1How fio works 2------------- 3 4The first step in getting fio to simulate a desired I/O workload, is writing a 5job file describing that specific setup. A job file may contain any number of 6threads and/or files -- the typical contents of the job file is a *global* 7section defining shared parameters, and one or more job sections describing the 8jobs involved. When run, fio parses this file and sets everything up as 9described. If we break down a job from top to bottom, it contains the following 10basic parameters: 11 12`I/O type`_ 13 14 Defines the I/O pattern issued to the file(s). We may only be reading 15 sequentially from this file(s), or we may be writing randomly. Or even 16 mixing reads and writes, sequentially or randomly. 17 Should we be doing buffered I/O, or direct/raw I/O? 18 19`Block size`_ 20 21 In how large chunks are we issuing I/O? This may be a single value, 22 or it may describe a range of block sizes. 23 24`I/O size`_ 25 26 How much data are we going to be reading/writing. 27 28`I/O engine`_ 29 30 How do we issue I/O? We could be memory mapping the file, we could be 31 using regular read/write, we could be using splice, async I/O, or even 32 SG (SCSI generic sg). 33 34`I/O depth`_ 35 36 If the I/O engine is async, how large a queuing depth do we want to 37 maintain? 38 39 40`Target file/device`_ 41 42 How many files are we spreading the workload over. 43 44`Threads, processes and job synchronization`_ 45 46 How many threads or processes should we spread this workload over. 47 48The above are the basic parameters defined for a workload, in addition there's a 49multitude of parameters that modify other aspects of how this job behaves. 50 51 52Command line options 53-------------------- 54 55.. option:: --debug=type 56 57 Enable verbose tracing `type` of various fio actions. May be ``all`` for all types 58 or individual types separated by a comma (e.g. ``--debug=file,mem`` will 59 enable file and memory debugging). Currently, additional logging is 60 available for: 61 62 *process* 63 Dump info related to processes. 64 *file* 65 Dump info related to file actions. 66 *io* 67 Dump info related to I/O queuing. 68 *mem* 69 Dump info related to memory allocations. 70 *blktrace* 71 Dump info related to blktrace setup. 72 *verify* 73 Dump info related to I/O verification. 74 *all* 75 Enable all debug options. 76 *random* 77 Dump info related to random offset generation. 78 *parse* 79 Dump info related to option matching and parsing. 80 *diskutil* 81 Dump info related to disk utilization updates. 82 *job:x* 83 Dump info only related to job number x. 84 *mutex* 85 Dump info only related to mutex up/down ops. 86 *profile* 87 Dump info related to profile extensions. 88 *time* 89 Dump info related to internal time keeping. 90 *net* 91 Dump info related to networking connections. 92 *rate* 93 Dump info related to I/O rate switching. 94 *compress* 95 Dump info related to log compress/decompress. 96 *steadystate* 97 Dump info related to steadystate detection. 98 *helperthread* 99 Dump info related to the helper thread. 100 *zbd* 101 Dump info related to support for zoned block devices. 102 *?* or *help* 103 Show available debug options. 104 105.. option:: --parse-only 106 107 Parse options only, don't start any I/O. 108 109.. option:: --merge-blktrace-only 110 111 Merge blktraces only, don't start any I/O. 112 113.. option:: --output=filename 114 115 Write output to file `filename`. 116 117.. option:: --output-format=format 118 119 Set the reporting `format` to `normal`, `terse`, `json`, or `json+`. Multiple 120 formats can be selected, separated by a comma. `terse` is a CSV based 121 format. `json+` is like `json`, except it adds a full dump of the latency 122 buckets. 123 124.. option:: --bandwidth-log 125 126 Generate aggregate bandwidth logs. 127 128.. option:: --minimal 129 130 Print statistics in a terse, semicolon-delimited format. 131 132.. option:: --append-terse 133 134 Print statistics in selected mode AND terse, semicolon-delimited format. 135 **Deprecated**, use :option:`--output-format` instead to select multiple 136 formats. 137 138.. option:: --terse-version=version 139 140 Set terse `version` output format (default 3, or 2 or 4 or 5). 141 142.. option:: --version 143 144 Print version information and exit. 145 146.. option:: --help 147 148 Print a summary of the command line options and exit. 149 150.. option:: --cpuclock-test 151 152 Perform test and validation of internal CPU clock. 153 154.. option:: --crctest=[test] 155 156 Test the speed of the built-in checksumming functions. If no argument is 157 given, all of them are tested. Alternatively, a comma separated list can 158 be passed, in which case the given ones are tested. 159 160.. option:: --cmdhelp=command 161 162 Print help information for `command`. May be ``all`` for all commands. 163 164.. option:: --enghelp=[ioengine[,command]] 165 166 List all commands defined by `ioengine`, or print help for `command` 167 defined by `ioengine`. If no `ioengine` is given, list all 168 available ioengines. 169 170.. option:: --showcmd=jobfile 171 172 Convert `jobfile` to a set of command-line options. 173 174.. option:: --readonly 175 176 Turn on safety read-only checks, preventing writes and trims. The 177 ``--readonly`` option is an extra safety guard to prevent users from 178 accidentally starting a write or trim workload when that is not desired. 179 Fio will only modify the device under test if 180 `rw=write/randwrite/rw/randrw/trim/randtrim/trimwrite` is given. This 181 safety net can be used as an extra precaution. 182 183.. option:: --eta=when 184 185 Specifies when real-time ETA estimate should be printed. `when` may be 186 `always`, `never` or `auto`. `auto` is the default, it prints ETA 187 when requested if the output is a TTY. `always` disregards the output 188 type, and prints ETA when requested. `never` never prints ETA. 189 190.. option:: --eta-interval=time 191 192 By default, fio requests client ETA status roughly every second. With 193 this option, the interval is configurable. Fio imposes a minimum 194 allowed time to avoid flooding the console, less than 250 msec is 195 not supported. 196 197.. option:: --eta-newline=time 198 199 Force a new line for every `time` period passed. When the unit is omitted, 200 the value is interpreted in seconds. 201 202.. option:: --status-interval=time 203 204 Force a full status dump of cumulative (from job start) values at `time` 205 intervals. This option does *not* provide per-period measurements. So 206 values such as bandwidth are running averages. When the time unit is omitted, 207 `time` is interpreted in seconds. Note that using this option with 208 ``--output-format=json`` will yield output that technically isn't valid 209 json, since the output will be collated sets of valid json. It will need 210 to be split into valid sets of json after the run. 211 212.. option:: --section=name 213 214 Only run specified section `name` in job file. Multiple sections can be specified. 215 The ``--section`` option allows one to combine related jobs into one file. 216 E.g. one job file could define light, moderate, and heavy sections. Tell 217 fio to run only the "heavy" section by giving ``--section=heavy`` 218 command line option. One can also specify the "write" operations in one 219 section and "verify" operation in another section. The ``--section`` option 220 only applies to job sections. The reserved *global* section is always 221 parsed and used. 222 223.. option:: --alloc-size=kb 224 225 Allocate additional internal smalloc pools of size `kb` in KiB. The 226 ``--alloc-size`` option increases shared memory set aside for use by fio. 227 If running large jobs with randommap enabled, fio can run out of memory. 228 Smalloc is an internal allocator for shared structures from a fixed size 229 memory pool and can grow to 16 pools. The pool size defaults to 16MiB. 230 231 NOTE: While running :file:`.fio_smalloc.*` backing store files are visible 232 in :file:`/tmp`. 233 234.. option:: --warnings-fatal 235 236 All fio parser warnings are fatal, causing fio to exit with an 237 error. 238 239.. option:: --max-jobs=nr 240 241 Set the maximum number of threads/processes to support to `nr`. 242 NOTE: On Linux, it may be necessary to increase the shared-memory 243 limit (:file:`/proc/sys/kernel/shmmax`) if fio runs into errors while 244 creating jobs. 245 246.. option:: --server=args 247 248 Start a backend server, with `args` specifying what to listen to. 249 See `Client/Server`_ section. 250 251.. option:: --daemonize=pidfile 252 253 Background a fio server, writing the pid to the given `pidfile` file. 254 255.. option:: --client=hostname 256 257 Instead of running the jobs locally, send and run them on the given `hostname` 258 or set of `hostname`\s. See `Client/Server`_ section. 259 260.. option:: --remote-config=file 261 262 Tell fio server to load this local `file`. 263 264.. option:: --idle-prof=option 265 266 Report CPU idleness. `option` is one of the following: 267 268 **calibrate** 269 Run unit work calibration only and exit. 270 271 **system** 272 Show aggregate system idleness and unit work. 273 274 **percpu** 275 As **system** but also show per CPU idleness. 276 277.. option:: --inflate-log=log 278 279 Inflate and output compressed `log`. 280 281.. option:: --trigger-file=file 282 283 Execute trigger command when `file` exists. 284 285.. option:: --trigger-timeout=time 286 287 Execute trigger at this `time`. 288 289.. option:: --trigger=command 290 291 Set this `command` as local trigger. 292 293.. option:: --trigger-remote=command 294 295 Set this `command` as remote trigger. 296 297.. option:: --aux-path=path 298 299 Use the directory specified by `path` for generated state files instead 300 of the current working directory. 301 302Any parameters following the options will be assumed to be job files, unless 303they match a job file parameter. Multiple job files can be listed and each job 304file will be regarded as a separate group. Fio will :option:`stonewall` 305execution between each group. 306 307 308Job file format 309--------------- 310 311As previously described, fio accepts one or more job files describing what it is 312supposed to do. The job file format is the classic ini file, where the names 313enclosed in [] brackets define the job name. You are free to use any ASCII name 314you want, except *global* which has special meaning. Following the job name is 315a sequence of zero or more parameters, one per line, that define the behavior of 316the job. If the first character in a line is a ';' or a '#', the entire line is 317discarded as a comment. 318 319A *global* section sets defaults for the jobs described in that file. A job may 320override a *global* section parameter, and a job file may even have several 321*global* sections if so desired. A job is only affected by a *global* section 322residing above it. 323 324The :option:`--cmdhelp` option also lists all options. If used with a `command` 325argument, :option:`--cmdhelp` will detail the given `command`. 326 327See the `examples/` directory for inspiration on how to write job files. Note 328the copyright and license requirements currently apply to `examples/` files. 329 330So let's look at a really simple job file that defines two processes, each 331randomly reading from a 128MiB file: 332 333.. code-block:: ini 334 335 ; -- start job file -- 336 [global] 337 rw=randread 338 size=128m 339 340 [job1] 341 342 [job2] 343 344 ; -- end job file -- 345 346As you can see, the job file sections themselves are empty as all the described 347parameters are shared. As no :option:`filename` option is given, fio makes up a 348`filename` for each of the jobs as it sees fit. On the command line, this job 349would look as follows:: 350 351$ fio --name=global --rw=randread --size=128m --name=job1 --name=job2 352 353 354Let's look at an example that has a number of processes writing randomly to 355files: 356 357.. code-block:: ini 358 359 ; -- start job file -- 360 [random-writers] 361 ioengine=libaio 362 iodepth=4 363 rw=randwrite 364 bs=32k 365 direct=0 366 size=64m 367 numjobs=4 368 ; -- end job file -- 369 370Here we have no *global* section, as we only have one job defined anyway. We 371want to use async I/O here, with a depth of 4 for each file. We also increased 372the buffer size used to 32KiB and define numjobs to 4 to fork 4 identical 373jobs. The result is 4 processes each randomly writing to their own 64MiB 374file. Instead of using the above job file, you could have given the parameters 375on the command line. For this case, you would specify:: 376 377$ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4 378 379When fio is utilized as a basis of any reasonably large test suite, it might be 380desirable to share a set of standardized settings across multiple job files. 381Instead of copy/pasting such settings, any section may pull in an external 382:file:`filename.fio` file with *include filename* directive, as in the following 383example:: 384 385 ; -- start job file including.fio -- 386 [global] 387 filename=/tmp/test 388 filesize=1m 389 include glob-include.fio 390 391 [test] 392 rw=randread 393 bs=4k 394 time_based=1 395 runtime=10 396 include test-include.fio 397 ; -- end job file including.fio -- 398 399.. code-block:: ini 400 401 ; -- start job file glob-include.fio -- 402 thread=1 403 group_reporting=1 404 ; -- end job file glob-include.fio -- 405 406.. code-block:: ini 407 408 ; -- start job file test-include.fio -- 409 ioengine=libaio 410 iodepth=4 411 ; -- end job file test-include.fio -- 412 413Settings pulled into a section apply to that section only (except *global* 414section). Include directives may be nested in that any included file may contain 415further include directive(s). Include files may not contain [] sections. 416 417 418Environment variables 419~~~~~~~~~~~~~~~~~~~~~ 420 421Fio also supports environment variable expansion in job files. Any sub-string of 422the form ``${VARNAME}`` as part of an option value (in other words, on the right 423of the '='), will be expanded to the value of the environment variable called 424`VARNAME`. If no such environment variable is defined, or `VARNAME` is the 425empty string, the empty string will be substituted. 426 427As an example, let's look at a sample fio invocation and job file:: 428 429$ SIZE=64m NUMJOBS=4 fio jobfile.fio 430 431.. code-block:: ini 432 433 ; -- start job file -- 434 [random-writers] 435 rw=randwrite 436 size=${SIZE} 437 numjobs=${NUMJOBS} 438 ; -- end job file -- 439 440This will expand to the following equivalent job file at runtime: 441 442.. code-block:: ini 443 444 ; -- start job file -- 445 [random-writers] 446 rw=randwrite 447 size=64m 448 numjobs=4 449 ; -- end job file -- 450 451Fio ships with a few example job files, you can also look there for inspiration. 452 453Reserved keywords 454~~~~~~~~~~~~~~~~~ 455 456Additionally, fio has a set of reserved keywords that will be replaced 457internally with the appropriate value. Those keywords are: 458 459**$pagesize** 460 461 The architecture page size of the running system. 462 463**$mb_memory** 464 465 Megabytes of total memory in the system. 466 467**$ncpus** 468 469 Number of online available CPUs. 470 471These can be used on the command line or in the job file, and will be 472automatically substituted with the current system values when the job is 473run. Simple math is also supported on these keywords, so you can perform actions 474like:: 475 476 size=8*$mb_memory 477 478and get that properly expanded to 8 times the size of memory in the machine. 479 480 481Job file parameters 482------------------- 483 484This section describes in details each parameter associated with a job. Some 485parameters take an option of a given type, such as an integer or a 486string. Anywhere a numeric value is required, an arithmetic expression may be 487used, provided it is surrounded by parentheses. Supported operators are: 488 489 - addition (+) 490 - subtraction (-) 491 - multiplication (*) 492 - division (/) 493 - modulus (%) 494 - exponentiation (^) 495 496For time values in expressions, units are microseconds by default. This is 497different than for time values not in expressions (not enclosed in 498parentheses). The following types are used: 499 500 501Parameter types 502~~~~~~~~~~~~~~~ 503 504**str** 505 String: A sequence of alphanumeric characters. 506 507**time** 508 Integer with possible time suffix. Without a unit value is interpreted as 509 seconds unless otherwise specified. Accepts a suffix of 'd' for days, 'h' for 510 hours, 'm' for minutes, 's' for seconds, 'ms' (or 'msec') for milliseconds and 511 'us' (or 'usec') for microseconds. For example, use 10m for 10 minutes. 512 513.. _int: 514 515**int** 516 Integer. A whole number value, which may contain an integer prefix 517 and an integer suffix: 518 519 [*integer prefix*] **number** [*integer suffix*] 520 521 The optional *integer prefix* specifies the number's base. The default 522 is decimal. *0x* specifies hexadecimal. 523 524 The optional *integer suffix* specifies the number's units, and includes an 525 optional unit prefix and an optional unit. For quantities of data, the 526 default unit is bytes. For quantities of time, the default unit is seconds 527 unless otherwise specified. 528 529 With :option:`kb_base`\=1000, fio follows international standards for unit 530 prefixes. To specify power-of-10 decimal values defined in the 531 International System of Units (SI): 532 533 * *K* -- means kilo (K) or 1000 534 * *M* -- means mega (M) or 1000**2 535 * *G* -- means giga (G) or 1000**3 536 * *T* -- means tera (T) or 1000**4 537 * *P* -- means peta (P) or 1000**5 538 539 To specify power-of-2 binary values defined in IEC 80000-13: 540 541 * *Ki* -- means kibi (Ki) or 1024 542 * *Mi* -- means mebi (Mi) or 1024**2 543 * *Gi* -- means gibi (Gi) or 1024**3 544 * *Ti* -- means tebi (Ti) or 1024**4 545 * *Pi* -- means pebi (Pi) or 1024**5 546 547 For Zone Block Device Mode: 548 * *z* -- means Zone 549 550 With :option:`kb_base`\=1024 (the default), the unit prefixes are opposite 551 from those specified in the SI and IEC 80000-13 standards to provide 552 compatibility with old scripts. For example, 4k means 4096. 553 554 For quantities of data, an optional unit of 'B' may be included 555 (e.g., 'kB' is the same as 'k'). 556 557 The *integer suffix* is not case sensitive (e.g., m/mi mean mebi/mega, 558 not milli). 'b' and 'B' both mean byte, not bit. 559 560 Examples with :option:`kb_base`\=1000: 561 562 * *4 KiB*: 4096, 4096b, 4096B, 4ki, 4kib, 4kiB, 4Ki, 4KiB 563 * *1 MiB*: 1048576, 1mi, 1024ki 564 * *1 MB*: 1000000, 1m, 1000k 565 * *1 TiB*: 1099511627776, 1ti, 1024gi, 1048576mi 566 * *1 TB*: 1000000000, 1t, 1000m, 1000000k 567 568 Examples with :option:`kb_base`\=1024 (default): 569 570 * *4 KiB*: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB 571 * *1 MiB*: 1048576, 1m, 1024k 572 * *1 MB*: 1000000, 1mi, 1000ki 573 * *1 TiB*: 1099511627776, 1t, 1024g, 1048576m 574 * *1 TB*: 1000000000, 1ti, 1000mi, 1000000ki 575 576 To specify times (units are not case sensitive): 577 578 * *D* -- means days 579 * *H* -- means hours 580 * *M* -- means minutes 581 * *s* -- or sec means seconds (default) 582 * *ms* -- or *msec* means milliseconds 583 * *us* -- or *usec* means microseconds 584 585 If the option accepts an upper and lower range, use a colon ':' or 586 minus '-' to separate such values. See :ref:`irange <irange>`. 587 If the lower value specified happens to be larger than the upper value 588 the two values are swapped. 589 590.. _bool: 591 592**bool** 593 Boolean. Usually parsed as an integer, however only defined for 594 true and false (1 and 0). 595 596.. _irange: 597 598**irange** 599 Integer range with suffix. Allows value range to be given, such as 600 1024-4096. A colon may also be used as the separator, e.g. 1k:4k. If the 601 option allows two sets of ranges, they can be specified with a ',' or '/' 602 delimiter: 1k-4k/8k-32k. Also see :ref:`int <int>`. 603 604**float_list** 605 A list of floating point numbers, separated by a ':' character. 606 607With the above in mind, here follows the complete list of fio job parameters. 608 609 610Units 611~~~~~ 612 613.. option:: kb_base=int 614 615 Select the interpretation of unit prefixes in input parameters. 616 617 **1000** 618 Inputs comply with IEC 80000-13 and the International 619 System of Units (SI). Use: 620 621 - power-of-2 values with IEC prefixes (e.g., KiB) 622 - power-of-10 values with SI prefixes (e.g., kB) 623 624 **1024** 625 Compatibility mode (default). To avoid breaking old scripts: 626 627 - power-of-2 values with SI prefixes 628 - power-of-10 values with IEC prefixes 629 630 See :option:`bs` for more details on input parameters. 631 632 Outputs always use correct prefixes. Most outputs include both 633 side-by-side, like:: 634 635 bw=2383.3kB/s (2327.4KiB/s) 636 637 If only one value is reported, then kb_base selects the one to use: 638 639 **1000** -- SI prefixes 640 641 **1024** -- IEC prefixes 642 643.. option:: unit_base=int 644 645 Base unit for reporting. Allowed values are: 646 647 **0** 648 Use auto-detection (default). 649 **8** 650 Byte based. 651 **1** 652 Bit based. 653 654 655Job description 656~~~~~~~~~~~~~~~ 657 658.. option:: name=str 659 660 ASCII name of the job. This may be used to override the name printed by fio 661 for this job. Otherwise the job name is used. On the command line this 662 parameter has the special purpose of also signaling the start of a new job. 663 664.. option:: description=str 665 666 Text description of the job. Doesn't do anything except dump this text 667 description when this job is run. It's not parsed. 668 669.. option:: loops=int 670 671 Run the specified number of iterations of this job. Used to repeat the same 672 workload a given number of times. Defaults to 1. 673 674.. option:: numjobs=int 675 676 Create the specified number of clones of this job. Each clone of job 677 is spawned as an independent thread or process. May be used to setup a 678 larger number of threads/processes doing the same thing. Each thread is 679 reported separately; to see statistics for all clones as a whole, use 680 :option:`group_reporting` in conjunction with :option:`new_group`. 681 See :option:`--max-jobs`. Default: 1. 682 683 684Time related parameters 685~~~~~~~~~~~~~~~~~~~~~~~ 686 687.. option:: runtime=time 688 689 Tell fio to terminate processing after the specified period of time. It 690 can be quite hard to determine for how long a specified job will run, so 691 this parameter is handy to cap the total runtime to a given time. When 692 the unit is omitted, the value is interpreted in seconds. 693 694.. option:: time_based 695 696 If set, fio will run for the duration of the :option:`runtime` specified 697 even if the file(s) are completely read or written. It will simply loop over 698 the same workload as many times as the :option:`runtime` allows. 699 700.. option:: startdelay=irange(time) 701 702 Delay the start of job for the specified amount of time. Can be a single 703 value or a range. When given as a range, each thread will choose a value 704 randomly from within the range. Value is in seconds if a unit is omitted. 705 706.. option:: ramp_time=time 707 708 If set, fio will run the specified workload for this amount of time before 709 logging any performance numbers. Useful for letting performance settle 710 before logging results, thus minimizing the runtime required for stable 711 results. Note that the ``ramp_time`` is considered lead in time for a job, 712 thus it will increase the total runtime if a special timeout or 713 :option:`runtime` is specified. When the unit is omitted, the value is 714 given in seconds. 715 716.. option:: clocksource=str 717 718 Use the given clocksource as the base of timing. The supported options are: 719 720 **gettimeofday** 721 :manpage:`gettimeofday(2)` 722 723 **clock_gettime** 724 :manpage:`clock_gettime(2)` 725 726 **cpu** 727 Internal CPU clock source 728 729 cpu is the preferred clocksource if it is reliable, as it is very fast (and 730 fio is heavy on time calls). Fio will automatically use this clocksource if 731 it's supported and considered reliable on the system it is running on, 732 unless another clocksource is specifically set. For x86/x86-64 CPUs, this 733 means supporting TSC Invariant. 734 735.. option:: gtod_reduce=bool 736 737 Enable all of the :manpage:`gettimeofday(2)` reducing options 738 (:option:`disable_clat`, :option:`disable_slat`, :option:`disable_bw_measurement`) plus 739 reduce precision of the timeout somewhat to really shrink the 740 :manpage:`gettimeofday(2)` call count. With this option enabled, we only do 741 about 0.4% of the :manpage:`gettimeofday(2)` calls we would have done if all 742 time keeping was enabled. 743 744.. option:: gtod_cpu=int 745 746 Sometimes it's cheaper to dedicate a single thread of execution to just 747 getting the current time. Fio (and databases, for instance) are very 748 intensive on :manpage:`gettimeofday(2)` calls. With this option, you can set 749 one CPU aside for doing nothing but logging current time to a shared memory 750 location. Then the other threads/processes that run I/O workloads need only 751 copy that segment, instead of entering the kernel with a 752 :manpage:`gettimeofday(2)` call. The CPU set aside for doing these time 753 calls will be excluded from other uses. Fio will manually clear it from the 754 CPU mask of other jobs. 755 756 757Target file/device 758~~~~~~~~~~~~~~~~~~ 759 760.. option:: directory=str 761 762 Prefix filenames with this directory. Used to place files in a different 763 location than :file:`./`. You can specify a number of directories by 764 separating the names with a ':' character. These directories will be 765 assigned equally distributed to job clones created by :option:`numjobs` as 766 long as they are using generated filenames. If specific `filename(s)` are 767 set fio will use the first listed directory, and thereby matching the 768 `filename` semantic (which generates a file for each clone if not 769 specified, but lets all clones use the same file if set). 770 771 See the :option:`filename` option for information on how to escape "``:``" 772 characters within the directory path itself. 773 774 Note: To control the directory fio will use for internal state files 775 use :option:`--aux-path`. 776 777.. option:: filename=str 778 779 Fio normally makes up a `filename` based on the job name, thread number, and 780 file number (see :option:`filename_format`). If you want to share files 781 between threads in a job or several 782 jobs with fixed file paths, specify a `filename` for each of them to override 783 the default. If the ioengine is file based, you can specify a number of files 784 by separating the names with a ':' colon. So if you wanted a job to open 785 :file:`/dev/sda` and :file:`/dev/sdb` as the two working files, you would use 786 ``filename=/dev/sda:/dev/sdb``. This also means that whenever this option is 787 specified, :option:`nrfiles` is ignored. The size of regular files specified 788 by this option will be :option:`size` divided by number of files unless an 789 explicit size is specified by :option:`filesize`. 790 791 Each colon in the wanted path must be escaped with a ``\`` 792 character. For instance, if the path is :file:`/dev/dsk/foo@3,0:c` then you 793 would use ``filename=/dev/dsk/foo@3,0\:c`` and if the path is 794 :file:`F:\\filename` then you would use ``filename=F\:\filename``. 795 796 On Windows, disk devices are accessed as :file:`\\\\.\\PhysicalDrive0` for 797 the first device, :file:`\\\\.\\PhysicalDrive1` for the second etc. 798 Note: Windows and FreeBSD prevent write access to areas 799 of the disk containing in-use data (e.g. filesystems). 800 801 The filename "`-`" is a reserved name, meaning *stdin* or *stdout*. Which 802 of the two depends on the read/write direction set. 803 804.. option:: filename_format=str 805 806 If sharing multiple files between jobs, it is usually necessary to have fio 807 generate the exact names that you want. By default, fio will name a file 808 based on the default file format specification of 809 :file:`jobname.jobnumber.filenumber`. With this option, that can be 810 customized. Fio will recognize and replace the following keywords in this 811 string: 812 813 **$jobname** 814 The name of the worker thread or process. 815 **$clientuid** 816 IP of the fio process when using client/server mode. 817 **$jobnum** 818 The incremental number of the worker thread or process. 819 **$filenum** 820 The incremental number of the file for that worker thread or 821 process. 822 823 To have dependent jobs share a set of files, this option can be set to have 824 fio generate filenames that are shared between the two. For instance, if 825 :file:`testfiles.$filenum` is specified, file number 4 for any job will be 826 named :file:`testfiles.4`. The default of :file:`$jobname.$jobnum.$filenum` 827 will be used if no other format specifier is given. 828 829 If you specify a path then the directories will be created up to the 830 main directory for the file. So for example if you specify 831 ``filename_format=a/b/c/$jobnum`` then the directories a/b/c will be 832 created before the file setup part of the job. If you specify 833 :option:`directory` then the path will be relative that directory, 834 otherwise it is treated as the absolute path. 835 836.. option:: unique_filename=bool 837 838 To avoid collisions between networked clients, fio defaults to prefixing any 839 generated filenames (with a directory specified) with the source of the 840 client connecting. To disable this behavior, set this option to 0. 841 842.. option:: opendir=str 843 844 Recursively open any files below directory `str`. 845 846.. option:: lockfile=str 847 848 Fio defaults to not locking any files before it does I/O to them. If a file 849 or file descriptor is shared, fio can serialize I/O to that file to make the 850 end result consistent. This is usual for emulating real workloads that share 851 files. The lock modes are: 852 853 **none** 854 No locking. The default. 855 **exclusive** 856 Only one thread or process may do I/O at a time, excluding all 857 others. 858 **readwrite** 859 Read-write locking on the file. Many readers may 860 access the file at the same time, but writes get exclusive access. 861 862.. option:: nrfiles=int 863 864 Number of files to use for this job. Defaults to 1. The size of files 865 will be :option:`size` divided by this unless explicit size is specified by 866 :option:`filesize`. Files are created for each thread separately, and each 867 file will have a file number within its name by default, as explained in 868 :option:`filename` section. 869 870 871.. option:: openfiles=int 872 873 Number of files to keep open at the same time. Defaults to the same as 874 :option:`nrfiles`, can be set smaller to limit the number simultaneous 875 opens. 876 877.. option:: file_service_type=str 878 879 Defines how fio decides which file from a job to service next. The following 880 types are defined: 881 882 **random** 883 Choose a file at random. 884 885 **roundrobin** 886 Round robin over opened files. This is the default. 887 888 **sequential** 889 Finish one file before moving on to the next. Multiple files can 890 still be open depending on :option:`openfiles`. 891 892 **zipf** 893 Use a *Zipf* distribution to decide what file to access. 894 895 **pareto** 896 Use a *Pareto* distribution to decide what file to access. 897 898 **normal** 899 Use a *Gaussian* (normal) distribution to decide what file to 900 access. 901 902 **gauss** 903 Alias for normal. 904 905 For *random*, *roundrobin*, and *sequential*, a postfix can be appended to 906 tell fio how many I/Os to issue before switching to a new file. For example, 907 specifying ``file_service_type=random:8`` would cause fio to issue 908 8 I/Os before selecting a new file at random. For the non-uniform 909 distributions, a floating point postfix can be given to influence how the 910 distribution is skewed. See :option:`random_distribution` for a description 911 of how that would work. 912 913.. option:: ioscheduler=str 914 915 Attempt to switch the device hosting the file to the specified I/O scheduler 916 before running. 917 918.. option:: create_serialize=bool 919 920 If true, serialize the file creation for the jobs. This may be handy to 921 avoid interleaving of data files, which may greatly depend on the filesystem 922 used and even the number of processors in the system. Default: true. 923 924.. option:: create_fsync=bool 925 926 :manpage:`fsync(2)` the data file after creation. This is the default. 927 928.. option:: create_on_open=bool 929 930 If true, don't pre-create files but allow the job's open() to create a file 931 when it's time to do I/O. Default: false -- pre-create all necessary files 932 when the job starts. 933 934.. option:: create_only=bool 935 936 If true, fio will only run the setup phase of the job. If files need to be 937 laid out or updated on disk, only that will be done -- the actual job contents 938 are not executed. Default: false. 939 940.. option:: allow_file_create=bool 941 942 If true, fio is permitted to create files as part of its workload. If this 943 option is false, then fio will error out if 944 the files it needs to use don't already exist. Default: true. 945 946.. option:: allow_mounted_write=bool 947 948 If this isn't set, fio will abort jobs that are destructive (e.g. that write) 949 to what appears to be a mounted device or partition. This should help catch 950 creating inadvertently destructive tests, not realizing that the test will 951 destroy data on the mounted file system. Note that some platforms don't allow 952 writing against a mounted device regardless of this option. Default: false. 953 954.. option:: pre_read=bool 955 956 If this is given, files will be pre-read into memory before starting the 957 given I/O operation. This will also clear the :option:`invalidate` flag, 958 since it is pointless to pre-read and then drop the cache. This will only 959 work for I/O engines that are seek-able, since they allow you to read the 960 same data multiple times. Thus it will not work on non-seekable I/O engines 961 (e.g. network, splice). Default: false. 962 963.. option:: unlink=bool 964 965 Unlink the job files when done. Not the default, as repeated runs of that 966 job would then waste time recreating the file set again and again. Default: 967 false. 968 969.. option:: unlink_each_loop=bool 970 971 Unlink job files after each iteration or loop. Default: false. 972 973.. option:: zonemode=str 974 975 Accepted values are: 976 977 **none** 978 The :option:`zonerange`, :option:`zonesize`, 979 :option `zonecapacity` and option:`zoneskip` 980 parameters are ignored. 981 **strided** 982 I/O happens in a single zone until 983 :option:`zonesize` bytes have been transferred. 984 After that number of bytes has been 985 transferred processing of the next zone 986 starts. :option `zonecapacity` is ignored. 987 **zbd** 988 Zoned block device mode. I/O happens 989 sequentially in each zone, even if random I/O 990 has been selected. Random I/O happens across 991 all zones instead of being restricted to a 992 single zone. The :option:`zoneskip` parameter 993 is ignored. :option:`zonerange` and 994 :option:`zonesize` must be identical. 995 Trim is handled using a zone reset operation. 996 Trim only considers non-empty sequential write 997 required and sequential write preferred zones. 998 999.. option:: zonerange=int 1000 1001 Size of a single zone. See also :option:`zonesize` and 1002 :option:`zoneskip`. 1003 1004.. option:: zonesize=int 1005 1006 For :option:`zonemode` =strided, this is the number of bytes to 1007 transfer before skipping :option:`zoneskip` bytes. If this parameter 1008 is smaller than :option:`zonerange` then only a fraction of each zone 1009 with :option:`zonerange` bytes will be accessed. If this parameter is 1010 larger than :option:`zonerange` then each zone will be accessed 1011 multiple times before skipping to the next zone. 1012 1013 For :option:`zonemode` =zbd, this is the size of a single zone. The 1014 :option:`zonerange` parameter is ignored in this mode. 1015 1016 1017.. option:: zonecapacity=int 1018 1019 For :option:`zonemode` =zbd, this defines the capacity of a single zone, 1020 which is the accessible area starting from the zone start address. 1021 This parameter only applies when using :option:`zonemode` =zbd in 1022 combination with regular block devices. If not specified it defaults to 1023 the zone size. If the target device is a zoned block device, the zone 1024 capacity is obtained from the device information and this option is 1025 ignored. 1026 1027.. option:: zoneskip=int 1028 1029 For :option:`zonemode` =strided, the number of bytes to skip after 1030 :option:`zonesize` bytes of data have been transferred. This parameter 1031 must be zero for :option:`zonemode` =zbd. 1032 1033.. option:: read_beyond_wp=bool 1034 1035 This parameter applies to :option:`zonemode` =zbd only. 1036 1037 Zoned block devices are block devices that consist of multiple zones. 1038 Each zone has a type, e.g. conventional or sequential. A conventional 1039 zone can be written at any offset that is a multiple of the block 1040 size. Sequential zones must be written sequentially. The position at 1041 which a write must occur is called the write pointer. A zoned block 1042 device can be either drive managed, host managed or host aware. For 1043 host managed devices the host must ensure that writes happen 1044 sequentially. Fio recognizes host managed devices and serializes 1045 writes to sequential zones for these devices. 1046 1047 If a read occurs in a sequential zone beyond the write pointer then 1048 the zoned block device will complete the read without reading any data 1049 from the storage medium. Since such reads lead to unrealistically high 1050 bandwidth and IOPS numbers fio only reads beyond the write pointer if 1051 explicitly told to do so. Default: false. 1052 1053.. option:: max_open_zones=int 1054 1055 When running a random write test across an entire drive many more 1056 zones will be open than in a typical application workload. Hence this 1057 command line option that allows to limit the number of open zones. The 1058 number of open zones is defined as the number of zones to which write 1059 commands are issued. 1060 1061.. option:: job_max_open_zones=int 1062 1063 Limit on the number of simultaneously opened zones per single 1064 thread/process. 1065 1066.. option:: ignore_zone_limits=bool 1067 If this option is used, fio will ignore the maximum number of open 1068 zones limit of the zoned block device in use, thus allowing the 1069 option :option:`max_open_zones` value to be larger than the device 1070 reported limit. Default: false. 1071 1072.. option:: zone_reset_threshold=float 1073 1074 A number between zero and one that indicates the ratio of logical 1075 blocks with data to the total number of logical blocks in the test 1076 above which zones should be reset periodically. 1077 1078.. option:: zone_reset_frequency=float 1079 1080 A number between zero and one that indicates how often a zone reset 1081 should be issued if the zone reset threshold has been exceeded. A zone 1082 reset is submitted after each (1 / zone_reset_frequency) write 1083 requests. This and the previous parameter can be used to simulate 1084 garbage collection activity. 1085 1086 1087I/O type 1088~~~~~~~~ 1089 1090.. option:: direct=bool 1091 1092 If value is true, use non-buffered I/O. This is usually O_DIRECT. Note that 1093 OpenBSD and ZFS on Solaris don't support direct I/O. On Windows the synchronous 1094 ioengines don't support direct I/O. Default: false. 1095 1096.. option:: atomic=bool 1097 1098 If value is true, attempt to use atomic direct I/O. Atomic writes are 1099 guaranteed to be stable once acknowledged by the operating system. Only 1100 Linux supports O_ATOMIC right now. 1101 1102.. option:: buffered=bool 1103 1104 If value is true, use buffered I/O. This is the opposite of the 1105 :option:`direct` option. Defaults to true. 1106 1107.. option:: readwrite=str, rw=str 1108 1109 Type of I/O pattern. Accepted values are: 1110 1111 **read** 1112 Sequential reads. 1113 **write** 1114 Sequential writes. 1115 **trim** 1116 Sequential trims (Linux block devices and SCSI 1117 character devices only). 1118 **randread** 1119 Random reads. 1120 **randwrite** 1121 Random writes. 1122 **randtrim** 1123 Random trims (Linux block devices and SCSI 1124 character devices only). 1125 **rw,readwrite** 1126 Sequential mixed reads and writes. 1127 **randrw** 1128 Random mixed reads and writes. 1129 **trimwrite** 1130 Sequential trim+write sequences. Blocks will be trimmed first, 1131 then the same blocks will be written to. 1132 1133 Fio defaults to read if the option is not specified. For the mixed I/O 1134 types, the default is to split them 50/50. For certain types of I/O the 1135 result may still be skewed a bit, since the speed may be different. 1136 1137 It is possible to specify the number of I/Os to do before getting a new 1138 offset by appending ``:<nr>`` to the end of the string given. For a 1139 random read, it would look like ``rw=randread:8`` for passing in an offset 1140 modifier with a value of 8. If the suffix is used with a sequential I/O 1141 pattern, then the *<nr>* value specified will be **added** to the generated 1142 offset for each I/O turning sequential I/O into sequential I/O with holes. 1143 For instance, using ``rw=write:4k`` will skip 4k for every write. Also see 1144 the :option:`rw_sequencer` option. 1145 1146.. option:: rw_sequencer=str 1147 1148 If an offset modifier is given by appending a number to the ``rw=<str>`` 1149 line, then this option controls how that number modifies the I/O offset 1150 being generated. Accepted values are: 1151 1152 **sequential** 1153 Generate sequential offset. 1154 **identical** 1155 Generate the same offset. 1156 1157 ``sequential`` is only useful for random I/O, where fio would normally 1158 generate a new random offset for every I/O. If you append e.g. 8 to randread, 1159 you would get a new random offset for every 8 I/Os. The result would be a 1160 seek for only every 8 I/Os, instead of for every I/O. Use ``rw=randread:8`` 1161 to specify that. As sequential I/O is already sequential, setting 1162 ``sequential`` for that would not result in any differences. ``identical`` 1163 behaves in a similar fashion, except it sends the same offset 8 number of 1164 times before generating a new offset. 1165 1166.. option:: unified_rw_reporting=str 1167 1168 Fio normally reports statistics on a per data direction basis, meaning that 1169 reads, writes, and trims are accounted and reported separately. This option 1170 determines whether fio reports the results normally, summed together, or as 1171 both options. 1172 Accepted values are: 1173 1174 **none** 1175 Normal statistics reporting. 1176 1177 **mixed** 1178 Statistics are summed per data direction and reported together. 1179 1180 **both** 1181 Statistics are reported normally, followed by the mixed statistics. 1182 1183 **0** 1184 Backward-compatible alias for **none**. 1185 1186 **1** 1187 Backward-compatible alias for **mixed**. 1188 1189 **2** 1190 Alias for **both**. 1191 1192.. option:: randrepeat=bool 1193 1194 Seed the random number generator used for random I/O patterns in a 1195 predictable way so the pattern is repeatable across runs. Default: true. 1196 1197.. option:: allrandrepeat=bool 1198 1199 Seed all random number generators in a predictable way so results are 1200 repeatable across runs. Default: false. 1201 1202.. option:: randseed=int 1203 1204 Seed the random number generators based on this seed value, to be able to 1205 control what sequence of output is being generated. If not set, the random 1206 sequence depends on the :option:`randrepeat` setting. 1207 1208.. option:: fallocate=str 1209 1210 Whether pre-allocation is performed when laying down files. 1211 Accepted values are: 1212 1213 **none** 1214 Do not pre-allocate space. 1215 1216 **native** 1217 Use a platform's native pre-allocation call but fall back to 1218 **none** behavior if it fails/is not implemented. 1219 1220 **posix** 1221 Pre-allocate via :manpage:`posix_fallocate(3)`. 1222 1223 **keep** 1224 Pre-allocate via :manpage:`fallocate(2)` with 1225 FALLOC_FL_KEEP_SIZE set. 1226 1227 **truncate** 1228 Extend file to final size via :manpage:`ftruncate(2)` 1229 instead of allocating. 1230 1231 **0** 1232 Backward-compatible alias for **none**. 1233 1234 **1** 1235 Backward-compatible alias for **posix**. 1236 1237 May not be available on all supported platforms. **keep** is only available 1238 on Linux. If using ZFS on Solaris this cannot be set to **posix** 1239 because ZFS doesn't support pre-allocation. Default: **native** if any 1240 pre-allocation methods except **truncate** are available, **none** if not. 1241 1242 Note that using **truncate** on Windows will interact surprisingly 1243 with non-sequential write patterns. When writing to a file that has 1244 been extended by setting the end-of-file information, Windows will 1245 backfill the unwritten portion of the file up to that offset with 1246 zeroes before issuing the new write. This means that a single small 1247 write to the end of an extended file will stall until the entire 1248 file has been filled with zeroes. 1249 1250.. option:: fadvise_hint=str 1251 1252 Use :manpage:`posix_fadvise(2)` or :manpage:`posix_fadvise(2)` to 1253 advise the kernel on what I/O patterns are likely to be issued. 1254 Accepted values are: 1255 1256 **0** 1257 Backwards-compatible hint for "no hint". 1258 1259 **1** 1260 Backwards compatible hint for "advise with fio workload type". This 1261 uses **FADV_RANDOM** for a random workload, and **FADV_SEQUENTIAL** 1262 for a sequential workload. 1263 1264 **sequential** 1265 Advise using **FADV_SEQUENTIAL**. 1266 1267 **random** 1268 Advise using **FADV_RANDOM**. 1269 1270.. option:: write_hint=str 1271 1272 Use :manpage:`fcntl(2)` to advise the kernel what life time to expect 1273 from a write. Only supported on Linux, as of version 4.13. Accepted 1274 values are: 1275 1276 **none** 1277 No particular life time associated with this file. 1278 1279 **short** 1280 Data written to this file has a short life time. 1281 1282 **medium** 1283 Data written to this file has a medium life time. 1284 1285 **long** 1286 Data written to this file has a long life time. 1287 1288 **extreme** 1289 Data written to this file has a very long life time. 1290 1291 The values are all relative to each other, and no absolute meaning 1292 should be associated with them. 1293 1294.. option:: offset=int 1295 1296 Start I/O at the provided offset in the file, given as either a fixed size in 1297 bytes, zones or a percentage. If a percentage is given, the generated offset will be 1298 aligned to the minimum ``blocksize`` or to the value of ``offset_align`` if 1299 provided. Data before the given offset will not be touched. This 1300 effectively caps the file size at `real_size - offset`. Can be combined with 1301 :option:`size` to constrain the start and end range of the I/O workload. 1302 A percentage can be specified by a number between 1 and 100 followed by '%', 1303 for example, ``offset=20%`` to specify 20%. In ZBD mode, value can be set as 1304 number of zones using 'z'. 1305 1306.. option:: offset_align=int 1307 1308 If set to non-zero value, the byte offset generated by a percentage ``offset`` 1309 is aligned upwards to this value. Defaults to 0 meaning that a percentage 1310 offset is aligned to the minimum block size. 1311 1312.. option:: offset_increment=int 1313 1314 If this is provided, then the real offset becomes `offset + offset_increment 1315 * thread_number`, where the thread number is a counter that starts at 0 and 1316 is incremented for each sub-job (i.e. when :option:`numjobs` option is 1317 specified). This option is useful if there are several jobs which are 1318 intended to operate on a file in parallel disjoint segments, with even 1319 spacing between the starting points. Percentages can be used for this option. 1320 If a percentage is given, the generated offset will be aligned to the minimum 1321 ``blocksize`` or to the value of ``offset_align`` if provided. In ZBD mode, value can 1322 also be set as number of zones using 'z'. 1323 1324.. option:: number_ios=int 1325 1326 Fio will normally perform I/Os until it has exhausted the size of the region 1327 set by :option:`size`, or if it exhaust the allocated time (or hits an error 1328 condition). With this setting, the range/size can be set independently of 1329 the number of I/Os to perform. When fio reaches this number, it will exit 1330 normally and report status. Note that this does not extend the amount of I/O 1331 that will be done, it will only stop fio if this condition is met before 1332 other end-of-job criteria. 1333 1334.. option:: fsync=int 1335 1336 If writing to a file, issue an :manpage:`fsync(2)` (or its equivalent) of 1337 the dirty data for every number of blocks given. For example, if you give 32 1338 as a parameter, fio will sync the file after every 32 writes issued. If fio is 1339 using non-buffered I/O, we may not sync the file. The exception is the sg 1340 I/O engine, which synchronizes the disk cache anyway. Defaults to 0, which 1341 means fio does not periodically issue and wait for a sync to complete. Also 1342 see :option:`end_fsync` and :option:`fsync_on_close`. 1343 1344.. option:: fdatasync=int 1345 1346 Like :option:`fsync` but uses :manpage:`fdatasync(2)` to only sync data and 1347 not metadata blocks. In Windows, FreeBSD, DragonFlyBSD or OSX there is no 1348 :manpage:`fdatasync(2)` so this falls back to using :manpage:`fsync(2)`. 1349 Defaults to 0, which means fio does not periodically issue and wait for a 1350 data-only sync to complete. 1351 1352.. option:: write_barrier=int 1353 1354 Make every `N-th` write a barrier write. 1355 1356.. option:: sync_file_range=str:int 1357 1358 Use :manpage:`sync_file_range(2)` for every `int` number of write 1359 operations. Fio will track range of writes that have happened since the last 1360 :manpage:`sync_file_range(2)` call. `str` can currently be one or more of: 1361 1362 **wait_before** 1363 SYNC_FILE_RANGE_WAIT_BEFORE 1364 **write** 1365 SYNC_FILE_RANGE_WRITE 1366 **wait_after** 1367 SYNC_FILE_RANGE_WAIT_AFTER 1368 1369 So if you do ``sync_file_range=wait_before,write:8``, fio would use 1370 ``SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE`` for every 8 1371 writes. Also see the :manpage:`sync_file_range(2)` man page. This option is 1372 Linux specific. 1373 1374.. option:: overwrite=bool 1375 1376 If true, writes to a file will always overwrite existing data. If the file 1377 doesn't already exist, it will be created before the write phase begins. If 1378 the file exists and is large enough for the specified write phase, nothing 1379 will be done. Default: false. 1380 1381.. option:: end_fsync=bool 1382 1383 If true, :manpage:`fsync(2)` file contents when a write stage has completed. 1384 Default: false. 1385 1386.. option:: fsync_on_close=bool 1387 1388 If true, fio will :manpage:`fsync(2)` a dirty file on close. This differs 1389 from :option:`end_fsync` in that it will happen on every file close, not 1390 just at the end of the job. Default: false. 1391 1392.. option:: rwmixread=int 1393 1394 Percentage of a mixed workload that should be reads. Default: 50. 1395 1396.. option:: rwmixwrite=int 1397 1398 Percentage of a mixed workload that should be writes. If both 1399 :option:`rwmixread` and :option:`rwmixwrite` is given and the values do not 1400 add up to 100%, the latter of the two will be used to override the 1401 first. This may interfere with a given rate setting, if fio is asked to 1402 limit reads or writes to a certain rate. If that is the case, then the 1403 distribution may be skewed. Default: 50. 1404 1405.. option:: random_distribution=str:float[:float][,str:float][,str:float] 1406 1407 By default, fio will use a completely uniform random distribution when asked 1408 to perform random I/O. Sometimes it is useful to skew the distribution in 1409 specific ways, ensuring that some parts of the data is more hot than others. 1410 fio includes the following distribution models: 1411 1412 **random** 1413 Uniform random distribution 1414 1415 **zipf** 1416 Zipf distribution 1417 1418 **pareto** 1419 Pareto distribution 1420 1421 **normal** 1422 Normal (Gaussian) distribution 1423 1424 **zoned** 1425 Zoned random distribution 1426 1427 **zoned_abs** 1428 Zone absolute random distribution 1429 1430 When using a **zipf** or **pareto** distribution, an input value is also 1431 needed to define the access pattern. For **zipf**, this is the `Zipf 1432 theta`. For **pareto**, it's the `Pareto power`. Fio includes a test 1433 program, :command:`fio-genzipf`, that can be used visualize what the given input 1434 values will yield in terms of hit rates. If you wanted to use **zipf** with 1435 a `theta` of 1.2, you would use ``random_distribution=zipf:1.2`` as the 1436 option. If a non-uniform model is used, fio will disable use of the random 1437 map. For the **normal** distribution, a normal (Gaussian) deviation is 1438 supplied as a value between 0 and 100. 1439 1440 The second, optional float is allowed for **pareto**, **zipf** and **normal** distributions. 1441 It allows to set base of distribution in non-default place, giving more control 1442 over most probable outcome. This value is in range [0-1] which maps linearly to 1443 range of possible random values. 1444 Defaults are: random for **pareto** and **zipf**, and 0.5 for **normal**. 1445 If you wanted to use **zipf** with a `theta` of 1.2 centered on 1/4 of allowed value range, 1446 you would use ``random_distibution=zipf:1.2:0.25``. 1447 1448 For a **zoned** distribution, fio supports specifying percentages of I/O 1449 access that should fall within what range of the file or device. For 1450 example, given a criteria of: 1451 1452 * 60% of accesses should be to the first 10% 1453 * 30% of accesses should be to the next 20% 1454 * 8% of accesses should be to the next 30% 1455 * 2% of accesses should be to the next 40% 1456 1457 we can define that through zoning of the random accesses. For the above 1458 example, the user would do:: 1459 1460 random_distribution=zoned:60/10:30/20:8/30:2/40 1461 1462 A **zoned_abs** distribution works exactly like the **zoned**, except 1463 that it takes absolute sizes. For example, let's say you wanted to 1464 define access according to the following criteria: 1465 1466 * 60% of accesses should be to the first 20G 1467 * 30% of accesses should be to the next 100G 1468 * 10% of accesses should be to the next 500G 1469 1470 we can define an absolute zoning distribution with: 1471 1472 random_distribution=zoned_abs=60/20G:30/100G:10/500g 1473 1474 For both **zoned** and **zoned_abs**, fio supports defining up to 1475 256 separate zones. 1476 1477 Similarly to how :option:`bssplit` works for setting ranges and 1478 percentages of block sizes. Like :option:`bssplit`, it's possible to 1479 specify separate zones for reads, writes, and trims. If just one set 1480 is given, it'll apply to all of them. This goes for both **zoned** 1481 **zoned_abs** distributions. 1482 1483.. option:: percentage_random=int[,int][,int] 1484 1485 For a random workload, set how big a percentage should be random. This 1486 defaults to 100%, in which case the workload is fully random. It can be set 1487 from anywhere from 0 to 100. Setting it to 0 would make the workload fully 1488 sequential. Any setting in between will result in a random mix of sequential 1489 and random I/O, at the given percentages. Comma-separated values may be 1490 specified for reads, writes, and trims as described in :option:`blocksize`. 1491 1492.. option:: norandommap 1493 1494 Normally fio will cover every block of the file when doing random I/O. If 1495 this option is given, fio will just get a new random offset without looking 1496 at past I/O history. This means that some blocks may not be read or written, 1497 and that some blocks may be read/written more than once. If this option is 1498 used with :option:`verify` and multiple blocksizes (via :option:`bsrange`), 1499 only intact blocks are verified, i.e., partially-overwritten blocks are 1500 ignored. With an async I/O engine and an I/O depth > 1, it is possible for 1501 the same block to be overwritten, which can cause verification errors. Either 1502 do not use norandommap in this case, or also use the lfsr random generator. 1503 1504.. option:: softrandommap=bool 1505 1506 See :option:`norandommap`. If fio runs with the random block map enabled and 1507 it fails to allocate the map, if this option is set it will continue without 1508 a random block map. As coverage will not be as complete as with random maps, 1509 this option is disabled by default. 1510 1511.. option:: random_generator=str 1512 1513 Fio supports the following engines for generating I/O offsets for random I/O: 1514 1515 **tausworthe** 1516 Strong 2^88 cycle random number generator. 1517 **lfsr** 1518 Linear feedback shift register generator. 1519 **tausworthe64** 1520 Strong 64-bit 2^258 cycle random number generator. 1521 1522 **tausworthe** is a strong random number generator, but it requires tracking 1523 on the side if we want to ensure that blocks are only read or written 1524 once. **lfsr** guarantees that we never generate the same offset twice, and 1525 it's also less computationally expensive. It's not a true random generator, 1526 however, though for I/O purposes it's typically good enough. **lfsr** only 1527 works with single block sizes, not with workloads that use multiple block 1528 sizes. If used with such a workload, fio may read or write some blocks 1529 multiple times. The default value is **tausworthe**, unless the required 1530 space exceeds 2^32 blocks. If it does, then **tausworthe64** is 1531 selected automatically. 1532 1533 1534Block size 1535~~~~~~~~~~ 1536 1537.. option:: blocksize=int[,int][,int], bs=int[,int][,int] 1538 1539 The block size in bytes used for I/O units. Default: 4096. A single value 1540 applies to reads, writes, and trims. Comma-separated values may be 1541 specified for reads, writes, and trims. A value not terminated in a comma 1542 applies to subsequent types. 1543 1544 Examples: 1545 1546 **bs=256k** 1547 means 256k for reads, writes and trims. 1548 1549 **bs=8k,32k** 1550 means 8k for reads, 32k for writes and trims. 1551 1552 **bs=8k,32k,** 1553 means 8k for reads, 32k for writes, and default for trims. 1554 1555 **bs=,8k** 1556 means default for reads, 8k for writes and trims. 1557 1558 **bs=,8k,** 1559 means default for reads, 8k for writes, and default for trims. 1560 1561.. option:: blocksize_range=irange[,irange][,irange], bsrange=irange[,irange][,irange] 1562 1563 A range of block sizes in bytes for I/O units. The issued I/O unit will 1564 always be a multiple of the minimum size, unless 1565 :option:`blocksize_unaligned` is set. 1566 1567 Comma-separated ranges may be specified for reads, writes, and trims as 1568 described in :option:`blocksize`. 1569 1570 Example: ``bsrange=1k-4k,2k-8k``. 1571 1572.. option:: bssplit=str[,str][,str] 1573 1574 Sometimes you want even finer grained control of the block sizes 1575 issued, not just an even split between them. This option allows you to 1576 weight various block sizes, so that you are able to define a specific 1577 amount of block sizes issued. The format for this option is:: 1578 1579 bssplit=blocksize/percentage:blocksize/percentage 1580 1581 for as many block sizes as needed. So if you want to define a workload 1582 that has 50% 64k blocks, 10% 4k blocks, and 40% 32k blocks, you would 1583 write:: 1584 1585 bssplit=4k/10:64k/50:32k/40 1586 1587 Ordering does not matter. If the percentage is left blank, fio will 1588 fill in the remaining values evenly. So a bssplit option like this one:: 1589 1590 bssplit=4k/50:1k/:32k/ 1591 1592 would have 50% 4k ios, and 25% 1k and 32k ios. The percentages always 1593 add up to 100, if bssplit is given a range that adds up to more, it 1594 will error out. 1595 1596 Comma-separated values may be specified for reads, writes, and trims as 1597 described in :option:`blocksize`. 1598 1599 If you want a workload that has 50% 2k reads and 50% 4k reads, while 1600 having 90% 4k writes and 10% 8k writes, you would specify:: 1601 1602 bssplit=2k/50:4k/50,4k/90:8k/10 1603 1604 Fio supports defining up to 64 different weights for each data 1605 direction. 1606 1607.. option:: blocksize_unaligned, bs_unaligned 1608 1609 If set, fio will issue I/O units with any size within 1610 :option:`blocksize_range`, not just multiples of the minimum size. This 1611 typically won't work with direct I/O, as that normally requires sector 1612 alignment. 1613 1614.. option:: bs_is_seq_rand=bool 1615 1616 If this option is set, fio will use the normal read,write blocksize settings 1617 as sequential,random blocksize settings instead. Any random read or write 1618 will use the WRITE blocksize settings, and any sequential read or write will 1619 use the READ blocksize settings. 1620 1621.. option:: blockalign=int[,int][,int], ba=int[,int][,int] 1622 1623 Boundary to which fio will align random I/O units. Default: 1624 :option:`blocksize`. Minimum alignment is typically 512b for using direct 1625 I/O, though it usually depends on the hardware block size. This option is 1626 mutually exclusive with using a random map for files, so it will turn off 1627 that option. Comma-separated values may be specified for reads, writes, and 1628 trims as described in :option:`blocksize`. 1629 1630 1631Buffers and memory 1632~~~~~~~~~~~~~~~~~~ 1633 1634.. option:: zero_buffers 1635 1636 Initialize buffers with all zeros. Default: fill buffers with random data. 1637 1638.. option:: refill_buffers 1639 1640 If this option is given, fio will refill the I/O buffers on every 1641 submit. Only makes sense if :option:`zero_buffers` isn't specified, 1642 naturally. Defaults to being unset i.e., the buffer is only filled at 1643 init time and the data in it is reused when possible but if any of 1644 :option:`verify`, :option:`buffer_compress_percentage` or 1645 :option:`dedupe_percentage` are enabled then `refill_buffers` is also 1646 automatically enabled. 1647 1648.. option:: scramble_buffers=bool 1649 1650 If :option:`refill_buffers` is too costly and the target is using data 1651 deduplication, then setting this option will slightly modify the I/O buffer 1652 contents to defeat normal de-dupe attempts. This is not enough to defeat 1653 more clever block compression attempts, but it will stop naive dedupe of 1654 blocks. Default: true. 1655 1656.. option:: buffer_compress_percentage=int 1657 1658 If this is set, then fio will attempt to provide I/O buffer content 1659 (on WRITEs) that compresses to the specified level. Fio does this by 1660 providing a mix of random data followed by fixed pattern data. The 1661 fixed pattern is either zeros, or the pattern specified by 1662 :option:`buffer_pattern`. If the `buffer_pattern` option is used, it 1663 might skew the compression ratio slightly. Setting 1664 `buffer_compress_percentage` to a value other than 100 will also 1665 enable :option:`refill_buffers` in order to reduce the likelihood that 1666 adjacent blocks are so similar that they over compress when seen 1667 together. See :option:`buffer_compress_chunk` for how to set a finer or 1668 coarser granularity for the random/fixed data region. Defaults to unset 1669 i.e., buffer data will not adhere to any compression level. 1670 1671.. option:: buffer_compress_chunk=int 1672 1673 This setting allows fio to manage how big the random/fixed data region 1674 is when using :option:`buffer_compress_percentage`. When 1675 `buffer_compress_chunk` is set to some non-zero value smaller than the 1676 block size, fio can repeat the random/fixed region throughout the I/O 1677 buffer at the specified interval (which particularly useful when 1678 bigger block sizes are used for a job). When set to 0, fio will use a 1679 chunk size that matches the block size resulting in a single 1680 random/fixed region within the I/O buffer. Defaults to 512. When the 1681 unit is omitted, the value is interpreted in bytes. 1682 1683.. option:: buffer_pattern=str 1684 1685 If set, fio will fill the I/O buffers with this pattern or with the contents 1686 of a file. If not set, the contents of I/O buffers are defined by the other 1687 options related to buffer contents. The setting can be any pattern of bytes, 1688 and can be prefixed with 0x for hex values. It may also be a string, where 1689 the string must then be wrapped with ``""``. Or it may also be a filename, 1690 where the filename must be wrapped with ``''`` in which case the file is 1691 opened and read. Note that not all the file contents will be read if that 1692 would cause the buffers to overflow. So, for example:: 1693 1694 buffer_pattern='filename' 1695 1696 or:: 1697 1698 buffer_pattern="abcd" 1699 1700 or:: 1701 1702 buffer_pattern=-12 1703 1704 or:: 1705 1706 buffer_pattern=0xdeadface 1707 1708 Also you can combine everything together in any order:: 1709 1710 buffer_pattern=0xdeadface"abcd"-12'filename' 1711 1712.. option:: dedupe_percentage=int 1713 1714 If set, fio will generate this percentage of identical buffers when 1715 writing. These buffers will be naturally dedupable. The contents of the 1716 buffers depend on what other buffer compression settings have been set. It's 1717 possible to have the individual buffers either fully compressible, or not at 1718 all -- this option only controls the distribution of unique buffers. Setting 1719 this option will also enable :option:`refill_buffers` to prevent every buffer 1720 being identical. 1721 1722.. option:: dedupe_mode=str 1723 1724 If ``dedupe_percentage=<int>`` is given, then this option controls how fio 1725 generates the dedupe buffers. 1726 1727 **repeat** 1728 Generate dedupe buffers by repeating previous writes 1729 **working_set** 1730 Generate dedupe buffers from working set 1731 1732 ``repeat`` is the default option for fio. Dedupe buffers are generated 1733 by repeating previous unique write. 1734 1735 ``working_set`` is a more realistic workload. 1736 With ``working_set``, ``dedupe_working_set_percentage=<int>`` should be provided. 1737 Given that, fio will use the initial unique write buffers as its working set. 1738 Upon deciding to dedupe, fio will randomly choose a buffer from the working set. 1739 Note that by using ``working_set`` the dedupe percentage will converge 1740 to the desired over time while ``repeat`` maintains the desired percentage 1741 throughout the job. 1742 1743.. option:: dedupe_working_set_percentage=int 1744 1745 If ``dedupe_mode=<str>`` is set to ``working_set``, then this controls 1746 the percentage of size of the file or device used as the buffers 1747 fio will choose to generate the dedupe buffers from 1748 1749 Note that size needs to be explicitly provided and only 1 file per 1750 job is supported 1751 1752.. option:: invalidate=bool 1753 1754 Invalidate the buffer/page cache parts of the files to be used prior to 1755 starting I/O if the platform and file type support it. Defaults to true. 1756 This will be ignored if :option:`pre_read` is also specified for the 1757 same job. 1758 1759.. option:: sync=str 1760 1761 Whether, and what type, of synchronous I/O to use for writes. The allowed 1762 values are: 1763 1764 **none** 1765 Do not use synchronous IO, the default. 1766 1767 **0** 1768 Same as **none**. 1769 1770 **sync** 1771 Use synchronous file IO. For the majority of I/O engines, 1772 this means using O_SYNC. 1773 1774 **1** 1775 Same as **sync**. 1776 1777 **dsync** 1778 Use synchronous data IO. For the majority of I/O engines, 1779 this means using O_DSYNC. 1780 1781 1782.. option:: iomem=str, mem=str 1783 1784 Fio can use various types of memory as the I/O unit buffer. The allowed 1785 values are: 1786 1787 **malloc** 1788 Use memory from :manpage:`malloc(3)` as the buffers. Default memory 1789 type. 1790 1791 **shm** 1792 Use shared memory as the buffers. Allocated through 1793 :manpage:`shmget(2)`. 1794 1795 **shmhuge** 1796 Same as shm, but use huge pages as backing. 1797 1798 **mmap** 1799 Use :manpage:`mmap(2)` to allocate buffers. May either be anonymous memory, or can 1800 be file backed if a filename is given after the option. The format 1801 is `mem=mmap:/path/to/file`. 1802 1803 **mmaphuge** 1804 Use a memory mapped huge file as the buffer backing. Append filename 1805 after mmaphuge, ala `mem=mmaphuge:/hugetlbfs/file`. 1806 1807 **mmapshared** 1808 Same as mmap, but use a MMAP_SHARED mapping. 1809 1810 **cudamalloc** 1811 Use GPU memory as the buffers for GPUDirect RDMA benchmark. 1812 The :option:`ioengine` must be `rdma`. 1813 1814 The area allocated is a function of the maximum allowed bs size for the job, 1815 multiplied by the I/O depth given. Note that for **shmhuge** and 1816 **mmaphuge** to work, the system must have free huge pages allocated. This 1817 can normally be checked and set by reading/writing 1818 :file:`/proc/sys/vm/nr_hugepages` on a Linux system. Fio assumes a huge page 1819 is 4MiB in size. So to calculate the number of huge pages you need for a 1820 given job file, add up the I/O depth of all jobs (normally one unless 1821 :option:`iodepth` is used) and multiply by the maximum bs set. Then divide 1822 that number by the huge page size. You can see the size of the huge pages in 1823 :file:`/proc/meminfo`. If no huge pages are allocated by having a non-zero 1824 number in `nr_hugepages`, using **mmaphuge** or **shmhuge** will fail. Also 1825 see :option:`hugepage-size`. 1826 1827 **mmaphuge** also needs to have hugetlbfs mounted and the file location 1828 should point there. So if it's mounted in :file:`/huge`, you would use 1829 `mem=mmaphuge:/huge/somefile`. 1830 1831.. option:: iomem_align=int, mem_align=int 1832 1833 This indicates the memory alignment of the I/O memory buffers. Note that 1834 the given alignment is applied to the first I/O unit buffer, if using 1835 :option:`iodepth` the alignment of the following buffers are given by the 1836 :option:`bs` used. In other words, if using a :option:`bs` that is a 1837 multiple of the page sized in the system, all buffers will be aligned to 1838 this value. If using a :option:`bs` that is not page aligned, the alignment 1839 of subsequent I/O memory buffers is the sum of the :option:`iomem_align` and 1840 :option:`bs` used. 1841 1842.. option:: hugepage-size=int 1843 1844 Defines the size of a huge page. Must at least be equal to the system 1845 setting, see :file:`/proc/meminfo`. Defaults to 4MiB. Should probably 1846 always be a multiple of megabytes, so using ``hugepage-size=Xm`` is the 1847 preferred way to set this to avoid setting a non-pow-2 bad value. 1848 1849.. option:: lockmem=int 1850 1851 Pin the specified amount of memory with :manpage:`mlock(2)`. Can be used to 1852 simulate a smaller amount of memory. The amount specified is per worker. 1853 1854 1855I/O size 1856~~~~~~~~ 1857 1858.. option:: size=int 1859 1860 The total size of file I/O for each thread of this job. Fio will run until 1861 this many bytes has been transferred, unless runtime is limited by other options 1862 (such as :option:`runtime`, for instance, or increased/decreased by :option:`io_size`). 1863 Fio will divide this size between the available files determined by options 1864 such as :option:`nrfiles`, :option:`filename`, unless :option:`filesize` is 1865 specified by the job. If the result of division happens to be 0, the size is 1866 set to the physical size of the given files or devices if they exist. 1867 If this option is not specified, fio will use the full size of the given 1868 files or devices. If the files do not exist, size must be given. It is also 1869 possible to give size as a percentage between 1 and 100. If ``size=20%`` is 1870 given, fio will use 20% of the full size of the given files or devices. 1871 In ZBD mode, value can also be set as number of zones using 'z'. 1872 Can be combined with :option:`offset` to constrain the start and end range 1873 that I/O will be done within. 1874 1875.. option:: io_size=int, io_limit=int 1876 1877 Normally fio operates within the region set by :option:`size`, which means 1878 that the :option:`size` option sets both the region and size of I/O to be 1879 performed. Sometimes that is not what you want. With this option, it is 1880 possible to define just the amount of I/O that fio should do. For instance, 1881 if :option:`size` is set to 20GiB and :option:`io_size` is set to 5GiB, fio 1882 will perform I/O within the first 20GiB but exit when 5GiB have been 1883 done. The opposite is also possible -- if :option:`size` is set to 20GiB, 1884 and :option:`io_size` is set to 40GiB, then fio will do 40GiB of I/O within 1885 the 0..20GiB region. 1886 1887.. option:: filesize=irange(int) 1888 1889 Individual file sizes. May be a range, in which case fio will select sizes 1890 for files at random within the given range and limited to :option:`size` in 1891 total (if that is given). If not given, each created file is the same size. 1892 This option overrides :option:`size` in terms of file size, which means 1893 this value is used as a fixed size or possible range of each file. 1894 1895.. option:: file_append=bool 1896 1897 Perform I/O after the end of the file. Normally fio will operate within the 1898 size of a file. If this option is set, then fio will append to the file 1899 instead. This has identical behavior to setting :option:`offset` to the size 1900 of a file. This option is ignored on non-regular files. 1901 1902.. option:: fill_device=bool, fill_fs=bool 1903 1904 Sets size to something really large and waits for ENOSPC (no space left on 1905 device) or EDQUOT (disk quota exceeded) 1906 as the terminating condition. Only makes sense with sequential 1907 write. For a read workload, the mount point will be filled first then I/O 1908 started on the result. This option doesn't make sense if operating on a raw 1909 device node, since the size of that is already known by the file system. 1910 Additionally, writing beyond end-of-device will not return ENOSPC there. 1911 1912 1913I/O engine 1914~~~~~~~~~~ 1915 1916.. option:: ioengine=str 1917 1918 Defines how the job issues I/O to the file. The following types are defined: 1919 1920 **sync** 1921 Basic :manpage:`read(2)` or :manpage:`write(2)` 1922 I/O. :manpage:`lseek(2)` is used to position the I/O location. 1923 See :option:`fsync` and :option:`fdatasync` for syncing write I/Os. 1924 1925 **psync** 1926 Basic :manpage:`pread(2)` or :manpage:`pwrite(2)` I/O. Default on 1927 all supported operating systems except for Windows. 1928 1929 **vsync** 1930 Basic :manpage:`readv(2)` or :manpage:`writev(2)` I/O. Will emulate 1931 queuing by coalescing adjacent I/Os into a single submission. 1932 1933 **pvsync** 1934 Basic :manpage:`preadv(2)` or :manpage:`pwritev(2)` I/O. 1935 1936 **pvsync2** 1937 Basic :manpage:`preadv2(2)` or :manpage:`pwritev2(2)` I/O. 1938 1939 **io_uring** 1940 Fast Linux native asynchronous I/O. Supports async IO 1941 for both direct and buffered IO. 1942 This engine defines engine specific options. 1943 1944 **libaio** 1945 Linux native asynchronous I/O. Note that Linux may only support 1946 queued behavior with non-buffered I/O (set ``direct=1`` or 1947 ``buffered=0``). 1948 This engine defines engine specific options. 1949 1950 **posixaio** 1951 POSIX asynchronous I/O using :manpage:`aio_read(3)` and 1952 :manpage:`aio_write(3)`. 1953 1954 **solarisaio** 1955 Solaris native asynchronous I/O. 1956 1957 **windowsaio** 1958 Windows native asynchronous I/O. Default on Windows. 1959 1960 **mmap** 1961 File is memory mapped with :manpage:`mmap(2)` and data copied 1962 to/from using :manpage:`memcpy(3)`. 1963 1964 **splice** 1965 :manpage:`splice(2)` is used to transfer the data and 1966 :manpage:`vmsplice(2)` to transfer data from user space to the 1967 kernel. 1968 1969 **sg** 1970 SCSI generic sg v3 I/O. May either be synchronous using the SG_IO 1971 ioctl, or if the target is an sg character device we use 1972 :manpage:`read(2)` and :manpage:`write(2)` for asynchronous 1973 I/O. Requires :option:`filename` option to specify either block or 1974 character devices. This engine supports trim operations. 1975 The sg engine includes engine specific options. 1976 1977 **libzbc** 1978 Read, write, trim and ZBC/ZAC operations to a zoned 1979 block device using libzbc library. The target can be 1980 either an SG character device or a block device file. 1981 1982 **null** 1983 Doesn't transfer any data, just pretends to. This is mainly used to 1984 exercise fio itself and for debugging/testing purposes. 1985 1986 **net** 1987 Transfer over the network to given ``host:port``. Depending on the 1988 :option:`protocol` used, the :option:`hostname`, :option:`port`, 1989 :option:`listen` and :option:`filename` options are used to specify 1990 what sort of connection to make, while the :option:`protocol` option 1991 determines which protocol will be used. This engine defines engine 1992 specific options. 1993 1994 **netsplice** 1995 Like **net**, but uses :manpage:`splice(2)` and 1996 :manpage:`vmsplice(2)` to map data and send/receive. 1997 This engine defines engine specific options. 1998 1999 **cpuio** 2000 Doesn't transfer any data, but burns CPU cycles according to the 2001 :option:`cpuload`, :option:`cpuchunks` and :option:`cpumode` options. 2002 Setting :option:`cpuload`\=85 will cause that job to do nothing but burn 85% 2003 of the CPU. In case of SMP machines, use :option:`numjobs`\=<nr_of_cpu> 2004 to get desired CPU usage, as the cpuload only loads a 2005 single CPU at the desired rate. A job never finishes unless there is 2006 at least one non-cpuio job. 2007 Setting :option:`cpumode`\=qsort replace the default noop instructions loop 2008 by a qsort algorithm to consume more energy. 2009 2010 **rdma** 2011 The RDMA I/O engine supports both RDMA memory semantics 2012 (RDMA_WRITE/RDMA_READ) and channel semantics (Send/Recv) for the 2013 InfiniBand, RoCE and iWARP protocols. This engine defines engine 2014 specific options. 2015 2016 **falloc** 2017 I/O engine that does regular fallocate to simulate data transfer as 2018 fio ioengine. 2019 2020 DDIR_READ 2021 does fallocate(,mode = FALLOC_FL_KEEP_SIZE,). 2022 2023 DDIR_WRITE 2024 does fallocate(,mode = 0). 2025 2026 DDIR_TRIM 2027 does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE). 2028 2029 **ftruncate** 2030 I/O engine that sends :manpage:`ftruncate(2)` operations in response 2031 to write (DDIR_WRITE) events. Each ftruncate issued sets the file's 2032 size to the current block offset. :option:`blocksize` is ignored. 2033 2034 **e4defrag** 2035 I/O engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate 2036 defragment activity in request to DDIR_WRITE event. 2037 2038 **rados** 2039 I/O engine supporting direct access to Ceph Reliable Autonomic 2040 Distributed Object Store (RADOS) via librados. This ioengine 2041 defines engine specific options. 2042 2043 **rbd** 2044 I/O engine supporting direct access to Ceph Rados Block Devices 2045 (RBD) via librbd without the need to use the kernel rbd driver. This 2046 ioengine defines engine specific options. 2047 2048 **http** 2049 I/O engine supporting GET/PUT requests over HTTP(S) with libcurl to 2050 a WebDAV or S3 endpoint. This ioengine defines engine specific options. 2051 2052 This engine only supports direct IO of iodepth=1; you need to scale this 2053 via numjobs. blocksize defines the size of the objects to be created. 2054 2055 TRIM is translated to object deletion. 2056 2057 **gfapi** 2058 Using GlusterFS libgfapi sync interface to direct access to 2059 GlusterFS volumes without having to go through FUSE. This ioengine 2060 defines engine specific options. 2061 2062 **gfapi_async** 2063 Using GlusterFS libgfapi async interface to direct access to 2064 GlusterFS volumes without having to go through FUSE. This ioengine 2065 defines engine specific options. 2066 2067 **libhdfs** 2068 Read and write through Hadoop (HDFS). The :option:`filename` option 2069 is used to specify host,port of the hdfs name-node to connect. This 2070 engine interprets offsets a little differently. In HDFS, files once 2071 created cannot be modified so random writes are not possible. To 2072 imitate this the libhdfs engine expects a bunch of small files to be 2073 created over HDFS and will randomly pick a file from them 2074 based on the offset generated by fio backend (see the example 2075 job file to create such files, use ``rw=write`` option). Please 2076 note, it may be necessary to set environment variables to work 2077 with HDFS/libhdfs properly. Each job uses its own connection to 2078 HDFS. 2079 2080 **mtd** 2081 Read, write and erase an MTD character device (e.g., 2082 :file:`/dev/mtd0`). Discards are treated as erases. Depending on the 2083 underlying device type, the I/O may have to go in a certain pattern, 2084 e.g., on NAND, writing sequentially to erase blocks and discarding 2085 before overwriting. The `trimwrite` mode works well for this 2086 constraint. 2087 2088 **pmemblk** 2089 Read and write using filesystem DAX to a file on a filesystem 2090 mounted with DAX on a persistent memory device through the PMDK 2091 libpmemblk library. 2092 2093 **dev-dax** 2094 Read and write using device DAX to a persistent memory device (e.g., 2095 /dev/dax0.0) through the PMDK libpmem library. 2096 2097 **external** 2098 Prefix to specify loading an external I/O engine object file. Append 2099 the engine filename, e.g. ``ioengine=external:/tmp/foo.o`` to load 2100 ioengine :file:`foo.o` in :file:`/tmp`. The path can be either 2101 absolute or relative. See :file:`engines/skeleton_external.c` for 2102 details of writing an external I/O engine. 2103 2104 **filecreate** 2105 Simply create the files and do no I/O to them. You still need to 2106 set `filesize` so that all the accounting still occurs, but no 2107 actual I/O will be done other than creating the file. 2108 2109 **filestat** 2110 Simply do stat() and do no I/O to the file. You need to set 'filesize' 2111 and 'nrfiles', so that files will be created. 2112 This engine is to measure file lookup and meta data access. 2113 2114 **filedelete** 2115 Simply delete the files by unlink() and do no I/O to them. You need to set 'filesize' 2116 and 'nrfiles', so that the files will be created. 2117 This engine is to measure file delete. 2118 2119 **libpmem** 2120 Read and write using mmap I/O to a file on a filesystem 2121 mounted with DAX on a persistent memory device through the PMDK 2122 libpmem library. 2123 2124 **ime_psync** 2125 Synchronous read and write using DDN's Infinite Memory Engine (IME). 2126 This engine is very basic and issues calls to IME whenever an IO is 2127 queued. 2128 2129 **ime_psyncv** 2130 Synchronous read and write using DDN's Infinite Memory Engine (IME). 2131 This engine uses iovecs and will try to stack as much IOs as possible 2132 (if the IOs are "contiguous" and the IO depth is not exceeded) 2133 before issuing a call to IME. 2134 2135 **ime_aio** 2136 Asynchronous read and write using DDN's Infinite Memory Engine (IME). 2137 This engine will try to stack as much IOs as possible by creating 2138 requests for IME. FIO will then decide when to commit these requests. 2139 **libiscsi** 2140 Read and write iscsi lun with libiscsi. 2141 **nbd** 2142 Read and write a Network Block Device (NBD). 2143 2144 **libcufile** 2145 I/O engine supporting libcufile synchronous access to nvidia-fs and a 2146 GPUDirect Storage-supported filesystem. This engine performs 2147 I/O without transferring buffers between user-space and the kernel, 2148 unless :option:`verify` is set or :option:`cuda_io` is `posix`. 2149 :option:`iomem` must not be `cudamalloc`. This ioengine defines 2150 engine specific options. 2151 **dfs** 2152 I/O engine supporting asynchronous read and write operations to the 2153 DAOS File System (DFS) via libdfs. 2154 2155 **nfs** 2156 I/O engine supporting asynchronous read and write operations to 2157 NFS filesystems from userspace via libnfs. This is useful for 2158 achieving higher concurrency and thus throughput than is possible 2159 via kernel NFS. 2160 2161 **exec** 2162 Execute 3rd party tools. Could be used to perform monitoring during jobs runtime. 2163 2164I/O engine specific parameters 2165~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2166 2167In addition, there are some parameters which are only valid when a specific 2168:option:`ioengine` is in use. These are used identically to normal parameters, 2169with the caveat that when used on the command line, they must come after the 2170:option:`ioengine` that defines them is selected. 2171 2172.. option:: cmdprio_percentage=int[,int] : [io_uring] [libaio] 2173 2174 Set the percentage of I/O that will be issued with the highest priority. 2175 Default: 0. A single value applies to reads and writes. Comma-separated 2176 values may be specified for reads and writes. For this option to be 2177 effective, NCQ priority must be supported and enabled, and `direct=1' 2178 option must be used. fio must also be run as the root user. Unlike 2179 slat/clat/lat stats, which can be tracked and reported independently, per 2180 priority stats only track and report a single type of latency. By default, 2181 completion latency (clat) will be reported, if :option:`lat_percentiles` is 2182 set, total latency (lat) will be reported. 2183 2184.. option:: cmdprio_class=int[,int] : [io_uring] [libaio] 2185 2186 Set the I/O priority class to use for I/Os that must be issued with 2187 a priority when :option:`cmdprio_percentage` or 2188 :option:`cmdprio_bssplit` is set. If not specified when 2189 :option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set, 2190 this defaults to the highest priority class. A single value applies 2191 to reads and writes. Comma-separated values may be specified for 2192 reads and writes. See :manpage:`ionice(1)`. See also the 2193 :option:`prioclass` option. 2194 2195.. option:: cmdprio=int[,int] : [io_uring] [libaio] 2196 2197 Set the I/O priority value to use for I/Os that must be issued with 2198 a priority when :option:`cmdprio_percentage` or 2199 :option:`cmdprio_bssplit` is set. If not specified when 2200 :option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set, 2201 this defaults to 0. 2202 Linux limits us to a positive value between 0 and 7, with 0 being the 2203 highest. A single value applies to reads and writes. Comma-separated 2204 values may be specified for reads and writes. See :manpage:`ionice(1)`. 2205 Refer to an appropriate manpage for other operating systems since 2206 meaning of priority may differ. See also the :option:`prio` option. 2207 2208.. option:: cmdprio_bssplit=str[,str] : [io_uring] [libaio] 2209 To get a finer control over I/O priority, this option allows 2210 specifying the percentage of IOs that must have a priority set 2211 depending on the block size of the IO. This option is useful only 2212 when used together with the :option:`bssplit` option, that is, 2213 multiple different block sizes are used for reads and writes. 2214 The format for this option is the same as the format of the 2215 :option:`bssplit` option, with the exception that values for 2216 trim IOs are ignored. This option is mutually exclusive with the 2217 :option:`cmdprio_percentage` option. 2218 2219.. option:: fixedbufs : [io_uring] 2220 2221 If fio is asked to do direct IO, then Linux will map pages for each 2222 IO call, and release them when IO is done. If this option is set, the 2223 pages are pre-mapped before IO is started. This eliminates the need to 2224 map and release for each IO. This is more efficient, and reduces the 2225 IO latency as well. 2226 2227.. option:: hipri : [io_uring] 2228 2229 If this option is set, fio will attempt to use polled IO completions. 2230 Normal IO completions generate interrupts to signal the completion of 2231 IO, polled completions do not. Hence they are require active reaping 2232 by the application. The benefits are more efficient IO for high IOPS 2233 scenarios, and lower latencies for low queue depth IO. 2234 2235.. option:: registerfiles : [io_uring] 2236 2237 With this option, fio registers the set of files being used with the 2238 kernel. This avoids the overhead of managing file counts in the kernel, 2239 making the submission and completion part more lightweight. Required 2240 for the below :option:`sqthread_poll` option. 2241 2242.. option:: sqthread_poll : [io_uring] 2243 2244 Normally fio will submit IO by issuing a system call to notify the 2245 kernel of available items in the SQ ring. If this option is set, the 2246 act of submitting IO will be done by a polling thread in the kernel. 2247 This frees up cycles for fio, at the cost of using more CPU in the 2248 system. 2249 2250.. option:: sqthread_poll_cpu : [io_uring] 2251 2252 When :option:`sqthread_poll` is set, this option provides a way to 2253 define which CPU should be used for the polling thread. 2254 2255.. option:: userspace_reap : [libaio] 2256 2257 Normally, with the libaio engine in use, fio will use the 2258 :manpage:`io_getevents(2)` system call to reap newly returned events. With 2259 this flag turned on, the AIO ring will be read directly from user-space to 2260 reap events. The reaping mode is only enabled when polling for a minimum of 2261 0 events (e.g. when :option:`iodepth_batch_complete` `=0`). 2262 2263.. option:: hipri : [pvsync2] 2264 2265 Set RWF_HIPRI on I/O, indicating to the kernel that it's of higher priority 2266 than normal. 2267 2268.. option:: hipri_percentage : [pvsync2] 2269 2270 When hipri is set this determines the probability of a pvsync2 I/O being high 2271 priority. The default is 100%. 2272 2273.. option:: nowait : [pvsync2] [libaio] [io_uring] 2274 2275 By default if a request cannot be executed immediately (e.g. resource starvation, 2276 waiting on locks) it is queued and the initiating process will be blocked until 2277 the required resource becomes free. 2278 2279 This option sets the RWF_NOWAIT flag (supported from the 4.14 Linux kernel) and 2280 the call will return instantly with EAGAIN or a partial result rather than waiting. 2281 2282 It is useful to also use ignore_error=EAGAIN when using this option. 2283 2284 Note: glibc 2.27, 2.28 have a bug in syscall wrappers preadv2, pwritev2. 2285 They return EOPNOTSUP instead of EAGAIN. 2286 2287 For cached I/O, using this option usually means a request operates only with 2288 cached data. Currently the RWF_NOWAIT flag does not supported for cached write. 2289 2290 For direct I/O, requests will only succeed if cache invalidation isn't required, 2291 file blocks are fully allocated and the disk request could be issued immediately. 2292 2293.. option:: cpuload=int : [cpuio] 2294 2295 Attempt to use the specified percentage of CPU cycles. This is a mandatory 2296 option when using cpuio I/O engine. 2297 2298.. option:: cpuchunks=int : [cpuio] 2299 2300 Split the load into cycles of the given time. In microseconds. 2301 2302.. option:: exit_on_io_done=bool : [cpuio] 2303 2304 Detect when I/O threads are done, then exit. 2305 2306.. option:: namenode=str : [libhdfs] 2307 2308 The hostname or IP address of a HDFS cluster namenode to contact. 2309 2310.. option:: port=int 2311 2312 [libhdfs] 2313 2314 The listening port of the HFDS cluster namenode. 2315 2316 [netsplice], [net] 2317 2318 The TCP or UDP port to bind to or connect to. If this is used with 2319 :option:`numjobs` to spawn multiple instances of the same job type, then 2320 this will be the starting port number since fio will use a range of 2321 ports. 2322 2323 [rdma], [librpma_*] 2324 2325 The port to use for RDMA-CM communication. This should be the same value 2326 on the client and the server side. 2327 2328.. option:: hostname=str : [netsplice] [net] [rdma] 2329 2330 The hostname or IP address to use for TCP, UDP or RDMA-CM based I/O. If the job 2331 is a TCP listener or UDP reader, the hostname is not used and must be omitted 2332 unless it is a valid UDP multicast address. 2333 2334.. option:: serverip=str : [librpma_*] 2335 2336 The IP address to be used for RDMA-CM based I/O. 2337 2338.. option:: direct_write_to_pmem=bool : [librpma_*] 2339 2340 Set to 1 only when Direct Write to PMem from the remote host is possible. 2341 Otherwise, set to 0. 2342 2343.. option:: busy_wait_polling=bool : [librpma_*_server] 2344 2345 Set to 0 to wait for completion instead of busy-wait polling completion. 2346 Default: 1. 2347 2348.. option:: interface=str : [netsplice] [net] 2349 2350 The IP address of the network interface used to send or receive UDP 2351 multicast. 2352 2353.. option:: ttl=int : [netsplice] [net] 2354 2355 Time-to-live value for outgoing UDP multicast packets. Default: 1. 2356 2357.. option:: nodelay=bool : [netsplice] [net] 2358 2359 Set TCP_NODELAY on TCP connections. 2360 2361.. option:: protocol=str, proto=str : [netsplice] [net] 2362 2363 The network protocol to use. Accepted values are: 2364 2365 **tcp** 2366 Transmission control protocol. 2367 **tcpv6** 2368 Transmission control protocol V6. 2369 **udp** 2370 User datagram protocol. 2371 **udpv6** 2372 User datagram protocol V6. 2373 **unix** 2374 UNIX domain socket. 2375 2376 When the protocol is TCP or UDP, the port must also be given, as well as the 2377 hostname if the job is a TCP listener or UDP reader. For unix sockets, the 2378 normal :option:`filename` option should be used and the port is invalid. 2379 2380.. option:: listen : [netsplice] [net] 2381 2382 For TCP network connections, tell fio to listen for incoming connections 2383 rather than initiating an outgoing connection. The :option:`hostname` must 2384 be omitted if this option is used. 2385 2386.. option:: pingpong : [netsplice] [net] 2387 2388 Normally a network writer will just continue writing data, and a network 2389 reader will just consume packages. If ``pingpong=1`` is set, a writer will 2390 send its normal payload to the reader, then wait for the reader to send the 2391 same payload back. This allows fio to measure network latencies. The 2392 submission and completion latencies then measure local time spent sending or 2393 receiving, and the completion latency measures how long it took for the 2394 other end to receive and send back. For UDP multicast traffic 2395 ``pingpong=1`` should only be set for a single reader when multiple readers 2396 are listening to the same address. 2397 2398.. option:: window_size : [netsplice] [net] 2399 2400 Set the desired socket buffer size for the connection. 2401 2402.. option:: mss : [netsplice] [net] 2403 2404 Set the TCP maximum segment size (TCP_MAXSEG). 2405 2406.. option:: donorname=str : [e4defrag] 2407 2408 File will be used as a block donor (swap extents between files). 2409 2410.. option:: inplace=int : [e4defrag] 2411 2412 Configure donor file blocks allocation strategy: 2413 2414 **0** 2415 Default. Preallocate donor's file on init. 2416 **1** 2417 Allocate space immediately inside defragment event, and free right 2418 after event. 2419 2420.. option:: clustername=str : [rbd,rados] 2421 2422 Specifies the name of the Ceph cluster. 2423 2424.. option:: rbdname=str : [rbd] 2425 2426 Specifies the name of the RBD. 2427 2428.. option:: pool=str : [rbd,rados] 2429 2430 Specifies the name of the Ceph pool containing RBD or RADOS data. 2431 2432.. option:: clientname=str : [rbd,rados] 2433 2434 Specifies the username (without the 'client.' prefix) used to access the 2435 Ceph cluster. If the *clustername* is specified, the *clientname* shall be 2436 the full *type.id* string. If no type. prefix is given, fio will add 2437 'client.' by default. 2438 2439.. option:: busy_poll=bool : [rbd,rados] 2440 2441 Poll store instead of waiting for completion. Usually this provides better 2442 throughput at cost of higher(up to 100%) CPU utilization. 2443 2444.. option:: touch_objects=bool : [rados] 2445 2446 During initialization, touch (create if do not exist) all objects (files). 2447 Touching all objects affects ceph caches and likely impacts test results. 2448 Enabled by default. 2449 2450.. option:: skip_bad=bool : [mtd] 2451 2452 Skip operations against known bad blocks. 2453 2454.. option:: hdfsdirectory : [libhdfs] 2455 2456 libhdfs will create chunk in this HDFS directory. 2457 2458.. option:: chunk_size : [libhdfs] 2459 2460 The size of the chunk to use for each file. 2461 2462.. option:: verb=str : [rdma] 2463 2464 The RDMA verb to use on this side of the RDMA ioengine connection. Valid 2465 values are write, read, send and recv. These correspond to the equivalent 2466 RDMA verbs (e.g. write = rdma_write etc.). Note that this only needs to be 2467 specified on the client side of the connection. See the examples folder. 2468 2469.. option:: bindname=str : [rdma] 2470 2471 The name to use to bind the local RDMA-CM connection to a local RDMA device. 2472 This could be a hostname or an IPv4 or IPv6 address. On the server side this 2473 will be passed into the rdma_bind_addr() function and on the client site it 2474 will be used in the rdma_resolve_add() function. This can be useful when 2475 multiple paths exist between the client and the server or in certain loopback 2476 configurations. 2477 2478.. option:: stat_type=str : [filestat] 2479 2480 Specify stat system call type to measure lookup/getattr performance. 2481 Default is **stat** for :manpage:`stat(2)`. 2482 2483.. option:: readfua=bool : [sg] 2484 2485 With readfua option set to 1, read operations include 2486 the force unit access (fua) flag. Default is 0. 2487 2488.. option:: writefua=bool : [sg] 2489 2490 With writefua option set to 1, write operations include 2491 the force unit access (fua) flag. Default is 0. 2492 2493.. option:: sg_write_mode=str : [sg] 2494 2495 Specify the type of write commands to issue. This option can take three values: 2496 2497 **write** 2498 This is the default where write opcodes are issued as usual. 2499 **verify** 2500 Issue WRITE AND VERIFY commands. The BYTCHK bit is set to 0. This 2501 directs the device to carry out a medium verification with no data 2502 comparison. The writefua option is ignored with this selection. 2503 **same** 2504 Issue WRITE SAME commands. This transfers a single block to the device 2505 and writes this same block of data to a contiguous sequence of LBAs 2506 beginning at the specified offset. fio's block size parameter specifies 2507 the amount of data written with each command. However, the amount of data 2508 actually transferred to the device is equal to the device's block 2509 (sector) size. For a device with 512 byte sectors, blocksize=8k will 2510 write 16 sectors with each command. fio will still generate 8k of data 2511 for each command but only the first 512 bytes will be used and 2512 transferred to the device. The writefua option is ignored with this 2513 selection. 2514 2515.. option:: hipri : [sg] 2516 2517 If this option is set, fio will attempt to use polled IO completions. 2518 This will have a similar effect as (io_uring)hipri. Only SCSI READ and 2519 WRITE commands will have the SGV4_FLAG_HIPRI set (not UNMAP (trim) nor 2520 VERIFY). Older versions of the Linux sg driver that do not support 2521 hipri will simply ignore this flag and do normal IO. The Linux SCSI 2522 Low Level Driver (LLD) that "owns" the device also needs to support 2523 hipri (also known as iopoll and mq_poll). The MegaRAID driver is an 2524 example of a SCSI LLD. Default: clear (0) which does normal 2525 (interrupted based) IO. 2526 2527.. option:: http_host=str : [http] 2528 2529 Hostname to connect to. For S3, this could be the bucket hostname. 2530 Default is **localhost** 2531 2532.. option:: http_user=str : [http] 2533 2534 Username for HTTP authentication. 2535 2536.. option:: http_pass=str : [http] 2537 2538 Password for HTTP authentication. 2539 2540.. option:: https=str : [http] 2541 2542 Enable HTTPS instead of http. *on* enables HTTPS; *insecure* 2543 will enable HTTPS, but disable SSL peer verification (use with 2544 caution!). Default is **off** 2545 2546.. option:: http_mode=str : [http] 2547 2548 Which HTTP access mode to use: *webdav*, *swift*, or *s3*. 2549 Default is **webdav** 2550 2551.. option:: http_s3_region=str : [http] 2552 2553 The S3 region/zone string. 2554 Default is **us-east-1** 2555 2556.. option:: http_s3_key=str : [http] 2557 2558 The S3 secret key. 2559 2560.. option:: http_s3_keyid=str : [http] 2561 2562 The S3 key/access id. 2563 2564.. option:: http_swift_auth_token=str : [http] 2565 2566 The Swift auth token. See the example configuration file on how 2567 to retrieve this. 2568 2569.. option:: http_verbose=int : [http] 2570 2571 Enable verbose requests from libcurl. Useful for debugging. 1 2572 turns on verbose logging from libcurl, 2 additionally enables 2573 HTTP IO tracing. Default is **0** 2574 2575.. option:: uri=str : [nbd] 2576 2577 Specify the NBD URI of the server to test. The string 2578 is a standard NBD URI 2579 (see https://github.com/NetworkBlockDevice/nbd/tree/master/doc). 2580 Example URIs: nbd://localhost:10809 2581 nbd+unix:///?socket=/tmp/socket 2582 nbds://tlshost/exportname 2583 2584.. option:: gpu_dev_ids=str : [libcufile] 2585 2586 Specify the GPU IDs to use with CUDA. This is a colon-separated list of 2587 int. GPUs are assigned to workers roundrobin. Default is 0. 2588 2589.. option:: cuda_io=str : [libcufile] 2590 2591 Specify the type of I/O to use with CUDA. Default is **cufile**. 2592 2593 **cufile** 2594 Use libcufile and nvidia-fs. This option performs I/O directly 2595 between a GPUDirect Storage filesystem and GPU buffers, 2596 avoiding use of a bounce buffer. If :option:`verify` is set, 2597 cudaMemcpy is used to copy verificaton data between RAM and GPU. 2598 Verification data is copied from RAM to GPU before a write 2599 and from GPU to RAM after a read. :option:`direct` must be 1. 2600 **posix** 2601 Use POSIX to perform I/O with a RAM buffer, and use cudaMemcpy 2602 to transfer data between RAM and the GPUs. Data is copied from 2603 GPU to RAM before a write and copied from RAM to GPU after a 2604 read. :option:`verify` does not affect use of cudaMemcpy. 2605 2606.. option:: pool=str : [dfs] 2607 2608 Specify the label or UUID of the DAOS pool to connect to. 2609 2610.. option:: cont=str : [dfs] 2611 2612 Specify the label or UUID of the DAOS container to open. 2613 2614.. option:: chunk_size=int : [dfs] 2615 2616 Specificy a different chunk size (in bytes) for the dfs file. 2617 Use DAOS container's chunk size by default. 2618 2619.. option:: object_class=str : [dfs] 2620 2621 Specificy a different object class for the dfs file. 2622 Use DAOS container's object class by default. 2623 2624.. option:: nfs_url=str : [nfs] 2625 2626 URL in libnfs format, eg nfs://<server|ipv4|ipv6>/path[?arg=val[&arg=val]*] 2627 Refer to the libnfs README for more details. 2628 2629.. option:: program=str : [exec] 2630 2631 Specify the program to execute. 2632 2633.. option:: arguments=str : [exec] 2634 2635 Specify arguments to pass to program. 2636 Some special variables can be expanded to pass fio's job details to the program. 2637 2638 **%r** 2639 Replaced by the duration of the job in seconds. 2640 **%n** 2641 Replaced by the name of the job. 2642 2643.. option:: grace_time=int : [exec] 2644 2645 Specify the time between the SIGTERM and SIGKILL signals. Default is 1 second. 2646 2647.. option:: std_redirect=bool : [exec] 2648 2649 If set, stdout and stderr streams are redirected to files named from the job name. Default is true. 2650 2651I/O depth 2652~~~~~~~~~ 2653 2654.. option:: iodepth=int 2655 2656 Number of I/O units to keep in flight against the file. Note that 2657 increasing *iodepth* beyond 1 will not affect synchronous ioengines (except 2658 for small degrees when :option:`verify_async` is in use). Even async 2659 engines may impose OS restrictions causing the desired depth not to be 2660 achieved. This may happen on Linux when using libaio and not setting 2661 :option:`direct`\=1, since buffered I/O is not async on that OS. Keep an 2662 eye on the I/O depth distribution in the fio output to verify that the 2663 achieved depth is as expected. Default: 1. 2664 2665.. option:: iodepth_batch_submit=int, iodepth_batch=int 2666 2667 This defines how many pieces of I/O to submit at once. It defaults to 1 2668 which means that we submit each I/O as soon as it is available, but can be 2669 raised to submit bigger batches of I/O at the time. If it is set to 0 the 2670 :option:`iodepth` value will be used. 2671 2672.. option:: iodepth_batch_complete_min=int, iodepth_batch_complete=int 2673 2674 This defines how many pieces of I/O to retrieve at once. It defaults to 1 2675 which means that we'll ask for a minimum of 1 I/O in the retrieval process 2676 from the kernel. The I/O retrieval will go on until we hit the limit set by 2677 :option:`iodepth_low`. If this variable is set to 0, then fio will always 2678 check for completed events before queuing more I/O. This helps reduce I/O 2679 latency, at the cost of more retrieval system calls. 2680 2681.. option:: iodepth_batch_complete_max=int 2682 2683 This defines maximum pieces of I/O to retrieve at once. This variable should 2684 be used along with :option:`iodepth_batch_complete_min`\=int variable, 2685 specifying the range of min and max amount of I/O which should be 2686 retrieved. By default it is equal to the :option:`iodepth_batch_complete_min` 2687 value. 2688 2689 Example #1:: 2690 2691 iodepth_batch_complete_min=1 2692 iodepth_batch_complete_max=<iodepth> 2693 2694 which means that we will retrieve at least 1 I/O and up to the whole 2695 submitted queue depth. If none of I/O has been completed yet, we will wait. 2696 2697 Example #2:: 2698 2699 iodepth_batch_complete_min=0 2700 iodepth_batch_complete_max=<iodepth> 2701 2702 which means that we can retrieve up to the whole submitted queue depth, but 2703 if none of I/O has been completed yet, we will NOT wait and immediately exit 2704 the system call. In this example we simply do polling. 2705 2706.. option:: iodepth_low=int 2707 2708 The low water mark indicating when to start filling the queue 2709 again. Defaults to the same as :option:`iodepth`, meaning that fio will 2710 attempt to keep the queue full at all times. If :option:`iodepth` is set to 2711 e.g. 16 and *iodepth_low* is set to 4, then after fio has filled the queue of 2712 16 requests, it will let the depth drain down to 4 before starting to fill 2713 it again. 2714 2715.. option:: serialize_overlap=bool 2716 2717 Serialize in-flight I/Os that might otherwise cause or suffer from data races. 2718 When two or more I/Os are submitted simultaneously, there is no guarantee that 2719 the I/Os will be processed or completed in the submitted order. Further, if 2720 two or more of those I/Os are writes, any overlapping region between them can 2721 become indeterminate/undefined on certain storage. These issues can cause 2722 verification to fail erratically when at least one of the racing I/Os is 2723 changing data and the overlapping region has a non-zero size. Setting 2724 ``serialize_overlap`` tells fio to avoid provoking this behavior by explicitly 2725 serializing in-flight I/Os that have a non-zero overlap. Note that setting 2726 this option can reduce both performance and the :option:`iodepth` achieved. 2727 2728 This option only applies to I/Os issued for a single job except when it is 2729 enabled along with :option:`io_submit_mode`\=offload. In offload mode, fio 2730 will check for overlap among all I/Os submitted by offload jobs with :option:`serialize_overlap` 2731 enabled. 2732 2733 Default: false. 2734 2735.. option:: io_submit_mode=str 2736 2737 This option controls how fio submits the I/O to the I/O engine. The default 2738 is `inline`, which means that the fio job threads submit and reap I/O 2739 directly. If set to `offload`, the job threads will offload I/O submission 2740 to a dedicated pool of I/O threads. This requires some coordination and thus 2741 has a bit of extra overhead, especially for lower queue depth I/O where it 2742 can increase latencies. The benefit is that fio can manage submission rates 2743 independently of the device completion rates. This avoids skewed latency 2744 reporting if I/O gets backed up on the device side (the coordinated omission 2745 problem). Note that this option cannot reliably be used with async IO 2746 engines. 2747 2748 2749I/O rate 2750~~~~~~~~ 2751 2752.. option:: thinktime=time 2753 2754 Stall the job for the specified period of time after an I/O has completed before issuing the 2755 next. May be used to simulate processing being done by an application. 2756 When the unit is omitted, the value is interpreted in microseconds. See 2757 :option:`thinktime_blocks`, :option:`thinktime_iotime` and :option:`thinktime_spin`. 2758 2759.. option:: thinktime_spin=time 2760 2761 Only valid if :option:`thinktime` is set - pretend to spend CPU time doing 2762 something with the data received, before falling back to sleeping for the 2763 rest of the period specified by :option:`thinktime`. When the unit is 2764 omitted, the value is interpreted in microseconds. 2765 2766.. option:: thinktime_blocks=int 2767 2768 Only valid if :option:`thinktime` is set - control how many blocks to issue, 2769 before waiting :option:`thinktime` usecs. If not set, defaults to 1 which will make 2770 fio wait :option:`thinktime` usecs after every block. This effectively makes any 2771 queue depth setting redundant, since no more than 1 I/O will be queued 2772 before we have to complete it and do our :option:`thinktime`. In other words, this 2773 setting effectively caps the queue depth if the latter is larger. 2774 2775.. option:: thinktime_blocks_type=str 2776 2777 Only valid if :option:`thinktime` is set - control how :option:`thinktime_blocks` 2778 triggers. The default is `complete`, which triggers thinktime when fio completes 2779 :option:`thinktime_blocks` blocks. If this is set to `issue`, then the trigger happens 2780 at the issue side. 2781 2782.. option:: thinktime_iotime=time 2783 2784 Only valid if :option:`thinktime` is set - control :option:`thinktime` 2785 interval by time. The :option:`thinktime` stall is repeated after IOs 2786 are executed for :option:`thinktime_iotime`. For example, 2787 ``--thinktime_iotime=9s --thinktime=1s`` repeat 10-second cycle with IOs 2788 for 9 seconds and stall for 1 second. When the unit is omitted, 2789 :option:`thinktime_iotime` is interpreted as a number of seconds. If 2790 this option is used together with :option:`thinktime_blocks`, the 2791 :option:`thinktime` stall is repeated after :option:`thinktime_iotime` 2792 or after :option:`thinktime_blocks` IOs, whichever happens first. 2793 2794.. option:: rate=int[,int][,int] 2795 2796 Cap the bandwidth used by this job. The number is in bytes/sec, the normal 2797 suffix rules apply. Comma-separated values may be specified for reads, 2798 writes, and trims as described in :option:`blocksize`. 2799 2800 For example, using `rate=1m,500k` would limit reads to 1MiB/sec and writes to 2801 500KiB/sec. Capping only reads or writes can be done with `rate=,500k` or 2802 `rate=500k,` where the former will only limit writes (to 500KiB/sec) and the 2803 latter will only limit reads. 2804 2805.. option:: rate_min=int[,int][,int] 2806 2807 Tell fio to do whatever it can to maintain at least this bandwidth. Failing 2808 to meet this requirement will cause the job to exit. Comma-separated values 2809 may be specified for reads, writes, and trims as described in 2810 :option:`blocksize`. 2811 2812.. option:: rate_iops=int[,int][,int] 2813 2814 Cap the bandwidth to this number of IOPS. Basically the same as 2815 :option:`rate`, just specified independently of bandwidth. If the job is 2816 given a block size range instead of a fixed value, the smallest block size 2817 is used as the metric. Comma-separated values may be specified for reads, 2818 writes, and trims as described in :option:`blocksize`. 2819 2820.. option:: rate_iops_min=int[,int][,int] 2821 2822 If fio doesn't meet this rate of I/O, it will cause the job to exit. 2823 Comma-separated values may be specified for reads, writes, and trims as 2824 described in :option:`blocksize`. 2825 2826.. option:: rate_process=str 2827 2828 This option controls how fio manages rated I/O submissions. The default is 2829 `linear`, which submits I/O in a linear fashion with fixed delays between 2830 I/Os that gets adjusted based on I/O completion rates. If this is set to 2831 `poisson`, fio will submit I/O based on a more real world random request 2832 flow, known as the Poisson process 2833 (https://en.wikipedia.org/wiki/Poisson_point_process). The lambda will be 2834 10^6 / IOPS for the given workload. 2835 2836.. option:: rate_ignore_thinktime=bool 2837 2838 By default, fio will attempt to catch up to the specified rate setting, 2839 if any kind of thinktime setting was used. If this option is set, then 2840 fio will ignore the thinktime and continue doing IO at the specified 2841 rate, instead of entering a catch-up mode after thinktime is done. 2842 2843 2844I/O latency 2845~~~~~~~~~~~ 2846 2847.. option:: latency_target=time 2848 2849 If set, fio will attempt to find the max performance point that the given 2850 workload will run at while maintaining a latency below this target. When 2851 the unit is omitted, the value is interpreted in microseconds. See 2852 :option:`latency_window` and :option:`latency_percentile`. 2853 2854.. option:: latency_window=time 2855 2856 Used with :option:`latency_target` to specify the sample window that the job 2857 is run at varying queue depths to test the performance. When the unit is 2858 omitted, the value is interpreted in microseconds. 2859 2860.. option:: latency_percentile=float 2861 2862 The percentage of I/Os that must fall within the criteria specified by 2863 :option:`latency_target` and :option:`latency_window`. If not set, this 2864 defaults to 100.0, meaning that all I/Os must be equal or below to the value 2865 set by :option:`latency_target`. 2866 2867.. option:: latency_run=bool 2868 2869 Used with :option:`latency_target`. If false (default), fio will find 2870 the highest queue depth that meets :option:`latency_target` and exit. If 2871 true, fio will continue running and try to meet :option:`latency_target` 2872 by adjusting queue depth. 2873 2874.. option:: max_latency=time[,time][,time] 2875 2876 If set, fio will exit the job with an ETIMEDOUT error if it exceeds this 2877 maximum latency. When the unit is omitted, the value is interpreted in 2878 microseconds. Comma-separated values may be specified for reads, writes, 2879 and trims as described in :option:`blocksize`. 2880 2881.. option:: rate_cycle=int 2882 2883 Average bandwidth for :option:`rate` and :option:`rate_min` over this number 2884 of milliseconds. Defaults to 1000. 2885 2886 2887I/O replay 2888~~~~~~~~~~ 2889 2890.. option:: write_iolog=str 2891 2892 Write the issued I/O patterns to the specified file. See 2893 :option:`read_iolog`. Specify a separate file for each job, otherwise the 2894 iologs will be interspersed and the file may be corrupt. 2895 2896.. option:: read_iolog=str 2897 2898 Open an iolog with the specified filename and replay the I/O patterns it 2899 contains. This can be used to store a workload and replay it sometime 2900 later. The iolog given may also be a blktrace binary file, which allows fio 2901 to replay a workload captured by :command:`blktrace`. See 2902 :manpage:`blktrace(8)` for how to capture such logging data. For blktrace 2903 replay, the file needs to be turned into a blkparse binary data file first 2904 (``blkparse <device> -o /dev/null -d file_for_fio.bin``). 2905 You can specify a number of files by separating the names with a ':' 2906 character. See the :option:`filename` option for information on how to 2907 escape ':' characters within the file names. These files will 2908 be sequentially assigned to job clones created by :option:`numjobs`. 2909 '-' is a reserved name, meaning read from stdin, notably if 2910 :option:`filename` is set to '-' which means stdin as well, then 2911 this flag can't be set to '-'. 2912 2913.. option:: read_iolog_chunked=bool 2914 2915 Determines how iolog is read. If false(default) entire :option:`read_iolog` 2916 will be read at once. If selected true, input from iolog will be read 2917 gradually. Useful when iolog is very large, or it is generated. 2918 2919.. option:: merge_blktrace_file=str 2920 2921 When specified, rather than replaying the logs passed to :option:`read_iolog`, 2922 the logs go through a merge phase which aggregates them into a single 2923 blktrace. The resulting file is then passed on as the :option:`read_iolog` 2924 parameter. The intention here is to make the order of events consistent. 2925 This limits the influence of the scheduler compared to replaying multiple 2926 blktraces via concurrent jobs. 2927 2928.. option:: merge_blktrace_scalars=float_list 2929 2930 This is a percentage based option that is index paired with the list of 2931 files passed to :option:`read_iolog`. When merging is performed, scale 2932 the time of each event by the corresponding amount. For example, 2933 ``--merge_blktrace_scalars="50:100"`` runs the first trace in halftime 2934 and the second trace in realtime. This knob is separately tunable from 2935 :option:`replay_time_scale` which scales the trace during runtime and 2936 does not change the output of the merge unlike this option. 2937 2938.. option:: merge_blktrace_iters=float_list 2939 2940 This is a whole number option that is index paired with the list of files 2941 passed to :option:`read_iolog`. When merging is performed, run each trace 2942 for the specified number of iterations. For example, 2943 ``--merge_blktrace_iters="2:1"`` runs the first trace for two iterations 2944 and the second trace for one iteration. 2945 2946.. option:: replay_no_stall=bool 2947 2948 When replaying I/O with :option:`read_iolog` the default behavior is to 2949 attempt to respect the timestamps within the log and replay them with the 2950 appropriate delay between IOPS. By setting this variable fio will not 2951 respect the timestamps and attempt to replay them as fast as possible while 2952 still respecting ordering. The result is the same I/O pattern to a given 2953 device, but different timings. 2954 2955.. option:: replay_time_scale=int 2956 2957 When replaying I/O with :option:`read_iolog`, fio will honor the 2958 original timing in the trace. With this option, it's possible to scale 2959 the time. It's a percentage option, if set to 50 it means run at 50% 2960 the original IO rate in the trace. If set to 200, run at twice the 2961 original IO rate. Defaults to 100. 2962 2963.. option:: replay_redirect=str 2964 2965 While replaying I/O patterns using :option:`read_iolog` the default behavior 2966 is to replay the IOPS onto the major/minor device that each IOP was recorded 2967 from. This is sometimes undesirable because on a different machine those 2968 major/minor numbers can map to a different device. Changing hardware on the 2969 same system can also result in a different major/minor mapping. 2970 ``replay_redirect`` causes all I/Os to be replayed onto the single specified 2971 device regardless of the device it was recorded 2972 from. i.e. :option:`replay_redirect`\= :file:`/dev/sdc` would cause all I/O 2973 in the blktrace or iolog to be replayed onto :file:`/dev/sdc`. This means 2974 multiple devices will be replayed onto a single device, if the trace 2975 contains multiple devices. If you want multiple devices to be replayed 2976 concurrently to multiple redirected devices you must blkparse your trace 2977 into separate traces and replay them with independent fio invocations. 2978 Unfortunately this also breaks the strict time ordering between multiple 2979 device accesses. 2980 2981.. option:: replay_align=int 2982 2983 Force alignment of the byte offsets in a trace to this value. The value 2984 must be a power of 2. 2985 2986.. option:: replay_scale=int 2987 2988 Scale byte offsets down by this factor when replaying traces. Should most 2989 likely use :option:`replay_align` as well. 2990 2991.. option:: replay_skip=str 2992 2993 Sometimes it's useful to skip certain IO types in a replay trace. 2994 This could be, for instance, eliminating the writes in the trace. 2995 Or not replaying the trims/discards, if you are redirecting to 2996 a device that doesn't support them. This option takes a comma 2997 separated list of read, write, trim, sync. 2998 2999 3000Threads, processes and job synchronization 3001~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3002 3003.. option:: thread 3004 3005 Fio defaults to creating jobs by using fork, however if this option is 3006 given, fio will create jobs by using POSIX Threads' function 3007 :manpage:`pthread_create(3)` to create threads instead. 3008 3009.. option:: wait_for=str 3010 3011 If set, the current job won't be started until all workers of the specified 3012 waitee job are done. 3013 3014 ``wait_for`` operates on the job name basis, so there are a few 3015 limitations. First, the waitee must be defined prior to the waiter job 3016 (meaning no forward references). Second, if a job is being referenced as a 3017 waitee, it must have a unique name (no duplicate waitees). 3018 3019.. option:: nice=int 3020 3021 Run the job with the given nice value. See man :manpage:`nice(2)`. 3022 3023 On Windows, values less than -15 set the process class to "High"; -1 through 3024 -15 set "Above Normal"; 1 through 15 "Below Normal"; and above 15 "Idle" 3025 priority class. 3026 3027.. option:: prio=int 3028 3029 Set the I/O priority value of this job. Linux limits us to a positive value 3030 between 0 and 7, with 0 being the highest. See man 3031 :manpage:`ionice(1)`. Refer to an appropriate manpage for other operating 3032 systems since meaning of priority may differ. For per-command priority 3033 setting, see I/O engine specific :option:`cmdprio_percentage` and 3034 :option:`cmdprio` options. 3035 3036.. option:: prioclass=int 3037 3038 Set the I/O priority class. See man :manpage:`ionice(1)`. For per-command 3039 priority setting, see I/O engine specific :option:`cmdprio_percentage` 3040 and :option:`cmdprio_class` options. 3041 3042.. option:: cpus_allowed=str 3043 3044 Controls the same options as :option:`cpumask`, but accepts a textual 3045 specification of the permitted CPUs instead and CPUs are indexed from 0. So 3046 to use CPUs 0 and 5 you would specify ``cpus_allowed=0,5``. This option also 3047 allows a range of CPUs to be specified -- say you wanted a binding to CPUs 3048 0, 5, and 8 to 15, you would set ``cpus_allowed=0,5,8-15``. 3049 3050 On Windows, when ``cpus_allowed`` is unset only CPUs from fio's current 3051 processor group will be used and affinity settings are inherited from the 3052 system. An fio build configured to target Windows 7 makes options that set 3053 CPUs processor group aware and values will set both the processor group 3054 and a CPU from within that group. For example, on a system where processor 3055 group 0 has 40 CPUs and processor group 1 has 32 CPUs, ``cpus_allowed`` 3056 values between 0 and 39 will bind CPUs from processor group 0 and 3057 ``cpus_allowed`` values between 40 and 71 will bind CPUs from processor 3058 group 1. When using ``cpus_allowed_policy=shared`` all CPUs specified by a 3059 single ``cpus_allowed`` option must be from the same processor group. For 3060 Windows fio builds not built for Windows 7, CPUs will only be selected from 3061 (and be relative to) whatever processor group fio happens to be running in 3062 and CPUs from other processor groups cannot be used. 3063 3064.. option:: cpus_allowed_policy=str 3065 3066 Set the policy of how fio distributes the CPUs specified by 3067 :option:`cpus_allowed` or :option:`cpumask`. Two policies are supported: 3068 3069 **shared** 3070 All jobs will share the CPU set specified. 3071 **split** 3072 Each job will get a unique CPU from the CPU set. 3073 3074 **shared** is the default behavior, if the option isn't specified. If 3075 **split** is specified, then fio will assign one cpu per job. If not 3076 enough CPUs are given for the jobs listed, then fio will roundrobin the CPUs 3077 in the set. 3078 3079.. option:: cpumask=int 3080 3081 Set the CPU affinity of this job. The parameter given is a bit mask of 3082 allowed CPUs the job may run on. So if you want the allowed CPUs to be 1 3083 and 5, you would pass the decimal value of (1 << 1 | 1 << 5), or 34. See man 3084 :manpage:`sched_setaffinity(2)`. This may not work on all supported 3085 operating systems or kernel versions. This option doesn't work well for a 3086 higher CPU count than what you can store in an integer mask, so it can only 3087 control cpus 1-32. For boxes with larger CPU counts, use 3088 :option:`cpus_allowed`. 3089 3090.. option:: numa_cpu_nodes=str 3091 3092 Set this job running on specified NUMA nodes' CPUs. The arguments allow 3093 comma delimited list of cpu numbers, A-B ranges, or `all`. Note, to enable 3094 NUMA options support, fio must be built on a system with libnuma-dev(el) 3095 installed. 3096 3097.. option:: numa_mem_policy=str 3098 3099 Set this job's memory policy and corresponding NUMA nodes. Format of the 3100 arguments:: 3101 3102 <mode>[:<nodelist>] 3103 3104 ``mode`` is one of the following memory policies: ``default``, ``prefer``, 3105 ``bind``, ``interleave`` or ``local``. For ``default`` and ``local`` memory 3106 policies, no node needs to be specified. For ``prefer``, only one node is 3107 allowed. For ``bind`` and ``interleave`` the ``nodelist`` may be as 3108 follows: a comma delimited list of numbers, A-B ranges, or `all`. 3109 3110.. option:: cgroup=str 3111 3112 Add job to this control group. If it doesn't exist, it will be created. The 3113 system must have a mounted cgroup blkio mount point for this to work. If 3114 your system doesn't have it mounted, you can do so with:: 3115 3116 # mount -t cgroup -o blkio none /cgroup 3117 3118.. option:: cgroup_weight=int 3119 3120 Set the weight of the cgroup to this value. See the documentation that comes 3121 with the kernel, allowed values are in the range of 100..1000. 3122 3123.. option:: cgroup_nodelete=bool 3124 3125 Normally fio will delete the cgroups it has created after the job 3126 completion. To override this behavior and to leave cgroups around after the 3127 job completion, set ``cgroup_nodelete=1``. This can be useful if one wants 3128 to inspect various cgroup files after job completion. Default: false. 3129 3130.. option:: flow_id=int 3131 3132 The ID of the flow. If not specified, it defaults to being a global 3133 flow. See :option:`flow`. 3134 3135.. option:: flow=int 3136 3137 Weight in token-based flow control. If this value is used, then there is a 3138 'flow counter' which is used to regulate the proportion of activity between 3139 two or more jobs. Fio attempts to keep this flow counter near zero. The 3140 ``flow`` parameter stands for how much should be added or subtracted to the 3141 flow counter on each iteration of the main I/O loop. That is, if one job has 3142 ``flow=8`` and another job has ``flow=-1``, then there will be a roughly 1:8 3143 ratio in how much one runs vs the other. 3144 3145.. option:: flow_sleep=int 3146 3147 The period of time, in microseconds, to wait after the flow counter 3148 has exceeded its proportion before retrying operations. 3149 3150.. option:: stonewall, wait_for_previous 3151 3152 Wait for preceding jobs in the job file to exit, before starting this 3153 one. Can be used to insert serialization points in the job file. A stone 3154 wall also implies starting a new reporting group, see 3155 :option:`group_reporting`. 3156 3157.. option:: exitall 3158 3159 By default, fio will continue running all other jobs when one job finishes. 3160 Sometimes this is not the desired action. Setting ``exitall`` will instead 3161 make fio terminate all jobs in the same group, as soon as one job of that 3162 group finishes. 3163 3164.. option:: exit_what 3165 3166 By default, fio will continue running all other jobs when one job finishes. 3167 Sometimes this is not the desired action. Setting ``exit_all`` will 3168 instead make fio terminate all jobs in the same group. The option 3169 ``exit_what`` allows to control which jobs get terminated when ``exitall`` is 3170 enabled. The default is ``group`` and does not change the behaviour of 3171 ``exitall``. The setting ``all`` terminates all jobs. The setting ``stonewall`` 3172 terminates all currently running jobs across all groups and continues execution 3173 with the next stonewalled group. 3174 3175.. option:: exec_prerun=str 3176 3177 Before running this job, issue the command specified through 3178 :manpage:`system(3)`. Output is redirected in a file called 3179 :file:`jobname.prerun.txt`. 3180 3181.. option:: exec_postrun=str 3182 3183 After the job completes, issue the command specified though 3184 :manpage:`system(3)`. Output is redirected in a file called 3185 :file:`jobname.postrun.txt`. 3186 3187.. option:: uid=int 3188 3189 Instead of running as the invoking user, set the user ID to this value 3190 before the thread/process does any work. 3191 3192.. option:: gid=int 3193 3194 Set group ID, see :option:`uid`. 3195 3196 3197Verification 3198~~~~~~~~~~~~ 3199 3200.. option:: verify_only 3201 3202 Do not perform specified workload, only verify data still matches previous 3203 invocation of this workload. This option allows one to check data multiple 3204 times at a later date without overwriting it. This option makes sense only 3205 for workloads that write data, and does not support workloads with the 3206 :option:`time_based` option set. 3207 3208.. option:: do_verify=bool 3209 3210 Run the verify phase after a write phase. Only valid if :option:`verify` is 3211 set. Default: true. 3212 3213.. option:: verify=str 3214 3215 If writing to a file, fio can verify the file contents after each iteration 3216 of the job. Each verification method also implies verification of special 3217 header, which is written to the beginning of each block. This header also 3218 includes meta information, like offset of the block, block number, timestamp 3219 when block was written, etc. :option:`verify` can be combined with 3220 :option:`verify_pattern` option. The allowed values are: 3221 3222 **md5** 3223 Use an md5 sum of the data area and store it in the header of 3224 each block. 3225 3226 **crc64** 3227 Use an experimental crc64 sum of the data area and store it in the 3228 header of each block. 3229 3230 **crc32c** 3231 Use a crc32c sum of the data area and store it in the header of 3232 each block. This will automatically use hardware acceleration 3233 (e.g. SSE4.2 on an x86 or CRC crypto extensions on ARM64) but will 3234 fall back to software crc32c if none is found. Generally the 3235 fastest checksum fio supports when hardware accelerated. 3236 3237 **crc32c-intel** 3238 Synonym for crc32c. 3239 3240 **crc32** 3241 Use a crc32 sum of the data area and store it in the header of each 3242 block. 3243 3244 **crc16** 3245 Use a crc16 sum of the data area and store it in the header of each 3246 block. 3247 3248 **crc7** 3249 Use a crc7 sum of the data area and store it in the header of each 3250 block. 3251 3252 **xxhash** 3253 Use xxhash as the checksum function. Generally the fastest software 3254 checksum that fio supports. 3255 3256 **sha512** 3257 Use sha512 as the checksum function. 3258 3259 **sha256** 3260 Use sha256 as the checksum function. 3261 3262 **sha1** 3263 Use optimized sha1 as the checksum function. 3264 3265 **sha3-224** 3266 Use optimized sha3-224 as the checksum function. 3267 3268 **sha3-256** 3269 Use optimized sha3-256 as the checksum function. 3270 3271 **sha3-384** 3272 Use optimized sha3-384 as the checksum function. 3273 3274 **sha3-512** 3275 Use optimized sha3-512 as the checksum function. 3276 3277 **meta** 3278 This option is deprecated, since now meta information is included in 3279 generic verification header and meta verification happens by 3280 default. For detailed information see the description of the 3281 :option:`verify` setting. This option is kept because of 3282 compatibility's sake with old configurations. Do not use it. 3283 3284 **pattern** 3285 Verify a strict pattern. Normally fio includes a header with some 3286 basic information and checksumming, but if this option is set, only 3287 the specific pattern set with :option:`verify_pattern` is verified. 3288 3289 **null** 3290 Only pretend to verify. Useful for testing internals with 3291 :option:`ioengine`\=null, not for much else. 3292 3293 This option can be used for repeated burn-in tests of a system to make sure 3294 that the written data is also correctly read back. If the data direction 3295 given is a read or random read, fio will assume that it should verify a 3296 previously written file. If the data direction includes any form of write, 3297 the verify will be of the newly written data. 3298 3299 To avoid false verification errors, do not use the norandommap option when 3300 verifying data with async I/O engines and I/O depths > 1. Or use the 3301 norandommap and the lfsr random generator together to avoid writing to the 3302 same offset with muliple outstanding I/Os. 3303 3304.. option:: verify_offset=int 3305 3306 Swap the verification header with data somewhere else in the block before 3307 writing. It is swapped back before verifying. 3308 3309.. option:: verify_interval=int 3310 3311 Write the verification header at a finer granularity than the 3312 :option:`blocksize`. It will be written for chunks the size of 3313 ``verify_interval``. :option:`blocksize` should divide this evenly. 3314 3315.. option:: verify_pattern=str 3316 3317 If set, fio will fill the I/O buffers with this pattern. Fio defaults to 3318 filling with totally random bytes, but sometimes it's interesting to fill 3319 with a known pattern for I/O verification purposes. Depending on the width 3320 of the pattern, fio will fill 1/2/3/4 bytes of the buffer at the time (it can 3321 be either a decimal or a hex number). The ``verify_pattern`` if larger than 3322 a 32-bit quantity has to be a hex number that starts with either "0x" or 3323 "0X". Use with :option:`verify`. Also, ``verify_pattern`` supports %o 3324 format, which means that for each block offset will be written and then 3325 verified back, e.g.:: 3326 3327 verify_pattern=%o 3328 3329 Or use combination of everything:: 3330 3331 verify_pattern=0xff%o"abcd"-12 3332 3333.. option:: verify_fatal=bool 3334 3335 Normally fio will keep checking the entire contents before quitting on a 3336 block verification failure. If this option is set, fio will exit the job on 3337 the first observed failure. Default: false. 3338 3339.. option:: verify_dump=bool 3340 3341 If set, dump the contents of both the original data block and the data block 3342 we read off disk to files. This allows later analysis to inspect just what 3343 kind of data corruption occurred. Off by default. 3344 3345.. option:: verify_async=int 3346 3347 Fio will normally verify I/O inline from the submitting thread. This option 3348 takes an integer describing how many async offload threads to create for I/O 3349 verification instead, causing fio to offload the duty of verifying I/O 3350 contents to one or more separate threads. If using this offload option, even 3351 sync I/O engines can benefit from using an :option:`iodepth` setting higher 3352 than 1, as it allows them to have I/O in flight while verifies are running. 3353 Defaults to 0 async threads, i.e. verification is not asynchronous. 3354 3355.. option:: verify_async_cpus=str 3356 3357 Tell fio to set the given CPU affinity on the async I/O verification 3358 threads. See :option:`cpus_allowed` for the format used. 3359 3360.. option:: verify_backlog=int 3361 3362 Fio will normally verify the written contents of a job that utilizes verify 3363 once that job has completed. In other words, everything is written then 3364 everything is read back and verified. You may want to verify continually 3365 instead for a variety of reasons. Fio stores the meta data associated with 3366 an I/O block in memory, so for large verify workloads, quite a bit of memory 3367 would be used up holding this meta data. If this option is enabled, fio will 3368 write only N blocks before verifying these blocks. 3369 3370.. option:: verify_backlog_batch=int 3371 3372 Control how many blocks fio will verify if :option:`verify_backlog` is 3373 set. If not set, will default to the value of :option:`verify_backlog` 3374 (meaning the entire queue is read back and verified). If 3375 ``verify_backlog_batch`` is less than :option:`verify_backlog` then not all 3376 blocks will be verified, if ``verify_backlog_batch`` is larger than 3377 :option:`verify_backlog`, some blocks will be verified more than once. 3378 3379.. option:: verify_state_save=bool 3380 3381 When a job exits during the write phase of a verify workload, save its 3382 current state. This allows fio to replay up until that point, if the verify 3383 state is loaded for the verify read phase. The format of the filename is, 3384 roughly:: 3385 3386 <type>-<jobname>-<jobindex>-verify.state. 3387 3388 <type> is "local" for a local run, "sock" for a client/server socket 3389 connection, and "ip" (192.168.0.1, for instance) for a networked 3390 client/server connection. Defaults to true. 3391 3392.. option:: verify_state_load=bool 3393 3394 If a verify termination trigger was used, fio stores the current write state 3395 of each thread. This can be used at verification time so that fio knows how 3396 far it should verify. Without this information, fio will run a full 3397 verification pass, according to the settings in the job file used. Default 3398 false. 3399 3400.. option:: trim_percentage=int 3401 3402 Number of verify blocks to discard/trim. 3403 3404.. option:: trim_verify_zero=bool 3405 3406 Verify that trim/discarded blocks are returned as zeros. 3407 3408.. option:: trim_backlog=int 3409 3410 Trim after this number of blocks are written. 3411 3412.. option:: trim_backlog_batch=int 3413 3414 Trim this number of I/O blocks. 3415 3416.. option:: experimental_verify=bool 3417 3418 Enable experimental verification. 3419 3420Steady state 3421~~~~~~~~~~~~ 3422 3423.. option:: steadystate=str:float, ss=str:float 3424 3425 Define the criterion and limit for assessing steady state performance. The 3426 first parameter designates the criterion whereas the second parameter sets 3427 the threshold. When the criterion falls below the threshold for the 3428 specified duration, the job will stop. For example, `iops_slope:0.1%` will 3429 direct fio to terminate the job when the least squares regression slope 3430 falls below 0.1% of the mean IOPS. If :option:`group_reporting` is enabled 3431 this will apply to all jobs in the group. Below is the list of available 3432 steady state assessment criteria. All assessments are carried out using only 3433 data from the rolling collection window. Threshold limits can be expressed 3434 as a fixed value or as a percentage of the mean in the collection window. 3435 3436 When using this feature, most jobs should include the :option:`time_based` 3437 and :option:`runtime` options or the :option:`loops` option so that fio does not 3438 stop running after it has covered the full size of the specified file(s) or device(s). 3439 3440 **iops** 3441 Collect IOPS data. Stop the job if all individual IOPS measurements 3442 are within the specified limit of the mean IOPS (e.g., ``iops:2`` 3443 means that all individual IOPS values must be within 2 of the mean, 3444 whereas ``iops:0.2%`` means that all individual IOPS values must be 3445 within 0.2% of the mean IOPS to terminate the job). 3446 3447 **iops_slope** 3448 Collect IOPS data and calculate the least squares regression 3449 slope. Stop the job if the slope falls below the specified limit. 3450 3451 **bw** 3452 Collect bandwidth data. Stop the job if all individual bandwidth 3453 measurements are within the specified limit of the mean bandwidth. 3454 3455 **bw_slope** 3456 Collect bandwidth data and calculate the least squares regression 3457 slope. Stop the job if the slope falls below the specified limit. 3458 3459.. option:: steadystate_duration=time, ss_dur=time 3460 3461 A rolling window of this duration will be used to judge whether steady state 3462 has been reached. Data will be collected once per second. The default is 0 3463 which disables steady state detection. When the unit is omitted, the 3464 value is interpreted in seconds. 3465 3466.. option:: steadystate_ramp_time=time, ss_ramp=time 3467 3468 Allow the job to run for the specified duration before beginning data 3469 collection for checking the steady state job termination criterion. The 3470 default is 0. When the unit is omitted, the value is interpreted in seconds. 3471 3472 3473Measurements and reporting 3474~~~~~~~~~~~~~~~~~~~~~~~~~~ 3475 3476.. option:: per_job_logs=bool 3477 3478 If set, this generates bw/clat/iops log with per file private filenames. If 3479 not set, jobs with identical names will share the log filename. Default: 3480 true. 3481 3482.. option:: group_reporting 3483 3484 It may sometimes be interesting to display statistics for groups of jobs as 3485 a whole instead of for each individual job. This is especially true if 3486 :option:`numjobs` is used; looking at individual thread/process output 3487 quickly becomes unwieldy. To see the final report per-group instead of 3488 per-job, use :option:`group_reporting`. Jobs in a file will be part of the 3489 same reporting group, unless if separated by a :option:`stonewall`, or by 3490 using :option:`new_group`. 3491 3492.. option:: new_group 3493 3494 Start a new reporting group. See: :option:`group_reporting`. If not given, 3495 all jobs in a file will be part of the same reporting group, unless 3496 separated by a :option:`stonewall`. 3497 3498.. option:: stats=bool 3499 3500 By default, fio collects and shows final output results for all jobs 3501 that run. If this option is set to 0, then fio will ignore it in 3502 the final stat output. 3503 3504.. option:: write_bw_log=str 3505 3506 If given, write a bandwidth log for this job. Can be used to store data of 3507 the bandwidth of the jobs in their lifetime. 3508 3509 If no str argument is given, the default filename of 3510 :file:`jobname_type.x.log` is used. Even when the argument is given, fio 3511 will still append the type of log. So if one specifies:: 3512 3513 write_bw_log=foo 3514 3515 The actual log name will be :file:`foo_bw.x.log` where `x` is the index 3516 of the job (`1..N`, where `N` is the number of jobs). If 3517 :option:`per_job_logs` is false, then the filename will not include the 3518 `.x` job index. 3519 3520 The included :command:`fio_generate_plots` script uses :command:`gnuplot` to turn these 3521 text files into nice graphs. See `Log File Formats`_ for how data is 3522 structured within the file. 3523 3524.. option:: write_lat_log=str 3525 3526 Same as :option:`write_bw_log`, except this option creates I/O 3527 submission (e.g., :file:`name_slat.x.log`), completion (e.g., 3528 :file:`name_clat.x.log`), and total (e.g., :file:`name_lat.x.log`) 3529 latency files instead. See :option:`write_bw_log` for details about 3530 the filename format and `Log File Formats`_ for how data is structured 3531 within the files. 3532 3533.. option:: write_hist_log=str 3534 3535 Same as :option:`write_bw_log` but writes an I/O completion latency 3536 histogram file (e.g., :file:`name_hist.x.log`) instead. Note that this 3537 file will be empty unless :option:`log_hist_msec` has also been set. 3538 See :option:`write_bw_log` for details about the filename format and 3539 `Log File Formats`_ for how data is structured within the file. 3540 3541.. option:: write_iops_log=str 3542 3543 Same as :option:`write_bw_log`, but writes an IOPS file (e.g. 3544 :file:`name_iops.x.log`) instead. Because fio defaults to individual 3545 I/O logging, the value entry in the IOPS log will be 1 unless windowed 3546 logging (see :option:`log_avg_msec`) has been enabled. See 3547 :option:`write_bw_log` for details about the filename format and `Log 3548 File Formats`_ for how data is structured within the file. 3549 3550.. option:: log_entries=int 3551 3552 By default, fio will log an entry in the iops, latency, or bw log for 3553 every I/O that completes. The initial number of I/O log entries is 1024. 3554 When the log entries are all used, new log entries are dynamically 3555 allocated. This dynamic log entry allocation may negatively impact 3556 time-related statistics such as I/O tail latencies (e.g. 99.9th percentile 3557 completion latency). This option allows specifying a larger initial 3558 number of log entries to avoid run-time allocations of new log entries, 3559 resulting in more precise time-related I/O statistics. 3560 Also see :option:`log_avg_msec`. Defaults to 1024. 3561 3562.. option:: log_avg_msec=int 3563 3564 By default, fio will log an entry in the iops, latency, or bw log for every 3565 I/O that completes. When writing to the disk log, that can quickly grow to a 3566 very large size. Setting this option makes fio average the each log entry 3567 over the specified period of time, reducing the resolution of the log. See 3568 :option:`log_max_value` as well. Defaults to 0, logging all entries. 3569 Also see `Log File Formats`_. 3570 3571.. option:: log_hist_msec=int 3572 3573 Same as :option:`log_avg_msec`, but logs entries for completion latency 3574 histograms. Computing latency percentiles from averages of intervals using 3575 :option:`log_avg_msec` is inaccurate. Setting this option makes fio log 3576 histogram entries over the specified period of time, reducing log sizes for 3577 high IOPS devices while retaining percentile accuracy. See 3578 :option:`log_hist_coarseness` and :option:`write_hist_log` as well. 3579 Defaults to 0, meaning histogram logging is disabled. 3580 3581.. option:: log_hist_coarseness=int 3582 3583 Integer ranging from 0 to 6, defining the coarseness of the resolution of 3584 the histogram logs enabled with :option:`log_hist_msec`. For each increment 3585 in coarseness, fio outputs half as many bins. Defaults to 0, for which 3586 histogram logs contain 1216 latency bins. See :option:`write_hist_log` 3587 and `Log File Formats`_. 3588 3589.. option:: log_max_value=bool 3590 3591 If :option:`log_avg_msec` is set, fio logs the average over that window. If 3592 you instead want to log the maximum value, set this option to 1. Defaults to 3593 0, meaning that averaged values are logged. 3594 3595.. option:: log_offset=bool 3596 3597 If this is set, the iolog options will include the byte offset for the I/O 3598 entry as well as the other data values. Defaults to 0 meaning that 3599 offsets are not present in logs. Also see `Log File Formats`_. 3600 3601.. option:: log_compression=int 3602 3603 If this is set, fio will compress the I/O logs as it goes, to keep the 3604 memory footprint lower. When a log reaches the specified size, that chunk is 3605 removed and compressed in the background. Given that I/O logs are fairly 3606 highly compressible, this yields a nice memory savings for longer runs. The 3607 downside is that the compression will consume some background CPU cycles, so 3608 it may impact the run. This, however, is also true if the logging ends up 3609 consuming most of the system memory. So pick your poison. The I/O logs are 3610 saved normally at the end of a run, by decompressing the chunks and storing 3611 them in the specified log file. This feature depends on the availability of 3612 zlib. 3613 3614.. option:: log_compression_cpus=str 3615 3616 Define the set of CPUs that are allowed to handle online log compression for 3617 the I/O jobs. This can provide better isolation between performance 3618 sensitive jobs, and background compression work. See 3619 :option:`cpus_allowed` for the format used. 3620 3621.. option:: log_store_compressed=bool 3622 3623 If set, fio will store the log files in a compressed format. They can be 3624 decompressed with fio, using the :option:`--inflate-log` command line 3625 parameter. The files will be stored with a :file:`.fz` suffix. 3626 3627.. option:: log_unix_epoch=bool 3628 3629 If set, fio will log Unix timestamps to the log files produced by enabling 3630 write_type_log for each log type, instead of the default zero-based 3631 timestamps. 3632 3633.. option:: block_error_percentiles=bool 3634 3635 If set, record errors in trim block-sized units from writes and trims and 3636 output a histogram of how many trims it took to get to errors, and what kind 3637 of error was encountered. 3638 3639.. option:: bwavgtime=int 3640 3641 Average the calculated bandwidth over the given time. Value is specified in 3642 milliseconds. If the job also does bandwidth logging through 3643 :option:`write_bw_log`, then the minimum of this option and 3644 :option:`log_avg_msec` will be used. Default: 500ms. 3645 3646.. option:: iopsavgtime=int 3647 3648 Average the calculated IOPS over the given time. Value is specified in 3649 milliseconds. If the job also does IOPS logging through 3650 :option:`write_iops_log`, then the minimum of this option and 3651 :option:`log_avg_msec` will be used. Default: 500ms. 3652 3653.. option:: disk_util=bool 3654 3655 Generate disk utilization statistics, if the platform supports it. 3656 Default: true. 3657 3658.. option:: disable_lat=bool 3659 3660 Disable measurements of total latency numbers. Useful only for cutting back 3661 the number of calls to :manpage:`gettimeofday(2)`, as that does impact 3662 performance at really high IOPS rates. Note that to really get rid of a 3663 large amount of these calls, this option must be used with 3664 :option:`disable_slat` and :option:`disable_bw_measurement` as well. 3665 3666.. option:: disable_clat=bool 3667 3668 Disable measurements of completion latency numbers. See 3669 :option:`disable_lat`. 3670 3671.. option:: disable_slat=bool 3672 3673 Disable measurements of submission latency numbers. See 3674 :option:`disable_lat`. 3675 3676.. option:: disable_bw_measurement=bool, disable_bw=bool 3677 3678 Disable measurements of throughput/bandwidth numbers. See 3679 :option:`disable_lat`. 3680 3681.. option:: slat_percentiles=bool 3682 3683 Report submission latency percentiles. Submission latency is not recorded 3684 for synchronous ioengines. 3685 3686.. option:: clat_percentiles=bool 3687 3688 Report completion latency percentiles. 3689 3690.. option:: lat_percentiles=bool 3691 3692 Report total latency percentiles. Total latency is the sum of submission 3693 latency and completion latency. 3694 3695.. option:: percentile_list=float_list 3696 3697 Overwrite the default list of percentiles for latencies and the block error 3698 histogram. Each number is a floating point number in the range (0,100], and 3699 the maximum length of the list is 20. Use ``:`` to separate the numbers. For 3700 example, ``--percentile_list=99.5:99.9`` will cause fio to report the 3701 latency durations below which 99.5% and 99.9% of the observed latencies fell, 3702 respectively. 3703 3704.. option:: significant_figures=int 3705 3706 If using :option:`--output-format` of `normal`, set the significant 3707 figures to this value. Higher values will yield more precise IOPS and 3708 throughput units, while lower values will round. Requires a minimum 3709 value of 1 and a maximum value of 10. Defaults to 4. 3710 3711 3712Error handling 3713~~~~~~~~~~~~~~ 3714 3715.. option:: exitall_on_error 3716 3717 When one job finishes in error, terminate the rest. The default is to wait 3718 for each job to finish. 3719 3720.. option:: continue_on_error=str 3721 3722 Normally fio will exit the job on the first observed failure. If this option 3723 is set, fio will continue the job when there is a 'non-fatal error' (EIO or 3724 EILSEQ) until the runtime is exceeded or the I/O size specified is 3725 completed. If this option is used, there are two more stats that are 3726 appended, the total error count and the first error. The error field given 3727 in the stats is the first error that was hit during the run. 3728 3729 The allowed values are: 3730 3731 **none** 3732 Exit on any I/O or verify errors. 3733 3734 **read** 3735 Continue on read errors, exit on all others. 3736 3737 **write** 3738 Continue on write errors, exit on all others. 3739 3740 **io** 3741 Continue on any I/O error, exit on all others. 3742 3743 **verify** 3744 Continue on verify errors, exit on all others. 3745 3746 **all** 3747 Continue on all errors. 3748 3749 **0** 3750 Backward-compatible alias for 'none'. 3751 3752 **1** 3753 Backward-compatible alias for 'all'. 3754 3755.. option:: ignore_error=str 3756 3757 Sometimes you want to ignore some errors during test in that case you can 3758 specify error list for each error type, instead of only being able to 3759 ignore the default 'non-fatal error' using :option:`continue_on_error`. 3760 ``ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST`` errors for 3761 given error type is separated with ':'. Error may be symbol ('ENOSPC', 3762 'ENOMEM') or integer. Example:: 3763 3764 ignore_error=EAGAIN,ENOSPC:122 3765 3766 This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from 3767 WRITE. This option works by overriding :option:`continue_on_error` with 3768 the list of errors for each error type if any. 3769 3770.. option:: error_dump=bool 3771 3772 If set dump every error even if it is non fatal, true by default. If 3773 disabled only fatal error will be dumped. 3774 3775Running predefined workloads 3776---------------------------- 3777 3778Fio includes predefined profiles that mimic the I/O workloads generated by 3779other tools. 3780 3781.. option:: profile=str 3782 3783 The predefined workload to run. Current profiles are: 3784 3785 **tiobench** 3786 Threaded I/O bench (tiotest/tiobench) like workload. 3787 3788 **act** 3789 Aerospike Certification Tool (ACT) like workload. 3790 3791To view a profile's additional options use :option:`--cmdhelp` after specifying 3792the profile. For example:: 3793 3794 $ fio --profile=act --cmdhelp 3795 3796Act profile options 3797~~~~~~~~~~~~~~~~~~~ 3798 3799.. option:: device-names=str 3800 :noindex: 3801 3802 Devices to use. 3803 3804.. option:: load=int 3805 :noindex: 3806 3807 ACT load multiplier. Default: 1. 3808 3809.. option:: test-duration=time 3810 :noindex: 3811 3812 How long the entire test takes to run. When the unit is omitted, the value 3813 is given in seconds. Default: 24h. 3814 3815.. option:: threads-per-queue=int 3816 :noindex: 3817 3818 Number of read I/O threads per device. Default: 8. 3819 3820.. option:: read-req-num-512-blocks=int 3821 :noindex: 3822 3823 Number of 512B blocks to read at the time. Default: 3. 3824 3825.. option:: large-block-op-kbytes=int 3826 :noindex: 3827 3828 Size of large block ops in KiB (writes). Default: 131072. 3829 3830.. option:: prep 3831 :noindex: 3832 3833 Set to run ACT prep phase. 3834 3835Tiobench profile options 3836~~~~~~~~~~~~~~~~~~~~~~~~ 3837 3838.. option:: size=str 3839 :noindex: 3840 3841 Size in MiB. 3842 3843.. option:: block=int 3844 :noindex: 3845 3846 Block size in bytes. Default: 4096. 3847 3848.. option:: numruns=int 3849 :noindex: 3850 3851 Number of runs. 3852 3853.. option:: dir=str 3854 :noindex: 3855 3856 Test directory. 3857 3858.. option:: threads=int 3859 :noindex: 3860 3861 Number of threads. 3862 3863Interpreting the output 3864----------------------- 3865 3866.. 3867 Example output was based on the following: 3868 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --time_based \ 3869 --rate=1256k --bs=14K --name=quick --runtime=1s --name=mixed \ 3870 --runtime=2m --rw=rw 3871 3872Fio spits out a lot of output. While running, fio will display the status of the 3873jobs created. An example of that would be:: 3874 3875 Jobs: 1 (f=1): [_(1),M(1)][24.8%][r=20.5MiB/s,w=23.5MiB/s][r=82,w=94 IOPS][eta 01m:31s] 3876 3877The characters inside the first set of square brackets denote the current status of 3878each thread. The first character is the first job defined in the job file, and so 3879forth. The possible values (in typical life cycle order) are: 3880 3881+------+-----+-----------------------------------------------------------+ 3882| Idle | Run | | 3883+======+=====+===========================================================+ 3884| P | | Thread setup, but not started. | 3885+------+-----+-----------------------------------------------------------+ 3886| C | | Thread created. | 3887+------+-----+-----------------------------------------------------------+ 3888| I | | Thread initialized, waiting or generating necessary data. | 3889+------+-----+-----------------------------------------------------------+ 3890| | p | Thread running pre-reading file(s). | 3891+------+-----+-----------------------------------------------------------+ 3892| | / | Thread is in ramp period. | 3893+------+-----+-----------------------------------------------------------+ 3894| | R | Running, doing sequential reads. | 3895+------+-----+-----------------------------------------------------------+ 3896| | r | Running, doing random reads. | 3897+------+-----+-----------------------------------------------------------+ 3898| | W | Running, doing sequential writes. | 3899+------+-----+-----------------------------------------------------------+ 3900| | w | Running, doing random writes. | 3901+------+-----+-----------------------------------------------------------+ 3902| | M | Running, doing mixed sequential reads/writes. | 3903+------+-----+-----------------------------------------------------------+ 3904| | m | Running, doing mixed random reads/writes. | 3905+------+-----+-----------------------------------------------------------+ 3906| | D | Running, doing sequential trims. | 3907+------+-----+-----------------------------------------------------------+ 3908| | d | Running, doing random trims. | 3909+------+-----+-----------------------------------------------------------+ 3910| | F | Running, currently waiting for :manpage:`fsync(2)`. | 3911+------+-----+-----------------------------------------------------------+ 3912| | V | Running, doing verification of written data. | 3913+------+-----+-----------------------------------------------------------+ 3914| f | | Thread finishing. | 3915+------+-----+-----------------------------------------------------------+ 3916| E | | Thread exited, not reaped by main thread yet. | 3917+------+-----+-----------------------------------------------------------+ 3918| _ | | Thread reaped. | 3919+------+-----+-----------------------------------------------------------+ 3920| X | | Thread reaped, exited with an error. | 3921+------+-----+-----------------------------------------------------------+ 3922| K | | Thread reaped, exited due to signal. | 3923+------+-----+-----------------------------------------------------------+ 3924 3925.. 3926 Example output was based on the following: 3927 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --runtime=58m \ 3928 --time_based --rate=2512k --bs=256K --numjobs=10 \ 3929 --name=readers --rw=read --name=writers --rw=write 3930 3931Fio will condense the thread string as not to take up more space on the command 3932line than needed. For instance, if you have 10 readers and 10 writers running, 3933the output would look like this:: 3934 3935 Jobs: 20 (f=20): [R(10),W(10)][4.0%][r=20.5MiB/s,w=23.5MiB/s][r=82,w=94 IOPS][eta 57m:36s] 3936 3937Note that the status string is displayed in order, so it's possible to tell which of 3938the jobs are currently doing what. In the example above this means that jobs 1--10 3939are readers and 11--20 are writers. 3940 3941The other values are fairly self explanatory -- number of threads currently 3942running and doing I/O, the number of currently open files (f=), the estimated 3943completion percentage, the rate of I/O since last check (read speed listed first, 3944then write speed and optionally trim speed) in terms of bandwidth and IOPS, 3945and time to completion for the current running group. It's impossible to estimate 3946runtime of the following groups (if any). 3947 3948.. 3949 Example output was based on the following: 3950 TZ=UTC fio --iodepth=16 --ioengine=posixaio --filename=/tmp/fiofile \ 3951 --direct=1 --size=100M --time_based --runtime=50s --rate_iops=89 \ 3952 --bs=7K --name=Client1 --rw=write 3953 3954When fio is done (or interrupted by :kbd:`Ctrl-C`), it will show the data for 3955each thread, group of threads, and disks in that order. For each overall thread (or 3956group) the output looks like:: 3957 3958 Client1: (groupid=0, jobs=1): err= 0: pid=16109: Sat Jun 24 12:07:54 2017 3959 write: IOPS=88, BW=623KiB/s (638kB/s)(30.4MiB/50032msec) 3960 slat (nsec): min=500, max=145500, avg=8318.00, stdev=4781.50 3961 clat (usec): min=170, max=78367, avg=4019.02, stdev=8293.31 3962 lat (usec): min=174, max=78375, avg=4027.34, stdev=8291.79 3963 clat percentiles (usec): 3964 | 1.00th=[ 302], 5.00th=[ 326], 10.00th=[ 343], 20.00th=[ 363], 3965 | 30.00th=[ 392], 40.00th=[ 404], 50.00th=[ 416], 60.00th=[ 445], 3966 | 70.00th=[ 816], 80.00th=[ 6718], 90.00th=[12911], 95.00th=[21627], 3967 | 99.00th=[43779], 99.50th=[51643], 99.90th=[68682], 99.95th=[72877], 3968 | 99.99th=[78119] 3969 bw ( KiB/s): min= 532, max= 686, per=0.10%, avg=622.87, stdev=24.82, samples= 100 3970 iops : min= 76, max= 98, avg=88.98, stdev= 3.54, samples= 100 3971 lat (usec) : 250=0.04%, 500=64.11%, 750=4.81%, 1000=2.79% 3972 lat (msec) : 2=4.16%, 4=1.84%, 10=4.90%, 20=11.33%, 50=5.37% 3973 lat (msec) : 100=0.65% 3974 cpu : usr=0.27%, sys=0.18%, ctx=12072, majf=0, minf=21 3975 IO depths : 1=85.0%, 2=13.1%, 4=1.8%, 8=0.1%, 16=0.0%, 32=0.0%, >=64=0.0% 3976 submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% 3977 complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0% 3978 issued rwt: total=0,4450,0, short=0,0,0, dropped=0,0,0 3979 latency : target=0, window=0, percentile=100.00%, depth=8 3980 3981The job name (or first job's name when using :option:`group_reporting`) is printed, 3982along with the group id, count of jobs being aggregated, last error id seen (which 3983is 0 when there are no errors), pid/tid of that thread and the time the job/group 3984completed. Below are the I/O statistics for each data direction performed (showing 3985writes in the example above). In the order listed, they denote: 3986 3987**read/write/trim** 3988 The string before the colon shows the I/O direction the statistics 3989 are for. **IOPS** is the average I/Os performed per second. **BW** 3990 is the average bandwidth rate shown as: value in power of 2 format 3991 (value in power of 10 format). The last two values show: (**total 3992 I/O performed** in power of 2 format / **runtime** of that thread). 3993 3994**slat** 3995 Submission latency (**min** being the minimum, **max** being the 3996 maximum, **avg** being the average, **stdev** being the standard 3997 deviation). This is the time it took to submit the I/O. For 3998 sync I/O this row is not displayed as the slat is really the 3999 completion latency (since queue/complete is one operation there). 4000 This value can be in nanoseconds, microseconds or milliseconds --- 4001 fio will choose the most appropriate base and print that (in the 4002 example above nanoseconds was the best scale). Note: in :option:`--minimal` mode 4003 latencies are always expressed in microseconds. 4004 4005**clat** 4006 Completion latency. Same names as slat, this denotes the time from 4007 submission to completion of the I/O pieces. For sync I/O, clat will 4008 usually be equal (or very close) to 0, as the time from submit to 4009 complete is basically just CPU time (I/O has already been done, see slat 4010 explanation). 4011 4012**lat** 4013 Total latency. Same names as slat and clat, this denotes the time from 4014 when fio created the I/O unit to completion of the I/O operation. 4015 4016**bw** 4017 Bandwidth statistics based on samples. Same names as the xlat stats, 4018 but also includes the number of samples taken (**samples**) and an 4019 approximate percentage of total aggregate bandwidth this thread 4020 received in its group (**per**). This last value is only really 4021 useful if the threads in this group are on the same disk, since they 4022 are then competing for disk access. 4023 4024**iops** 4025 IOPS statistics based on samples. Same names as bw. 4026 4027**lat (nsec/usec/msec)** 4028 The distribution of I/O completion latencies. This is the time from when 4029 I/O leaves fio and when it gets completed. Unlike the separate 4030 read/write/trim sections above, the data here and in the remaining 4031 sections apply to all I/Os for the reporting group. 250=0.04% means that 4032 0.04% of the I/Os completed in under 250us. 500=64.11% means that 64.11% 4033 of the I/Os required 250 to 499us for completion. 4034 4035**cpu** 4036 CPU usage. User and system time, along with the number of context 4037 switches this thread went through, usage of system and user time, and 4038 finally the number of major and minor page faults. The CPU utilization 4039 numbers are averages for the jobs in that reporting group, while the 4040 context and fault counters are summed. 4041 4042**IO depths** 4043 The distribution of I/O depths over the job lifetime. The numbers are 4044 divided into powers of 2 and each entry covers depths from that value 4045 up to those that are lower than the next entry -- e.g., 16= covers 4046 depths from 16 to 31. Note that the range covered by a depth 4047 distribution entry can be different to the range covered by the 4048 equivalent submit/complete distribution entry. 4049 4050**IO submit** 4051 How many pieces of I/O were submitting in a single submit call. Each 4052 entry denotes that amount and below, until the previous entry -- e.g., 4053 16=100% means that we submitted anywhere between 9 to 16 I/Os per submit 4054 call. Note that the range covered by a submit distribution entry can 4055 be different to the range covered by the equivalent depth distribution 4056 entry. 4057 4058**IO complete** 4059 Like the above submit number, but for completions instead. 4060 4061**IO issued rwt** 4062 The number of read/write/trim requests issued, and how many of them were 4063 short or dropped. 4064 4065**IO latency** 4066 These values are for :option:`latency_target` and related options. When 4067 these options are engaged, this section describes the I/O depth required 4068 to meet the specified latency target. 4069 4070.. 4071 Example output was based on the following: 4072 TZ=UTC fio --ioengine=null --iodepth=2 --size=100M --numjobs=2 \ 4073 --rate_process=poisson --io_limit=32M --name=read --bs=128k \ 4074 --rate=11M --name=write --rw=write --bs=2k --rate=700k 4075 4076After each client has been listed, the group statistics are printed. They 4077will look like this:: 4078 4079 Run status group 0 (all jobs): 4080 READ: bw=20.9MiB/s (21.9MB/s), 10.4MiB/s-10.8MiB/s (10.9MB/s-11.3MB/s), io=64.0MiB (67.1MB), run=2973-3069msec 4081 WRITE: bw=1231KiB/s (1261kB/s), 616KiB/s-621KiB/s (630kB/s-636kB/s), io=64.0MiB (67.1MB), run=52747-53223msec 4082 4083For each data direction it prints: 4084 4085**bw** 4086 Aggregate bandwidth of threads in this group followed by the 4087 minimum and maximum bandwidth of all the threads in this group. 4088 Values outside of brackets are power-of-2 format and those 4089 within are the equivalent value in a power-of-10 format. 4090**io** 4091 Aggregate I/O performed of all threads in this group. The 4092 format is the same as bw. 4093**run** 4094 The smallest and longest runtimes of the threads in this group. 4095 4096And finally, the disk statistics are printed. This is Linux specific. They will look like this:: 4097 4098 Disk stats (read/write): 4099 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00% 4100 4101Each value is printed for both reads and writes, with reads first. The 4102numbers denote: 4103 4104**ios** 4105 Number of I/Os performed by all groups. 4106**merge** 4107 Number of merges performed by the I/O scheduler. 4108**ticks** 4109 Number of ticks we kept the disk busy. 4110**in_queue** 4111 Total time spent in the disk queue. 4112**util** 4113 The disk utilization. A value of 100% means we kept the disk 4114 busy constantly, 50% would be a disk idling half of the time. 4115 4116It is also possible to get fio to dump the current output while it is running, 4117without terminating the job. To do that, send fio the **USR1** signal. You can 4118also get regularly timed dumps by using the :option:`--status-interval` 4119parameter, or by creating a file in :file:`/tmp` named 4120:file:`fio-dump-status`. If fio sees this file, it will unlink it and dump the 4121current output status. 4122 4123 4124Terse output 4125------------ 4126 4127For scripted usage where you typically want to generate tables or graphs of the 4128results, fio can output the results in a semicolon separated format. The format 4129is one long line of values, such as:: 4130 4131 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% 4132 A description of this job goes here. 4133 4134The job description (if provided) follows on a second line for terse v2. 4135It appears on the same line for other terse versions. 4136 4137To enable terse output, use the :option:`--minimal` or 4138:option:`--output-format`\=terse command line options. The 4139first value is the version of the terse output format. If the output has to be 4140changed for some reason, this number will be incremented by 1 to signify that 4141change. 4142 4143Split up, the format is as follows (comments in brackets denote when a 4144field was introduced or whether it's specific to some terse version): 4145 4146 :: 4147 4148 terse version, fio version [v3], jobname, groupid, error 4149 4150 READ status:: 4151 4152 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec) 4153 Submission latency: min, max, mean, stdev (usec) 4154 Completion latency: min, max, mean, stdev (usec) 4155 Completion latency percentiles: 20 fields (see below) 4156 Total latency: min, max, mean, stdev (usec) 4157 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5] 4158 IOPS [v5]: min, max, mean, stdev, number of samples 4159 4160 WRITE status: 4161 4162 :: 4163 4164 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec) 4165 Submission latency: min, max, mean, stdev (usec) 4166 Completion latency: min, max, mean, stdev (usec) 4167 Completion latency percentiles: 20 fields (see below) 4168 Total latency: min, max, mean, stdev (usec) 4169 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5] 4170 IOPS [v5]: min, max, mean, stdev, number of samples 4171 4172 TRIM status [all but version 3]: 4173 4174 Fields are similar to READ/WRITE status. 4175 4176 CPU usage:: 4177 4178 user, system, context switches, major faults, minor faults 4179 4180 I/O depths:: 4181 4182 <=1, 2, 4, 8, 16, 32, >=64 4183 4184 I/O latencies microseconds:: 4185 4186 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000 4187 4188 I/O latencies milliseconds:: 4189 4190 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000 4191 4192 Disk utilization [v3]:: 4193 4194 disk name, read ios, write ios, read merges, write merges, read ticks, write ticks, 4195 time spent in queue, disk utilization percentage 4196 4197 Additional Info (dependent on continue_on_error, default off):: 4198 4199 total # errors, first error code 4200 4201 Additional Info (dependent on description being set):: 4202 4203 Text description 4204 4205Completion latency percentiles can be a grouping of up to 20 sets, so for the 4206terse output fio writes all of them. Each field will look like this:: 4207 4208 1.00%=6112 4209 4210which is the Xth percentile, and the `usec` latency associated with it. 4211 4212For `Disk utilization`, all disks used by fio are shown. So for each disk there 4213will be a disk utilization section. 4214 4215Below is a single line containing short names for each of the fields in the 4216minimal output v3, separated by semicolons:: 4217 4218 terse_version_3;fio_version;jobname;groupid;error;read_kb;read_bandwidth_kb;read_iops;read_runtime_ms;read_slat_min_us;read_slat_max_us;read_slat_mean_us;read_slat_dev_us;read_clat_min_us;read_clat_max_us;read_clat_mean_us;read_clat_dev_us;read_clat_pct01;read_clat_pct02;read_clat_pct03;read_clat_pct04;read_clat_pct05;read_clat_pct06;read_clat_pct07;read_clat_pct08;read_clat_pct09;read_clat_pct10;read_clat_pct11;read_clat_pct12;read_clat_pct13;read_clat_pct14;read_clat_pct15;read_clat_pct16;read_clat_pct17;read_clat_pct18;read_clat_pct19;read_clat_pct20;read_tlat_min_us;read_lat_max_us;read_lat_mean_us;read_lat_dev_us;read_bw_min_kb;read_bw_max_kb;read_bw_agg_pct;read_bw_mean_kb;read_bw_dev_kb;write_kb;write_bandwidth_kb;write_iops;write_runtime_ms;write_slat_min_us;write_slat_max_us;write_slat_mean_us;write_slat_dev_us;write_clat_min_us;write_clat_max_us;write_clat_mean_us;write_clat_dev_us;write_clat_pct01;write_clat_pct02;write_clat_pct03;write_clat_pct04;write_clat_pct05;write_clat_pct06;write_clat_pct07;write_clat_pct08;write_clat_pct09;write_clat_pct10;write_clat_pct11;write_clat_pct12;write_clat_pct13;write_clat_pct14;write_clat_pct15;write_clat_pct16;write_clat_pct17;write_clat_pct18;write_clat_pct19;write_clat_pct20;write_tlat_min_us;write_lat_max_us;write_lat_mean_us;write_lat_dev_us;write_bw_min_kb;write_bw_max_kb;write_bw_agg_pct;write_bw_mean_kb;write_bw_dev_kb;cpu_user;cpu_sys;cpu_csw;cpu_mjf;cpu_minf;iodepth_1;iodepth_2;iodepth_4;iodepth_8;iodepth_16;iodepth_32;iodepth_64;lat_2us;lat_4us;lat_10us;lat_20us;lat_50us;lat_100us;lat_250us;lat_500us;lat_750us;lat_1000us;lat_2ms;lat_4ms;lat_10ms;lat_20ms;lat_50ms;lat_100ms;lat_250ms;lat_500ms;lat_750ms;lat_1000ms;lat_2000ms;lat_over_2000ms;disk_name;disk_read_iops;disk_write_iops;disk_read_merges;disk_write_merges;disk_read_ticks;write_ticks;disk_queue_time;disk_util 4219 4220In client/server mode terse output differs from what appears when jobs are run 4221locally. Disk utilization data is omitted from the standard terse output and 4222for v3 and later appears on its own separate line at the end of each terse 4223reporting cycle. 4224 4225 4226JSON output 4227------------ 4228 4229The `json` output format is intended to be both human readable and convenient 4230for automated parsing. For the most part its sections mirror those of the 4231`normal` output. The `runtime` value is reported in msec and the `bw` value is 4232reported in 1024 bytes per second units. 4233 4234 4235JSON+ output 4236------------ 4237 4238The `json+` output format is identical to the `json` output format except that it 4239adds a full dump of the completion latency bins. Each `bins` object contains a 4240set of (key, value) pairs where keys are latency durations and values count how 4241many I/Os had completion latencies of the corresponding duration. For example, 4242consider: 4243 4244 "bins" : { "87552" : 1, "89600" : 1, "94720" : 1, "96768" : 1, "97792" : 1, "99840" : 1, "100864" : 2, "103936" : 6, "104960" : 534, "105984" : 5995, "107008" : 7529, ... } 4245 4246This data indicates that one I/O required 87,552ns to complete, two I/Os required 4247100,864ns to complete, and 7529 I/Os required 107,008ns to complete. 4248 4249Also included with fio is a Python script `fio_jsonplus_clat2csv` that takes 4250json+ output and generates CSV-formatted latency data suitable for plotting. 4251 4252The latency durations actually represent the midpoints of latency intervals. 4253For details refer to :file:`stat.h`. 4254 4255 4256Trace file format 4257----------------- 4258 4259There are two trace file format that you can encounter. The older (v1) format is 4260unsupported since version 1.20-rc3 (March 2008). It will still be described 4261below in case that you get an old trace and want to understand it. 4262 4263In any case the trace is a simple text file with a single action per line. 4264 4265 4266Trace file format v1 4267~~~~~~~~~~~~~~~~~~~~ 4268 4269Each line represents a single I/O action in the following format:: 4270 4271 rw, offset, length 4272 4273where `rw=0/1` for read/write, and the `offset` and `length` entries being in bytes. 4274 4275This format is not supported in fio versions >= 1.20-rc3. 4276 4277 4278Trace file format v2 4279~~~~~~~~~~~~~~~~~~~~ 4280 4281The second version of the trace file format was added in fio version 1.17. It 4282allows to access more then one file per trace and has a bigger set of possible 4283file actions. 4284 4285The first line of the trace file has to be:: 4286 4287 fio version 2 iolog 4288 4289Following this can be lines in two different formats, which are described below. 4290 4291The file management format:: 4292 4293 filename action 4294 4295The `filename` is given as an absolute path. The `action` can be one of these: 4296 4297**add** 4298 Add the given `filename` to the trace. 4299**open** 4300 Open the file with the given `filename`. The `filename` has to have 4301 been added with the **add** action before. 4302**close** 4303 Close the file with the given `filename`. The file has to have been 4304 opened before. 4305 4306 4307The file I/O action format:: 4308 4309 filename action offset length 4310 4311The `filename` is given as an absolute path, and has to have been added and 4312opened before it can be used with this format. The `offset` and `length` are 4313given in bytes. The `action` can be one of these: 4314 4315**wait** 4316 Wait for `offset` microseconds. Everything below 100 is discarded. 4317 The time is relative to the previous `wait` statement. 4318**read** 4319 Read `length` bytes beginning from `offset`. 4320**write** 4321 Write `length` bytes beginning from `offset`. 4322**sync** 4323 :manpage:`fsync(2)` the file. 4324**datasync** 4325 :manpage:`fdatasync(2)` the file. 4326**trim** 4327 Trim the given file from the given `offset` for `length` bytes. 4328 4329 4330I/O Replay - Merging Traces 4331--------------------------- 4332 4333Colocation is a common practice used to get the most out of a machine. 4334Knowing which workloads play nicely with each other and which ones don't is 4335a much harder task. While fio can replay workloads concurrently via multiple 4336jobs, it leaves some variability up to the scheduler making results harder to 4337reproduce. Merging is a way to make the order of events consistent. 4338 4339Merging is integrated into I/O replay and done when a 4340:option:`merge_blktrace_file` is specified. The list of files passed to 4341:option:`read_iolog` go through the merge process and output a single file 4342stored to the specified file. The output file is passed on as if it were the 4343only file passed to :option:`read_iolog`. An example would look like:: 4344 4345 $ fio --read_iolog="<file1>:<file2>" --merge_blktrace_file="<output_file>" 4346 4347Creating only the merged file can be done by passing the command line argument 4348:option:`--merge-blktrace-only`. 4349 4350Scaling traces can be done to see the relative impact of any particular trace 4351being slowed down or sped up. :option:`merge_blktrace_scalars` takes in a colon 4352separated list of percentage scalars. It is index paired with the files passed 4353to :option:`read_iolog`. 4354 4355With scaling, it may be desirable to match the running time of all traces. 4356This can be done with :option:`merge_blktrace_iters`. It is index paired with 4357:option:`read_iolog` just like :option:`merge_blktrace_scalars`. 4358 4359In an example, given two traces, A and B, each 60s long. If we want to see 4360the impact of trace A issuing IOs twice as fast and repeat trace A over the 4361runtime of trace B, the following can be done:: 4362 4363 $ fio --read_iolog="<trace_a>:"<trace_b>" --merge_blktrace_file"<output_file>" --merge_blktrace_scalars="50:100" --merge_blktrace_iters="2:1" 4364 4365This runs trace A at 2x the speed twice for approximately the same runtime as 4366a single run of trace B. 4367 4368 4369CPU idleness profiling 4370---------------------- 4371 4372In some cases, we want to understand CPU overhead in a test. For example, we 4373test patches for the specific goodness of whether they reduce CPU usage. 4374Fio implements a balloon approach to create a thread per CPU that runs at idle 4375priority, meaning that it only runs when nobody else needs the cpu. 4376By measuring the amount of work completed by the thread, idleness of each CPU 4377can be derived accordingly. 4378 4379An unit work is defined as touching a full page of unsigned characters. Mean and 4380standard deviation of time to complete an unit work is reported in "unit work" 4381section. Options can be chosen to report detailed percpu idleness or overall 4382system idleness by aggregating percpu stats. 4383 4384 4385Verification and triggers 4386------------------------- 4387 4388Fio is usually run in one of two ways, when data verification is done. The first 4389is a normal write job of some sort with verify enabled. When the write phase has 4390completed, fio switches to reads and verifies everything it wrote. The second 4391model is running just the write phase, and then later on running the same job 4392(but with reads instead of writes) to repeat the same I/O patterns and verify 4393the contents. Both of these methods depend on the write phase being completed, 4394as fio otherwise has no idea how much data was written. 4395 4396With verification triggers, fio supports dumping the current write state to 4397local files. Then a subsequent read verify workload can load this state and know 4398exactly where to stop. This is useful for testing cases where power is cut to a 4399server in a managed fashion, for instance. 4400 4401A verification trigger consists of two things: 4402 44031) Storing the write state of each job. 44042) Executing a trigger command. 4405 4406The write state is relatively small, on the order of hundreds of bytes to single 4407kilobytes. It contains information on the number of completions done, the last X 4408completions, etc. 4409 4410A trigger is invoked either through creation ('touch') of a specified file in 4411the system, or through a timeout setting. If fio is run with 4412:option:`--trigger-file`\= :file:`/tmp/trigger-file`, then it will continually 4413check for the existence of :file:`/tmp/trigger-file`. When it sees this file, it 4414will fire off the trigger (thus saving state, and executing the trigger 4415command). 4416 4417For client/server runs, there's both a local and remote trigger. If fio is 4418running as a server backend, it will send the job states back to the client for 4419safe storage, then execute the remote trigger, if specified. If a local trigger 4420is specified, the server will still send back the write state, but the client 4421will then execute the trigger. 4422 4423Verification trigger example 4424~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4425 4426Let's say we want to run a powercut test on the remote Linux machine 'server'. 4427Our write workload is in :file:`write-test.fio`. We want to cut power to 'server' at 4428some point during the run, and we'll run this test from the safety or our local 4429machine, 'localbox'. On the server, we'll start the fio backend normally:: 4430 4431 server# fio --server 4432 4433and on the client, we'll fire off the workload:: 4434 4435 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger-remote="bash -c \"echo b > /proc/sysrq-triger\"" 4436 4437We set :file:`/tmp/my-trigger` as the trigger file, and we tell fio to execute:: 4438 4439 echo b > /proc/sysrq-trigger 4440 4441on the server once it has received the trigger and sent us the write state. This 4442will work, but it's not **really** cutting power to the server, it's merely 4443abruptly rebooting it. If we have a remote way of cutting power to the server 4444through IPMI or similar, we could do that through a local trigger command 4445instead. Let's assume we have a script that does IPMI reboot of a given hostname, 4446ipmi-reboot. On localbox, we could then have run fio with a local trigger 4447instead:: 4448 4449 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger="ipmi-reboot server" 4450 4451For this case, fio would wait for the server to send us the write state, then 4452execute ``ipmi-reboot server`` when that happened. 4453 4454Loading verify state 4455~~~~~~~~~~~~~~~~~~~~ 4456 4457To load stored write state, a read verification job file must contain the 4458:option:`verify_state_load` option. If that is set, fio will load the previously 4459stored state. For a local fio run this is done by loading the files directly, 4460and on a client/server run, the server backend will ask the client to send the 4461files over and load them from there. 4462 4463 4464Log File Formats 4465---------------- 4466 4467Fio supports a variety of log file formats, for logging latencies, bandwidth, 4468and IOPS. The logs share a common format, which looks like this: 4469 4470 *time* (`msec`), *value*, *data direction*, *block size* (`bytes`), 4471 *offset* (`bytes`), *command priority* 4472 4473*Time* for the log entry is always in milliseconds. The *value* logged depends 4474on the type of log, it will be one of the following: 4475 4476 **Latency log** 4477 Value is latency in nsecs 4478 **Bandwidth log** 4479 Value is in KiB/sec 4480 **IOPS log** 4481 Value is IOPS 4482 4483*Data direction* is one of the following: 4484 4485 **0** 4486 I/O is a READ 4487 **1** 4488 I/O is a WRITE 4489 **2** 4490 I/O is a TRIM 4491 4492The entry's *block size* is always in bytes. The *offset* is the position in bytes 4493from the start of the file for that particular I/O. The logging of the offset can be 4494toggled with :option:`log_offset`. 4495 4496*Command priority* is 0 for normal priority and 1 for high priority. This is controlled 4497by the ioengine specific :option:`cmdprio_percentage`. 4498 4499Fio defaults to logging every individual I/O but when windowed logging is set 4500through :option:`log_avg_msec`, either the average (by default) or the maximum 4501(:option:`log_max_value` is set) *value* seen over the specified period of time 4502is recorded. Each *data direction* seen within the window period will aggregate 4503its values in a separate row. Further, when using windowed logging the *block 4504size* and *offset* entries will always contain 0. 4505 4506 4507Client/Server 4508------------- 4509 4510Normally fio is invoked as a stand-alone application on the machine where the 4511I/O workload should be generated. However, the backend and frontend of fio can 4512be run separately i.e., the fio server can generate an I/O workload on the "Device 4513Under Test" while being controlled by a client on another machine. 4514 4515Start the server on the machine which has access to the storage DUT:: 4516 4517 $ fio --server=args 4518 4519where `args` defines what fio listens to. The arguments are of the form 4520``type,hostname`` or ``IP,port``. *type* is either ``ip`` (or ip4) for TCP/IP 4521v4, ``ip6`` for TCP/IP v6, or ``sock`` for a local unix domain socket. 4522*hostname* is either a hostname or IP address, and *port* is the port to listen 4523to (only valid for TCP/IP, not a local socket). Some examples: 4524 45251) ``fio --server`` 4526 4527 Start a fio server, listening on all interfaces on the default port (8765). 4528 45292) ``fio --server=ip:hostname,4444`` 4530 4531 Start a fio server, listening on IP belonging to hostname and on port 4444. 4532 45333) ``fio --server=ip6:::1,4444`` 4534 4535 Start a fio server, listening on IPv6 localhost ::1 and on port 4444. 4536 45374) ``fio --server=,4444`` 4538 4539 Start a fio server, listening on all interfaces on port 4444. 4540 45415) ``fio --server=1.2.3.4`` 4542 4543 Start a fio server, listening on IP 1.2.3.4 on the default port. 4544 45456) ``fio --server=sock:/tmp/fio.sock`` 4546 4547 Start a fio server, listening on the local socket :file:`/tmp/fio.sock`. 4548 4549Once a server is running, a "client" can connect to the fio server with:: 4550 4551 fio <local-args> --client=<server> <remote-args> <job file(s)> 4552 4553where `local-args` are arguments for the client where it is running, `server` 4554is the connect string, and `remote-args` and `job file(s)` are sent to the 4555server. The `server` string follows the same format as it does on the server 4556side, to allow IP/hostname/socket and port strings. 4557 4558Fio can connect to multiple servers this way:: 4559 4560 fio --client=<server1> <job file(s)> --client=<server2> <job file(s)> 4561 4562If the job file is located on the fio server, then you can tell the server to 4563load a local file as well. This is done by using :option:`--remote-config` :: 4564 4565 fio --client=server --remote-config /path/to/file.fio 4566 4567Then fio will open this local (to the server) job file instead of being passed 4568one from the client. 4569 4570If you have many servers (example: 100 VMs/containers), you can input a pathname 4571of a file containing host IPs/names as the parameter value for the 4572:option:`--client` option. For example, here is an example :file:`host.list` 4573file containing 2 hostnames:: 4574 4575 host1.your.dns.domain 4576 host2.your.dns.domain 4577 4578The fio command would then be:: 4579 4580 fio --client=host.list <job file(s)> 4581 4582In this mode, you cannot input server-specific parameters or job files -- all 4583servers receive the same job file. 4584 4585In order to let ``fio --client`` runs use a shared filesystem from multiple 4586hosts, ``fio --client`` now prepends the IP address of the server to the 4587filename. For example, if fio is using the directory :file:`/mnt/nfs/fio` and is 4588writing filename :file:`fileio.tmp`, with a :option:`--client` `hostfile` 4589containing two hostnames ``h1`` and ``h2`` with IP addresses 192.168.10.120 and 4590192.168.10.121, then fio will create two files:: 4591 4592 /mnt/nfs/fio/192.168.10.120.fileio.tmp 4593 /mnt/nfs/fio/192.168.10.121.fileio.tmp 4594 4595Terse output in client/server mode will differ slightly from what is produced 4596when fio is run in stand-alone mode. See the terse output section for details. 4597