | ||
e0ee7a8b | 2563 | \fBfio \-\-client=host.list <job file>\fR |
39b5f61e BE |
2564 | |
2565 | In this mode, you cannot input server-specific parameters or job files, and all | |
2566 | servers receive the same job file. | |
2567 | ||
2568 | In order to enable fio \-\-client runs utilizing a shared filesystem from multiple hosts, | |
ff6bb260 SL |
2569 | fio \-\-client now prepends the IP address of the server to the filename. For example, |
2570 | if fio is using directory /mnt/nfs/fio and is writing filename fileio.tmp, | |
39b5f61e BE |
2571 | with a \-\-client hostfile |
2572 | containing two hostnames h1 and h2 with IP addresses 192.168.10.120 and 192.168.10.121, then | |
2573 | fio will create two files: | |
2574 | ||
2575 | /mnt/nfs/fio/192.168.10.120.fileio.tmp | |
2576 | .br | |
2577 | /mnt/nfs/fio/192.168.10.121.fileio.tmp | |
2578 | ||
d60e92d1 | 2579 | .SH AUTHORS |
49da1240 | 2580 | |
d60e92d1 | 2581 | .B fio |
aa58d252 | 2582 | was written by Jens Axboe <jens.axboe@oracle.com>, |
f8b8f7da | 2583 | now Jens Axboe <axboe@fb.com>. |
d1429b5c AC |
2584 | .br |
2585 | This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based | |
d60e92d1 AC |
2586 | on documentation by Jens Axboe. |
2587 | .SH "REPORTING BUGS" | |
482900c9 | 2588 | Report bugs to the \fBfio\fR mailing list <fio@vger.kernel.org>. |
d1429b5c | 2589 | See \fBREADME\fR. |
d60e92d1 | 2590 | .SH "SEE ALSO" |
d1429b5c AC |
2591 | For further documentation see \fBHOWTO\fR and \fBREADME\fR. |
2592 | .br | |
2593 | Sample jobfiles are available in the \fBexamples\fR directory. | |
9040e236 TK |
2594 | .br |
2595 | These are typically located under /usr/share/doc/fio. | |
2596 | ||
2597 | \fBHOWTO\fR: http://git.kernel.dk/?p=fio.git;a=blob_plain;f=HOWTO | |
2598 | .br | |
2599 | \fBREADME\fR: http://git.kernel.dk/?p=fio.git;a=blob_plain;f=README | |
2600 | .br |