| 1 | Table of contents |
| 2 | ----------------- |
| 3 | |
| 4 | 1. Overview |
| 5 | 2. How fio works |
| 6 | 3. Running fio |
| 7 | 4. Job file format |
| 8 | 5. Detailed list of parameters |
| 9 | 6. Normal output |
| 10 | 7. Terse output |
| 11 | 8. Trace file format |
| 12 | 9. CPU idleness profiling |
| 13 | 10. Verification and triggers |
| 14 | 11. Log File Formats |
| 15 | |
| 16 | |
| 17 | 1.0 Overview and history |
| 18 | ------------------------ |
| 19 | fio was originally written to save me the hassle of writing special test |
| 20 | case programs when I wanted to test a specific workload, either for |
| 21 | performance reasons or to find/reproduce a bug. The process of writing |
| 22 | such a test app can be tiresome, especially if you have to do it often. |
| 23 | Hence I needed a tool that would be able to simulate a given io workload |
| 24 | without resorting to writing a tailored test case again and again. |
| 25 | |
| 26 | A test work load is difficult to define, though. There can be any number |
| 27 | of processes or threads involved, and they can each be using their own |
| 28 | way of generating io. You could have someone dirtying large amounts of |
| 29 | memory in an memory mapped file, or maybe several threads issuing |
| 30 | reads using asynchronous io. fio needed to be flexible enough to |
| 31 | simulate both of these cases, and many more. |
| 32 | |
| 33 | 2.0 How fio works |
| 34 | ----------------- |
| 35 | The first step in getting fio to simulate a desired io workload, is |
| 36 | writing a job file describing that specific setup. A job file may contain |
| 37 | any number of threads and/or files - the typical contents of the job file |
| 38 | is a global section defining shared parameters, and one or more job |
| 39 | sections describing the jobs involved. When run, fio parses this file |
| 40 | and sets everything up as described. If we break down a job from top to |
| 41 | bottom, it contains the following basic parameters: |
| 42 | |
| 43 | IO type Defines the io pattern issued to the file(s). |
| 44 | We may only be reading sequentially from this |
| 45 | file(s), or we may be writing randomly. Or even |
| 46 | mixing reads and writes, sequentially or randomly. |
| 47 | |
| 48 | Block size In how large chunks are we issuing io? This may be |
| 49 | a single value, or it may describe a range of |
| 50 | block sizes. |
| 51 | |
| 52 | IO size How much data are we going to be reading/writing. |
| 53 | |
| 54 | IO engine How do we issue io? We could be memory mapping the |
| 55 | file, we could be using regular read/write, we |
| 56 | could be using splice, async io, or even SG |
| 57 | (SCSI generic sg). |
| 58 | |
| 59 | IO depth If the io engine is async, how large a queuing |
| 60 | depth do we want to maintain? |
| 61 | |
| 62 | IO type Should we be doing buffered io, or direct/raw io? |
| 63 | |
| 64 | Num files How many files are we spreading the workload over. |
| 65 | |
| 66 | Num threads How many threads or processes should we spread |
| 67 | this workload over. |
| 68 | |
| 69 | The above are the basic parameters defined for a workload, in addition |
| 70 | there's a multitude of parameters that modify other aspects of how this |
| 71 | job behaves. |
| 72 | |
| 73 | |
| 74 | 3.0 Running fio |
| 75 | --------------- |
| 76 | See the README file for command line parameters, there are only a few |
| 77 | of them. |
| 78 | |
| 79 | Running fio is normally the easiest part - you just give it the job file |
| 80 | (or job files) as parameters: |
| 81 | |
| 82 | $ fio job_file |
| 83 | |
| 84 | and it will start doing what the job_file tells it to do. You can give |
| 85 | more than one job file on the command line, fio will serialize the running |
| 86 | of those files. Internally that is the same as using the 'stonewall' |
| 87 | parameter described in the parameter section. |
| 88 | |
| 89 | If the job file contains only one job, you may as well just give the |
| 90 | parameters on the command line. The command line parameters are identical |
| 91 | to the job parameters, with a few extra that control global parameters |
| 92 | (see README). For example, for the job file parameter iodepth=2, the |
| 93 | mirror command line option would be --iodepth 2 or --iodepth=2. You can |
| 94 | also use the command line for giving more than one job entry. For each |
| 95 | --name option that fio sees, it will start a new job with that name. |
| 96 | Command line entries following a --name entry will apply to that job, |
| 97 | until there are no more entries or a new --name entry is seen. This is |
| 98 | similar to the job file options, where each option applies to the current |
| 99 | job until a new [] job entry is seen. |
| 100 | |
| 101 | fio does not need to run as root, except if the files or devices specified |
| 102 | in the job section requires that. Some other options may also be restricted, |
| 103 | such as memory locking, io scheduler switching, and decreasing the nice value. |
| 104 | |
| 105 | |
| 106 | 4.0 Job file format |
| 107 | ------------------- |
| 108 | As previously described, fio accepts one or more job files describing |
| 109 | what it is supposed to do. The job file format is the classic ini file, |
| 110 | where the names enclosed in [] brackets define the job name. You are free |
| 111 | to use any ascii name you want, except 'global' which has special meaning. |
| 112 | A global section sets defaults for the jobs described in that file. A job |
| 113 | may override a global section parameter, and a job file may even have |
| 114 | several global sections if so desired. A job is only affected by a global |
| 115 | section residing above it. If the first character in a line is a ';' or a |
| 116 | '#', the entire line is discarded as a comment. |
| 117 | |
| 118 | So let's look at a really simple job file that defines two processes, each |
| 119 | randomly reading from a 128MiB file. |
| 120 | |
| 121 | ; -- start job file -- |
| 122 | [global] |
| 123 | rw=randread |
| 124 | size=128m |
| 125 | |
| 126 | [job1] |
| 127 | |
| 128 | [job2] |
| 129 | |
| 130 | ; -- end job file -- |
| 131 | |
| 132 | As you can see, the job file sections themselves are empty as all the |
| 133 | described parameters are shared. As no filename= option is given, fio |
| 134 | makes up a filename for each of the jobs as it sees fit. On the command |
| 135 | line, this job would look as follows: |
| 136 | |
| 137 | $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2 |
| 138 | |
| 139 | |
| 140 | Let's look at an example that has a number of processes writing randomly |
| 141 | to files. |
| 142 | |
| 143 | ; -- start job file -- |
| 144 | [random-writers] |
| 145 | ioengine=libaio |
| 146 | iodepth=4 |
| 147 | rw=randwrite |
| 148 | bs=32k |
| 149 | direct=0 |
| 150 | size=64m |
| 151 | numjobs=4 |
| 152 | |
| 153 | ; -- end job file -- |
| 154 | |
| 155 | Here we have no global section, as we only have one job defined anyway. |
| 156 | We want to use async io here, with a depth of 4 for each file. We also |
| 157 | increased the buffer size used to 32KiB and define numjobs to 4 to |
| 158 | fork 4 identical jobs. The result is 4 processes each randomly writing |
| 159 | to their own 64MiB file. Instead of using the above job file, you could |
| 160 | have given the parameters on the command line. For this case, you would |
| 161 | specify: |
| 162 | |
| 163 | $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4 |
| 164 | |
| 165 | When fio is utilized as a basis of any reasonably large test suite, it might be |
| 166 | desirable to share a set of standardized settings across multiple job files. |
| 167 | Instead of copy/pasting such settings, any section may pull in an external |
| 168 | .fio file with 'include filename' directive, as in the following example: |
| 169 | |
| 170 | ; -- start job file including.fio -- |
| 171 | [global] |
| 172 | filename=/tmp/test |
| 173 | filesize=1m |
| 174 | include glob-include.fio |
| 175 | |
| 176 | [test] |
| 177 | rw=randread |
| 178 | bs=4k |
| 179 | time_based=1 |
| 180 | runtime=10 |
| 181 | include test-include.fio |
| 182 | ; -- end job file including.fio -- |
| 183 | |
| 184 | ; -- start job file glob-include.fio -- |
| 185 | thread=1 |
| 186 | group_reporting=1 |
| 187 | ; -- end job file glob-include.fio -- |
| 188 | |
| 189 | ; -- start job file test-include.fio -- |
| 190 | ioengine=libaio |
| 191 | iodepth=4 |
| 192 | ; -- end job file test-include.fio -- |
| 193 | |
| 194 | Settings pulled into a section apply to that section only (except global |
| 195 | section). Include directives may be nested in that any included file may |
| 196 | contain further include directive(s). Include files may not contain [] |
| 197 | sections. |
| 198 | |
| 199 | |
| 200 | 4.1 Environment variables |
| 201 | ------------------------- |
| 202 | |
| 203 | fio also supports environment variable expansion in job files. Any |
| 204 | sub-string of the form "${VARNAME}" as part of an option value (in other |
| 205 | words, on the right of the `='), will be expanded to the value of the |
| 206 | environment variable called VARNAME. If no such environment variable |
| 207 | is defined, or VARNAME is the empty string, the empty string will be |
| 208 | substituted. |
| 209 | |
| 210 | As an example, let's look at a sample fio invocation and job file: |
| 211 | |
| 212 | $ SIZE=64m NUMJOBS=4 fio jobfile.fio |
| 213 | |
| 214 | ; -- start job file -- |
| 215 | [random-writers] |
| 216 | rw=randwrite |
| 217 | size=${SIZE} |
| 218 | numjobs=${NUMJOBS} |
| 219 | ; -- end job file -- |
| 220 | |
| 221 | This will expand to the following equivalent job file at runtime: |
| 222 | |
| 223 | ; -- start job file -- |
| 224 | [random-writers] |
| 225 | rw=randwrite |
| 226 | size=64m |
| 227 | numjobs=4 |
| 228 | ; -- end job file -- |
| 229 | |
| 230 | fio ships with a few example job files, you can also look there for |
| 231 | inspiration. |
| 232 | |
| 233 | 4.2 Reserved keywords |
| 234 | --------------------- |
| 235 | |
| 236 | Additionally, fio has a set of reserved keywords that will be replaced |
| 237 | internally with the appropriate value. Those keywords are: |
| 238 | |
| 239 | $pagesize The architecture page size of the running system |
| 240 | $mb_memory Megabytes of total memory in the system |
| 241 | $ncpus Number of online available CPUs |
| 242 | |
| 243 | These can be used on the command line or in the job file, and will be |
| 244 | automatically substituted with the current system values when the job |
| 245 | is run. Simple math is also supported on these keywords, so you can |
| 246 | perform actions like: |
| 247 | |
| 248 | size=8*$mb_memory |
| 249 | |
| 250 | and get that properly expanded to 8 times the size of memory in the |
| 251 | machine. |
| 252 | |
| 253 | |
| 254 | 5.0 Detailed list of parameters |
| 255 | ------------------------------- |
| 256 | |
| 257 | This section describes in details each parameter associated with a job. |
| 258 | Some parameters take an option of a given type, such as an integer or |
| 259 | a string. Anywhere a numeric value is required, an arithmetic expression |
| 260 | may be used, provided it is surrounded by parentheses. Supported operators |
| 261 | are: |
| 262 | |
| 263 | addition (+) |
| 264 | subtraction (-) |
| 265 | multiplication (*) |
| 266 | division (/) |
| 267 | modulus (%) |
| 268 | exponentiation (^) |
| 269 | |
| 270 | For time values in expressions, units are microseconds by default. This is |
| 271 | different than for time values not in expressions (not enclosed in |
| 272 | parentheses). The following types are used: |
| 273 | |
| 274 | str String. This is a sequence of alpha characters. |
| 275 | time Integer with possible time suffix. In seconds unless otherwise |
| 276 | specified, use eg 10m for 10 minutes. Accepts s/m/h for seconds, |
| 277 | minutes, and hours, and accepts 'ms' (or 'msec') for milliseconds, |
| 278 | and 'us' (or 'usec') for microseconds. |
| 279 | |
| 280 | int Integer. A whole number value, which may contain an integer prefix |
| 281 | and an integer suffix. |
| 282 | [integer prefix]number[integer suffix] |
| 283 | |
| 284 | The optional integer prefix specifies the number's base. The default |
| 285 | is decimal. 0x specifies hexadecimal. |
| 286 | |
| 287 | The optional integer suffix specifies the number's units, and includes |
| 288 | an optional unit prefix and an optional unit. For quantities of data, |
| 289 | the default unit is bytes. For quantities of time, the default unit |
| 290 | is seconds. |
| 291 | |
| 292 | With kb_base=1000, fio follows international standards for unit prefixes. |
| 293 | To specify power-of-10 decimal values defined in the International |
| 294 | System of Units (SI): |
| 295 | Ki means kilo (K) or 1000 |
| 296 | Mi means mega (M) or 1000**2 |
| 297 | Gi means giga (G) or 1000**3 |
| 298 | Ti means tera (T) or 1000**4 |
| 299 | Pi means peta (P) or 1000**5 |
| 300 | |
| 301 | To specify power-of-2 binary values defined in IEC 80000-13: |
| 302 | k means kibi (Ki) or 1024 |
| 303 | M means mebi (Mi) or 1024**2 |
| 304 | G means gibi (Gi) or 1024**3 |
| 305 | T means tebi (Ti) or 1024**4 |
| 306 | P means pebi (Pi) or 1024**5 |
| 307 | |
| 308 | With kb_base=1024 (the default), the unit prefixes are opposite from |
| 309 | those specified in the SI and IEC 80000-13 standards to provide |
| 310 | compatibility with old scripts. For example, 4k means 4096. |
| 311 | |
| 312 | For quantities of data, an optional unit of 'B' may be included |
| 313 | (e.g., 'kB' is the same as 'k'). |
| 314 | |
| 315 | The integer suffix is not case sensitive (e.g., m/mi mean mebi/mega, |
| 316 | not milli). 'b' and 'B' both mean byte, not bit. |
| 317 | |
| 318 | Examples with kb_base=1000: |
| 319 | 4 KiB: 4096, 4096b, 4096B, 4ki, 4kib, 4kiB, 4Ki, 4KiB |
| 320 | 1 MiB: 1048576, 1mi, 1024ki |
| 321 | 1 MB: 1000000, 1m, 1000k |
| 322 | 1 TiB: 1073741824, 1ti, 1024mi, 1048576ki |
| 323 | 1 TB: 1000000000, 1t, 1000m, 1000000k |
| 324 | |
| 325 | Examples with kb_base=1024 (default): |
| 326 | 4 KiB: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB |
| 327 | 1 MiB: 1048576, 1m, 1024k |
| 328 | 1 MB: 1000000, 1mi, 1000ki |
| 329 | 1 TiB: 1073741824, 1t, 1024m, 1048576k |
| 330 | 1 TB: 1000000000, 1ti, 1000mi, 1000000ki |
| 331 | |
| 332 | To specify times (units are not case sensitive): |
| 333 | D means days |
| 334 | H means hours |
| 335 | M mean minutes |
| 336 | s or sec means seconds (default) |
| 337 | ms or msec means milliseconds |
| 338 | us or usec means microseconds |
| 339 | |
| 340 | If the option accepts an upper and lower range, use a colon ':' or |
| 341 | minus '-' to separate such values. See irange. |
| 342 | |
| 343 | bool Boolean. Usually parsed as an integer, however only defined for |
| 344 | true and false (1 and 0). |
| 345 | irange Integer range with suffix. Allows value range to be given, such |
| 346 | as 1024-4096. A colon may also be used as the separator, eg |
| 347 | 1k:4k. If the option allows two sets of ranges, they can be |
| 348 | specified with a ',' or '/' delimiter: 1k-4k/8k-32k. Also see |
| 349 | int. |
| 350 | float_list A list of floating point numbers, separated by a ':' character. |
| 351 | |
| 352 | With the above in mind, here follows the complete list of fio job |
| 353 | parameters. |
| 354 | |
| 355 | name=str ASCII name of the job. This may be used to override the |
| 356 | name printed by fio for this job. Otherwise the job |
| 357 | name is used. On the command line this parameter has the |
| 358 | special purpose of also signaling the start of a new |
| 359 | job. |
| 360 | |
| 361 | wait_for=str Specifies the name of the already defined job to wait |
| 362 | for. Single waitee name only may be specified. If set, the job |
| 363 | won't be started until all workers of the waitee job are done. |
| 364 | |
| 365 | Wait_for operates on the job name basis, so there are a few |
| 366 | limitations. First, the waitee must be defined prior to the |
| 367 | waiter job (meaning no forward references). Second, if a job |
| 368 | is being referenced as a waitee, it must have a unique name |
| 369 | (no duplicate waitees). |
| 370 | |
| 371 | description=str Text description of the job. Doesn't do anything except |
| 372 | dump this text description when this job is run. It's |
| 373 | not parsed. |
| 374 | |
| 375 | directory=str Prefix filenames with this directory. Used to place files |
| 376 | in a different location than "./". See the 'filename' option |
| 377 | for escaping certain characters. |
| 378 | |
| 379 | filename=str Fio normally makes up a filename based on the job name, |
| 380 | thread number, and file number. If you want to share |
| 381 | files between threads in a job or several jobs, specify |
| 382 | a filename for each of them to override the default. |
| 383 | If the ioengine is file based, you can specify a number of |
| 384 | files by separating the names with a ':' colon. So if you |
| 385 | wanted a job to open /dev/sda and /dev/sdb as the two working |
| 386 | files, you would use filename=/dev/sda:/dev/sdb. On Windows, |
| 387 | disk devices are accessed as \\.\PhysicalDrive0 for the first |
| 388 | device, \\.\PhysicalDrive1 for the second etc. Note: Windows |
| 389 | and FreeBSD prevent write access to areas of the disk |
| 390 | containing in-use data (e.g. filesystems). |
| 391 | If the wanted filename does need to include a colon, then |
| 392 | escape that with a '\' character. For instance, if the filename |
| 393 | is "/dev/dsk/foo@3,0:c", then you would use |
| 394 | filename="/dev/dsk/foo@3,0\:c". '-' is a reserved name, meaning |
| 395 | stdin or stdout. Which of the two depends on the read/write |
| 396 | direction set. |
| 397 | |
| 398 | filename_format=str |
| 399 | If sharing multiple files between jobs, it is usually necessary |
| 400 | to have fio generate the exact names that you want. By default, |
| 401 | fio will name a file based on the default file format |
| 402 | specification of jobname.jobnumber.filenumber. With this |
| 403 | option, that can be customized. Fio will recognize and replace |
| 404 | the following keywords in this string: |
| 405 | |
| 406 | $jobname |
| 407 | The name of the worker thread or process. |
| 408 | |
| 409 | $jobnum |
| 410 | The incremental number of the worker thread or |
| 411 | process. |
| 412 | |
| 413 | $filenum |
| 414 | The incremental number of the file for that worker |
| 415 | thread or process. |
| 416 | |
| 417 | To have dependent jobs share a set of files, this option can |
| 418 | be set to have fio generate filenames that are shared between |
| 419 | the two. For instance, if testfiles.$filenum is specified, |
| 420 | file number 4 for any job will be named testfiles.4. The |
| 421 | default of $jobname.$jobnum.$filenum will be used if |
| 422 | no other format specifier is given. |
| 423 | |
| 424 | unique_filename=bool To avoid collisions between networked clients, fio |
| 425 | defaults to prefixing any generated filenames (with a directory |
| 426 | specified) with the source of the client connecting. To disable |
| 427 | this behavior, set this option to 0. |
| 428 | |
| 429 | opendir=str Tell fio to recursively add any file it can find in this |
| 430 | directory and down the file system tree. |
| 431 | |
| 432 | lockfile=str Fio defaults to not locking any files before it does |
| 433 | IO to them. If a file or file descriptor is shared, fio |
| 434 | can serialize IO to that file to make the end result |
| 435 | consistent. This is usual for emulating real workloads that |
| 436 | share files. The lock modes are: |
| 437 | |
| 438 | none No locking. The default. |
| 439 | exclusive Only one thread/process may do IO, |
| 440 | excluding all others. |
| 441 | readwrite Read-write locking on the file. Many |
| 442 | readers may access the file at the |
| 443 | same time, but writes get exclusive |
| 444 | access. |
| 445 | |
| 446 | readwrite=str |
| 447 | rw=str Type of io pattern. Accepted values are: |
| 448 | |
| 449 | read Sequential reads |
| 450 | write Sequential writes |
| 451 | trim Sequential trims |
| 452 | randwrite Random writes |
| 453 | randread Random reads |
| 454 | randtrim Random trims |
| 455 | rw,readwrite Sequential mixed reads and writes |
| 456 | randrw Random mixed reads and writes |
| 457 | trimwrite Sequential trim+write sequences |
| 458 | |
| 459 | Fio defaults to read if the option is not specified. |
| 460 | For the mixed io types, the default is to split them 50/50. |
| 461 | For certain types of io the result may still be skewed a bit, |
| 462 | since the speed may be different. It is possible to specify |
| 463 | a number of IO's to do before getting a new offset, this is |
| 464 | done by appending a ':<nr>' to the end of the string given. |
| 465 | For a random read, it would look like 'rw=randread:8' for |
| 466 | passing in an offset modifier with a value of 8. If the |
| 467 | suffix is used with a sequential IO pattern, then the value |
| 468 | specified will be added to the generated offset for each IO. |
| 469 | For instance, using rw=write:4k will skip 4k for every |
| 470 | write. It turns sequential IO into sequential IO with holes. |
| 471 | See the 'rw_sequencer' option. |
| 472 | |
| 473 | rw_sequencer=str If an offset modifier is given by appending a number to |
| 474 | the rw=<str> line, then this option controls how that |
| 475 | number modifies the IO offset being generated. Accepted |
| 476 | values are: |
| 477 | |
| 478 | sequential Generate sequential offset |
| 479 | identical Generate the same offset |
| 480 | |
| 481 | 'sequential' is only useful for random IO, where fio would |
| 482 | normally generate a new random offset for every IO. If you |
| 483 | append eg 8 to randread, you would get a new random offset for |
| 484 | every 8 IO's. The result would be a seek for only every 8 |
| 485 | IO's, instead of for every IO. Use rw=randread:8 to specify |
| 486 | that. As sequential IO is already sequential, setting |
| 487 | 'sequential' for that would not result in any differences. |
| 488 | 'identical' behaves in a similar fashion, except it sends |
| 489 | the same offset 8 number of times before generating a new |
| 490 | offset. |
| 491 | |
| 492 | kb_base=int Select the interpretation of unit prefixes in input parameters. |
| 493 | 1000 = Inputs comply with IEC 80000-13 and the International |
| 494 | System of Units (SI). Use: |
| 495 | - power-of-2 values with IEC prefixes (e.g., KiB) |
| 496 | - power-of-10 values with SI prefixes (e.g., kB) |
| 497 | 1024 = Compatibility mode (default). To avoid breaking |
| 498 | old scripts: |
| 499 | - power-of-2 values with SI prefixes |
| 500 | - power-of-10 values with IEC prefixes |
| 501 | See bs= for more details on input parameters. |
| 502 | |
| 503 | Outputs always use correct prefixes. Most outputs include |
| 504 | both side-by-side, like: |
| 505 | bw=2383.3kB/s (2327.4KiB/s) |
| 506 | If only one value is reported, then kb_base selects the |
| 507 | one to use: |
| 508 | 1000 = SI prefixes |
| 509 | 1024 = IEC prefixes |
| 510 | |
| 511 | unified_rw_reporting=bool Fio normally reports statistics on a per |
| 512 | data direction basis, meaning that reads, writes, and trims are |
| 513 | accounted and reported separately. If this option is set, |
| 514 | the fio will sum the results and report them as "mixed" |
| 515 | instead. |
| 516 | |
| 517 | randrepeat=bool For random IO workloads, seed the generator in a predictable |
| 518 | way so that results are repeatable across repetitions. |
| 519 | Defaults to true. |
| 520 | |
| 521 | randseed=int Seed the random number generators based on this seed value, to |
| 522 | be able to control what sequence of output is being generated. |
| 523 | If not set, the random sequence depends on the randrepeat |
| 524 | setting. |
| 525 | |
| 526 | fallocate=str Whether pre-allocation is performed when laying down files. |
| 527 | Accepted values are: |
| 528 | |
| 529 | none Do not pre-allocate space |
| 530 | posix Pre-allocate via posix_fallocate() |
| 531 | keep Pre-allocate via fallocate() with |
| 532 | FALLOC_FL_KEEP_SIZE set |
| 533 | 0 Backward-compatible alias for 'none' |
| 534 | 1 Backward-compatible alias for 'posix' |
| 535 | |
| 536 | May not be available on all supported platforms. 'keep' is only |
| 537 | available on Linux.If using ZFS on Solaris this must be set to |
| 538 | 'none' because ZFS doesn't support it. Default: 'posix'. |
| 539 | |
| 540 | fadvise_hint=bool By default, fio will use fadvise() to advise the kernel |
| 541 | on what IO patterns it is likely to issue. Sometimes you |
| 542 | want to test specific IO patterns without telling the |
| 543 | kernel about it, in which case you can disable this option. |
| 544 | The following options are supported: |
| 545 | |
| 546 | sequential Use FADV_SEQUENTIAL |
| 547 | random Use FADV_RANDOM |
| 548 | 1 Backwards-compatible hint for basing |
| 549 | the hint on the fio workload. Will use |
| 550 | FADV_SEQUENTIAL for a sequential |
| 551 | workload, and FADV_RANDOM for a random |
| 552 | workload. |
| 553 | 0 Backwards-compatible setting for not |
| 554 | issing a fadvise hint. |
| 555 | |
| 556 | fadvise_stream=int Notify the kernel what write stream ID to place these |
| 557 | writes under. Only supported on Linux. Note, this option |
| 558 | may change going forward. |
| 559 | |
| 560 | size=int The total size of file io for this job. Fio will run until |
| 561 | this many bytes has been transferred, unless runtime is |
| 562 | limited by other options (such as 'runtime', for instance, |
| 563 | or increased/decreased by 'io_size'). Unless specific nrfiles |
| 564 | and filesize options are given, fio will divide this size |
| 565 | between the available files specified by the job. If not set, |
| 566 | fio will use the full size of the given files or devices. |
| 567 | If the files do not exist, size must be given. It is also |
| 568 | possible to give size as a percentage between 1 and 100. If |
| 569 | size=20% is given, fio will use 20% of the full size of the |
| 570 | given files or devices. |
| 571 | |
| 572 | io_size=int |
| 573 | io_limit=int Normally fio operates within the region set by 'size', which |
| 574 | means that the 'size' option sets both the region and size of |
| 575 | IO to be performed. Sometimes that is not what you want. With |
| 576 | this option, it is possible to define just the amount of IO |
| 577 | that fio should do. For instance, if 'size' is set to 20GiB and |
| 578 | 'io_size' is set to 5GiB, fio will perform IO within the first |
| 579 | 20GiB but exit when 5GiB have been done. The opposite is also |
| 580 | possible - if 'size' is set to 20GiB, and 'io_size' is set to |
| 581 | 40GiB, then fio will do 40GiB of IO within the 0..20GiB region. |
| 582 | |
| 583 | filesize=int Individual file sizes. May be a range, in which case fio |
| 584 | will select sizes for files at random within the given range |
| 585 | and limited to 'size' in total (if that is given). If not |
| 586 | given, each created file is the same size. |
| 587 | |
| 588 | file_append=bool Perform IO after the end of the file. Normally fio will |
| 589 | operate within the size of a file. If this option is set, then |
| 590 | fio will append to the file instead. This has identical |
| 591 | behavior to setting offset to the size of a file. This option |
| 592 | is ignored on non-regular files. |
| 593 | |
| 594 | fill_device=bool |
| 595 | fill_fs=bool Sets size to something really large and waits for ENOSPC (no |
| 596 | space left on device) as the terminating condition. Only makes |
| 597 | sense with sequential write. For a read workload, the mount |
| 598 | point will be filled first then IO started on the result. This |
| 599 | option doesn't make sense if operating on a raw device node, |
| 600 | since the size of that is already known by the file system. |
| 601 | Additionally, writing beyond end-of-device will not return |
| 602 | ENOSPC there. |
| 603 | |
| 604 | blocksize=int[,int][,int] |
| 605 | bs=int[,int][,int] |
| 606 | The block size in bytes used for I/O units. Default: 4096. |
| 607 | A single value applies to reads, writes, and trims. |
| 608 | Comma-separated values may be specified for reads, writes, |
| 609 | and trims. A value not terminated in a comma applies to |
| 610 | subsequent types. |
| 611 | |
| 612 | Examples: |
| 613 | bs=256k means 256k for reads, writes and trims |
| 614 | bs=8k,32k means 8k for reads, 32k for writes and trims |
| 615 | bs=8k,32k, means 8k for reads, 32k for writes, and |
| 616 | default for trims |
| 617 | bs=,8k means default for reads, 8k for writes and trims |
| 618 | bs=,8k, means default for reads, 8k for writes, and |
| 619 | default for writes |
| 620 | |
| 621 | blocksize_range=irange[,irange][,irange] |
| 622 | bsrange=irange[,irange][,irange] |
| 623 | A range of block sizes in bytes for I/O units. |
| 624 | The issued I/O unit will always be a multiple of the minimum |
| 625 | size, unless blocksize_unaligned is set. |
| 626 | |
| 627 | Comma-separated ranges may be specified for reads, writes, |
| 628 | and trims as described in 'blocksize'. |
| 629 | |
| 630 | Example: bsrange=1k-4k,2k-8k |
| 631 | |
| 632 | bssplit=str[,str][,str] |
| 633 | Sometimes you want even finer grained control of the |
| 634 | block sizes issued, not just an even split between them. |
| 635 | This option allows you to weight various block sizes, |
| 636 | so that you are able to define a specific amount of |
| 637 | block sizes issued. The format for this option is: |
| 638 | |
| 639 | bssplit=blocksize/percentage:blocksize/percentage |
| 640 | |
| 641 | for as many block sizes as needed. So if you want to define |
| 642 | a workload that has 50% 64k blocks, 10% 4k blocks, and |
| 643 | 40% 32k blocks, you would write: |
| 644 | |
| 645 | bssplit=4k/10:64k/50:32k/40 |
| 646 | |
| 647 | Ordering does not matter. If the percentage is left blank, |
| 648 | fio will fill in the remaining values evenly. So a bssplit |
| 649 | option like this one: |
| 650 | |
| 651 | bssplit=4k/50:1k/:32k/ |
| 652 | |
| 653 | would have 50% 4k ios, and 25% 1k and 32k ios. The percentages |
| 654 | always add up to 100, if bssplit is given a range that adds |
| 655 | up to more, it will error out. |
| 656 | |
| 657 | Comma-separated values may be specified for reads, writes, |
| 658 | and trims as described in 'blocksize'. |
| 659 | |
| 660 | If you want a workload that has 50% 2k reads and 50% 4k reads, |
| 661 | while having 90% 4k writes and 10% 8k writes, you would |
| 662 | specify: |
| 663 | |
| 664 | bssplit=2k/50:4k/50,4k/90:8k/10 |
| 665 | |
| 666 | blocksize_unaligned |
| 667 | bs_unaligned If set, fio will issue I/O units with any size within |
| 668 | blocksize_range, not just multiples of the minimum size. |
| 669 | This typically won't work with direct I/O, as that normally |
| 670 | requires sector alignment. |
| 671 | |
| 672 | bs_is_seq_rand If this option is set, fio will use the normal read,write |
| 673 | blocksize settings as sequential,random blocksize settings |
| 674 | instead. Any random read or write will use the WRITE blocksize |
| 675 | settings, and any sequential read or write will use the READ |
| 676 | blocksize settings. |
| 677 | |
| 678 | blockalign=int[,int][,int] |
| 679 | ba=int[,int][,int] |
| 680 | Boundary to which fio will align random I/O units. |
| 681 | Default: 'blocksize'. |
| 682 | Minimum alignment is typically 512b for using direct IO, |
| 683 | though it usually depends on the hardware block size. This |
| 684 | option is mutually exclusive with using a random map for |
| 685 | files, so it will turn off that option. |
| 686 | Comma-separated values may be specified for reads, writes, |
| 687 | and trims as described in 'blocksize'. |
| 688 | |
| 689 | zero_buffers If this option is given, fio will init the IO buffers to |
| 690 | all zeroes. The default is to fill them with random data. |
| 691 | |
| 692 | refill_buffers If this option is given, fio will refill the IO buffers |
| 693 | on every submit. The default is to only fill it at init |
| 694 | time and reuse that data. Only makes sense if zero_buffers |
| 695 | isn't specified, naturally. If data verification is enabled, |
| 696 | refill_buffers is also automatically enabled. |
| 697 | |
| 698 | scramble_buffers=bool If refill_buffers is too costly and the target is |
| 699 | using data deduplication, then setting this option will |
| 700 | slightly modify the IO buffer contents to defeat normal |
| 701 | de-dupe attempts. This is not enough to defeat more clever |
| 702 | block compression attempts, but it will stop naive dedupe of |
| 703 | blocks. Default: true. |
| 704 | |
| 705 | buffer_compress_percentage=int If this is set, then fio will attempt to |
| 706 | provide IO buffer content (on WRITEs) that compress to |
| 707 | the specified level. Fio does this by providing a mix of |
| 708 | random data and a fixed pattern. The fixed pattern is either |
| 709 | zeroes, or the pattern specified by buffer_pattern. If the |
| 710 | pattern option is used, it might skew the compression ratio |
| 711 | slightly. Note that this is per block size unit, for file/disk |
| 712 | wide compression level that matches this setting, you'll also |
| 713 | want to set refill_buffers. |
| 714 | |
| 715 | buffer_compress_chunk=int See buffer_compress_percentage. This |
| 716 | setting allows fio to manage how big the ranges of random |
| 717 | data and zeroed data is. Without this set, fio will |
| 718 | provide buffer_compress_percentage of blocksize random |
| 719 | data, followed by the remaining zeroed. With this set |
| 720 | to some chunk size smaller than the block size, fio can |
| 721 | alternate random and zeroed data throughout the IO |
| 722 | buffer. |
| 723 | |
| 724 | buffer_pattern=str If set, fio will fill the io buffers with this |
| 725 | pattern. If not set, the contents of io buffers is defined by |
| 726 | the other options related to buffer contents. The setting can |
| 727 | be any pattern of bytes, and can be prefixed with 0x for hex |
| 728 | values. It may also be a string, where the string must then |
| 729 | be wrapped with "", e.g.: |
| 730 | |
| 731 | buffer_pattern="abcd" |
| 732 | or |
| 733 | buffer_pattern=-12 |
| 734 | or |
| 735 | buffer_pattern=0xdeadface |
| 736 | |
| 737 | Also you can combine everything together in any order: |
| 738 | buffer_pattern=0xdeadface"abcd"-12 |
| 739 | |
| 740 | dedupe_percentage=int If set, fio will generate this percentage of |
| 741 | identical buffers when writing. These buffers will be |
| 742 | naturally dedupable. The contents of the buffers depend on |
| 743 | what other buffer compression settings have been set. It's |
| 744 | possible to have the individual buffers either fully |
| 745 | compressible, or not at all. This option only controls the |
| 746 | distribution of unique buffers. |
| 747 | |
| 748 | nrfiles=int Number of files to use for this job. Defaults to 1. |
| 749 | |
| 750 | openfiles=int Number of files to keep open at the same time. Defaults to |
| 751 | the same as nrfiles, can be set smaller to limit the number |
| 752 | simultaneous opens. |
| 753 | |
| 754 | file_service_type=str Defines how fio decides which file from a job to |
| 755 | service next. The following types are defined: |
| 756 | |
| 757 | random Just choose a file at random. |
| 758 | |
| 759 | roundrobin Round robin over open files. This |
| 760 | is the default. |
| 761 | |
| 762 | sequential Finish one file before moving on to |
| 763 | the next. Multiple files can still be |
| 764 | open depending on 'openfiles'. |
| 765 | |
| 766 | zipf Use a zipfian distribution to decide what file |
| 767 | to access. |
| 768 | |
| 769 | pareto Use a pareto distribution to decide what file |
| 770 | to access. |
| 771 | |
| 772 | gauss Use a gaussian (normal) distribution to decide |
| 773 | what file to access. |
| 774 | |
| 775 | For random, roundrobin, and sequential, a postfix can be |
| 776 | appended to tell fio how many I/Os to issue before switching |
| 777 | to a new file. For example, specifying |
| 778 | 'file_service_type=random:8' would cause fio to issue 8 I/Os |
| 779 | before selecting a new file at random. For the non-uniform |
| 780 | distributions, a floating point postfix can be given to |
| 781 | influence how the distribution is skewed. See |
| 782 | 'random_distribution' for a description of how that would work. |
| 783 | |
| 784 | ioengine=str Defines how the job issues io to the file. The following |
| 785 | types are defined: |
| 786 | |
| 787 | sync Basic read(2) or write(2) io. lseek(2) is |
| 788 | used to position the io location. |
| 789 | |
| 790 | psync Basic pread(2) or pwrite(2) io. Default on all |
| 791 | supported operating systems except for Windows. |
| 792 | |
| 793 | vsync Basic readv(2) or writev(2) IO. |
| 794 | |
| 795 | pvsync Basic preadv(2) or pwritev(2) IO. |
| 796 | |
| 797 | pvsync2 Basic preadv2(2) or pwritev2(2) IO. |
| 798 | |
| 799 | libaio Linux native asynchronous io. Note that Linux |
| 800 | may only support queued behaviour with |
| 801 | non-buffered IO (set direct=1 or buffered=0). |
| 802 | This engine defines engine specific options. |
| 803 | |
| 804 | posixaio glibc posix asynchronous io. |
| 805 | |
| 806 | solarisaio Solaris native asynchronous io. |
| 807 | |
| 808 | windowsaio Windows native asynchronous io. |
| 809 | Default on Windows. |
| 810 | |
| 811 | mmap File is memory mapped and data copied |
| 812 | to/from using memcpy(3). |
| 813 | |
| 814 | splice splice(2) is used to transfer the data and |
| 815 | vmsplice(2) to transfer data from user |
| 816 | space to the kernel. |
| 817 | |
| 818 | sg SCSI generic sg v3 io. May either be |
| 819 | synchronous using the SG_IO ioctl, or if |
| 820 | the target is an sg character device |
| 821 | we use read(2) and write(2) for asynchronous |
| 822 | io. |
| 823 | |
| 824 | null Doesn't transfer any data, just pretends |
| 825 | to. This is mainly used to exercise fio |
| 826 | itself and for debugging/testing purposes. |
| 827 | |
| 828 | net Transfer over the network to given host:port. |
| 829 | Depending on the protocol used, the hostname, |
| 830 | port, listen and filename options are used to |
| 831 | specify what sort of connection to make, while |
| 832 | the protocol option determines which protocol |
| 833 | will be used. |
| 834 | This engine defines engine specific options. |
| 835 | |
| 836 | netsplice Like net, but uses splice/vmsplice to |
| 837 | map data and send/receive. |
| 838 | This engine defines engine specific options. |
| 839 | |
| 840 | cpuio Doesn't transfer any data, but burns CPU |
| 841 | cycles according to the cpuload= and |
| 842 | cpuchunks= options. Setting cpuload=85 |
| 843 | will cause that job to do nothing but burn |
| 844 | 85% of the CPU. In case of SMP machines, |
| 845 | use numjobs=<no_of_cpu> to get desired CPU |
| 846 | usage, as the cpuload only loads a single |
| 847 | CPU at the desired rate. A job never finishes |
| 848 | unless there is at least one non-cpuio job. |
| 849 | |
| 850 | guasi The GUASI IO engine is the Generic Userspace |
| 851 | Asyncronous Syscall Interface approach |
| 852 | to async IO. See |
| 853 | |
| 854 | http://www.xmailserver.org/guasi-lib.html |
| 855 | |
| 856 | for more info on GUASI. |
| 857 | |
| 858 | rdma The RDMA I/O engine supports both RDMA |
| 859 | memory semantics (RDMA_WRITE/RDMA_READ) and |
| 860 | channel semantics (Send/Recv) for the |
| 861 | InfiniBand, RoCE and iWARP protocols. |
| 862 | |
| 863 | falloc IO engine that does regular fallocate to |
| 864 | simulate data transfer as fio ioengine. |
| 865 | DDIR_READ does fallocate(,mode = keep_size,) |
| 866 | DDIR_WRITE does fallocate(,mode = 0) |
| 867 | DDIR_TRIM does fallocate(,mode = punch_hole) |
| 868 | |
| 869 | e4defrag IO engine that does regular EXT4_IOC_MOVE_EXT |
| 870 | ioctls to simulate defragment activity in |
| 871 | request to DDIR_WRITE event |
| 872 | |
| 873 | rbd IO engine supporting direct access to Ceph |
| 874 | Rados Block Devices (RBD) via librbd without |
| 875 | the need to use the kernel rbd driver. This |
| 876 | ioengine defines engine specific options. |
| 877 | |
| 878 | gfapi Using Glusterfs libgfapi sync interface to |
| 879 | direct access to Glusterfs volumes without |
| 880 | options. |
| 881 | |
| 882 | gfapi_async Using Glusterfs libgfapi async interface |
| 883 | to direct access to Glusterfs volumes without |
| 884 | having to go through FUSE. This ioengine |
| 885 | defines engine specific options. |
| 886 | |
| 887 | libhdfs Read and write through Hadoop (HDFS). |
| 888 | This engine interprets offsets a little |
| 889 | differently. In HDFS, files once created |
| 890 | cannot be modified. So random writes are not |
| 891 | possible. To imitate this, libhdfs engine |
| 892 | creates bunch of small files, and engine will |
| 893 | pick a file out of those files based on the |
| 894 | offset generated by fio backend. Each jobs uses |
| 895 | it's own connection to HDFS. |
| 896 | |
| 897 | mtd Read, write and erase an MTD character device |
| 898 | (e.g., /dev/mtd0). Discards are treated as |
| 899 | erases. Depending on the underlying device |
| 900 | type, the I/O may have to go in a certain |
| 901 | pattern, e.g., on NAND, writing sequentially |
| 902 | to erase blocks and discarding before |
| 903 | overwriting. The writetrim mode works well |
| 904 | for this constraint. |
| 905 | |
| 906 | pmemblk Read and write through the NVML libpmemblk |
| 907 | interface. |
| 908 | |
| 909 | dev-dax Read and write through a DAX device exposed |
| 910 | from persistent memory. |
| 911 | |
| 912 | external Prefix to specify loading an external |
| 913 | IO engine object file. Append the engine |
| 914 | filename, eg ioengine=external:/tmp/foo.o |
| 915 | to load ioengine foo.o in /tmp. |
| 916 | |
| 917 | iodepth=int This defines how many I/O units to keep in flight against |
| 918 | the file. The default is 1 for each file defined in this |
| 919 | job, can be overridden with a larger value for higher |
| 920 | concurrency. Note that increasing iodepth beyond 1 will not |
| 921 | affect synchronous ioengines (except for small degress when |
| 922 | verify_async is in use). Even async engines may impose OS |
| 923 | restrictions causing the desired depth not to be achieved. |
| 924 | This may happen on Linux when using libaio and not setting |
| 925 | direct=1, since buffered IO is not async on that OS. Keep an |
| 926 | eye on the IO depth distribution in the fio output to verify |
| 927 | that the achieved depth is as expected. Default: 1. |
| 928 | |
| 929 | iodepth_batch_submit=int |
| 930 | iodepth_batch=int This defines how many pieces of IO to submit at once. |
| 931 | It defaults to 1 which means that we submit each IO |
| 932 | as soon as it is available, but can be raised to submit |
| 933 | bigger batches of IO at the time. If it is set to 0 the iodepth |
| 934 | value will be used. |
| 935 | |
| 936 | iodepth_batch_complete_min=int |
| 937 | iodepth_batch_complete=int This defines how many pieces of IO to retrieve |
| 938 | at once. It defaults to 1 which means that we'll ask |
| 939 | for a minimum of 1 IO in the retrieval process from |
| 940 | the kernel. The IO retrieval will go on until we |
| 941 | hit the limit set by iodepth_low. If this variable is |
| 942 | set to 0, then fio will always check for completed |
| 943 | events before queuing more IO. This helps reduce |
| 944 | IO latency, at the cost of more retrieval system calls. |
| 945 | |
| 946 | iodepth_batch_complete_max=int This defines maximum pieces of IO to |
| 947 | retrieve at once. This variable should be used along with |
| 948 | iodepth_batch_complete_min=int variable, specifying the range |
| 949 | of min and max amount of IO which should be retrieved. By default |
| 950 | it is equal to iodepth_batch_complete_min value. |
| 951 | |
| 952 | Example #1: |
| 953 | |
| 954 | iodepth_batch_complete_min=1 |
| 955 | iodepth_batch_complete_max=<iodepth> |
| 956 | |
| 957 | which means that we will retrieve at least 1 IO and up to the |
| 958 | whole submitted queue depth. If none of IO has been completed |
| 959 | yet, we will wait. |
| 960 | |
| 961 | Example #2: |
| 962 | |
| 963 | iodepth_batch_complete_min=0 |
| 964 | iodepth_batch_complete_max=<iodepth> |
| 965 | |
| 966 | which means that we can retrieve up to the whole submitted |
| 967 | queue depth, but if none of IO has been completed yet, we will |
| 968 | NOT wait and immediately exit the system call. In this example |
| 969 | we simply do polling. |
| 970 | |
| 971 | iodepth_low=int The low water mark indicating when to start filling |
| 972 | the queue again. Defaults to the same as iodepth, meaning |
| 973 | that fio will attempt to keep the queue full at all times. |
| 974 | If iodepth is set to eg 16 and iodepth_low is set to 4, then |
| 975 | after fio has filled the queue of 16 requests, it will let |
| 976 | the depth drain down to 4 before starting to fill it again. |
| 977 | |
| 978 | io_submit_mode=str This option controls how fio submits the IO to |
| 979 | the IO engine. The default is 'inline', which means that the |
| 980 | fio job threads submit and reap IO directly. If set to |
| 981 | 'offload', the job threads will offload IO submission to a |
| 982 | dedicated pool of IO threads. This requires some coordination |
| 983 | and thus has a bit of extra overhead, especially for lower |
| 984 | queue depth IO where it can increase latencies. The benefit |
| 985 | is that fio can manage submission rates independently of |
| 986 | the device completion rates. This avoids skewed latency |
| 987 | reporting if IO gets back up on the device side (the |
| 988 | coordinated omission problem). |
| 989 | |
| 990 | direct=bool If value is true, use non-buffered io. This is usually |
| 991 | O_DIRECT. Note that ZFS on Solaris doesn't support direct io. |
| 992 | On Windows the synchronous ioengines don't support direct io. |
| 993 | |
| 994 | atomic=bool If value is true, attempt to use atomic direct IO. Atomic |
| 995 | writes are guaranteed to be stable once acknowledged by |
| 996 | the operating system. Only Linux supports O_ATOMIC right |
| 997 | now. |
| 998 | |
| 999 | buffered=bool If value is true, use buffered io. This is the opposite |
| 1000 | of the 'direct' option. Defaults to true. |
| 1001 | |
| 1002 | offset=int Start io at the given offset in the file. The data before |
| 1003 | the given offset will not be touched. This effectively |
| 1004 | caps the file size at real_size - offset. |
| 1005 | |
| 1006 | offset_increment=int If this is provided, then the real offset becomes |
| 1007 | offset + offset_increment * thread_number, where the thread |
| 1008 | number is a counter that starts at 0 and is incremented for |
| 1009 | each sub-job (i.e. when numjobs option is specified). This |
| 1010 | option is useful if there are several jobs which are intended |
| 1011 | to operate on a file in parallel disjoint segments, with |
| 1012 | even spacing between the starting points. |
| 1013 | |
| 1014 | number_ios=int Fio will normally perform IOs until it has exhausted the size |
| 1015 | of the region set by size=, or if it exhaust the allocated |
| 1016 | time (or hits an error condition). With this setting, the |
| 1017 | range/size can be set independently of the number of IOs to |
| 1018 | perform. When fio reaches this number, it will exit normally |
| 1019 | and report status. Note that this does not extend the amount |
| 1020 | of IO that will be done, it will only stop fio if this |
| 1021 | condition is met before other end-of-job criteria. |
| 1022 | |
| 1023 | fsync=int If writing to a file, issue a sync of the dirty data |
| 1024 | for every number of blocks given. For example, if you give |
| 1025 | 32 as a parameter, fio will sync the file for every 32 |
| 1026 | writes issued. If fio is using non-buffered io, we may |
| 1027 | not sync the file. The exception is the sg io engine, which |
| 1028 | synchronizes the disk cache anyway. |
| 1029 | |
| 1030 | fdatasync=int Like fsync= but uses fdatasync() to only sync data and not |
| 1031 | metadata blocks. |
| 1032 | In FreeBSD and Windows there is no fdatasync(), this falls back |
| 1033 | to using fsync() |
| 1034 | |
| 1035 | sync_file_range=str:val Use sync_file_range() for every 'val' number of |
| 1036 | write operations. Fio will track range of writes that |
| 1037 | have happened since the last sync_file_range() call. 'str' |
| 1038 | can currently be one or more of: |
| 1039 | |
| 1040 | wait_before SYNC_FILE_RANGE_WAIT_BEFORE |
| 1041 | write SYNC_FILE_RANGE_WRITE |
| 1042 | wait_after SYNC_FILE_RANGE_WAIT_AFTER |
| 1043 | |
| 1044 | So if you do sync_file_range=wait_before,write:8, fio would |
| 1045 | use SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE for |
| 1046 | every 8 writes. Also see the sync_file_range(2) man page. |
| 1047 | This option is Linux specific. |
| 1048 | |
| 1049 | overwrite=bool If true, writes to a file will always overwrite existing |
| 1050 | data. If the file doesn't already exist, it will be |
| 1051 | created before the write phase begins. If the file exists |
| 1052 | and is large enough for the specified write phase, nothing |
| 1053 | will be done. |
| 1054 | |
| 1055 | end_fsync=bool If true, fsync file contents when a write stage has completed. |
| 1056 | |
| 1057 | fsync_on_close=bool If true, fio will fsync() a dirty file on close. |
| 1058 | This differs from end_fsync in that it will happen on every |
| 1059 | file close, not just at the end of the job. |
| 1060 | |
| 1061 | rwmixread=int How large a percentage of the mix should be reads. |
| 1062 | |
| 1063 | rwmixwrite=int How large a percentage of the mix should be writes. If both |
| 1064 | rwmixread and rwmixwrite is given and the values do not add |
| 1065 | up to 100%, the latter of the two will be used to override |
| 1066 | the first. This may interfere with a given rate setting, |
| 1067 | if fio is asked to limit reads or writes to a certain rate. |
| 1068 | If that is the case, then the distribution may be skewed. |
| 1069 | |
| 1070 | random_distribution=str:float[,str:float][,str:float] |
| 1071 | By default, fio will use a completely uniform |
| 1072 | random distribution when asked to perform random IO. Sometimes |
| 1073 | it is useful to skew the distribution in specific ways, |
| 1074 | ensuring that some parts of the data is more hot than others. |
| 1075 | fio includes the following distribution models: |
| 1076 | |
| 1077 | random Uniform random distribution |
| 1078 | zipf Zipf distribution |
| 1079 | pareto Pareto distribution |
| 1080 | gauss Normal (gaussian) distribution |
| 1081 | zoned Zoned random distribution |
| 1082 | |
| 1083 | When using a zipf or pareto distribution, an input value |
| 1084 | is also needed to define the access pattern. For zipf, this |
| 1085 | is the zipf theta. For pareto, it's the pareto power. Fio |
| 1086 | includes a test program, genzipf, that can be used visualize |
| 1087 | what the given input values will yield in terms of hit rates. |
| 1088 | If you wanted to use zipf with a theta of 1.2, you would use |
| 1089 | random_distribution=zipf:1.2 as the option. If a non-uniform |
| 1090 | model is used, fio will disable use of the random map. For |
| 1091 | the gauss distribution, a normal deviation is supplied as |
| 1092 | a value between 0 and 100. |
| 1093 | |
| 1094 | For a zoned distribution, fio supports specifying percentages |
| 1095 | of IO access that should fall within what range of the file or |
| 1096 | device. For example, given a criteria of: |
| 1097 | |
| 1098 | 60% of accesses should be to the first 10% |
| 1099 | 30% of accesses should be to the next 20% |
| 1100 | 8% of accesses should be to to the next 30% |
| 1101 | 2% of accesses should be to the next 40% |
| 1102 | |
| 1103 | we can define that through zoning of the random accesses. For |
| 1104 | the above example, the user would do: |
| 1105 | |
| 1106 | random_distribution=zoned:60/10:30/20:8/30:2/40 |
| 1107 | |
| 1108 | similarly to how bssplit works for setting ranges and |
| 1109 | percentages of block sizes. Like bssplit, it's possible to |
| 1110 | specify separate zones for reads, writes, and trims. If just |
| 1111 | one set is given, it'll apply to all of them. |
| 1112 | |
| 1113 | percentage_random=int[,int][,int] |
| 1114 | For a random workload, set how big a percentage should |
| 1115 | be random. This defaults to 100%, in which case the workload |
| 1116 | is fully random. It can be set from anywhere from 0 to 100. |
| 1117 | Setting it to 0 would make the workload fully sequential. Any |
| 1118 | setting in between will result in a random mix of sequential |
| 1119 | and random IO, at the given percentages. |
| 1120 | Comma-separated values may be specified for reads, writes, |
| 1121 | and trims as described in 'blocksize'. |
| 1122 | |
| 1123 | norandommap Normally fio will cover every block of the file when doing |
| 1124 | random IO. If this option is given, fio will just get a |
| 1125 | new random offset without looking at past io history. This |
| 1126 | means that some blocks may not be read or written, and that |
| 1127 | some blocks may be read/written more than once. If this option |
| 1128 | is used with verify= and multiple blocksizes (via bsrange=), |
| 1129 | only intact blocks are verified, i.e., partially-overwritten |
| 1130 | blocks are ignored. |
| 1131 | |
| 1132 | softrandommap=bool See norandommap. If fio runs with the random block map |
| 1133 | enabled and it fails to allocate the map, if this option is |
| 1134 | set it will continue without a random block map. As coverage |
| 1135 | will not be as complete as with random maps, this option is |
| 1136 | disabled by default. |
| 1137 | |
| 1138 | random_generator=str Fio supports the following engines for generating |
| 1139 | IO offsets for random IO: |
| 1140 | |
| 1141 | tausworthe Strong 2^88 cycle random number generator |
| 1142 | lfsr Linear feedback shift register generator |
| 1143 | tausworthe64 Strong 64-bit 2^258 cycle random number |
| 1144 | generator |
| 1145 | |
| 1146 | Tausworthe is a strong random number generator, but it |
| 1147 | requires tracking on the side if we want to ensure that |
| 1148 | blocks are only read or written once. LFSR guarantees |
| 1149 | that we never generate the same offset twice, and it's |
| 1150 | also less computationally expensive. It's not a true |
| 1151 | random generator, however, though for IO purposes it's |
| 1152 | typically good enough. LFSR only works with single |
| 1153 | block sizes, not with workloads that use multiple block |
| 1154 | sizes. If used with such a workload, fio may read or write |
| 1155 | some blocks multiple times. The default value is tausworthe, |
| 1156 | unless the required space exceeds 2^32 blocks. If it does, |
| 1157 | then tausworthe64 is selected automatically. |
| 1158 | |
| 1159 | nice=int Run the job with the given nice value. See man nice(2). |
| 1160 | |
| 1161 | On Windows, values less than -15 set the process class to "High"; |
| 1162 | -1 through -15 set "Above Normal"; 1 through 15 "Below Normal"; |
| 1163 | and above 15 "Idle" priority class. |
| 1164 | |
| 1165 | prio=int Set the io priority value of this job. Linux limits us to |
| 1166 | a positive value between 0 and 7, with 0 being the highest. |
| 1167 | See man ionice(1). Refer to an appropriate manpage for |
| 1168 | other operating systems since meaning of priority may differ. |
| 1169 | |
| 1170 | prioclass=int Set the io priority class. See man ionice(1). |
| 1171 | |
| 1172 | thinktime=int Stall the job x microseconds after an io has completed before |
| 1173 | issuing the next. May be used to simulate processing being |
| 1174 | done by an application. See thinktime_blocks and |
| 1175 | thinktime_spin. |
| 1176 | |
| 1177 | thinktime_spin=int |
| 1178 | Only valid if thinktime is set - pretend to spend CPU time |
| 1179 | doing something with the data received, before falling back |
| 1180 | to sleeping for the rest of the period specified by |
| 1181 | thinktime. |
| 1182 | |
| 1183 | thinktime_blocks=int |
| 1184 | Only valid if thinktime is set - control how many blocks |
| 1185 | to issue, before waiting 'thinktime' usecs. If not set, |
| 1186 | defaults to 1 which will make fio wait 'thinktime' usecs |
| 1187 | after every block. This effectively makes any queue depth |
| 1188 | setting redundant, since no more than 1 IO will be queued |
| 1189 | before we have to complete it and do our thinktime. In |
| 1190 | other words, this setting effectively caps the queue depth |
| 1191 | if the latter is larger. |
| 1192 | |
| 1193 | rate=int[,int][,int] |
| 1194 | Cap the bandwidth used by this job. The number is in bytes/sec, |
| 1195 | the normal suffix rules apply. |
| 1196 | Comma-separated values may be specified for reads, writes, |
| 1197 | and trims as described in 'blocksize'. |
| 1198 | |
| 1199 | rate_min=int[,int][,int] |
| 1200 | Tell fio to do whatever it can to maintain at least this |
| 1201 | bandwidth. Failing to meet this requirement will cause |
| 1202 | the job to exit. |
| 1203 | Comma-separated values may be specified for reads, writes, |
| 1204 | and trims as described in 'blocksize'. |
| 1205 | |
| 1206 | rate_iops=int[,int][,int] |
| 1207 | Cap the bandwidth to this number of IOPS. Basically the same |
| 1208 | as rate, just specified independently of bandwidth. If the |
| 1209 | job is given a block size range instead of a fixed value, |
| 1210 | the smallest block size is used as the metric. |
| 1211 | Comma-separated values may be specified for reads, writes, |
| 1212 | and trims as described in 'blocksize'. |
| 1213 | |
| 1214 | rate_iops_min=int[,int][,int] |
| 1215 | If fio doesn't meet this rate of IO, it will cause |
| 1216 | the job to exit. |
| 1217 | Comma-separated values may be specified for reads, writes, |
| 1218 | and trims as described in 'blocksize'. |
| 1219 | |
| 1220 | rate_process=str This option controls how fio manages rated IO |
| 1221 | submissions. The default is 'linear', which submits IO in a |
| 1222 | linear fashion with fixed delays between IOs that gets |
| 1223 | adjusted based on IO completion rates. If this is set to |
| 1224 | 'poisson', fio will submit IO based on a more real world |
| 1225 | random request flow, known as the Poisson process |
| 1226 | (https://en.wikipedia.org/wiki/Poisson_process). The lambda |
| 1227 | will be 10^6 / IOPS for the given workload. |
| 1228 | |
| 1229 | latency_target=int If set, fio will attempt to find the max performance |
| 1230 | point that the given workload will run at while maintaining a |
| 1231 | latency below this target. The values is given in microseconds. |
| 1232 | See latency_window and latency_percentile |
| 1233 | |
| 1234 | latency_window=int Used with latency_target to specify the sample window |
| 1235 | that the job is run at varying queue depths to test the |
| 1236 | performance. The value is given in microseconds. |
| 1237 | |
| 1238 | latency_percentile=float The percentage of IOs that must fall within the |
| 1239 | criteria specified by latency_target and latency_window. If not |
| 1240 | set, this defaults to 100.0, meaning that all IOs must be equal |
| 1241 | or below to the value set by latency_target. |
| 1242 | |
| 1243 | max_latency=int If set, fio will exit the job if it exceeds this maximum |
| 1244 | latency. It will exit with an ETIME error. |
| 1245 | |
| 1246 | rate_cycle=int Average bandwidth for 'rate' and 'rate_min' over this number |
| 1247 | of milliseconds. |
| 1248 | |
| 1249 | cpumask=int Set the CPU affinity of this job. The parameter given is a |
| 1250 | bitmask of allowed CPU's the job may run on. So if you want |
| 1251 | the allowed CPUs to be 1 and 5, you would pass the decimal |
| 1252 | value of (1 << 1 | 1 << 5), or 34. See man |
| 1253 | sched_setaffinity(2). This may not work on all supported |
| 1254 | operating systems or kernel versions. This option doesn't |
| 1255 | work well for a higher CPU count than what you can store in |
| 1256 | an integer mask, so it can only control cpus 1-32. For |
| 1257 | boxes with larger CPU counts, use cpus_allowed. |
| 1258 | |
| 1259 | cpus_allowed=str Controls the same options as cpumask, but it allows a text |
| 1260 | setting of the permitted CPUs instead. So to use CPUs 1 and |
| 1261 | 5, you would specify cpus_allowed=1,5. This options also |
| 1262 | allows a range of CPUs. Say you wanted a binding to CPUs |
| 1263 | 1, 5, and 8-15, you would set cpus_allowed=1,5,8-15. |
| 1264 | |
| 1265 | cpus_allowed_policy=str Set the policy of how fio distributes the CPUs |
| 1266 | specified by cpus_allowed or cpumask. Two policies are |
| 1267 | supported: |
| 1268 | |
| 1269 | shared All jobs will share the CPU set specified. |
| 1270 | split Each job will get a unique CPU from the CPU set. |
| 1271 | |
| 1272 | 'shared' is the default behaviour, if the option isn't |
| 1273 | specified. If split is specified, then fio will will assign |
| 1274 | one cpu per job. If not enough CPUs are given for the jobs |
| 1275 | listed, then fio will roundrobin the CPUs in the set. |
| 1276 | |
| 1277 | numa_cpu_nodes=str Set this job running on specified NUMA nodes' CPUs. The |
| 1278 | arguments allow comma delimited list of cpu numbers, |
| 1279 | A-B ranges, or 'all'. Note, to enable numa options support, |
| 1280 | fio must be built on a system with libnuma-dev(el) installed. |
| 1281 | |
| 1282 | numa_mem_policy=str Set this job's memory policy and corresponding NUMA |
| 1283 | nodes. Format of the arguments: |
| 1284 | <mode>[:<nodelist>] |
| 1285 | `mode' is one of the following memory policy: |
| 1286 | default, prefer, bind, interleave, local |
| 1287 | For `default' and `local' memory policy, no node is |
| 1288 | needed to be specified. |
| 1289 | For `prefer', only one node is allowed. |
| 1290 | For `bind' and `interleave', it allow comma delimited |
| 1291 | list of numbers, A-B ranges, or 'all'. |
| 1292 | |
| 1293 | startdelay=time Start this job the specified number of seconds after fio |
| 1294 | has started. Only useful if the job file contains several |
| 1295 | jobs, and you want to delay starting some jobs to a certain |
| 1296 | time. |
| 1297 | |
| 1298 | runtime=time Tell fio to terminate processing after the specified number |
| 1299 | of seconds. It can be quite hard to determine for how long |
| 1300 | a specified job will run, so this parameter is handy to |
| 1301 | cap the total runtime to a given time. |
| 1302 | |
| 1303 | time_based If set, fio will run for the duration of the runtime |
| 1304 | specified even if the file(s) are completely read or |
| 1305 | written. It will simply loop over the same workload |
| 1306 | as many times as the runtime allows. |
| 1307 | |
| 1308 | ramp_time=time If set, fio will run the specified workload for this amount |
| 1309 | of time before logging any performance numbers. Useful for |
| 1310 | letting performance settle before logging results, thus |
| 1311 | minimizing the runtime required for stable results. Note |
| 1312 | that the ramp_time is considered lead in time for a job, |
| 1313 | thus it will increase the total runtime if a special timeout |
| 1314 | or runtime is specified. |
| 1315 | |
| 1316 | steadystate=str:float |
| 1317 | ss=str:float Define the criterion and limit for assessing steady state |
| 1318 | performance. The first parameter designates the criterion |
| 1319 | whereas the second parameter sets the threshold. When the |
| 1320 | criterion falls below the threshold for the specified duration, |
| 1321 | the job will stop. For example, iops_slope:0.1% will direct fio |
| 1322 | to terminate the job when the least squares regression slope |
| 1323 | falls below 0.1% of the mean IOPS. If group_reporting is |
| 1324 | enabled this will apply to all jobs in the group. Below is the |
| 1325 | list of available steady state assessment criteria. All |
| 1326 | assessments are carried out using only data from the rolling |
| 1327 | collection window. Threshold limits can be expressed as a fixed |
| 1328 | value or as a percentage of the mean in the collection window. |
| 1329 | iops Collect IOPS data. Stop the job if all |
| 1330 | individual IOPS measurements are within the |
| 1331 | specified limit of the mean IOPS (e.g., iops:2 |
| 1332 | means that all individual IOPS values must be |
| 1333 | within 2 of the mean, whereas iops:0.2% means |
| 1334 | that all individual IOPS values must be within |
| 1335 | 0.2% of the mean IOPS to terminate the job). |
| 1336 | iops_slope |
| 1337 | Collect IOPS data and calculate the least |
| 1338 | squares regression slope. Stop the job if the |
| 1339 | slope falls below the specified limit. |
| 1340 | bw Collect bandwidth data. Stop the job if all |
| 1341 | individual bandwidth measurements are within |
| 1342 | the specified limit of the mean bandwidth. |
| 1343 | bw_slope |
| 1344 | Collect bandwidth data and calculate the least |
| 1345 | squares regression slope. Stop the job if the |
| 1346 | slope falls below the specified limit. |
| 1347 | |
| 1348 | steadystate_duration=time |
| 1349 | ss_dur=time A rolling window of this duration will be used to judge whether |
| 1350 | steady state has been reached. Data will be collected once per |
| 1351 | second. The default is 0 which disables steady state detection. |
| 1352 | |
| 1353 | steadystate_ramp_time=time |
| 1354 | ss_ramp=time Allow the job to run for the specified duration before |
| 1355 | beginning data collection for checking the steady state job |
| 1356 | termination criterion. The default is 0. |
| 1357 | |
| 1358 | invalidate=bool Invalidate the buffer/page cache parts for this file prior |
| 1359 | to starting io. Defaults to true. |
| 1360 | |
| 1361 | sync=bool Use sync io for buffered writes. For the majority of the |
| 1362 | io engines, this means using O_SYNC. |
| 1363 | |
| 1364 | iomem=str |
| 1365 | mem=str Fio can use various types of memory as the I/O unit buffer. |
| 1366 | The allowed values are: |
| 1367 | |
| 1368 | malloc Use memory from malloc(3) as the buffers. |
| 1369 | Default memory type. |
| 1370 | |
| 1371 | shm Use shared memory as the buffers. Allocated |
| 1372 | through shmget(2). |
| 1373 | |
| 1374 | shmhuge Same as shm, but use huge pages as backing. |
| 1375 | |
| 1376 | mmap Use mmap to allocate buffers. May either be |
| 1377 | anonymous memory, or can be file backed if |
| 1378 | a filename is given after the option. The |
| 1379 | format is mem=mmap:/path/to/file. |
| 1380 | |
| 1381 | mmaphuge Use a memory mapped huge file as the buffer |
| 1382 | backing. Append filename after mmaphuge, ala |
| 1383 | mem=mmaphuge:/hugetlbfs/file |
| 1384 | |
| 1385 | mmapshared Same as mmap, but use a MMAP_SHARED |
| 1386 | mapping. |
| 1387 | |
| 1388 | The area allocated is a function of the maximum allowed |
| 1389 | bs size for the job, multiplied by the io depth given. Note |
| 1390 | that for shmhuge and mmaphuge to work, the system must have |
| 1391 | free huge pages allocated. This can normally be checked |
| 1392 | and set by reading/writing /proc/sys/vm/nr_hugepages on a |
| 1393 | Linux system. Fio assumes a huge page is 4MiB in size. So |
| 1394 | to calculate the number of huge pages you need for a given |
| 1395 | job file, add up the io depth of all jobs (normally one unless |
| 1396 | iodepth= is used) and multiply by the maximum bs set. Then |
| 1397 | divide that number by the huge page size. You can see the |
| 1398 | size of the huge pages in /proc/meminfo. If no huge pages |
| 1399 | are allocated by having a non-zero number in nr_hugepages, |
| 1400 | using mmaphuge or shmhuge will fail. Also see hugepage-size. |
| 1401 | |
| 1402 | mmaphuge also needs to have hugetlbfs mounted and the file |
| 1403 | location should point there. So if it's mounted in /huge, |
| 1404 | you would use mem=mmaphuge:/huge/somefile. |
| 1405 | |
| 1406 | iomem_align=int This indicates the memory alignment of the IO memory buffers. |
| 1407 | Note that the given alignment is applied to the first I/O unit |
| 1408 | buffer, if using iodepth the alignment of the following buffers |
| 1409 | are given by the bs used. In other words, if using a bs that is |
| 1410 | a multiple of the page sized in the system, all buffers will |
| 1411 | be aligned to this value. If using a bs that is not page |
| 1412 | aligned, the alignment of subsequent IO memory buffers is the |
| 1413 | sum of the iomem_align and bs used. |
| 1414 | |
| 1415 | hugepage-size=int |
| 1416 | Defines the size of a huge page. Must at least be equal |
| 1417 | to the system setting, see /proc/meminfo. Defaults to 4MiB. |
| 1418 | Should probably always be a multiple of megabytes, so using |
| 1419 | hugepage-size=Xm is the preferred way to set this to avoid |
| 1420 | setting a non-pow-2 bad value. |
| 1421 | |
| 1422 | exitall When one job finishes, terminate the rest. The default is |
| 1423 | to wait for each job to finish, sometimes that is not the |
| 1424 | desired action. |
| 1425 | |
| 1426 | exitall_on_error When one job finishes in error, terminate the rest. The |
| 1427 | default is to wait for each job to finish. |
| 1428 | |
| 1429 | bwavgtime=int Average the calculated bandwidth over the given time. Value |
| 1430 | is specified in milliseconds. If the job also does bandwidth |
| 1431 | logging through 'write_bw_log', then the minimum of this option |
| 1432 | and 'log_avg_msec' will be used. Default: 500ms. |
| 1433 | |
| 1434 | iopsavgtime=int Average the calculated IOPS over the given time. Value |
| 1435 | is specified in milliseconds. If the job also does IOPS logging |
| 1436 | through 'write_iops_log', then the minimum of this option and |
| 1437 | 'log_avg_msec' will be used. Default: 500ms. |
| 1438 | |
| 1439 | create_serialize=bool If true, serialize the file creation for the jobs. |
| 1440 | This may be handy to avoid interleaving of data |
| 1441 | files, which may greatly depend on the filesystem |
| 1442 | used and even the number of processors in the system. |
| 1443 | |
| 1444 | create_fsync=bool fsync the data file after creation. This is the |
| 1445 | default. |
| 1446 | |
| 1447 | create_on_open=bool Don't pre-setup the files for IO, just create open() |
| 1448 | when it's time to do IO to that file. |
| 1449 | |
| 1450 | create_only=bool If true, fio will only run the setup phase of the job. |
| 1451 | If files need to be laid out or updated on disk, only |
| 1452 | that will be done. The actual job contents are not |
| 1453 | executed. |
| 1454 | |
| 1455 | allow_file_create=bool If true, fio is permitted to create files as part |
| 1456 | of its workload. This is the default behavior. If this |
| 1457 | option is false, then fio will error out if the files it |
| 1458 | needs to use don't already exist. Default: true. |
| 1459 | |
| 1460 | allow_mounted_write=bool If this isn't set, fio will abort jobs that |
| 1461 | are destructive (eg that write) to what appears to be a |
| 1462 | mounted device or partition. This should help catch creating |
| 1463 | inadvertently destructive tests, not realizing that the test |
| 1464 | will destroy data on the mounted file system. Default: false. |
| 1465 | |
| 1466 | pre_read=bool If this is given, files will be pre-read into memory before |
| 1467 | starting the given IO operation. This will also clear |
| 1468 | the 'invalidate' flag, since it is pointless to pre-read |
| 1469 | and then drop the cache. This will only work for IO engines |
| 1470 | that are seek-able, since they allow you to read the same data |
| 1471 | multiple times. Thus it will not work on eg network or splice |
| 1472 | IO. |
| 1473 | |
| 1474 | unlink=bool Unlink the job files when done. Not the default, as repeated |
| 1475 | runs of that job would then waste time recreating the file |
| 1476 | set again and again. |
| 1477 | |
| 1478 | unlink_each_loop=bool Unlink job files after each iteration or loop. |
| 1479 | |
| 1480 | loops=int Run the specified number of iterations of this job. Used |
| 1481 | to repeat the same workload a given number of times. Defaults |
| 1482 | to 1. |
| 1483 | |
| 1484 | verify_only Do not perform specified workload---only verify data still |
| 1485 | matches previous invocation of this workload. This option |
| 1486 | allows one to check data multiple times at a later date |
| 1487 | without overwriting it. This option makes sense only for |
| 1488 | workloads that write data, and does not support workloads |
| 1489 | with the time_based option set. |
| 1490 | |
| 1491 | do_verify=bool Run the verify phase after a write phase. Only makes sense if |
| 1492 | verify is set. Defaults to 1. |
| 1493 | |
| 1494 | verify=str If writing to a file, fio can verify the file contents |
| 1495 | after each iteration of the job. Each verification method also implies |
| 1496 | verification of special header, which is written to the beginning of |
| 1497 | each block. This header also includes meta information, like offset |
| 1498 | of the block, block number, timestamp when block was written, etc. |
| 1499 | verify=str can be combined with verify_pattern=str option. |
| 1500 | The allowed values are: |
| 1501 | |
| 1502 | md5 Use an md5 sum of the data area and store |
| 1503 | it in the header of each block. |
| 1504 | |
| 1505 | crc64 Use an experimental crc64 sum of the data |
| 1506 | area and store it in the header of each |
| 1507 | block. |
| 1508 | |
| 1509 | crc32c Use a crc32c sum of the data area and store |
| 1510 | it in the header of each block. |
| 1511 | |
| 1512 | crc32c-intel Use hardware assisted crc32c calculation |
| 1513 | provided on SSE4.2 enabled processors. Falls |
| 1514 | back to regular software crc32c, if not |
| 1515 | supported by the system. |
| 1516 | |
| 1517 | crc32c-arm64 Use hardware assisted crc32c calculation |
| 1518 | provided on CRC enabled ARM 64-bits processors. |
| 1519 | Falls back to regular software crc32c, if not |
| 1520 | supported by the system. |
| 1521 | |
| 1522 | crc32 Use a crc32 sum of the data area and store |
| 1523 | it in the header of each block. |
| 1524 | |
| 1525 | crc16 Use a crc16 sum of the data area and store |
| 1526 | it in the header of each block. |
| 1527 | |
| 1528 | crc7 Use a crc7 sum of the data area and store |
| 1529 | it in the header of each block. |
| 1530 | |
| 1531 | xxhash Use xxhash as the checksum function. Generally |
| 1532 | the fastest software checksum that fio |
| 1533 | supports. |
| 1534 | |
| 1535 | sha512 Use sha512 as the checksum function. |
| 1536 | |
| 1537 | sha256 Use sha256 as the checksum function. |
| 1538 | |
| 1539 | sha1 Use optimized sha1 as the checksum function. |
| 1540 | |
| 1541 | meta This option is deprecated, since now meta information is |
| 1542 | included in generic verification header and meta verification |
| 1543 | happens by default. For detailed information see the description |
| 1544 | of the verify=str setting. This option is kept because of |
| 1545 | compatibility's sake with old configurations. Do not use it. |
| 1546 | |
| 1547 | pattern Verify a strict pattern. Normally fio includes |
| 1548 | a header with some basic information and |
| 1549 | checksumming, but if this option is set, only |
| 1550 | the specific pattern set with 'verify_pattern' |
| 1551 | is verified. |
| 1552 | |
| 1553 | null Only pretend to verify. Useful for testing |
| 1554 | internals with ioengine=null, not for much |
| 1555 | else. |
| 1556 | |
| 1557 | This option can be used for repeated burn-in tests of a |
| 1558 | system to make sure that the written data is also |
| 1559 | correctly read back. If the data direction given is |
| 1560 | a read or random read, fio will assume that it should |
| 1561 | verify a previously written file. If the data direction |
| 1562 | includes any form of write, the verify will be of the |
| 1563 | newly written data. |
| 1564 | |
| 1565 | verifysort=bool If set, fio will sort written verify blocks when it deems |
| 1566 | it faster to read them back in a sorted manner. This is |
| 1567 | often the case when overwriting an existing file, since |
| 1568 | the blocks are already laid out in the file system. You |
| 1569 | can ignore this option unless doing huge amounts of really |
| 1570 | fast IO where the red-black tree sorting CPU time becomes |
| 1571 | significant. |
| 1572 | |
| 1573 | verify_offset=int Swap the verification header with data somewhere else |
| 1574 | in the block before writing. Its swapped back before |
| 1575 | verifying. |
| 1576 | |
| 1577 | verify_interval=int Write the verification header at a finer granularity |
| 1578 | than the blocksize. It will be written for chunks the |
| 1579 | size of header_interval. blocksize should divide this |
| 1580 | evenly. |
| 1581 | |
| 1582 | verify_pattern=str If set, fio will fill the io buffers with this |
| 1583 | pattern. Fio defaults to filling with totally random |
| 1584 | bytes, but sometimes it's interesting to fill with a known |
| 1585 | pattern for io verification purposes. Depending on the |
| 1586 | width of the pattern, fio will fill 1/2/3/4 bytes of the |
| 1587 | buffer at the time(it can be either a decimal or a hex number). |
| 1588 | The verify_pattern if larger than a 32-bit quantity has to |
| 1589 | be a hex number that starts with either "0x" or "0X". Use |
| 1590 | with verify=str. Also, verify_pattern supports %o format, |
| 1591 | which means that for each block offset will be written and |
| 1592 | then verified back, e.g.: |
| 1593 | |
| 1594 | verify_pattern=%o |
| 1595 | |
| 1596 | Or use combination of everything: |
| 1597 | verify_pattern=0xff%o"abcd"-12 |
| 1598 | |
| 1599 | verify_fatal=bool Normally fio will keep checking the entire contents |
| 1600 | before quitting on a block verification failure. If this |
| 1601 | option is set, fio will exit the job on the first observed |
| 1602 | failure. |
| 1603 | |
| 1604 | verify_dump=bool If set, dump the contents of both the original data |
| 1605 | block and the data block we read off disk to files. This |
| 1606 | allows later analysis to inspect just what kind of data |
| 1607 | corruption occurred. Off by default. |
| 1608 | |
| 1609 | verify_async=int Fio will normally verify IO inline from the submitting |
| 1610 | thread. This option takes an integer describing how many |
| 1611 | async offload threads to create for IO verification instead, |
| 1612 | causing fio to offload the duty of verifying IO contents |
| 1613 | to one or more separate threads. If using this offload |
| 1614 | option, even sync IO engines can benefit from using an |
| 1615 | iodepth setting higher than 1, as it allows them to have |
| 1616 | IO in flight while verifies are running. |
| 1617 | |
| 1618 | verify_async_cpus=str Tell fio to set the given CPU affinity on the |
| 1619 | async IO verification threads. See cpus_allowed for the |
| 1620 | format used. |
| 1621 | |
| 1622 | verify_backlog=int Fio will normally verify the written contents of a |
| 1623 | job that utilizes verify once that job has completed. In |
| 1624 | other words, everything is written then everything is read |
| 1625 | back and verified. You may want to verify continually |
| 1626 | instead for a variety of reasons. Fio stores the meta data |
| 1627 | associated with an IO block in memory, so for large |
| 1628 | verify workloads, quite a bit of memory would be used up |
| 1629 | holding this meta data. If this option is enabled, fio |
| 1630 | will write only N blocks before verifying these blocks. |
| 1631 | |
| 1632 | verify_backlog_batch=int Control how many blocks fio will verify |
| 1633 | if verify_backlog is set. If not set, will default to |
| 1634 | the value of verify_backlog (meaning the entire queue |
| 1635 | is read back and verified). If verify_backlog_batch is |
| 1636 | less than verify_backlog then not all blocks will be verified, |
| 1637 | if verify_backlog_batch is larger than verify_backlog, some |
| 1638 | blocks will be verified more than once. |
| 1639 | |
| 1640 | verify_state_save=bool When a job exits during the write phase of a verify |
| 1641 | workload, save its current state. This allows fio to replay |
| 1642 | up until that point, if the verify state is loaded for the |
| 1643 | verify read phase. The format of the filename is, roughly, |
| 1644 | <type>-<jobname>-<jobindex>-verify.state. <type> is "local" |
| 1645 | for a local run, "sock" for a client/server socket connection, |
| 1646 | and "ip" (192.168.0.1, for instance) for a networked |
| 1647 | client/server connection. |
| 1648 | |
| 1649 | verify_state_load=bool If a verify termination trigger was used, fio stores |
| 1650 | the current write state of each thread. This can be used at |
| 1651 | verification time so that fio knows how far it should verify. |
| 1652 | Without this information, fio will run a full verification |
| 1653 | pass, according to the settings in the job file used. |
| 1654 | |
| 1655 | stonewall |
| 1656 | wait_for_previous Wait for preceding jobs in the job file to exit, before |
| 1657 | starting this one. Can be used to insert serialization |
| 1658 | points in the job file. A stone wall also implies starting |
| 1659 | a new reporting group. |
| 1660 | |
| 1661 | new_group Start a new reporting group. See: group_reporting. |
| 1662 | |
| 1663 | numjobs=int Create the specified number of clones of this job. May be |
| 1664 | used to setup a larger number of threads/processes doing |
| 1665 | the same thing. Each thread is reported separately; to see |
| 1666 | statistics for all clones as a whole, use group_reporting in |
| 1667 | conjunction with new_group. |
| 1668 | |
| 1669 | group_reporting It may sometimes be interesting to display statistics for |
| 1670 | groups of jobs as a whole instead of for each individual job. |
| 1671 | This is especially true if 'numjobs' is used; looking at |
| 1672 | individual thread/process output quickly becomes unwieldy. |
| 1673 | To see the final report per-group instead of per-job, use |
| 1674 | 'group_reporting'. Jobs in a file will be part of the same |
| 1675 | reporting group, unless if separated by a stonewall, or by |
| 1676 | using 'new_group'. |
| 1677 | |
| 1678 | thread fio defaults to forking jobs, however if this option is |
| 1679 | given, fio will use pthread_create(3) to create threads |
| 1680 | instead. |
| 1681 | |
| 1682 | zonesize=int Divide a file into zones of the specified size. See zoneskip. |
| 1683 | |
| 1684 | zoneskip=int Skip the specified number of bytes when zonesize data has |
| 1685 | been read. The two zone options can be used to only do |
| 1686 | io on zones of a file. |
| 1687 | |
| 1688 | write_iolog=str Write the issued io patterns to the specified file. See |
| 1689 | read_iolog. Specify a separate file for each job, otherwise |
| 1690 | the iologs will be interspersed and the file may be corrupt. |
| 1691 | |
| 1692 | read_iolog=str Open an iolog with the specified file name and replay the |
| 1693 | io patterns it contains. This can be used to store a |
| 1694 | workload and replay it sometime later. The iolog given |
| 1695 | may also be a blktrace binary file, which allows fio |
| 1696 | to replay a workload captured by blktrace. See blktrace |
| 1697 | for how to capture such logging data. For blktrace replay, |
| 1698 | the file needs to be turned into a blkparse binary data |
| 1699 | file first (blkparse <device> -o /dev/null -d file_for_fio.bin). |
| 1700 | |
| 1701 | replay_no_stall=int When replaying I/O with read_iolog the default behavior |
| 1702 | is to attempt to respect the time stamps within the log and |
| 1703 | replay them with the appropriate delay between IOPS. By |
| 1704 | setting this variable fio will not respect the timestamps and |
| 1705 | attempt to replay them as fast as possible while still |
| 1706 | respecting ordering. The result is the same I/O pattern to a |
| 1707 | given device, but different timings. |
| 1708 | |
| 1709 | replay_redirect=str While replaying I/O patterns using read_iolog the |
| 1710 | default behavior is to replay the IOPS onto the major/minor |
| 1711 | device that each IOP was recorded from. This is sometimes |
| 1712 | undesirable because on a different machine those major/minor |
| 1713 | numbers can map to a different device. Changing hardware on |
| 1714 | the same system can also result in a different major/minor |
| 1715 | mapping. Replay_redirect causes all IOPS to be replayed onto |
| 1716 | the single specified device regardless of the device it was |
| 1717 | recorded from. i.e. replay_redirect=/dev/sdc would cause all |
| 1718 | IO in the blktrace or iolog to be replayed onto /dev/sdc. |
| 1719 | This means multiple devices will be replayed onto a single |
| 1720 | device, if the trace contains multiple devices. If you want |
| 1721 | multiple devices to be replayed concurrently to multiple |
| 1722 | redirected devices you must blkparse your trace into separate |
| 1723 | traces and replay them with independent fio invocations. |
| 1724 | Unfortunately this also breaks the strict time ordering |
| 1725 | between multiple device accesses. |
| 1726 | |
| 1727 | replay_align=int Force alignment of IO offsets and lengths in a trace |
| 1728 | to this power of 2 value. |
| 1729 | |
| 1730 | replay_scale=int Scale sector offsets down by this factor when |
| 1731 | replaying traces. |
| 1732 | |
| 1733 | per_job_logs=bool If set, this generates bw/clat/iops log with per |
| 1734 | file private filenames. If not set, jobs with identical names |
| 1735 | will share the log filename. Default: true. |
| 1736 | |
| 1737 | write_bw_log=str If given, write a bandwidth log of the jobs in this job |
| 1738 | file. Can be used to store data of the bandwidth of the |
| 1739 | jobs in their lifetime. The included fio_generate_plots |
| 1740 | script uses gnuplot to turn these text files into nice |
| 1741 | graphs. See write_lat_log for behaviour of given |
| 1742 | filename. For this option, the suffix is _bw.x.log, where |
| 1743 | x is the index of the job (1..N, where N is the number of |
| 1744 | jobs). If 'per_job_logs' is false, then the filename will not |
| 1745 | include the job index. See 'Log File Formats'. |
| 1746 | |
| 1747 | write_lat_log=str Same as write_bw_log, except that this option stores io |
| 1748 | submission, completion, and total latencies instead. If no |
| 1749 | filename is given with this option, the default filename of |
| 1750 | "jobname_type.log" is used. Even if the filename is given, |
| 1751 | fio will still append the type of log. So if one specifies |
| 1752 | |
| 1753 | write_lat_log=foo |
| 1754 | |
| 1755 | The actual log names will be foo_slat.x.log, foo_clat.x.log, |
| 1756 | and foo_lat.x.log, where x is the index of the job (1..N, |
| 1757 | where N is the number of jobs). This helps fio_generate_plot |
| 1758 | find the logs automatically. If 'per_job_logs' is false, then |
| 1759 | the filename will not include the job index. See 'Log File |
| 1760 | Formats'. |
| 1761 | |
| 1762 | write_hist_log=str Same as write_lat_log, but writes I/O completion |
| 1763 | latency histograms. If no filename is given with this option, the |
| 1764 | default filename of "jobname_clat_hist.x.log" is used, where x is |
| 1765 | the index of the job (1..N, where N is the number of jobs). Even |
| 1766 | if the filename is given, fio will still append the type of log. |
| 1767 | If per_job_logs is false, then the filename will not include the |
| 1768 | job index. See 'Log File Formats'. |
| 1769 | |
| 1770 | write_iops_log=str Same as write_bw_log, but writes IOPS. If no filename is |
| 1771 | given with this option, the default filename of |
| 1772 | "jobname_type.x.log" is used,where x is the index of the job |
| 1773 | (1..N, where N is the number of jobs). Even if the filename |
| 1774 | is given, fio will still append the type of log. If |
| 1775 | 'per_job_logs' is false, then the filename will not include |
| 1776 | the job index. See 'Log File Formats'. |
| 1777 | |
| 1778 | log_avg_msec=int By default, fio will log an entry in the iops, latency, |
| 1779 | or bw log for every IO that completes. When writing to the |
| 1780 | disk log, that can quickly grow to a very large size. Setting |
| 1781 | this option makes fio average the each log entry over the |
| 1782 | specified period of time, reducing the resolution of the log. |
| 1783 | See log_max_value as well. Defaults to 0, logging all entries. |
| 1784 | |
| 1785 | log_hist_msec=int Same as log_avg_msec, but logs entries for completion |
| 1786 | latency histograms. Computing latency percentiles from averages of |
| 1787 | intervals using log_avg_msec is innacurate. Setting this option makes |
| 1788 | fio log histogram entries over the specified period of time, reducing |
| 1789 | log sizes for high IOPS devices while retaining percentile accuracy. |
| 1790 | See log_hist_coarseness as well. Defaults to 0, meaning histogram |
| 1791 | logging is disabled. |
| 1792 | |
| 1793 | log_hist_coarseness=int Integer ranging from 0 to 6, defining the coarseness |
| 1794 | of the resolution of the histogram logs enabled with log_hist_msec. For |
| 1795 | each increment in coarseness, fio outputs half as many bins. Defaults to |
| 1796 | 0, for which histogram logs contain 1216 latency bins. See |
| 1797 | 'Log File Formats'. |
| 1798 | |
| 1799 | log_max_value=bool If log_avg_msec is set, fio logs the average over that |
| 1800 | window. If you instead want to log the maximum value, set this |
| 1801 | option to 1. Defaults to 0, meaning that averaged values are |
| 1802 | logged. |
| 1803 | |
| 1804 | log_offset=int If this is set, the iolog options will include the byte |
| 1805 | offset for the IO entry as well as the other data values. |
| 1806 | |
| 1807 | log_compression=int If this is set, fio will compress the IO logs as |
| 1808 | it goes, to keep the memory footprint lower. When a log |
| 1809 | reaches the specified size, that chunk is removed and |
| 1810 | compressed in the background. Given that IO logs are |
| 1811 | fairly highly compressible, this yields a nice memory |
| 1812 | savings for longer runs. The downside is that the |
| 1813 | compression will consume some background CPU cycles, so |
| 1814 | it may impact the run. This, however, is also true if |
| 1815 | the logging ends up consuming most of the system memory. |
| 1816 | So pick your poison. The IO logs are saved normally at the |
| 1817 | end of a run, by decompressing the chunks and storing them |
| 1818 | in the specified log file. This feature depends on the |
| 1819 | availability of zlib. |
| 1820 | |
| 1821 | log_compression_cpus=str Define the set of CPUs that are allowed to |
| 1822 | handle online log compression for the IO jobs. This can |
| 1823 | provide better isolation between performance sensitive jobs, |
| 1824 | and background compression work. |
| 1825 | |
| 1826 | log_store_compressed=bool If set, fio will store the log files in a |
| 1827 | compressed format. They can be decompressed with fio, using |
| 1828 | the --inflate-log command line parameter. The files will be |
| 1829 | stored with a .fz suffix. |
| 1830 | |
| 1831 | log_unix_epoch=bool If set, fio will log Unix timestamps to the log |
| 1832 | files produced by enabling write_type_log for each log type, instead |
| 1833 | of the default zero-based timestamps. |
| 1834 | |
| 1835 | block_error_percentiles=bool If set, record errors in trim block-sized |
| 1836 | units from writes and trims and output a histogram of |
| 1837 | how many trims it took to get to errors, and what kind |
| 1838 | of error was encountered. |
| 1839 | |
| 1840 | lockmem=int Pin down the specified amount of memory with mlock(2). Can |
| 1841 | potentially be used instead of removing memory or booting |
| 1842 | with less memory to simulate a smaller amount of memory. |
| 1843 | The amount specified is per worker. |
| 1844 | |
| 1845 | exec_prerun=str Before running this job, issue the command specified |
| 1846 | through system(3). Output is redirected in a file called |
| 1847 | jobname.prerun.txt. |
| 1848 | |
| 1849 | exec_postrun=str After the job completes, issue the command specified |
| 1850 | though system(3). Output is redirected in a file called |
| 1851 | jobname.postrun.txt. |
| 1852 | |
| 1853 | ioscheduler=str Attempt to switch the device hosting the file to the specified |
| 1854 | io scheduler before running. |
| 1855 | |
| 1856 | disk_util=bool Generate disk utilization statistics, if the platform |
| 1857 | supports it. Defaults to on. |
| 1858 | |
| 1859 | disable_lat=bool Disable measurements of total latency numbers. Useful |
| 1860 | only for cutting back the number of calls to gettimeofday, |
| 1861 | as that does impact performance at really high IOPS rates. |
| 1862 | Note that to really get rid of a large amount of these |
| 1863 | calls, this option must be used with disable_slat and |
| 1864 | disable_bw as well. |
| 1865 | |
| 1866 | disable_clat=bool Disable measurements of completion latency numbers. See |
| 1867 | disable_lat. |
| 1868 | |
| 1869 | disable_slat=bool Disable measurements of submission latency numbers. See |
| 1870 | disable_slat. |
| 1871 | |
| 1872 | disable_bw=bool Disable measurements of throughput/bandwidth numbers. See |
| 1873 | disable_lat. |
| 1874 | |
| 1875 | clat_percentiles=bool Enable the reporting of percentiles of |
| 1876 | completion latencies. |
| 1877 | |
| 1878 | percentile_list=float_list Overwrite the default list of percentiles |
| 1879 | for completion latencies and the block error histogram. |
| 1880 | Each number is a floating number in the range (0,100], |
| 1881 | and the maximum length of the list is 20. Use ':' |
| 1882 | to separate the numbers, and list the numbers in ascending |
| 1883 | order. For example, --percentile_list=99.5:99.9 will cause |
| 1884 | fio to report the values of completion latency below which |
| 1885 | 99.5% and 99.9% of the observed latencies fell, respectively. |
| 1886 | |
| 1887 | clocksource=str Use the given clocksource as the base of timing. The |
| 1888 | supported options are: |
| 1889 | |
| 1890 | gettimeofday gettimeofday(2) |
| 1891 | |
| 1892 | clock_gettime clock_gettime(2) |
| 1893 | |
| 1894 | cpu Internal CPU clock source |
| 1895 | |
| 1896 | cpu is the preferred clocksource if it is reliable, as it |
| 1897 | is very fast (and fio is heavy on time calls). Fio will |
| 1898 | automatically use this clocksource if it's supported and |
| 1899 | considered reliable on the system it is running on, unless |
| 1900 | another clocksource is specifically set. For x86/x86-64 CPUs, |
| 1901 | this means supporting TSC Invariant. |
| 1902 | |
| 1903 | gtod_reduce=bool Enable all of the gettimeofday() reducing options |
| 1904 | (disable_clat, disable_slat, disable_bw) plus reduce |
| 1905 | precision of the timeout somewhat to really shrink |
| 1906 | the gettimeofday() call count. With this option enabled, |
| 1907 | we only do about 0.4% of the gtod() calls we would have |
| 1908 | done if all time keeping was enabled. |
| 1909 | |
| 1910 | gtod_cpu=int Sometimes it's cheaper to dedicate a single thread of |
| 1911 | execution to just getting the current time. Fio (and |
| 1912 | databases, for instance) are very intensive on gettimeofday() |
| 1913 | calls. With this option, you can set one CPU aside for |
| 1914 | doing nothing but logging current time to a shared memory |
| 1915 | location. Then the other threads/processes that run IO |
| 1916 | workloads need only copy that segment, instead of entering |
| 1917 | the kernel with a gettimeofday() call. The CPU set aside |
| 1918 | for doing these time calls will be excluded from other |
| 1919 | uses. Fio will manually clear it from the CPU mask of other |
| 1920 | jobs. |
| 1921 | |
| 1922 | continue_on_error=str Normally fio will exit the job on the first observed |
| 1923 | failure. If this option is set, fio will continue the job when |
| 1924 | there is a 'non-fatal error' (EIO or EILSEQ) until the runtime |
| 1925 | is exceeded or the I/O size specified is completed. If this |
| 1926 | option is used, there are two more stats that are appended, |
| 1927 | the total error count and the first error. The error field |
| 1928 | given in the stats is the first error that was hit during the |
| 1929 | run. |
| 1930 | |
| 1931 | The allowed values are: |
| 1932 | |
| 1933 | none Exit on any IO or verify errors. |
| 1934 | |
| 1935 | read Continue on read errors, exit on all others. |
| 1936 | |
| 1937 | write Continue on write errors, exit on all others. |
| 1938 | |
| 1939 | io Continue on any IO error, exit on all others. |
| 1940 | |
| 1941 | verify Continue on verify errors, exit on all others. |
| 1942 | |
| 1943 | all Continue on all errors. |
| 1944 | |
| 1945 | 0 Backward-compatible alias for 'none'. |
| 1946 | |
| 1947 | 1 Backward-compatible alias for 'all'. |
| 1948 | |
| 1949 | ignore_error=str Sometimes you want to ignore some errors during test |
| 1950 | in that case you can specify error list for each error type. |
| 1951 | ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST |
| 1952 | errors for given error type is separated with ':'. Error |
| 1953 | may be symbol ('ENOSPC', 'ENOMEM') or integer. |
| 1954 | Example: |
| 1955 | ignore_error=EAGAIN,ENOSPC:122 |
| 1956 | This option will ignore EAGAIN from READ, and ENOSPC and |
| 1957 | 122(EDQUOT) from WRITE. |
| 1958 | |
| 1959 | error_dump=bool If set dump every error even if it is non fatal, true |
| 1960 | by default. If disabled only fatal error will be dumped |
| 1961 | |
| 1962 | cgroup=str Add job to this control group. If it doesn't exist, it will |
| 1963 | be created. The system must have a mounted cgroup blkio |
| 1964 | mount point for this to work. If your system doesn't have it |
| 1965 | mounted, you can do so with: |
| 1966 | |
| 1967 | # mount -t cgroup -o blkio none /cgroup |
| 1968 | |
| 1969 | cgroup_weight=int Set the weight of the cgroup to this value. See |
| 1970 | the documentation that comes with the kernel, allowed values |
| 1971 | are in the range of 100..1000. |
| 1972 | |
| 1973 | cgroup_nodelete=bool Normally fio will delete the cgroups it has created after |
| 1974 | the job completion. To override this behavior and to leave |
| 1975 | cgroups around after the job completion, set cgroup_nodelete=1. |
| 1976 | This can be useful if one wants to inspect various cgroup |
| 1977 | files after job completion. Default: false |
| 1978 | |
| 1979 | uid=int Instead of running as the invoking user, set the user ID to |
| 1980 | this value before the thread/process does any work. |
| 1981 | |
| 1982 | gid=int Set group ID, see uid. |
| 1983 | |
| 1984 | flow_id=int The ID of the flow. If not specified, it defaults to being a |
| 1985 | global flow. See flow. |
| 1986 | |
| 1987 | flow=int Weight in token-based flow control. If this value is used, then |
| 1988 | there is a 'flow counter' which is used to regulate the |
| 1989 | proportion of activity between two or more jobs. fio attempts |
| 1990 | to keep this flow counter near zero. The 'flow' parameter |
| 1991 | stands for how much should be added or subtracted to the flow |
| 1992 | counter on each iteration of the main I/O loop. That is, if |
| 1993 | one job has flow=8 and another job has flow=-1, then there |
| 1994 | will be a roughly 1:8 ratio in how much one runs vs the other. |
| 1995 | |
| 1996 | flow_watermark=int The maximum value that the absolute value of the flow |
| 1997 | counter is allowed to reach before the job must wait for a |
| 1998 | lower value of the counter. |
| 1999 | |
| 2000 | flow_sleep=int The period of time, in microseconds, to wait after the flow |
| 2001 | watermark has been exceeded before retrying operations |
| 2002 | |
| 2003 | In addition, there are some parameters which are only valid when a specific |
| 2004 | ioengine is in use. These are used identically to normal parameters, with the |
| 2005 | caveat that when used on the command line, they must come after the ioengine |
| 2006 | that defines them is selected. |
| 2007 | |
| 2008 | [libaio] userspace_reap Normally, with the libaio engine in use, fio will use |
| 2009 | the io_getevents system call to reap newly returned events. |
| 2010 | With this flag turned on, the AIO ring will be read directly |
| 2011 | from user-space to reap events. The reaping mode is only |
| 2012 | enabled when polling for a minimum of 0 events (eg when |
| 2013 | iodepth_batch_complete=0). |
| 2014 | |
| 2015 | [psyncv2] hipri Set RWF_HIPRI on IO, indicating to the kernel that |
| 2016 | it's of higher priority than normal. |
| 2017 | |
| 2018 | [cpuio] cpuload=int Attempt to use the specified percentage of CPU cycles. |
| 2019 | |
| 2020 | [cpuio] cpuchunks=int Split the load into cycles of the given time. In |
| 2021 | microseconds. |
| 2022 | |
| 2023 | [cpuio] exit_on_io_done=bool Detect when IO threads are done, then exit. |
| 2024 | |
| 2025 | [netsplice] hostname=str |
| 2026 | [net] hostname=str The host name or IP address to use for TCP or UDP based IO. |
| 2027 | If the job is a TCP listener or UDP reader, the hostname is not |
| 2028 | used and must be omitted unless it is a valid UDP multicast |
| 2029 | address. |
| 2030 | [libhdfs] namenode=str The host name or IP address of a HDFS cluster namenode to contact. |
| 2031 | |
| 2032 | [netsplice] port=int |
| 2033 | [net] port=int The TCP or UDP port to bind to or connect to. If this is used |
| 2034 | with numjobs to spawn multiple instances of the same job type, then this will |
| 2035 | be the starting port number since fio will use a range of ports. |
| 2036 | [libhdfs] port=int the listening port of the HFDS cluster namenode. |
| 2037 | |
| 2038 | [netsplice] interface=str |
| 2039 | [net] interface=str The IP address of the network interface used to send or |
| 2040 | receive UDP multicast |
| 2041 | |
| 2042 | [netsplice] ttl=int |
| 2043 | [net] ttl=int Time-to-live value for outgoing UDP multicast packets. |
| 2044 | Default: 1 |
| 2045 | |
| 2046 | [netsplice] nodelay=bool |
| 2047 | [net] nodelay=bool Set TCP_NODELAY on TCP connections. |
| 2048 | |
| 2049 | [netsplice] protocol=str |
| 2050 | [netsplice] proto=str |
| 2051 | [net] protocol=str |
| 2052 | [net] proto=str The network protocol to use. Accepted values are: |
| 2053 | |
| 2054 | tcp Transmission control protocol |
| 2055 | tcpv6 Transmission control protocol V6 |
| 2056 | udp User datagram protocol |
| 2057 | udpv6 User datagram protocol V6 |
| 2058 | unix UNIX domain socket |
| 2059 | |
| 2060 | When the protocol is TCP or UDP, the port must also be given, |
| 2061 | as well as the hostname if the job is a TCP listener or UDP |
| 2062 | reader. For unix sockets, the normal filename option should be |
| 2063 | used and the port is invalid. |
| 2064 | |
| 2065 | [net] listen For TCP network connections, tell fio to listen for incoming |
| 2066 | connections rather than initiating an outgoing connection. The |
| 2067 | hostname must be omitted if this option is used. |
| 2068 | |
| 2069 | [net] pingpong Normally a network writer will just continue writing data, and |
| 2070 | a network reader will just consume packages. If pingpong=1 |
| 2071 | is set, a writer will send its normal payload to the reader, |
| 2072 | then wait for the reader to send the same payload back. This |
| 2073 | allows fio to measure network latencies. The submission |
| 2074 | and completion latencies then measure local time spent |
| 2075 | sending or receiving, and the completion latency measures |
| 2076 | how long it took for the other end to receive and send back. |
| 2077 | For UDP multicast traffic pingpong=1 should only be set for a |
| 2078 | single reader when multiple readers are listening to the same |
| 2079 | address. |
| 2080 | |
| 2081 | [net] window_size Set the desired socket buffer size for the connection. |
| 2082 | |
| 2083 | [net] mss Set the TCP maximum segment size (TCP_MAXSEG). |
| 2084 | |
| 2085 | [e4defrag] donorname=str |
| 2086 | File will be used as a block donor(swap extents between files) |
| 2087 | [e4defrag] inplace=int |
| 2088 | Configure donor file blocks allocation strategy |
| 2089 | 0(default): Preallocate donor's file on init |
| 2090 | 1 : allocate space immediately inside defragment event, |
| 2091 | and free right after event |
| 2092 | |
| 2093 | [rbd] clustername=str Specifies the name of the Ceph cluster. |
| 2094 | [rbd] rbdname=str Specifies the name of the RBD. |
| 2095 | [rbd] pool=str Specifies the name of the Ceph pool containing RBD. |
| 2096 | [rbd] clientname=str Specifies the username (without the 'client.' prefix) |
| 2097 | used to access the Ceph cluster. If the clustername is |
| 2098 | specified, the clientname shall be the full type.id |
| 2099 | string. If no type. prefix is given, fio will add |
| 2100 | 'client.' by default. |
| 2101 | |
| 2102 | [mtd] skip_bad=bool Skip operations against known bad blocks. |
| 2103 | |
| 2104 | [libhdfs] hdfsdirectory libhdfs will create chunk in this HDFS directory |
| 2105 | [libhdfs] chunk_size the size of the chunk to use for each file. |
| 2106 | |
| 2107 | |
| 2108 | 6.0 Interpreting the output |
| 2109 | --------------------------- |
| 2110 | |
| 2111 | fio spits out a lot of output. While running, fio will display the |
| 2112 | status of the jobs created. An example of that would be: |
| 2113 | |
| 2114 | Jobs: 1: [_r] [24.8% done] [r=20992KiB/s,w=24064KiB/s,t=0KiB/s] [r=82,w=94,t=0 iops] [eta 00h:01m:31s] |
| 2115 | |
| 2116 | The characters inside the square brackets denote the current status of |
| 2117 | each thread. The possible values (in typical life cycle order) are: |
| 2118 | |
| 2119 | Idle Run |
| 2120 | ---- --- |
| 2121 | P Thread setup, but not started. |
| 2122 | C Thread created. |
| 2123 | I Thread initialized, waiting or generating necessary data. |
| 2124 | p Thread running pre-reading file(s). |
| 2125 | R Running, doing sequential reads. |
| 2126 | r Running, doing random reads. |
| 2127 | W Running, doing sequential writes. |
| 2128 | w Running, doing random writes. |
| 2129 | M Running, doing mixed sequential reads/writes. |
| 2130 | m Running, doing mixed random reads/writes. |
| 2131 | F Running, currently waiting for fsync() |
| 2132 | f Running, finishing up (writing IO logs, etc) |
| 2133 | V Running, doing verification of written data. |
| 2134 | E Thread exited, not reaped by main thread yet. |
| 2135 | _ Thread reaped, or |
| 2136 | X Thread reaped, exited with an error. |
| 2137 | K Thread reaped, exited due to signal. |
| 2138 | |
| 2139 | Fio will condense the thread string as not to take up more space on the |
| 2140 | command line as is needed. For instance, if you have 10 readers and 10 |
| 2141 | writers running, the output would look like this: |
| 2142 | |
| 2143 | Jobs: 20 (f=20): [R(10),W(10)] [4.0% done] [r=20992KiB/s,w=24064KiB/s,t=0KiB/s] [r=82,w=94,t=0 iops] [eta 57m:36s] |
| 2144 | |
| 2145 | Fio will still maintain the ordering, though. So the above means that jobs |
| 2146 | 1..10 are readers, and 11..20 are writers. |
| 2147 | |
| 2148 | The other values are fairly self explanatory - number of threads |
| 2149 | currently running and doing io, rate of io since last check (read speed |
| 2150 | listed first, then write speed), and the estimated completion percentage |
| 2151 | and time for the running group. It's impossible to estimate runtime of |
| 2152 | the following groups (if any). Note that the string is displayed in order, |
| 2153 | so it's possible to tell which of the jobs are currently doing what. The |
| 2154 | first character is the first job defined in the job file, and so forth. |
| 2155 | |
| 2156 | When fio is done (or interrupted by ctrl-c), it will show the data for |
| 2157 | each thread, group of threads, and disks in that order. For each data |
| 2158 | direction, the output looks like: |
| 2159 | |
| 2160 | Client1 (g=0): err= 0: |
| 2161 | write: io= 32MiB, bw= 666KiB/s, iops=89 , runt= 50320msec |
| 2162 | slat (msec): min= 0, max= 136, avg= 0.03, stdev= 1.92 |
| 2163 | clat (msec): min= 0, max= 631, avg=48.50, stdev=86.82 |
| 2164 | bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, stdev=681.68 |
| 2165 | cpu : usr=1.49%, sys=0.25%, ctx=7969, majf=0, minf=17 |
| 2166 | IO depths : 1=0.1%, 2=0.3%, 4=0.5%, 8=99.0%, 16=0.0%, 32=0.0%, >32=0.0% |
| 2167 | submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% |
| 2168 | complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% |
| 2169 | issued r/w: total=0/32768, short=0/0 |
| 2170 | lat (msec): 2=1.6%, 4=0.0%, 10=3.2%, 20=12.8%, 50=38.4%, 100=24.8%, |
| 2171 | lat (msec): 250=15.2%, 500=0.0%, 750=0.0%, 1000=0.0%, >=2048=0.0% |
| 2172 | |
| 2173 | The client number is printed, along with the group id and error of that |
| 2174 | thread. Below is the io statistics, here for writes. In the order listed, |
| 2175 | they denote: |
| 2176 | |
| 2177 | io= Number of megabytes io performed |
| 2178 | bw= Average bandwidth rate |
| 2179 | iops= Average IOs performed per second |
| 2180 | runt= The runtime of that thread |
| 2181 | slat= Submission latency (avg being the average, stdev being the |
| 2182 | standard deviation). This is the time it took to submit |
| 2183 | the io. For sync io, the slat is really the completion |
| 2184 | latency, since queue/complete is one operation there. This |
| 2185 | value can be in milliseconds or microseconds, fio will choose |
| 2186 | the most appropriate base and print that. In the example |
| 2187 | above, milliseconds is the best scale. Note: in --minimal mode |
| 2188 | latencies are always expressed in microseconds. |
| 2189 | clat= Completion latency. Same names as slat, this denotes the |
| 2190 | time from submission to completion of the io pieces. For |
| 2191 | sync io, clat will usually be equal (or very close) to 0, |
| 2192 | as the time from submit to complete is basically just |
| 2193 | CPU time (io has already been done, see slat explanation). |
| 2194 | bw= Bandwidth. Same names as the xlat stats, but also includes |
| 2195 | an approximate percentage of total aggregate bandwidth |
| 2196 | this thread received in this group. This last value is |
| 2197 | only really useful if the threads in this group are on the |
| 2198 | same disk, since they are then competing for disk access. |
| 2199 | cpu= CPU usage. User and system time, along with the number |
| 2200 | of context switches this thread went through, usage of |
| 2201 | system and user time, and finally the number of major |
| 2202 | and minor page faults. The CPU utilization numbers are |
| 2203 | averages for the jobs in that reporting group, while the |
| 2204 | context and fault counters are summed. |
| 2205 | IO depths= The distribution of io depths over the job life time. The |
| 2206 | numbers are divided into powers of 2, so for example the |
| 2207 | 16= entries includes depths up to that value but higher |
| 2208 | than the previous entry. In other words, it covers the |
| 2209 | range from 16 to 31. |
| 2210 | IO submit= How many pieces of IO were submitting in a single submit |
| 2211 | call. Each entry denotes that amount and below, until |
| 2212 | the previous entry - eg, 8=100% mean that we submitted |
| 2213 | anywhere in between 5-8 ios per submit call. |
| 2214 | IO complete= Like the above submit number, but for completions instead. |
| 2215 | IO issued= The number of read/write requests issued, and how many |
| 2216 | of them were short. |
| 2217 | IO latencies= The distribution of IO completion latencies. This is the |
| 2218 | time from when IO leaves fio and when it gets completed. |
| 2219 | The numbers follow the same pattern as the IO depths, |
| 2220 | meaning that 2=1.6% means that 1.6% of the IO completed |
| 2221 | within 2 msecs, 20=12.8% means that 12.8% of the IO |
| 2222 | took more than 10 msecs, but less than (or equal to) 20 msecs. |
| 2223 | |
| 2224 | After each client has been listed, the group statistics are printed. They |
| 2225 | will look like this: |
| 2226 | |
| 2227 | Run status group 0 (all jobs): |
| 2228 | READ: io=64MB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec |
| 2229 | WRITE: io=64MB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec |
| 2230 | |
| 2231 | For each data direction, it prints: |
| 2232 | |
| 2233 | io= Number of megabytes io performed. |
| 2234 | aggrb= Aggregate bandwidth of threads in this group. |
| 2235 | minb= The minimum average bandwidth a thread saw. |
| 2236 | maxb= The maximum average bandwidth a thread saw. |
| 2237 | mint= The smallest runtime of the threads in that group. |
| 2238 | maxt= The longest runtime of the threads in that group. |
| 2239 | |
| 2240 | And finally, the disk statistics are printed. They will look like this: |
| 2241 | |
| 2242 | Disk stats (read/write): |
| 2243 | sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00% |
| 2244 | |
| 2245 | Each value is printed for both reads and writes, with reads first. The |
| 2246 | numbers denote: |
| 2247 | |
| 2248 | ios= Number of ios performed by all groups. |
| 2249 | merge= Number of merges io the io scheduler. |
| 2250 | ticks= Number of ticks we kept the disk busy. |
| 2251 | io_queue= Total time spent in the disk queue. |
| 2252 | util= The disk utilization. A value of 100% means we kept the disk |
| 2253 | busy constantly, 50% would be a disk idling half of the time. |
| 2254 | |
| 2255 | It is also possible to get fio to dump the current output while it is |
| 2256 | running, without terminating the job. To do that, send fio the USR1 signal. |
| 2257 | You can also get regularly timed dumps by using the --status-interval |
| 2258 | parameter, or by creating a file in /tmp named fio-dump-status. If fio |
| 2259 | sees this file, it will unlink it and dump the current output status. |
| 2260 | |
| 2261 | |
| 2262 | 7.0 Terse output |
| 2263 | ---------------- |
| 2264 | |
| 2265 | For scripted usage where you typically want to generate tables or graphs |
| 2266 | of the results, fio can output the results in a semicolon separated format. |
| 2267 | The format is one long line of values, such as: |
| 2268 | |
| 2269 | 2;card0;0;0;7139336;121836;60004;1;10109;27.932460;116.933948;220;126861;3495.446807;1085.368601;226;126864;3523.635629;1089.012448;24063;99944;50.275485%;59818.274627;5540.657370;7155060;122104;60004;1;8338;29.086342;117.839068;388;128077;5032.488518;1234.785715;391;128085;5061.839412;1236.909129;23436;100928;50.287926%;59964.832030;5644.844189;14.595833%;19.394167%;123706;0;7313;0.1%;0.1%;0.1%;0.1%;0.1%;0.1%;100.0%;0.00%;0.00%;0.00%;0.00%;0.00%;0.00%;0.01%;0.02%;0.05%;0.16%;6.04%;40.40%;52.68%;0.64%;0.01%;0.00%;0.01%;0.00%;0.00%;0.00%;0.00%;0.00% |
| 2270 | A description of this job goes here. |
| 2271 | |
| 2272 | The job description (if provided) follows on a second line. |
| 2273 | |
| 2274 | To enable terse output, use the --minimal command line option. The first |
| 2275 | value is the version of the terse output format. If the output has to |
| 2276 | be changed for some reason, this number will be incremented by 1 to |
| 2277 | signify that change. |
| 2278 | |
| 2279 | Split up, the format is as follows: |
| 2280 | |
| 2281 | terse version, fio version, jobname, groupid, error |
| 2282 | READ status: |
| 2283 | Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec) |
| 2284 | Submission latency: min, max, mean, stdev (usec) |
| 2285 | Completion latency: min, max, mean, stdev (usec) |
| 2286 | Completion latency percentiles: 20 fields (see below) |
| 2287 | Total latency: min, max, mean, stdev (usec) |
| 2288 | Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev |
| 2289 | WRITE status: |
| 2290 | Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec) |
| 2291 | Submission latency: min, max, mean, stdev (usec) |
| 2292 | Completion latency: min, max, mean, stdev(usec) |
| 2293 | Completion latency percentiles: 20 fields (see below) |
| 2294 | Total latency: min, max, mean, stdev (usec) |
| 2295 | Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev |
| 2296 | CPU usage: user, system, context switches, major faults, minor faults |
| 2297 | IO depths: <=1, 2, 4, 8, 16, 32, >=64 |
| 2298 | IO latencies microseconds: <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000 |
| 2299 | IO latencies milliseconds: <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000 |
| 2300 | Disk utilization: Disk name, Read ios, write ios, |
| 2301 | Read merges, write merges, |
| 2302 | Read ticks, write ticks, |
| 2303 | Time spent in queue, disk utilization percentage |
| 2304 | Additional Info (dependent on continue_on_error, default off): total # errors, first error code |
| 2305 | |
| 2306 | Additional Info (dependent on description being set): Text description |
| 2307 | |
| 2308 | Completion latency percentiles can be a grouping of up to 20 sets, so |
| 2309 | for the terse output fio writes all of them. Each field will look like this: |
| 2310 | |
| 2311 | 1.00%=6112 |
| 2312 | |
| 2313 | which is the Xth percentile, and the usec latency associated with it. |
| 2314 | |
| 2315 | For disk utilization, all disks used by fio are shown. So for each disk |
| 2316 | there will be a disk utilization section. |
| 2317 | |
| 2318 | |
| 2319 | 8.0 Trace file format |
| 2320 | --------------------- |
| 2321 | There are two trace file format that you can encounter. The older (v1) format |
| 2322 | is unsupported since version 1.20-rc3 (March 2008). It will still be described |
| 2323 | below in case that you get an old trace and want to understand it. |
| 2324 | |
| 2325 | In any case the trace is a simple text file with a single action per line. |
| 2326 | |
| 2327 | |
| 2328 | 8.1 Trace file format v1 |
| 2329 | ------------------------ |
| 2330 | Each line represents a single io action in the following format: |
| 2331 | |
| 2332 | rw, offset, length |
| 2333 | |
| 2334 | where rw=0/1 for read/write, and the offset and length entries being in bytes. |
| 2335 | |
| 2336 | This format is not supported in Fio versions => 1.20-rc3. |
| 2337 | |
| 2338 | |
| 2339 | 8.2 Trace file format v2 |
| 2340 | ------------------------ |
| 2341 | The second version of the trace file format was added in Fio version 1.17. |
| 2342 | It allows to access more then one file per trace and has a bigger set of |
| 2343 | possible file actions. |
| 2344 | |
| 2345 | The first line of the trace file has to be: |
| 2346 | |
| 2347 | fio version 2 iolog |
| 2348 | |
| 2349 | Following this can be lines in two different formats, which are described below. |
| 2350 | |
| 2351 | The file management format: |
| 2352 | |
| 2353 | filename action |
| 2354 | |
| 2355 | The filename is given as an absolute path. The action can be one of these: |
| 2356 | |
| 2357 | add Add the given filename to the trace |
| 2358 | open Open the file with the given filename. The filename has to have |
| 2359 | been added with the add action before. |
| 2360 | close Close the file with the given filename. The file has to have been |
| 2361 | opened before. |
| 2362 | |
| 2363 | |
| 2364 | The file io action format: |
| 2365 | |
| 2366 | filename action offset length |
| 2367 | |
| 2368 | The filename is given as an absolute path, and has to have been added and opened |
| 2369 | before it can be used with this format. The offset and length are given in |
| 2370 | bytes. The action can be one of these: |
| 2371 | |
| 2372 | wait Wait for 'offset' microseconds. Everything below 100 is discarded. |
| 2373 | The time is relative to the previous wait statement. |
| 2374 | read Read 'length' bytes beginning from 'offset' |
| 2375 | write Write 'length' bytes beginning from 'offset' |
| 2376 | sync fsync() the file |
| 2377 | datasync fdatasync() the file |
| 2378 | trim trim the given file from the given 'offset' for 'length' bytes |
| 2379 | |
| 2380 | |
| 2381 | 9.0 CPU idleness profiling |
| 2382 | -------------------------- |
| 2383 | In some cases, we want to understand CPU overhead in a test. For example, |
| 2384 | we test patches for the specific goodness of whether they reduce CPU usage. |
| 2385 | fio implements a balloon approach to create a thread per CPU that runs at |
| 2386 | idle priority, meaning that it only runs when nobody else needs the cpu. |
| 2387 | By measuring the amount of work completed by the thread, idleness of each |
| 2388 | CPU can be derived accordingly. |
| 2389 | |
| 2390 | An unit work is defined as touching a full page of unsigned characters. Mean |
| 2391 | and standard deviation of time to complete an unit work is reported in "unit |
| 2392 | work" section. Options can be chosen to report detailed percpu idleness or |
| 2393 | overall system idleness by aggregating percpu stats. |
| 2394 | |
| 2395 | |
| 2396 | 10.0 Verification and triggers |
| 2397 | ------------------------------ |
| 2398 | Fio is usually run in one of two ways, when data verification is done. The |
| 2399 | first is a normal write job of some sort with verify enabled. When the |
| 2400 | write phase has completed, fio switches to reads and verifies everything |
| 2401 | it wrote. The second model is running just the write phase, and then later |
| 2402 | on running the same job (but with reads instead of writes) to repeat the |
| 2403 | same IO patterns and verify the contents. Both of these methods depend |
| 2404 | on the write phase being completed, as fio otherwise has no idea how much |
| 2405 | data was written. |
| 2406 | |
| 2407 | With verification triggers, fio supports dumping the current write state |
| 2408 | to local files. Then a subsequent read verify workload can load this state |
| 2409 | and know exactly where to stop. This is useful for testing cases where |
| 2410 | power is cut to a server in a managed fashion, for instance. |
| 2411 | |
| 2412 | A verification trigger consists of two things: |
| 2413 | |
| 2414 | 1) Storing the write state of each job |
| 2415 | 2) Executing a trigger command |
| 2416 | |
| 2417 | The write state is relatively small, on the order of hundreds of bytes |
| 2418 | to single kilobytes. It contains information on the number of completions |
| 2419 | done, the last X completions, etc. |
| 2420 | |
| 2421 | A trigger is invoked either through creation ('touch') of a specified |
| 2422 | file in the system, or through a timeout setting. If fio is run with |
| 2423 | --trigger-file=/tmp/trigger-file, then it will continually check for |
| 2424 | the existence of /tmp/trigger-file. When it sees this file, it will |
| 2425 | fire off the trigger (thus saving state, and executing the trigger |
| 2426 | command). |
| 2427 | |
| 2428 | For client/server runs, there's both a local and remote trigger. If |
| 2429 | fio is running as a server backend, it will send the job states back |
| 2430 | to the client for safe storage, then execute the remote trigger, if |
| 2431 | specified. If a local trigger is specified, the server will still send |
| 2432 | back the write state, but the client will then execute the trigger. |
| 2433 | |
| 2434 | 10.1 Verification trigger example |
| 2435 | --------------------------------- |
| 2436 | Lets say we want to run a powercut test on the remote machine 'server'. |
| 2437 | Our write workload is in write-test.fio. We want to cut power to 'server' |
| 2438 | at some point during the run, and we'll run this test from the safety |
| 2439 | or our local machine, 'localbox'. On the server, we'll start the fio |
| 2440 | backend normally: |
| 2441 | |
| 2442 | server# fio --server |
| 2443 | |
| 2444 | and on the client, we'll fire off the workload: |
| 2445 | |
| 2446 | localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger-remote="bash -c \"echo b > /proc/sysrq-triger\"" |
| 2447 | |
| 2448 | We set /tmp/my-trigger as the trigger file, and we tell fio to execute |
| 2449 | |
| 2450 | echo b > /proc/sysrq-trigger |
| 2451 | |
| 2452 | on the server once it has received the trigger and sent us the write |
| 2453 | state. This will work, but it's not _really_ cutting power to the server, |
| 2454 | it's merely abruptly rebooting it. If we have a remote way of cutting |
| 2455 | power to the server through IPMI or similar, we could do that through |
| 2456 | a local trigger command instead. Lets assume we have a script that does |
| 2457 | IPMI reboot of a given hostname, ipmi-reboot. On localbox, we could |
| 2458 | then have run fio with a local trigger instead: |
| 2459 | |
| 2460 | localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger="ipmi-reboot server" |
| 2461 | |
| 2462 | For this case, fio would wait for the server to send us the write state, |
| 2463 | then execute 'ipmi-reboot server' when that happened. |
| 2464 | |
| 2465 | 10.2 Loading verify state |
| 2466 | ------------------------- |
| 2467 | To load store write state, read verification job file must contain |
| 2468 | the verify_state_load option. If that is set, fio will load the previously |
| 2469 | stored state. For a local fio run this is done by loading the files directly, |
| 2470 | and on a client/server run, the server backend will ask the client to send |
| 2471 | the files over and load them from there. |
| 2472 | |
| 2473 | |
| 2474 | 11.0 Log File Formats |
| 2475 | --------------------- |
| 2476 | |
| 2477 | Fio supports a variety of log file formats, for logging latencies, bandwidth, |
| 2478 | and IOPS. The logs share a common format, which looks like this: |
| 2479 | |
| 2480 | time (msec), value, data direction, offset |
| 2481 | |
| 2482 | Time for the log entry is always in milliseconds. The value logged depends |
| 2483 | on the type of log, it will be one of the following: |
| 2484 | |
| 2485 | Latency log Value is latency in usecs |
| 2486 | Bandwidth log Value is in KiB/sec |
| 2487 | IOPS log Value is IOPS |
| 2488 | |
| 2489 | Data direction is one of the following: |
| 2490 | |
| 2491 | 0 IO is a READ |
| 2492 | 1 IO is a WRITE |
| 2493 | 2 IO is a TRIM |
| 2494 | |
| 2495 | The offset is the offset, in bytes, from the start of the file, for that |
| 2496 | particular IO. The logging of the offset can be toggled with 'log_offset'. |
| 2497 | |
| 2498 | If windowed logging is enabled through 'log_avg_msec', then fio doesn't log |
| 2499 | individual IOs. Instead of logs the average values over the specified |
| 2500 | period of time. Since 'data direction' and 'offset' are per-IO values, |
| 2501 | they aren't applicable if windowed logging is enabled. If windowed logging |
| 2502 | is enabled and 'log_max_value' is set, then fio logs maximum values in |
| 2503 | that window instead of averages. |