4 The first step in getting fio to simulate a desired I/O workload, is writing a
5 job file describing that specific setup. A job file may contain any number of
6 threads and/or files -- the typical contents of the job file is a *global*
7 section defining shared parameters, and one or more job sections describing the
8 jobs involved. When run, fio parses this file and sets everything up as
9 described. If we break down a job from top to bottom, it contains the following
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?
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.
26 How much data are we going to be reading/writing.
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
36 If the I/O engine is async, how large a queuing depth do we want to
42 How many files are we spreading the workload over.
44 `Threads, processes and job synchronization`_
46 How many threads or processes should we spread this workload over.
48 The above are the basic parameters defined for a workload, in addition there's a
49 multitude of parameters that modify other aspects of how this job behaves.
55 .. option:: --debug=type
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
63 Dump info related to processes.
65 Dump info related to file actions.
67 Dump info related to I/O queuing.
69 Dump info related to memory allocations.
71 Dump info related to blktrace setup.
73 Dump info related to I/O verification.
75 Enable all debug options.
77 Dump info related to random offset generation.
79 Dump info related to option matching and parsing.
81 Dump info related to disk utilization updates.
83 Dump info only related to job number x.
85 Dump info only related to mutex up/down ops.
87 Dump info related to profile extensions.
89 Dump info related to internal time keeping.
91 Dump info related to networking connections.
93 Dump info related to I/O rate switching.
95 Dump info related to log compress/decompress.
97 Dump info related to steadystate detection.
99 Dump info related to the helper thread.
101 Dump info related to support for zoned block devices.
103 Show available debug options.
105 .. option:: --parse-only
107 Parse options only, don't start any I/O.
109 .. option:: --merge-blktrace-only
111 Merge blktraces only, don't start any I/O.
113 .. option:: --output=filename
115 Write output to file `filename`.
117 .. option:: --output-format=format
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
124 .. option:: --bandwidth-log
126 Generate aggregate bandwidth logs.
128 .. option:: --minimal
130 Print statistics in a terse, semicolon-delimited format.
132 .. option:: --append-terse
134 Print statistics in selected mode AND terse, semicolon-delimited format.
135 **Deprecated**, use :option:`--output-format` instead to select multiple
138 .. option:: --terse-version=version
140 Set terse `version` output format (default 3, or 2 or 4 or 5).
142 .. option:: --version
144 Print version information and exit.
148 Print a summary of the command line options and exit.
150 .. option:: --cpuclock-test
152 Perform test and validation of internal CPU clock.
154 .. option:: --crctest=[test]
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.
160 .. option:: --cmdhelp=command
162 Print help information for `command`. May be ``all`` for all commands.
164 .. option:: --enghelp=[ioengine[,command]]
166 List all commands defined by `ioengine`, or print help for `command`
167 defined by `ioengine`. If no `ioengine` is given, list all
170 .. option:: --showcmd
172 Convert given job files to a set of command-line options.
174 .. option:: --readonly
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.
183 .. option:: --eta=when
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.
190 .. option:: --eta-interval=time
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
197 .. option:: --eta-newline=time
199 Force a new line for every `time` period passed. When the unit is omitted,
200 the value is interpreted in seconds.
202 .. option:: --status-interval=time
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.
212 .. option:: --section=name
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
223 .. option:: --alloc-size=kb
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.
231 NOTE: While running :file:`.fio_smalloc.*` backing store files are visible
234 .. option:: --warnings-fatal
236 All fio parser warnings are fatal, causing fio to exit with an
239 .. option:: --max-jobs=nr
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
246 .. option:: --server=args
248 Start a backend server, with `args` specifying what to listen to.
249 See `Client/Server`_ section.
251 .. option:: --daemonize=pidfile
253 Background a fio server, writing the pid to the given `pidfile` file.
255 .. option:: --client=hostname
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.
260 .. option:: --remote-config=file
262 Tell fio server to load this local `file`.
264 .. option:: --idle-prof=option
266 Report CPU idleness. `option` is one of the following:
269 Run unit work calibration only and exit.
272 Show aggregate system idleness and unit work.
275 As **system** but also show per CPU idleness.
277 .. option:: --inflate-log=log
279 Inflate and output compressed `log`.
281 .. option:: --trigger-file=file
283 Execute trigger command when `file` exists.
285 .. option:: --trigger-timeout=time
287 Execute trigger at this `time`.
289 .. option:: --trigger=command
291 Set this `command` as local trigger.
293 .. option:: --trigger-remote=command
295 Set this `command` as remote trigger.
297 .. option:: --aux-path=path
299 Use the directory specified by `path` for generated state files instead
300 of the current working directory.
302 Any parameters following the options will be assumed to be job files, unless
303 they match a job file parameter. Multiple job files can be listed and each job
304 file will be regarded as a separate group. Fio will :option:`stonewall`
305 execution between each group.
311 As previously described, fio accepts one or more job files describing what it is
312 supposed to do. The job file format is the classic ini file, where the names
313 enclosed in [] brackets define the job name. You are free to use any ASCII name
314 you want, except *global* which has special meaning. Following the job name is
315 a sequence of zero or more parameters, one per line, that define the behavior of
316 the job. If the first character in a line is a ';' or a '#', the entire line is
317 discarded as a comment.
319 A *global* section sets defaults for the jobs described in that file. A job may
320 override 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
324 The :option:`--cmdhelp` option also lists all options. If used with a `command`
325 argument, :option:`--cmdhelp` will detail the given `command`.
327 See the `examples/` directory for inspiration on how to write job files. Note
328 the copyright and license requirements currently apply to `examples/` files.
330 So let's look at a really simple job file that defines two processes, each
331 randomly reading from a 128MiB file:
335 ; -- start job file --
346 As you can see, the job file sections themselves are empty as all the described
347 parameters 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
349 would look as follows::
351 $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2
354 Let's look at an example that has a number of processes writing randomly to
359 ; -- start job file --
370 Here we have no *global* section, as we only have one job defined anyway. We
371 want to use async I/O here, with a depth of 4 for each file. We also increased
372 the buffer size used to 32KiB and define numjobs to 4 to fork 4 identical
373 jobs. The result is 4 processes each randomly writing to their own 64MiB
374 file. Instead of using the above job file, you could have given the parameters
375 on the command line. For this case, you would specify::
377 $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4
379 When fio is utilized as a basis of any reasonably large test suite, it might be
380 desirable to share a set of standardized settings across multiple job files.
381 Instead 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
385 ; -- start job file including.fio --
389 include glob-include.fio
396 include test-include.fio
397 ; -- end job file including.fio --
401 ; -- start job file glob-include.fio --
404 ; -- end job file glob-include.fio --
408 ; -- start job file test-include.fio --
411 ; -- end job file test-include.fio --
413 Settings pulled into a section apply to that section only (except *global*
414 section). Include directives may be nested in that any included file may contain
415 further include directive(s). Include files may not contain [] sections.
418 Environment variables
419 ~~~~~~~~~~~~~~~~~~~~~
421 Fio also supports environment variable expansion in job files. Any sub-string of
422 the form ``${VARNAME}`` as part of an option value (in other words, on the right
423 of 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
425 empty string, the empty string will be substituted.
427 As an example, let's look at a sample fio invocation and job file::
429 $ SIZE=64m NUMJOBS=4 fio jobfile.fio
433 ; -- start job file --
440 This will expand to the following equivalent job file at runtime:
444 ; -- start job file --
451 Fio ships with a few example job files, you can also look there for inspiration.
456 Additionally, fio has a set of reserved keywords that will be replaced
457 internally with the appropriate value. Those keywords are:
461 The architecture page size of the running system.
465 Megabytes of total memory in the system.
469 Number of online available CPUs.
471 These can be used on the command line or in the job file, and will be
472 automatically substituted with the current system values when the job is
473 run. Simple math is also supported on these keywords, so you can perform actions
478 and get that properly expanded to 8 times the size of memory in the machine.
484 This section describes in details each parameter associated with a job. Some
485 parameters take an option of a given type, such as an integer or a
486 string. Anywhere a numeric value is required, an arithmetic expression may be
487 used, provided it is surrounded by parentheses. Supported operators are:
496 For time values in expressions, units are microseconds by default. This is
497 different than for time values not in expressions (not enclosed in
498 parentheses). The following types are used:
505 String: A sequence of alphanumeric characters.
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.
516 Integer. A whole number value, which may contain an integer prefix
517 and an integer suffix:
519 [*integer prefix*] **number** [*integer suffix*]
521 The optional *integer prefix* specifies the number's base. The default
522 is decimal. *0x* specifies hexadecimal.
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.
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):
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
539 To specify power-of-2 binary values defined in IEC 80000-13:
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
547 For Zone Block Device Mode:
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.
554 For quantities of data, an optional unit of 'B' may be included
555 (e.g., 'kB' is the same as 'k').
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.
560 Examples with :option:`kb_base`\=1000:
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
568 Examples with :option:`kb_base`\=1024 (default):
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
576 To specify times (units are not case sensitive):
580 * *M* -- means minutes
581 * *s* -- or sec means seconds (default)
582 * *ms* -- or *msec* means milliseconds
583 * *us* -- or *usec* means microseconds
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.
593 Boolean. Usually parsed as an integer, however only defined for
594 true and false (1 and 0).
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>`.
605 A list of floating point numbers, separated by a ':' character.
607 With the above in mind, here follows the complete list of fio job parameters.
613 .. option:: kb_base=int
615 Select the interpretation of unit prefixes in input parameters.
618 Inputs comply with IEC 80000-13 and the International
619 System of Units (SI). Use:
621 - power-of-2 values with IEC prefixes (e.g., KiB)
622 - power-of-10 values with SI prefixes (e.g., kB)
625 Compatibility mode (default). To avoid breaking old scripts:
627 - power-of-2 values with SI prefixes
628 - power-of-10 values with IEC prefixes
630 See :option:`bs` for more details on input parameters.
632 Outputs always use correct prefixes. Most outputs include both
635 bw=2383.3kB/s (2327.4KiB/s)
637 If only one value is reported, then kb_base selects the one to use:
639 **1000** -- SI prefixes
641 **1024** -- IEC prefixes
643 .. option:: unit_base=int
645 Base unit for reporting. Allowed values are:
648 Use auto-detection (default).
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.
664 .. option:: description=str
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.
669 .. option:: loops=int
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.
674 .. option:: numjobs=int
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.
684 Time related parameters
685 ~~~~~~~~~~~~~~~~~~~~~~~
687 .. option:: runtime=time
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.
694 .. option:: time_based
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.
700 .. option:: startdelay=irange(time)
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.
706 .. option:: ramp_time=time
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
716 .. option:: clocksource=str
718 Use the given clocksource as the base of timing. The supported options are:
721 :manpage:`gettimeofday(2)`
724 :manpage:`clock_gettime(2)`
727 Internal CPU clock source
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.
735 .. option:: gtod_reduce=bool
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.
744 .. option:: gtod_cpu=int
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.
760 .. option:: directory=str
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).
771 See the :option:`filename` option for information on how to escape "``:``"
772 characters within the directory path itself.
774 Note: To control the directory fio will use for internal state files
775 use :option:`--aux-path`.
777 .. option:: filename=str
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`.
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``.
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).
801 The filename "`-`" is a reserved name, meaning *stdin* or *stdout*. Which
802 of the two depends on the read/write direction set.
804 .. option:: filename_format=str
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
814 The name of the worker thread or process.
816 IP of the fio process when using client/server mode.
818 The incremental number of the worker thread or process.
820 The incremental number of the file for that worker thread or
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.
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.
836 .. option:: unique_filename=bool
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.
842 .. option:: opendir=str
844 Recursively open any files below directory `str`.
846 .. option:: lockfile=str
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:
854 No locking. The default.
856 Only one thread or process may do I/O at a time, excluding all
859 Read-write locking on the file. Many readers may
860 access the file at the same time, but writes get exclusive access.
862 .. option:: nrfiles=int
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.
871 .. option:: openfiles=int
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
877 .. option:: file_service_type=str
879 Defines how fio decides which file from a job to service next. The following
883 Choose a file at random.
886 Round robin over opened files. This is the default.
889 Finish one file before moving on to the next. Multiple files can
890 still be open depending on :option:`openfiles`.
893 Use a *Zipf* distribution to decide what file to access.
896 Use a *Pareto* distribution to decide what file to access.
899 Use a *Gaussian* (normal) distribution to decide what file to
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.
913 .. option:: ioscheduler=str
915 Attempt to switch the device hosting the file to the specified I/O scheduler
918 .. option:: create_serialize=bool
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.
924 .. option:: create_fsync=bool
926 :manpage:`fsync(2)` the data file after creation. This is the default.
928 .. option:: create_on_open=bool
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
934 .. option:: create_only=bool
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.
940 .. option:: allow_file_create=bool
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.
946 .. option:: allow_mounted_write=bool
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.
954 .. option:: pre_read=bool
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.
963 .. option:: unlink=bool
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:
969 .. option:: unlink_each_loop=bool
971 Unlink job files after each iteration or loop. Default: false.
973 .. option:: zonemode=str
978 The :option:`zonerange`, :option:`zonesize`,
979 :option `zonecapacity` and option:`zoneskip`
980 parameters are ignored.
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.
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.
999 .. option:: zonerange=int
1001 Size of a single zone. See also :option:`zonesize` and
1004 .. option:: zonesize=int
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.
1013 For :option:`zonemode` =zbd, this is the size of a single zone. The
1014 :option:`zonerange` parameter is ignored in this mode.
1017 .. option:: zonecapacity=int
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
1027 .. option:: zoneskip=int
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.
1033 .. option:: read_beyond_wp=bool
1035 This parameter applies to :option:`zonemode` =zbd only.
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.
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.
1053 .. option:: max_open_zones=int
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 one 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.
1061 .. option:: job_max_open_zones=int
1063 Limit on the number of simultaneously opened zones per single
1066 .. option:: ignore_zone_limits=bool
1068 If this option is used, fio will ignore the maximum number of open
1069 zones limit of the zoned block device in use, thus allowing the
1070 option :option:`max_open_zones` value to be larger than the device
1071 reported limit. Default: false.
1073 .. option:: zone_reset_threshold=float
1075 A number between zero and one that indicates the ratio of logical
1076 blocks with data to the total number of logical blocks in the test
1077 above which zones should be reset periodically.
1079 .. option:: zone_reset_frequency=float
1081 A number between zero and one that indicates how often a zone reset
1082 should be issued if the zone reset threshold has been exceeded. A zone
1083 reset is submitted after each (1 / zone_reset_frequency) write
1084 requests. This and the previous parameter can be used to simulate
1085 garbage collection activity.
1091 .. option:: direct=bool
1093 If value is true, use non-buffered I/O. This is usually O_DIRECT. Note that
1094 OpenBSD and ZFS on Solaris don't support direct I/O. On Windows the synchronous
1095 ioengines don't support direct I/O. Default: false.
1097 .. option:: atomic=bool
1099 If value is true, attempt to use atomic direct I/O. Atomic writes are
1100 guaranteed to be stable once acknowledged by the operating system. Only
1101 Linux supports O_ATOMIC right now.
1103 .. option:: buffered=bool
1105 If value is true, use buffered I/O. This is the opposite of the
1106 :option:`direct` option. Defaults to true.
1108 .. option:: readwrite=str, rw=str
1110 Type of I/O pattern. Accepted values are:
1117 Sequential trims (Linux block devices and SCSI
1118 character devices only).
1124 Random trims (Linux block devices and SCSI
1125 character devices only).
1127 Sequential mixed reads and writes.
1129 Random mixed reads and writes.
1131 Sequential trim+write sequences. Blocks will be trimmed first,
1132 then the same blocks will be written to. So if ``io_size=64K``
1133 is specified, Fio will trim a total of 64K bytes and also
1134 write 64K bytes on the same trimmed blocks. This behaviour
1135 will be consistent with ``number_ios`` or other Fio options
1136 limiting the total bytes or number of I/O's.
1138 Like trimwrite, but uses random offsets rather
1139 than sequential writes.
1141 Fio defaults to read if the option is not specified. For the mixed I/O
1142 types, the default is to split them 50/50. For certain types of I/O the
1143 result may still be skewed a bit, since the speed may be different.
1145 It is possible to specify the number of I/Os to do before getting a new
1146 offset by appending ``:<nr>`` to the end of the string given. For a
1147 random read, it would look like ``rw=randread:8`` for passing in an offset
1148 modifier with a value of 8. If the suffix is used with a sequential I/O
1149 pattern, then the *<nr>* value specified will be **added** to the generated
1150 offset for each I/O turning sequential I/O into sequential I/O with holes.
1151 For instance, using ``rw=write:4k`` will skip 4k for every write. Also see
1152 the :option:`rw_sequencer` option.
1154 .. option:: rw_sequencer=str
1156 If an offset modifier is given by appending a number to the ``rw=<str>``
1157 line, then this option controls how that number modifies the I/O offset
1158 being generated. Accepted values are:
1161 Generate sequential offset.
1163 Generate the same offset.
1165 ``sequential`` is only useful for random I/O, where fio would normally
1166 generate a new random offset for every I/O. If you append e.g. 8 to randread,
1167 you would get a new random offset for every 8 I/Os. The result would be a
1168 seek for only every 8 I/Os, instead of for every I/O. Use ``rw=randread:8``
1169 to specify that. As sequential I/O is already sequential, setting
1170 ``sequential`` for that would not result in any differences. ``identical``
1171 behaves in a similar fashion, except it sends the same offset 8 number of
1172 times before generating a new offset.
1174 .. option:: unified_rw_reporting=str
1176 Fio normally reports statistics on a per data direction basis, meaning that
1177 reads, writes, and trims are accounted and reported separately. This option
1178 determines whether fio reports the results normally, summed together, or as
1180 Accepted values are:
1183 Normal statistics reporting.
1186 Statistics are summed per data direction and reported together.
1189 Statistics are reported normally, followed by the mixed statistics.
1192 Backward-compatible alias for **none**.
1195 Backward-compatible alias for **mixed**.
1200 .. option:: randrepeat=bool
1202 Seed the random number generator used for random I/O patterns in a
1203 predictable way so the pattern is repeatable across runs. Default: true.
1205 .. option:: allrandrepeat=bool
1207 Seed all random number generators in a predictable way so results are
1208 repeatable across runs. Default: false.
1210 .. option:: randseed=int
1212 Seed the random number generators based on this seed value, to be able to
1213 control what sequence of output is being generated. If not set, the random
1214 sequence depends on the :option:`randrepeat` setting.
1216 .. option:: fallocate=str
1218 Whether pre-allocation is performed when laying down files.
1219 Accepted values are:
1222 Do not pre-allocate space.
1225 Use a platform's native pre-allocation call but fall back to
1226 **none** behavior if it fails/is not implemented.
1229 Pre-allocate via :manpage:`posix_fallocate(3)`.
1232 Pre-allocate via :manpage:`fallocate(2)` with
1233 FALLOC_FL_KEEP_SIZE set.
1236 Extend file to final size via :manpage:`ftruncate(2)`
1237 instead of allocating.
1240 Backward-compatible alias for **none**.
1243 Backward-compatible alias for **posix**.
1245 May not be available on all supported platforms. **keep** is only available
1246 on Linux. If using ZFS on Solaris this cannot be set to **posix**
1247 because ZFS doesn't support pre-allocation. Default: **native** if any
1248 pre-allocation methods except **truncate** are available, **none** if not.
1250 Note that using **truncate** on Windows will interact surprisingly
1251 with non-sequential write patterns. When writing to a file that has
1252 been extended by setting the end-of-file information, Windows will
1253 backfill the unwritten portion of the file up to that offset with
1254 zeroes before issuing the new write. This means that a single small
1255 write to the end of an extended file will stall until the entire
1256 file has been filled with zeroes.
1258 .. option:: fadvise_hint=str
1260 Use :manpage:`posix_fadvise(2)` or :manpage:`posix_fadvise(2)` to
1261 advise the kernel on what I/O patterns are likely to be issued.
1262 Accepted values are:
1265 Backwards-compatible hint for "no hint".
1268 Backwards compatible hint for "advise with fio workload type". This
1269 uses **FADV_RANDOM** for a random workload, and **FADV_SEQUENTIAL**
1270 for a sequential workload.
1273 Advise using **FADV_SEQUENTIAL**.
1276 Advise using **FADV_RANDOM**.
1278 .. option:: write_hint=str
1280 Use :manpage:`fcntl(2)` to advise the kernel what life time to expect
1281 from a write. Only supported on Linux, as of version 4.13. Accepted
1285 No particular life time associated with this file.
1288 Data written to this file has a short life time.
1291 Data written to this file has a medium life time.
1294 Data written to this file has a long life time.
1297 Data written to this file has a very long life time.
1299 The values are all relative to each other, and no absolute meaning
1300 should be associated with them.
1302 .. option:: offset=int
1304 Start I/O at the provided offset in the file, given as either a fixed size in
1305 bytes, zones or a percentage. If a percentage is given, the generated offset will be
1306 aligned to the minimum ``blocksize`` or to the value of ``offset_align`` if
1307 provided. Data before the given offset will not be touched. This
1308 effectively caps the file size at `real_size - offset`. Can be combined with
1309 :option:`size` to constrain the start and end range of the I/O workload.
1310 A percentage can be specified by a number between 1 and 100 followed by '%',
1311 for example, ``offset=20%`` to specify 20%. In ZBD mode, value can be set as
1312 number of zones using 'z'.
1314 .. option:: offset_align=int
1316 If set to non-zero value, the byte offset generated by a percentage ``offset``
1317 is aligned upwards to this value. Defaults to 0 meaning that a percentage
1318 offset is aligned to the minimum block size.
1320 .. option:: offset_increment=int
1322 If this is provided, then the real offset becomes `offset + offset_increment
1323 * thread_number`, where the thread number is a counter that starts at 0 and
1324 is incremented for each sub-job (i.e. when :option:`numjobs` option is
1325 specified). This option is useful if there are several jobs which are
1326 intended to operate on a file in parallel disjoint segments, with even
1327 spacing between the starting points. Percentages can be used for this option.
1328 If a percentage is given, the generated offset will be aligned to the minimum
1329 ``blocksize`` or to the value of ``offset_align`` if provided. In ZBD mode, value can
1330 also be set as number of zones using 'z'.
1332 .. option:: number_ios=int
1334 Fio will normally perform I/Os until it has exhausted the size of the region
1335 set by :option:`size`, or if it exhaust the allocated time (or hits an error
1336 condition). With this setting, the range/size can be set independently of
1337 the number of I/Os to perform. When fio reaches this number, it will exit
1338 normally and report status. Note that this does not extend the amount of I/O
1339 that will be done, it will only stop fio if this condition is met before
1340 other end-of-job criteria.
1342 .. option:: fsync=int
1344 If writing to a file, issue an :manpage:`fsync(2)` (or its equivalent) of
1345 the dirty data for every number of blocks given. For example, if you give 32
1346 as a parameter, fio will sync the file after every 32 writes issued. If fio is
1347 using non-buffered I/O, we may not sync the file. The exception is the sg
1348 I/O engine, which synchronizes the disk cache anyway. Defaults to 0, which
1349 means fio does not periodically issue and wait for a sync to complete. Also
1350 see :option:`end_fsync` and :option:`fsync_on_close`.
1352 .. option:: fdatasync=int
1354 Like :option:`fsync` but uses :manpage:`fdatasync(2)` to only sync data and
1355 not metadata blocks. In Windows, DragonFlyBSD or OSX there is no
1356 :manpage:`fdatasync(2)` so this falls back to using :manpage:`fsync(2)`.
1357 Defaults to 0, which means fio does not periodically issue and wait for a
1358 data-only sync to complete.
1360 .. option:: write_barrier=int
1362 Make every `N-th` write a barrier write.
1364 .. option:: sync_file_range=str:int
1366 Use :manpage:`sync_file_range(2)` for every `int` number of write
1367 operations. Fio will track range of writes that have happened since the last
1368 :manpage:`sync_file_range(2)` call. `str` can currently be one or more of:
1371 SYNC_FILE_RANGE_WAIT_BEFORE
1373 SYNC_FILE_RANGE_WRITE
1375 SYNC_FILE_RANGE_WAIT_AFTER
1377 So if you do ``sync_file_range=wait_before,write:8``, fio would use
1378 ``SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE`` for every 8
1379 writes. Also see the :manpage:`sync_file_range(2)` man page. This option is
1382 .. option:: overwrite=bool
1384 If true, writes to a file will always overwrite existing data. If the file
1385 doesn't already exist, it will be created before the write phase begins. If
1386 the file exists and is large enough for the specified write phase, nothing
1387 will be done. Default: false.
1389 .. option:: end_fsync=bool
1391 If true, :manpage:`fsync(2)` file contents when a write stage has completed.
1394 .. option:: fsync_on_close=bool
1396 If true, fio will :manpage:`fsync(2)` a dirty file on close. This differs
1397 from :option:`end_fsync` in that it will happen on every file close, not
1398 just at the end of the job. Default: false.
1400 .. option:: rwmixread=int
1402 Percentage of a mixed workload that should be reads. Default: 50.
1404 .. option:: rwmixwrite=int
1406 Percentage of a mixed workload that should be writes. If both
1407 :option:`rwmixread` and :option:`rwmixwrite` is given and the values do not
1408 add up to 100%, the latter of the two will be used to override the
1409 first. This may interfere with a given rate setting, if fio is asked to
1410 limit reads or writes to a certain rate. If that is the case, then the
1411 distribution may be skewed. Default: 50.
1413 .. option:: random_distribution=str:float[:float][,str:float][,str:float]
1415 By default, fio will use a completely uniform random distribution when asked
1416 to perform random I/O. Sometimes it is useful to skew the distribution in
1417 specific ways, ensuring that some parts of the data is more hot than others.
1418 fio includes the following distribution models:
1421 Uniform random distribution
1430 Normal (Gaussian) distribution
1433 Zoned random distribution
1436 Zone absolute random distribution
1438 When using a **zipf** or **pareto** distribution, an input value is also
1439 needed to define the access pattern. For **zipf**, this is the `Zipf
1440 theta`. For **pareto**, it's the `Pareto power`. Fio includes a test
1441 program, :command:`fio-genzipf`, that can be used visualize what the given input
1442 values will yield in terms of hit rates. If you wanted to use **zipf** with
1443 a `theta` of 1.2, you would use ``random_distribution=zipf:1.2`` as the
1444 option. If a non-uniform model is used, fio will disable use of the random
1445 map. For the **normal** distribution, a normal (Gaussian) deviation is
1446 supplied as a value between 0 and 100.
1448 The second, optional float is allowed for **pareto**, **zipf** and **normal** distributions.
1449 It allows one to set base of distribution in non-default place, giving more control
1450 over most probable outcome. This value is in range [0-1] which maps linearly to
1451 range of possible random values.
1452 Defaults are: random for **pareto** and **zipf**, and 0.5 for **normal**.
1453 If you wanted to use **zipf** with a `theta` of 1.2 centered on 1/4 of allowed value range,
1454 you would use ``random_distribution=zipf:1.2:0.25``.
1456 For a **zoned** distribution, fio supports specifying percentages of I/O
1457 access that should fall within what range of the file or device. For
1458 example, given a criteria of:
1460 * 60% of accesses should be to the first 10%
1461 * 30% of accesses should be to the next 20%
1462 * 8% of accesses should be to the next 30%
1463 * 2% of accesses should be to the next 40%
1465 we can define that through zoning of the random accesses. For the above
1466 example, the user would do::
1468 random_distribution=zoned:60/10:30/20:8/30:2/40
1470 A **zoned_abs** distribution works exactly like the **zoned**, except
1471 that it takes absolute sizes. For example, let's say you wanted to
1472 define access according to the following criteria:
1474 * 60% of accesses should be to the first 20G
1475 * 30% of accesses should be to the next 100G
1476 * 10% of accesses should be to the next 500G
1478 we can define an absolute zoning distribution with:
1480 random_distribution=zoned_abs=60/20G:30/100G:10/500g
1482 For both **zoned** and **zoned_abs**, fio supports defining up to
1485 Similarly to how :option:`bssplit` works for setting ranges and
1486 percentages of block sizes. Like :option:`bssplit`, it's possible to
1487 specify separate zones for reads, writes, and trims. If just one set
1488 is given, it'll apply to all of them. This goes for both **zoned**
1489 **zoned_abs** distributions.
1491 .. option:: percentage_random=int[,int][,int]
1493 For a random workload, set how big a percentage should be random. This
1494 defaults to 100%, in which case the workload is fully random. It can be set
1495 from anywhere from 0 to 100. Setting it to 0 would make the workload fully
1496 sequential. Any setting in between will result in a random mix of sequential
1497 and random I/O, at the given percentages. Comma-separated values may be
1498 specified for reads, writes, and trims as described in :option:`blocksize`.
1500 .. option:: norandommap
1502 Normally fio will cover every block of the file when doing random I/O. If
1503 this option is given, fio will just get a new random offset without looking
1504 at past I/O history. This means that some blocks may not be read or written,
1505 and that some blocks may be read/written more than once. If this option is
1506 used with :option:`verify` and multiple blocksizes (via :option:`bsrange`),
1507 only intact blocks are verified, i.e., partially-overwritten blocks are
1508 ignored. With an async I/O engine and an I/O depth > 1, it is possible for
1509 the same block to be overwritten, which can cause verification errors. Either
1510 do not use norandommap in this case, or also use the lfsr random generator.
1512 .. option:: softrandommap=bool
1514 See :option:`norandommap`. If fio runs with the random block map enabled and
1515 it fails to allocate the map, if this option is set it will continue without
1516 a random block map. As coverage will not be as complete as with random maps,
1517 this option is disabled by default.
1519 .. option:: random_generator=str
1521 Fio supports the following engines for generating I/O offsets for random I/O:
1524 Strong 2^88 cycle random number generator.
1526 Linear feedback shift register generator.
1528 Strong 64-bit 2^258 cycle random number generator.
1530 **tausworthe** is a strong random number generator, but it requires tracking
1531 on the side if we want to ensure that blocks are only read or written
1532 once. **lfsr** guarantees that we never generate the same offset twice, and
1533 it's also less computationally expensive. It's not a true random generator,
1534 however, though for I/O purposes it's typically good enough. **lfsr** only
1535 works with single block sizes, not with workloads that use multiple block
1536 sizes. If used with such a workload, fio may read or write some blocks
1537 multiple times. The default value is **tausworthe**, unless the required
1538 space exceeds 2^32 blocks. If it does, then **tausworthe64** is
1539 selected automatically.
1545 .. option:: blocksize=int[,int][,int], bs=int[,int][,int]
1547 The block size in bytes used for I/O units. Default: 4096. A single value
1548 applies to reads, writes, and trims. Comma-separated values may be
1549 specified for reads, writes, and trims. A value not terminated in a comma
1550 applies to subsequent types.
1555 means 256k for reads, writes and trims.
1558 means 8k for reads, 32k for writes and trims.
1561 means 8k for reads, 32k for writes, and default for trims.
1564 means default for reads, 8k for writes and trims.
1567 means default for reads, 8k for writes, and default for trims.
1569 .. option:: blocksize_range=irange[,irange][,irange], bsrange=irange[,irange][,irange]
1571 A range of block sizes in bytes for I/O units. The issued I/O unit will
1572 always be a multiple of the minimum size, unless
1573 :option:`blocksize_unaligned` is set.
1575 Comma-separated ranges may be specified for reads, writes, and trims as
1576 described in :option:`blocksize`.
1578 Example: ``bsrange=1k-4k,2k-8k``.
1580 .. option:: bssplit=str[,str][,str]
1582 Sometimes you want even finer grained control of the block sizes
1583 issued, not just an even split between them. This option allows you to
1584 weight various block sizes, so that you are able to define a specific
1585 amount of block sizes issued. The format for this option is::
1587 bssplit=blocksize/percentage:blocksize/percentage
1589 for as many block sizes as needed. So if you want to define a workload
1590 that has 50% 64k blocks, 10% 4k blocks, and 40% 32k blocks, you would
1593 bssplit=4k/10:64k/50:32k/40
1595 Ordering does not matter. If the percentage is left blank, fio will
1596 fill in the remaining values evenly. So a bssplit option like this one::
1598 bssplit=4k/50:1k/:32k/
1600 would have 50% 4k ios, and 25% 1k and 32k ios. The percentages always
1601 add up to 100, if bssplit is given a range that adds up to more, it
1604 Comma-separated values may be specified for reads, writes, and trims as
1605 described in :option:`blocksize`.
1607 If you want a workload that has 50% 2k reads and 50% 4k reads, while
1608 having 90% 4k writes and 10% 8k writes, you would specify::
1610 bssplit=2k/50:4k/50,4k/90:8k/10
1612 Fio supports defining up to 64 different weights for each data
1615 .. option:: blocksize_unaligned, bs_unaligned
1617 If set, fio will issue I/O units with any size within
1618 :option:`blocksize_range`, not just multiples of the minimum size. This
1619 typically won't work with direct I/O, as that normally requires sector
1622 .. option:: bs_is_seq_rand=bool
1624 If this option is set, fio will use the normal read,write blocksize settings
1625 as sequential,random blocksize settings instead. Any random read or write
1626 will use the WRITE blocksize settings, and any sequential read or write will
1627 use the READ blocksize settings.
1629 .. option:: blockalign=int[,int][,int], ba=int[,int][,int]
1631 Boundary to which fio will align random I/O units. Default:
1632 :option:`blocksize`. Minimum alignment is typically 512b for using direct
1633 I/O, though it usually depends on the hardware block size. This option is
1634 mutually exclusive with using a random map for files, so it will turn off
1635 that option. Comma-separated values may be specified for reads, writes, and
1636 trims as described in :option:`blocksize`.
1642 .. option:: zero_buffers
1644 Initialize buffers with all zeros. Default: fill buffers with random data.
1646 .. option:: refill_buffers
1648 If this option is given, fio will refill the I/O buffers on every
1649 submit. Only makes sense if :option:`zero_buffers` isn't specified,
1650 naturally. Defaults to being unset i.e., the buffer is only filled at
1651 init time and the data in it is reused when possible but if any of
1652 :option:`verify`, :option:`buffer_compress_percentage` or
1653 :option:`dedupe_percentage` are enabled then `refill_buffers` is also
1654 automatically enabled.
1656 .. option:: scramble_buffers=bool
1658 If :option:`refill_buffers` is too costly and the target is using data
1659 deduplication, then setting this option will slightly modify the I/O buffer
1660 contents to defeat normal de-dupe attempts. This is not enough to defeat
1661 more clever block compression attempts, but it will stop naive dedupe of
1662 blocks. Default: true.
1664 .. option:: buffer_compress_percentage=int
1666 If this is set, then fio will attempt to provide I/O buffer content
1667 (on WRITEs) that compresses to the specified level. Fio does this by
1668 providing a mix of random data followed by fixed pattern data. The
1669 fixed pattern is either zeros, or the pattern specified by
1670 :option:`buffer_pattern`. If the `buffer_pattern` option is used, it
1671 might skew the compression ratio slightly. Setting
1672 `buffer_compress_percentage` to a value other than 100 will also
1673 enable :option:`refill_buffers` in order to reduce the likelihood that
1674 adjacent blocks are so similar that they over compress when seen
1675 together. See :option:`buffer_compress_chunk` for how to set a finer or
1676 coarser granularity for the random/fixed data region. Defaults to unset
1677 i.e., buffer data will not adhere to any compression level.
1679 .. option:: buffer_compress_chunk=int
1681 This setting allows fio to manage how big the random/fixed data region
1682 is when using :option:`buffer_compress_percentage`. When
1683 `buffer_compress_chunk` is set to some non-zero value smaller than the
1684 block size, fio can repeat the random/fixed region throughout the I/O
1685 buffer at the specified interval (which particularly useful when
1686 bigger block sizes are used for a job). When set to 0, fio will use a
1687 chunk size that matches the block size resulting in a single
1688 random/fixed region within the I/O buffer. Defaults to 512. When the
1689 unit is omitted, the value is interpreted in bytes.
1691 .. option:: buffer_pattern=str
1693 If set, fio will fill the I/O buffers with this pattern or with the contents
1694 of a file. If not set, the contents of I/O buffers are defined by the other
1695 options related to buffer contents. The setting can be any pattern of bytes,
1696 and can be prefixed with 0x for hex values. It may also be a string, where
1697 the string must then be wrapped with ``""``. Or it may also be a filename,
1698 where the filename must be wrapped with ``''`` in which case the file is
1699 opened and read. Note that not all the file contents will be read if that
1700 would cause the buffers to overflow. So, for example::
1702 buffer_pattern='filename'
1706 buffer_pattern="abcd"
1714 buffer_pattern=0xdeadface
1716 Also you can combine everything together in any order::
1718 buffer_pattern=0xdeadface"abcd"-12'filename'
1720 .. option:: dedupe_percentage=int
1722 If set, fio will generate this percentage of identical buffers when
1723 writing. These buffers will be naturally dedupable. The contents of the
1724 buffers depend on what other buffer compression settings have been set. It's
1725 possible to have the individual buffers either fully compressible, or not at
1726 all -- this option only controls the distribution of unique buffers. Setting
1727 this option will also enable :option:`refill_buffers` to prevent every buffer
1730 .. option:: dedupe_mode=str
1732 If ``dedupe_percentage=<int>`` is given, then this option controls how fio
1733 generates the dedupe buffers.
1736 Generate dedupe buffers by repeating previous writes
1738 Generate dedupe buffers from working set
1740 ``repeat`` is the default option for fio. Dedupe buffers are generated
1741 by repeating previous unique write.
1743 ``working_set`` is a more realistic workload.
1744 With ``working_set``, ``dedupe_working_set_percentage=<int>`` should be provided.
1745 Given that, fio will use the initial unique write buffers as its working set.
1746 Upon deciding to dedupe, fio will randomly choose a buffer from the working set.
1747 Note that by using ``working_set`` the dedupe percentage will converge
1748 to the desired over time while ``repeat`` maintains the desired percentage
1751 .. option:: dedupe_working_set_percentage=int
1753 If ``dedupe_mode=<str>`` is set to ``working_set``, then this controls
1754 the percentage of size of the file or device used as the buffers
1755 fio will choose to generate the dedupe buffers from
1757 Note that size needs to be explicitly provided and only 1 file per
1760 .. option:: dedupe_global=bool
1762 This controls whether the deduplication buffers will be shared amongst
1763 all jobs that have this option set. The buffers are spread evenly between
1766 .. option:: invalidate=bool
1768 Invalidate the buffer/page cache parts of the files to be used prior to
1769 starting I/O if the platform and file type support it. Defaults to true.
1770 This will be ignored if :option:`pre_read` is also specified for the
1773 .. option:: sync=str
1775 Whether, and what type, of synchronous I/O to use for writes. The allowed
1779 Do not use synchronous IO, the default.
1785 Use synchronous file IO. For the majority of I/O engines,
1786 this means using O_SYNC.
1792 Use synchronous data IO. For the majority of I/O engines,
1793 this means using O_DSYNC.
1796 .. option:: iomem=str, mem=str
1798 Fio can use various types of memory as the I/O unit buffer. The allowed
1802 Use memory from :manpage:`malloc(3)` as the buffers. Default memory
1806 Use shared memory as the buffers. Allocated through
1807 :manpage:`shmget(2)`.
1810 Same as shm, but use huge pages as backing.
1813 Use :manpage:`mmap(2)` to allocate buffers. May either be anonymous memory, or can
1814 be file backed if a filename is given after the option. The format
1815 is `mem=mmap:/path/to/file`.
1818 Use a memory mapped huge file as the buffer backing. Append filename
1819 after mmaphuge, ala `mem=mmaphuge:/hugetlbfs/file`.
1822 Same as mmap, but use a MMAP_SHARED mapping.
1825 Use GPU memory as the buffers for GPUDirect RDMA benchmark.
1826 The :option:`ioengine` must be `rdma`.
1828 The area allocated is a function of the maximum allowed bs size for the job,
1829 multiplied by the I/O depth given. Note that for **shmhuge** and
1830 **mmaphuge** to work, the system must have free huge pages allocated. This
1831 can normally be checked and set by reading/writing
1832 :file:`/proc/sys/vm/nr_hugepages` on a Linux system. Fio assumes a huge page
1833 is 2 or 4MiB in size depending on the platform. So to calculate the
1834 number of huge pages you need for a given job file, add up the I/O
1835 depth of all jobs (normally one unless :option:`iodepth` is used) and
1836 multiply by the maximum bs set. Then divide that number by the huge
1837 page size. You can see the size of the huge pages in
1838 :file:`/proc/meminfo`. If no huge pages are allocated by having a
1839 non-zero number in `nr_hugepages`, using **mmaphuge** or **shmhuge**
1840 will fail. Also see :option:`hugepage-size`.
1842 **mmaphuge** also needs to have hugetlbfs mounted and the file location
1843 should point there. So if it's mounted in :file:`/huge`, you would use
1844 `mem=mmaphuge:/huge/somefile`.
1846 .. option:: iomem_align=int, mem_align=int
1848 This indicates the memory alignment of the I/O memory buffers. Note that
1849 the given alignment is applied to the first I/O unit buffer, if using
1850 :option:`iodepth` the alignment of the following buffers are given by the
1851 :option:`bs` used. In other words, if using a :option:`bs` that is a
1852 multiple of the page sized in the system, all buffers will be aligned to
1853 this value. If using a :option:`bs` that is not page aligned, the alignment
1854 of subsequent I/O memory buffers is the sum of the :option:`iomem_align` and
1857 .. option:: hugepage-size=int
1859 Defines the size of a huge page. Must at least be equal to the system
1860 setting, see :file:`/proc/meminfo` and
1861 :file:`/sys/kernel/mm/hugepages/`. Defaults to 2 or 4MiB depending on
1862 the platform. Should probably always be a multiple of megabytes, so
1863 using ``hugepage-size=Xm`` is the preferred way to set this to avoid
1864 setting a non-pow-2 bad value.
1866 .. option:: lockmem=int
1868 Pin the specified amount of memory with :manpage:`mlock(2)`. Can be used to
1869 simulate a smaller amount of memory. The amount specified is per worker.
1875 .. option:: size=int
1877 The total size of file I/O for each thread of this job. Fio will run until
1878 this many bytes has been transferred, unless runtime is altered by other means
1879 such as (1) :option:`runtime`, (2) :option:`io_size` (3) :option:`number_ios`,
1880 (4) gaps/holes while doing I/O's such as ``rw=read:16K``, or (5) sequential
1881 I/O reaching end of the file which is possible when :option:`percentage_random`
1883 Fio will divide this size between the available files determined by options
1884 such as :option:`nrfiles`, :option:`filename`, unless :option:`filesize` is
1885 specified by the job. If the result of division happens to be 0, the size is
1886 set to the physical size of the given files or devices if they exist.
1887 If this option is not specified, fio will use the full size of the given
1888 files or devices. If the files do not exist, size must be given. It is also
1889 possible to give size as a percentage between 1 and 100. If ``size=20%`` is
1890 given, fio will use 20% of the full size of the given files or devices.
1891 In ZBD mode, value can also be set as number of zones using 'z'.
1892 Can be combined with :option:`offset` to constrain the start and end range
1893 that I/O will be done within.
1895 .. option:: io_size=int, io_limit=int
1897 Normally fio operates within the region set by :option:`size`, which means
1898 that the :option:`size` option sets both the region and size of I/O to be
1899 performed. Sometimes that is not what you want. With this option, it is
1900 possible to define just the amount of I/O that fio should do. For instance,
1901 if :option:`size` is set to 20GiB and :option:`io_size` is set to 5GiB, fio
1902 will perform I/O within the first 20GiB but exit when 5GiB have been
1903 done. The opposite is also possible -- if :option:`size` is set to 20GiB,
1904 and :option:`io_size` is set to 40GiB, then fio will do 40GiB of I/O within
1905 the 0..20GiB region.
1907 .. option:: filesize=irange(int)
1909 Individual file sizes. May be a range, in which case fio will select sizes for
1910 files at random within the given range. If not given, each created file is the
1911 same size. This option overrides :option:`size` in terms of file size, i.e. if
1912 :option:`filesize` is specified then :option:`size` becomes merely the default
1913 for :option:`io_size` and has no effect at all if :option:`io_size` is set
1916 .. option:: file_append=bool
1918 Perform I/O after the end of the file. Normally fio will operate within the
1919 size of a file. If this option is set, then fio will append to the file
1920 instead. This has identical behavior to setting :option:`offset` to the size
1921 of a file. This option is ignored on non-regular files.
1923 .. option:: fill_device=bool, fill_fs=bool
1925 Sets size to something really large and waits for ENOSPC (no space left on
1926 device) or EDQUOT (disk quota exceeded)
1927 as the terminating condition. Only makes sense with sequential
1928 write. For a read workload, the mount point will be filled first then I/O
1929 started on the result. This option doesn't make sense if operating on a raw
1930 device node, since the size of that is already known by the file system.
1931 Additionally, writing beyond end-of-device will not return ENOSPC there.
1937 .. option:: ioengine=str
1939 Defines how the job issues I/O to the file. The following types are defined:
1942 Basic :manpage:`read(2)` or :manpage:`write(2)`
1943 I/O. :manpage:`lseek(2)` is used to position the I/O location.
1944 See :option:`fsync` and :option:`fdatasync` for syncing write I/Os.
1947 Basic :manpage:`pread(2)` or :manpage:`pwrite(2)` I/O. Default on
1948 all supported operating systems except for Windows.
1951 Basic :manpage:`readv(2)` or :manpage:`writev(2)` I/O. Will emulate
1952 queuing by coalescing adjacent I/Os into a single submission.
1955 Basic :manpage:`preadv(2)` or :manpage:`pwritev(2)` I/O.
1958 Basic :manpage:`preadv2(2)` or :manpage:`pwritev2(2)` I/O.
1961 Fast Linux native asynchronous I/O. Supports async IO
1962 for both direct and buffered IO.
1963 This engine defines engine specific options.
1966 Fast Linux native asynchronous I/O for pass through commands.
1967 This engine defines engine specific options.
1970 Linux native asynchronous I/O. Note that Linux may only support
1971 queued behavior with non-buffered I/O (set ``direct=1`` or
1973 This engine defines engine specific options.
1976 POSIX asynchronous I/O using :manpage:`aio_read(3)` and
1977 :manpage:`aio_write(3)`.
1980 Solaris native asynchronous I/O.
1983 Windows native asynchronous I/O. Default on Windows.
1986 File is memory mapped with :manpage:`mmap(2)` and data copied
1987 to/from using :manpage:`memcpy(3)`.
1990 :manpage:`splice(2)` is used to transfer the data and
1991 :manpage:`vmsplice(2)` to transfer data from user space to the
1995 SCSI generic sg v3 I/O. May either be synchronous using the SG_IO
1996 ioctl, or if the target is an sg character device we use
1997 :manpage:`read(2)` and :manpage:`write(2)` for asynchronous
1998 I/O. Requires :option:`filename` option to specify either block or
1999 character devices. This engine supports trim operations.
2000 The sg engine includes engine specific options.
2003 Read, write, trim and ZBC/ZAC operations to a zoned
2004 block device using libzbc library. The target can be
2005 either an SG character device or a block device file.
2008 Doesn't transfer any data, just pretends to. This is mainly used to
2009 exercise fio itself and for debugging/testing purposes.
2012 Transfer over the network to given ``host:port``. Depending on the
2013 :option:`protocol` used, the :option:`hostname`, :option:`port`,
2014 :option:`listen` and :option:`filename` options are used to specify
2015 what sort of connection to make, while the :option:`protocol` option
2016 determines which protocol will be used. This engine defines engine
2020 Like **net**, but uses :manpage:`splice(2)` and
2021 :manpage:`vmsplice(2)` to map data and send/receive.
2022 This engine defines engine specific options.
2025 Doesn't transfer any data, but burns CPU cycles according to the
2026 :option:`cpuload`, :option:`cpuchunks` and :option:`cpumode` options.
2027 Setting :option:`cpuload`\=85 will cause that job to do nothing but burn 85%
2028 of the CPU. In case of SMP machines, use :option:`numjobs`\=<nr_of_cpu>
2029 to get desired CPU usage, as the cpuload only loads a
2030 single CPU at the desired rate. A job never finishes unless there is
2031 at least one non-cpuio job.
2032 Setting :option:`cpumode`\=qsort replace the default noop instructions loop
2033 by a qsort algorithm to consume more energy.
2036 The RDMA I/O engine supports both RDMA memory semantics
2037 (RDMA_WRITE/RDMA_READ) and channel semantics (Send/Recv) for the
2038 InfiniBand, RoCE and iWARP protocols. This engine defines engine
2042 I/O engine that does regular fallocate to simulate data transfer as
2046 does fallocate(,mode = FALLOC_FL_KEEP_SIZE,).
2049 does fallocate(,mode = 0).
2052 does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE).
2055 I/O engine that sends :manpage:`ftruncate(2)` operations in response
2056 to write (DDIR_WRITE) events. Each ftruncate issued sets the file's
2057 size to the current block offset. :option:`blocksize` is ignored.
2060 I/O engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate
2061 defragment activity in request to DDIR_WRITE event.
2064 I/O engine supporting direct access to Ceph Reliable Autonomic
2065 Distributed Object Store (RADOS) via librados. This ioengine
2066 defines engine specific options.
2069 I/O engine supporting direct access to Ceph Rados Block Devices
2070 (RBD) via librbd without the need to use the kernel rbd driver. This
2071 ioengine defines engine specific options.
2074 I/O engine supporting GET/PUT requests over HTTP(S) with libcurl to
2075 a WebDAV or S3 endpoint. This ioengine defines engine specific options.
2077 This engine only supports direct IO of iodepth=1; you need to scale this
2078 via numjobs. blocksize defines the size of the objects to be created.
2080 TRIM is translated to object deletion.
2083 Using GlusterFS libgfapi sync interface to direct access to
2084 GlusterFS volumes without having to go through FUSE. This ioengine
2085 defines engine specific options.
2088 Using GlusterFS libgfapi async interface to direct access to
2089 GlusterFS volumes without having to go through FUSE. This ioengine
2090 defines engine specific options.
2093 Read and write through Hadoop (HDFS). The :option:`filename` option
2094 is used to specify host,port of the hdfs name-node to connect. This
2095 engine interprets offsets a little differently. In HDFS, files once
2096 created cannot be modified so random writes are not possible. To
2097 imitate this the libhdfs engine expects a bunch of small files to be
2098 created over HDFS and will randomly pick a file from them
2099 based on the offset generated by fio backend (see the example
2100 job file to create such files, use ``rw=write`` option). Please
2101 note, it may be necessary to set environment variables to work
2102 with HDFS/libhdfs properly. Each job uses its own connection to
2106 Read, write and erase an MTD character device (e.g.,
2107 :file:`/dev/mtd0`). Discards are treated as erases. Depending on the
2108 underlying device type, the I/O may have to go in a certain pattern,
2109 e.g., on NAND, writing sequentially to erase blocks and discarding
2110 before overwriting. The `trimwrite` mode works well for this
2114 Read and write using filesystem DAX to a file on a filesystem
2115 mounted with DAX on a persistent memory device through the PMDK
2119 Read and write using device DAX to a persistent memory device (e.g.,
2120 /dev/dax0.0) through the PMDK libpmem library.
2123 Prefix to specify loading an external I/O engine object file. Append
2124 the engine filename, e.g. ``ioengine=external:/tmp/foo.o`` to load
2125 ioengine :file:`foo.o` in :file:`/tmp`. The path can be either
2126 absolute or relative. See :file:`engines/skeleton_external.c` for
2127 details of writing an external I/O engine.
2130 Simply create the files and do no I/O to them. You still need to
2131 set `filesize` so that all the accounting still occurs, but no
2132 actual I/O will be done other than creating the file.
2135 Simply do stat() and do no I/O to the file. You need to set 'filesize'
2136 and 'nrfiles', so that files will be created.
2137 This engine is to measure file lookup and meta data access.
2140 Simply delete the files by unlink() and do no I/O to them. You need to set 'filesize'
2141 and 'nrfiles', so that the files will be created.
2142 This engine is to measure file delete.
2145 Read and write using mmap I/O to a file on a filesystem
2146 mounted with DAX on a persistent memory device through the PMDK
2150 Synchronous read and write using DDN's Infinite Memory Engine (IME).
2151 This engine is very basic and issues calls to IME whenever an IO is
2155 Synchronous read and write using DDN's Infinite Memory Engine (IME).
2156 This engine uses iovecs and will try to stack as much IOs as possible
2157 (if the IOs are "contiguous" and the IO depth is not exceeded)
2158 before issuing a call to IME.
2161 Asynchronous read and write using DDN's Infinite Memory Engine (IME).
2162 This engine will try to stack as much IOs as possible by creating
2163 requests for IME. FIO will then decide when to commit these requests.
2166 Read and write iscsi lun with libiscsi.
2169 Read and write a Network Block Device (NBD).
2172 I/O engine supporting libcufile synchronous access to nvidia-fs and a
2173 GPUDirect Storage-supported filesystem. This engine performs
2174 I/O without transferring buffers between user-space and the kernel,
2175 unless :option:`verify` is set or :option:`cuda_io` is `posix`.
2176 :option:`iomem` must not be `cudamalloc`. This ioengine defines
2177 engine specific options.
2180 I/O engine supporting asynchronous read and write operations to the
2181 DAOS File System (DFS) via libdfs.
2184 I/O engine supporting asynchronous read and write operations to
2185 NFS filesystems from userspace via libnfs. This is useful for
2186 achieving higher concurrency and thus throughput than is possible
2190 Execute 3rd party tools. Could be used to perform monitoring during jobs runtime.
2193 I/O engine using the xNVMe C API, for NVMe devices. The xnvme engine provides
2194 flexibility to access GNU/Linux Kernel NVMe driver via libaio, IOCTLs, io_uring,
2195 the SPDK NVMe driver, or your own custom NVMe driver. The xnvme engine includes
2196 engine specific options. (See https://xnvme.io).
2199 Use the libblkio library
2200 (https://gitlab.com/libblkio/libblkio). The specific
2201 *driver* to use must be set using
2202 :option:`libblkio_driver`. If
2203 :option:`mem`/:option:`iomem` is not specified, memory
2204 allocation is delegated to libblkio (and so is
2205 guaranteed to work with the selected *driver*).
2207 I/O engine specific parameters
2208 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2210 In addition, there are some parameters which are only valid when a specific
2211 :option:`ioengine` is in use. These are used identically to normal parameters,
2212 with the caveat that when used on the command line, they must come after the
2213 :option:`ioengine` that defines them is selected.
2215 .. option:: cmdprio_percentage=int[,int] : [io_uring] [libaio]
2217 Set the percentage of I/O that will be issued with the highest priority.
2218 Default: 0. A single value applies to reads and writes. Comma-separated
2219 values may be specified for reads and writes. For this option to be
2220 effective, NCQ priority must be supported and enabled, and the :option:`direct`
2221 option must be set. fio must also be run as the root user. Unlike
2222 slat/clat/lat stats, which can be tracked and reported independently, per
2223 priority stats only track and report a single type of latency. By default,
2224 completion latency (clat) will be reported, if :option:`lat_percentiles` is
2225 set, total latency (lat) will be reported.
2227 .. option:: cmdprio_class=int[,int] : [io_uring] [libaio]
2229 Set the I/O priority class to use for I/Os that must be issued with
2230 a priority when :option:`cmdprio_percentage` or
2231 :option:`cmdprio_bssplit` is set. If not specified when
2232 :option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set,
2233 this defaults to the highest priority class. A single value applies
2234 to reads and writes. Comma-separated values may be specified for
2235 reads and writes. See :manpage:`ionice(1)`. See also the
2236 :option:`prioclass` option.
2238 .. option:: cmdprio=int[,int] : [io_uring] [libaio]
2240 Set the I/O priority value to use for I/Os that must be issued with
2241 a priority when :option:`cmdprio_percentage` or
2242 :option:`cmdprio_bssplit` is set. If not specified when
2243 :option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set,
2245 Linux limits us to a positive value between 0 and 7, with 0 being the
2246 highest. A single value applies to reads and writes. Comma-separated
2247 values may be specified for reads and writes. See :manpage:`ionice(1)`.
2248 Refer to an appropriate manpage for other operating systems since
2249 meaning of priority may differ. See also the :option:`prio` option.
2251 .. option:: cmdprio_bssplit=str[,str] : [io_uring] [libaio]
2253 To get a finer control over I/O priority, this option allows
2254 specifying the percentage of IOs that must have a priority set
2255 depending on the block size of the IO. This option is useful only
2256 when used together with the :option:`bssplit` option, that is,
2257 multiple different block sizes are used for reads and writes.
2259 The first accepted format for this option is the same as the format of
2260 the :option:`bssplit` option:
2262 cmdprio_bssplit=blocksize/percentage:blocksize/percentage
2264 In this case, each entry will use the priority class and priority
2265 level defined by the options :option:`cmdprio_class` and
2266 :option:`cmdprio` respectively.
2268 The second accepted format for this option is:
2270 cmdprio_bssplit=blocksize/percentage/class/level:blocksize/percentage/class/level
2272 In this case, the priority class and priority level is defined inside
2273 each entry. In comparison with the first accepted format, the second
2274 accepted format does not restrict all entries to have the same priority
2275 class and priority level.
2277 For both formats, only the read and write data directions are supported,
2278 values for trim IOs are ignored. This option is mutually exclusive with
2279 the :option:`cmdprio_percentage` option.
2281 .. option:: fixedbufs : [io_uring] [io_uring_cmd]
2283 If fio is asked to do direct IO, then Linux will map pages for each
2284 IO call, and release them when IO is done. If this option is set, the
2285 pages are pre-mapped before IO is started. This eliminates the need to
2286 map and release for each IO. This is more efficient, and reduces the
2289 .. option:: nonvectored=int : [io_uring] [io_uring_cmd]
2291 With this option, fio will use non-vectored read/write commands, where
2292 address must contain the address directly. Default is -1.
2294 .. option:: force_async=int : [io_uring] [io_uring_cmd]
2296 Normal operation for io_uring is to try and issue an sqe as
2297 non-blocking first, and if that fails, execute it in an async manner.
2298 With this option set to N, then every N request fio will ask sqe to
2299 be issued in an async manner. Default is 0.
2301 .. option:: registerfiles : [io_uring] [io_uring_cmd]
2303 With this option, fio registers the set of files being used with the
2304 kernel. This avoids the overhead of managing file counts in the kernel,
2305 making the submission and completion part more lightweight. Required
2306 for the below :option:`sqthread_poll` option.
2308 .. option:: sqthread_poll : [io_uring] [io_uring_cmd] [xnvme]
2310 Normally fio will submit IO by issuing a system call to notify the
2311 kernel of available items in the SQ ring. If this option is set, the
2312 act of submitting IO will be done by a polling thread in the kernel.
2313 This frees up cycles for fio, at the cost of using more CPU in the
2314 system. As submission is just the time it takes to fill in the sqe
2315 entries and any syscall required to wake up the idle kernel thread,
2316 fio will not report submission latencies.
2318 .. option:: sqthread_poll_cpu=int : [io_uring] [io_uring_cmd]
2320 When :option:`sqthread_poll` is set, this option provides a way to
2321 define which CPU should be used for the polling thread.
2323 .. option:: cmd_type=str : [io_uring_cmd]
2325 Specifies the type of uring passthrough command to be used. Supported
2326 value is nvme. Default is nvme.
2330 [io_uring] [io_uring_cmd] [xnvme]
2332 If this option is set, fio will attempt to use polled IO completions.
2333 Normal IO completions generate interrupts to signal the completion of
2334 IO, polled completions do not. Hence they are require active reaping
2335 by the application. The benefits are more efficient IO for high IOPS
2336 scenarios, and lower latencies for low queue depth IO.
2340 Use poll queues. This is incompatible with
2341 :option:`libblkio_wait_mode=eventfd <libblkio_wait_mode>` and
2342 :option:`libblkio_force_enable_completion_eventfd`.
2346 Set RWF_HIPRI on I/O, indicating to the kernel that it's of higher priority
2351 If this option is set, fio will attempt to use polled IO completions.
2352 This will have a similar effect as (io_uring)hipri. Only SCSI READ and
2353 WRITE commands will have the SGV4_FLAG_HIPRI set (not UNMAP (trim) nor
2354 VERIFY). Older versions of the Linux sg driver that do not support
2355 hipri will simply ignore this flag and do normal IO. The Linux SCSI
2356 Low Level Driver (LLD) that "owns" the device also needs to support
2357 hipri (also known as iopoll and mq_poll). The MegaRAID driver is an
2358 example of a SCSI LLD. Default: clear (0) which does normal
2359 (interrupted based) IO.
2361 .. option:: userspace_reap : [libaio]
2363 Normally, with the libaio engine in use, fio will use the
2364 :manpage:`io_getevents(2)` system call to reap newly returned events. With
2365 this flag turned on, the AIO ring will be read directly from user-space to
2366 reap events. The reaping mode is only enabled when polling for a minimum of
2367 0 events (e.g. when :option:`iodepth_batch_complete` `=0`).
2369 .. option:: hipri_percentage : [pvsync2]
2371 When hipri is set this determines the probability of a pvsync2 I/O being high
2372 priority. The default is 100%.
2374 .. option:: nowait=bool : [pvsync2] [libaio] [io_uring] [io_uring_cmd]
2376 By default if a request cannot be executed immediately (e.g. resource starvation,
2377 waiting on locks) it is queued and the initiating process will be blocked until
2378 the required resource becomes free.
2380 This option sets the RWF_NOWAIT flag (supported from the 4.14 Linux kernel) and
2381 the call will return instantly with EAGAIN or a partial result rather than waiting.
2383 It is useful to also use ignore_error=EAGAIN when using this option.
2385 Note: glibc 2.27, 2.28 have a bug in syscall wrappers preadv2, pwritev2.
2386 They return EOPNOTSUP instead of EAGAIN.
2388 For cached I/O, using this option usually means a request operates only with
2389 cached data. Currently the RWF_NOWAIT flag does not supported for cached write.
2391 For direct I/O, requests will only succeed if cache invalidation isn't required,
2392 file blocks are fully allocated and the disk request could be issued immediately.
2394 .. option:: cpuload=int : [cpuio]
2396 Attempt to use the specified percentage of CPU cycles. This is a mandatory
2397 option when using cpuio I/O engine.
2399 .. option:: cpuchunks=int : [cpuio]
2401 Split the load into cycles of the given time. In microseconds.
2403 .. option:: cpumode=str : [cpuio]
2405 Specify how to stress the CPU. It can take these two values:
2408 This is the default where the CPU executes noop instructions.
2410 Replace the default noop instructions loop with a qsort algorithm to
2411 consume more energy.
2413 .. option:: exit_on_io_done=bool : [cpuio]
2415 Detect when I/O threads are done, then exit.
2417 .. option:: namenode=str : [libhdfs]
2419 The hostname or IP address of a HDFS cluster namenode to contact.
2421 .. option:: port=int
2425 The listening port of the HFDS cluster namenode.
2429 The TCP or UDP port to bind to or connect to. If this is used with
2430 :option:`numjobs` to spawn multiple instances of the same job type, then
2431 this will be the starting port number since fio will use a range of
2436 The port to use for RDMA-CM communication. This should be the same value
2437 on the client and the server side.
2439 .. option:: hostname=str : [netsplice] [net] [rdma]
2441 The hostname or IP address to use for TCP, UDP or RDMA-CM based I/O. If the job
2442 is a TCP listener or UDP reader, the hostname is not used and must be omitted
2443 unless it is a valid UDP multicast address.
2445 .. option:: serverip=str : [librpma_*]
2447 The IP address to be used for RDMA-CM based I/O.
2449 .. option:: direct_write_to_pmem=bool : [librpma_*]
2451 Set to 1 only when Direct Write to PMem from the remote host is possible.
2452 Otherwise, set to 0.
2454 .. option:: busy_wait_polling=bool : [librpma_*_server]
2456 Set to 0 to wait for completion instead of busy-wait polling completion.
2459 .. option:: interface=str : [netsplice] [net]
2461 The IP address of the network interface used to send or receive UDP
2464 .. option:: ttl=int : [netsplice] [net]
2466 Time-to-live value for outgoing UDP multicast packets. Default: 1.
2468 .. option:: nodelay=bool : [netsplice] [net]
2470 Set TCP_NODELAY on TCP connections.
2472 .. option:: protocol=str, proto=str : [netsplice] [net]
2474 The network protocol to use. Accepted values are:
2477 Transmission control protocol.
2479 Transmission control protocol V6.
2481 User datagram protocol.
2483 User datagram protocol V6.
2487 When the protocol is TCP or UDP, the port must also be given, as well as the
2488 hostname if the job is a TCP listener or UDP reader. For unix sockets, the
2489 normal :option:`filename` option should be used and the port is invalid.
2491 .. option:: listen : [netsplice] [net]
2493 For TCP network connections, tell fio to listen for incoming connections
2494 rather than initiating an outgoing connection. The :option:`hostname` must
2495 be omitted if this option is used.
2497 .. option:: pingpong : [netsplice] [net]
2499 Normally a network writer will just continue writing data, and a network
2500 reader will just consume packages. If ``pingpong=1`` is set, a writer will
2501 send its normal payload to the reader, then wait for the reader to send the
2502 same payload back. This allows fio to measure network latencies. The
2503 submission and completion latencies then measure local time spent sending or
2504 receiving, and the completion latency measures how long it took for the
2505 other end to receive and send back. For UDP multicast traffic
2506 ``pingpong=1`` should only be set for a single reader when multiple readers
2507 are listening to the same address.
2509 .. option:: window_size : [netsplice] [net]
2511 Set the desired socket buffer size for the connection.
2513 .. option:: mss : [netsplice] [net]
2515 Set the TCP maximum segment size (TCP_MAXSEG).
2517 .. option:: donorname=str : [e4defrag]
2519 File will be used as a block donor (swap extents between files).
2521 .. option:: inplace=int : [e4defrag]
2523 Configure donor file blocks allocation strategy:
2526 Default. Preallocate donor's file on init.
2528 Allocate space immediately inside defragment event, and free right
2531 .. option:: clustername=str : [rbd,rados]
2533 Specifies the name of the Ceph cluster.
2535 .. option:: rbdname=str : [rbd]
2537 Specifies the name of the RBD.
2539 .. option:: clientname=str : [rbd,rados]
2541 Specifies the username (without the 'client.' prefix) used to access the
2542 Ceph cluster. If the *clustername* is specified, the *clientname* shall be
2543 the full *type.id* string. If no type. prefix is given, fio will add
2544 'client.' by default.
2546 .. option:: conf=str : [rados]
2548 Specifies the configuration path of ceph cluster, so conf file does not
2549 have to be /etc/ceph/ceph.conf.
2551 .. option:: busy_poll=bool : [rbd,rados]
2553 Poll store instead of waiting for completion. Usually this provides better
2554 throughput at cost of higher(up to 100%) CPU utilization.
2556 .. option:: touch_objects=bool : [rados]
2558 During initialization, touch (create if do not exist) all objects (files).
2559 Touching all objects affects ceph caches and likely impacts test results.
2562 .. option:: pool=str :
2566 Specifies the name of the Ceph pool containing RBD or RADOS data.
2570 Specify the label or UUID of the DAOS pool to connect to.
2572 .. option:: cont=str : [dfs]
2574 Specify the label or UUID of the DAOS container to open.
2576 .. option:: chunk_size=int
2580 Specify a different chunk size (in bytes) for the dfs file.
2581 Use DAOS container's chunk size by default.
2585 The size of the chunk to use for each file.
2587 .. option:: object_class=str : [dfs]
2589 Specify a different object class for the dfs file.
2590 Use DAOS container's object class by default.
2592 .. option:: skip_bad=bool : [mtd]
2594 Skip operations against known bad blocks.
2596 .. option:: hdfsdirectory : [libhdfs]
2598 libhdfs will create chunk in this HDFS directory.
2600 .. option:: verb=str : [rdma]
2602 The RDMA verb to use on this side of the RDMA ioengine connection. Valid
2603 values are write, read, send and recv. These correspond to the equivalent
2604 RDMA verbs (e.g. write = rdma_write etc.). Note that this only needs to be
2605 specified on the client side of the connection. See the examples folder.
2607 .. option:: bindname=str : [rdma]
2609 The name to use to bind the local RDMA-CM connection to a local RDMA device.
2610 This could be a hostname or an IPv4 or IPv6 address. On the server side this
2611 will be passed into the rdma_bind_addr() function and on the client site it
2612 will be used in the rdma_resolve_add() function. This can be useful when
2613 multiple paths exist between the client and the server or in certain loopback
2616 .. option:: stat_type=str : [filestat]
2618 Specify stat system call type to measure lookup/getattr performance.
2619 Default is **stat** for :manpage:`stat(2)`.
2621 .. option:: readfua=bool : [sg]
2623 With readfua option set to 1, read operations include
2624 the force unit access (fua) flag. Default is 0.
2626 .. option:: writefua=bool : [sg]
2628 With writefua option set to 1, write operations include
2629 the force unit access (fua) flag. Default is 0.
2631 .. option:: sg_write_mode=str : [sg]
2633 Specify the type of write commands to issue. This option can take three values:
2636 This is the default where write opcodes are issued as usual.
2637 **write_and_verify**
2638 Issue WRITE AND VERIFY commands. The BYTCHK bit is set to 0. This
2639 directs the device to carry out a medium verification with no data
2640 comparison. The writefua option is ignored with this selection.
2642 This option is deprecated. Use write_and_verify instead.
2644 Issue WRITE SAME commands. This transfers a single block to the device
2645 and writes this same block of data to a contiguous sequence of LBAs
2646 beginning at the specified offset. fio's block size parameter specifies
2647 the amount of data written with each command. However, the amount of data
2648 actually transferred to the device is equal to the device's block
2649 (sector) size. For a device with 512 byte sectors, blocksize=8k will
2650 write 16 sectors with each command. fio will still generate 8k of data
2651 for each command but only the first 512 bytes will be used and
2652 transferred to the device. The writefua option is ignored with this
2655 This option is deprecated. Use write_same instead.
2657 Issue WRITE SAME(16) commands as above but with the No Data Output
2658 Buffer (NDOB) bit set. No data will be transferred to the device with
2659 this bit set. Data written will be a pre-determined pattern such as
2662 Issue WRITE STREAM(16) commands. Use the **stream_id** option to specify
2663 the stream identifier.
2664 **verify_bytchk_00**
2665 Issue VERIFY commands with BYTCHK set to 00. This directs the
2666 device to carry out a medium verification with no data comparison.
2667 **verify_bytchk_01**
2668 Issue VERIFY commands with BYTCHK set to 01. This directs the device to
2669 compare the data on the device with the data transferred to the device.
2670 **verify_bytchk_11**
2671 Issue VERIFY commands with BYTCHK set to 11. This transfers a
2672 single block to the device and compares the contents of this block with the
2673 data on the device beginning at the specified offset. fio's block size
2674 parameter specifies the total amount of data compared with this command.
2675 However, only one block (sector) worth of data is transferred to the device.
2676 This is similar to the WRITE SAME command except that data is compared instead
2679 .. option:: stream_id=int : [sg]
2681 Set the stream identifier for WRITE STREAM commands. If this is set to 0 (which is not
2682 a valid stream identifier) fio will open a stream and then close it when done. Default
2685 .. option:: http_host=str : [http]
2687 Hostname to connect to. For S3, this could be the bucket hostname.
2688 Default is **localhost**
2690 .. option:: http_user=str : [http]
2692 Username for HTTP authentication.
2694 .. option:: http_pass=str : [http]
2696 Password for HTTP authentication.
2698 .. option:: https=str : [http]
2700 Enable HTTPS instead of http. *on* enables HTTPS; *insecure*
2701 will enable HTTPS, but disable SSL peer verification (use with
2702 caution!). Default is **off**
2704 .. option:: http_mode=str : [http]
2706 Which HTTP access mode to use: *webdav*, *swift*, or *s3*.
2707 Default is **webdav**
2709 .. option:: http_s3_region=str : [http]
2711 The S3 region/zone string.
2712 Default is **us-east-1**
2714 .. option:: http_s3_key=str : [http]
2718 .. option:: http_s3_keyid=str : [http]
2720 The S3 key/access id.
2722 .. option:: http_s3_sse_customer_key=str : [http]
2724 The encryption customer key in SSE server side.
2726 .. option:: http_s3_sse_customer_algorithm=str : [http]
2728 The encryption customer algorithm in SSE server side.
2729 Default is **AES256**
2731 .. option:: http_s3_storage_class=str : [http]
2733 Which storage class to access. User-customizable settings.
2734 Default is **STANDARD**
2736 .. option:: http_swift_auth_token=str : [http]
2738 The Swift auth token. See the example configuration file on how
2741 .. option:: http_verbose=int : [http]
2743 Enable verbose requests from libcurl. Useful for debugging. 1
2744 turns on verbose logging from libcurl, 2 additionally enables
2745 HTTP IO tracing. Default is **0**
2747 .. option:: uri=str : [nbd]
2749 Specify the NBD URI of the server to test. The string
2750 is a standard NBD URI
2751 (see https://github.com/NetworkBlockDevice/nbd/tree/master/doc).
2752 Example URIs: nbd://localhost:10809
2753 nbd+unix:///?socket=/tmp/socket
2754 nbds://tlshost/exportname
2756 .. option:: gpu_dev_ids=str : [libcufile]
2758 Specify the GPU IDs to use with CUDA. This is a colon-separated list of
2759 int. GPUs are assigned to workers roundrobin. Default is 0.
2761 .. option:: cuda_io=str : [libcufile]
2763 Specify the type of I/O to use with CUDA. Default is **cufile**.
2766 Use libcufile and nvidia-fs. This option performs I/O directly
2767 between a GPUDirect Storage filesystem and GPU buffers,
2768 avoiding use of a bounce buffer. If :option:`verify` is set,
2769 cudaMemcpy is used to copy verificaton data between RAM and GPU.
2770 Verification data is copied from RAM to GPU before a write
2771 and from GPU to RAM after a read. :option:`direct` must be 1.
2773 Use POSIX to perform I/O with a RAM buffer, and use cudaMemcpy
2774 to transfer data between RAM and the GPUs. Data is copied from
2775 GPU to RAM before a write and copied from RAM to GPU after a
2776 read. :option:`verify` does not affect use of cudaMemcpy.
2778 .. option:: nfs_url=str : [nfs]
2780 URL in libnfs format, eg nfs://<server|ipv4|ipv6>/path[?arg=val[&arg=val]*]
2781 Refer to the libnfs README for more details.
2783 .. option:: program=str : [exec]
2785 Specify the program to execute.
2787 .. option:: arguments=str : [exec]
2789 Specify arguments to pass to program.
2790 Some special variables can be expanded to pass fio's job details to the program.
2793 Replaced by the duration of the job in seconds.
2795 Replaced by the name of the job.
2797 .. option:: grace_time=int : [exec]
2799 Specify the time between the SIGTERM and SIGKILL signals. Default is 1 second.
2801 .. option:: std_redirect=bool : [exec]
2803 If set, stdout and stderr streams are redirected to files named from the job name. Default is true.
2805 .. option:: xnvme_async=str : [xnvme]
2807 Select the xnvme async command interface. This can take these values.
2810 This is default and use to emulate asynchronous I/O by using a
2811 single thread to create a queue pair on top of a synchronous
2812 I/O interface using the NVMe driver IOCTL.
2814 Emulate an asynchronous I/O interface with a pool of userspace
2815 threads on top of a synchronous I/O interface using the NVMe
2816 driver IOCTL. By default four threads are used.
2818 Linux native asynchronous I/O interface which supports both
2819 direct and buffered I/O.
2821 Fast Linux native asynchronous I/O interface for NVMe pass
2822 through commands. This only works with NVMe character device
2825 Use Linux aio for Asynchronous I/O.
2827 Use the posix asynchronous I/O interface to perform one or
2828 more I/O operations asynchronously.
2830 Do not transfer any data; just pretend to. This is mainly used
2831 for introspective performance evaluation.
2833 .. option:: xnvme_sync=str : [xnvme]
2835 Select the xnvme synchronous command interface. This can take these values.
2838 This is default and uses Linux NVMe Driver ioctl() for
2841 This supports regular as well as vectored pread() and pwrite()
2844 This is the same as psync except that it also supports zone
2845 management commands using Linux block layer IOCTLs.
2847 .. option:: xnvme_admin=str : [xnvme]
2849 Select the xnvme admin command interface. This can take these values.
2852 This is default and uses linux NVMe Driver ioctl() for admin
2855 Use Linux Block Layer ioctl() and sysfs for admin commands.
2857 .. option:: xnvme_dev_nsid=int : [xnvme]
2859 xnvme namespace identifier for userspace NVMe driver, such as SPDK.
2861 .. option:: xnvme_iovec=int : [xnvme]
2863 If this option is set. xnvme will use vectored read/write commands.
2865 .. option:: libblkio_driver=str : [libblkio]
2867 The libblkio *driver* to use. Different drivers access devices through
2868 different underlying interfaces. Available drivers depend on the
2869 libblkio version in use and are listed at
2870 https://libblkio.gitlab.io/libblkio/blkio.html#drivers
2872 .. option:: libblkio_pre_connect_props=str : [libblkio]
2874 A colon-separated list of libblkio properties to be set after creating
2875 but before connecting the libblkio instance. Each property must have the
2876 format ``<name>=<value>``. Colons can be escaped as ``\:``. These are
2877 set after the engine sets any other properties, so those can be
2878 overriden. Available properties depend on the libblkio version in use
2880 https://libblkio.gitlab.io/libblkio/blkio.html#properties
2882 .. option:: libblkio_pre_start_props=str : [libblkio]
2884 A colon-separated list of libblkio properties to be set after connecting
2885 but before starting the libblkio instance. Each property must have the
2886 format ``<name>=<value>``. Colons can be escaped as ``\:``. These are
2887 set after the engine sets any other properties, so those can be
2888 overriden. Available properties depend on the libblkio version in use
2890 https://libblkio.gitlab.io/libblkio/blkio.html#properties
2892 .. option:: libblkio_vectored : [libblkio]
2894 Submit vectored read and write requests.
2896 .. option:: libblkio_write_zeroes_on_trim : [libblkio]
2898 Submit trims as "write zeroes" requests instead of discard requests.
2900 .. option:: libblkio_wait_mode=str : [libblkio]
2902 How to wait for completions:
2905 Use a blocking call to ``blkioq_do_io()``.
2907 Use a blocking call to ``read()`` on the completion eventfd.
2909 Use a busy loop with a non-blocking call to ``blkioq_do_io()``.
2911 .. option:: libblkio_force_enable_completion_eventfd : [libblkio]
2913 Enable the queue's completion eventfd even when unused. This may impact
2914 performance. The default is to enable it only if
2915 :option:`libblkio_wait_mode=eventfd <libblkio_wait_mode>`.
2920 .. option:: iodepth=int
2922 Number of I/O units to keep in flight against the file. Note that
2923 increasing *iodepth* beyond 1 will not affect synchronous ioengines (except
2924 for small degrees when :option:`verify_async` is in use). Even async
2925 engines may impose OS restrictions causing the desired depth not to be
2926 achieved. This may happen on Linux when using libaio and not setting
2927 :option:`direct`\=1, since buffered I/O is not async on that OS. Keep an
2928 eye on the I/O depth distribution in the fio output to verify that the
2929 achieved depth is as expected. Default: 1.
2931 .. option:: iodepth_batch_submit=int, iodepth_batch=int
2933 This defines how many pieces of I/O to submit at once. It defaults to 1
2934 which means that we submit each I/O as soon as it is available, but can be
2935 raised to submit bigger batches of I/O at the time. If it is set to 0 the
2936 :option:`iodepth` value will be used.
2938 .. option:: iodepth_batch_complete_min=int, iodepth_batch_complete=int
2940 This defines how many pieces of I/O to retrieve at once. It defaults to 1
2941 which means that we'll ask for a minimum of 1 I/O in the retrieval process
2942 from the kernel. The I/O retrieval will go on until we hit the limit set by
2943 :option:`iodepth_low`. If this variable is set to 0, then fio will always
2944 check for completed events before queuing more I/O. This helps reduce I/O
2945 latency, at the cost of more retrieval system calls.
2947 .. option:: iodepth_batch_complete_max=int
2949 This defines maximum pieces of I/O to retrieve at once. This variable should
2950 be used along with :option:`iodepth_batch_complete_min`\=int variable,
2951 specifying the range of min and max amount of I/O which should be
2952 retrieved. By default it is equal to the :option:`iodepth_batch_complete_min`
2957 iodepth_batch_complete_min=1
2958 iodepth_batch_complete_max=<iodepth>
2960 which means that we will retrieve at least 1 I/O and up to the whole
2961 submitted queue depth. If none of I/O has been completed yet, we will wait.
2965 iodepth_batch_complete_min=0
2966 iodepth_batch_complete_max=<iodepth>
2968 which means that we can retrieve up to the whole submitted queue depth, but
2969 if none of I/O has been completed yet, we will NOT wait and immediately exit
2970 the system call. In this example we simply do polling.
2972 .. option:: iodepth_low=int
2974 The low water mark indicating when to start filling the queue
2975 again. Defaults to the same as :option:`iodepth`, meaning that fio will
2976 attempt to keep the queue full at all times. If :option:`iodepth` is set to
2977 e.g. 16 and *iodepth_low* is set to 4, then after fio has filled the queue of
2978 16 requests, it will let the depth drain down to 4 before starting to fill
2981 .. option:: serialize_overlap=bool
2983 Serialize in-flight I/Os that might otherwise cause or suffer from data races.
2984 When two or more I/Os are submitted simultaneously, there is no guarantee that
2985 the I/Os will be processed or completed in the submitted order. Further, if
2986 two or more of those I/Os are writes, any overlapping region between them can
2987 become indeterminate/undefined on certain storage. These issues can cause
2988 verification to fail erratically when at least one of the racing I/Os is
2989 changing data and the overlapping region has a non-zero size. Setting
2990 ``serialize_overlap`` tells fio to avoid provoking this behavior by explicitly
2991 serializing in-flight I/Os that have a non-zero overlap. Note that setting
2992 this option can reduce both performance and the :option:`iodepth` achieved.
2994 This option only applies to I/Os issued for a single job except when it is
2995 enabled along with :option:`io_submit_mode`\=offload. In offload mode, fio
2996 will check for overlap among all I/Os submitted by offload jobs with :option:`serialize_overlap`
3001 .. option:: io_submit_mode=str
3003 This option controls how fio submits the I/O to the I/O engine. The default
3004 is `inline`, which means that the fio job threads submit and reap I/O
3005 directly. If set to `offload`, the job threads will offload I/O submission
3006 to a dedicated pool of I/O threads. This requires some coordination and thus
3007 has a bit of extra overhead, especially for lower queue depth I/O where it
3008 can increase latencies. The benefit is that fio can manage submission rates
3009 independently of the device completion rates. This avoids skewed latency
3010 reporting if I/O gets backed up on the device side (the coordinated omission
3011 problem). Note that this option cannot reliably be used with async IO
3018 .. option:: thinktime=time
3020 Stall the job for the specified period of time after an I/O has completed before issuing the
3021 next. May be used to simulate processing being done by an application.
3022 When the unit is omitted, the value is interpreted in microseconds. See
3023 :option:`thinktime_blocks`, :option:`thinktime_iotime` and :option:`thinktime_spin`.
3025 .. option:: thinktime_spin=time
3027 Only valid if :option:`thinktime` is set - pretend to spend CPU time doing
3028 something with the data received, before falling back to sleeping for the
3029 rest of the period specified by :option:`thinktime`. When the unit is
3030 omitted, the value is interpreted in microseconds.
3032 .. option:: thinktime_blocks=int
3034 Only valid if :option:`thinktime` is set - control how many blocks to issue,
3035 before waiting :option:`thinktime` usecs. If not set, defaults to 1 which will make
3036 fio wait :option:`thinktime` usecs after every block. This effectively makes any
3037 queue depth setting redundant, since no more than 1 I/O will be queued
3038 before we have to complete it and do our :option:`thinktime`. In other words, this
3039 setting effectively caps the queue depth if the latter is larger.
3041 .. option:: thinktime_blocks_type=str
3043 Only valid if :option:`thinktime` is set - control how :option:`thinktime_blocks`
3044 triggers. The default is `complete`, which triggers thinktime when fio completes
3045 :option:`thinktime_blocks` blocks. If this is set to `issue`, then the trigger happens
3048 .. option:: thinktime_iotime=time
3050 Only valid if :option:`thinktime` is set - control :option:`thinktime`
3051 interval by time. The :option:`thinktime` stall is repeated after IOs
3052 are executed for :option:`thinktime_iotime`. For example,
3053 ``--thinktime_iotime=9s --thinktime=1s`` repeat 10-second cycle with IOs
3054 for 9 seconds and stall for 1 second. When the unit is omitted,
3055 :option:`thinktime_iotime` is interpreted as a number of seconds. If
3056 this option is used together with :option:`thinktime_blocks`, the
3057 :option:`thinktime` stall is repeated after :option:`thinktime_iotime`
3058 or after :option:`thinktime_blocks` IOs, whichever happens first.
3060 .. option:: rate=int[,int][,int]
3062 Cap the bandwidth used by this job. The number is in bytes/sec, the normal
3063 suffix rules apply. Comma-separated values may be specified for reads,
3064 writes, and trims as described in :option:`blocksize`.
3066 For example, using `rate=1m,500k` would limit reads to 1MiB/sec and writes to
3067 500KiB/sec. Capping only reads or writes can be done with `rate=,500k` or
3068 `rate=500k,` where the former will only limit writes (to 500KiB/sec) and the
3069 latter will only limit reads.
3071 .. option:: rate_min=int[,int][,int]
3073 Tell fio to do whatever it can to maintain at least this bandwidth. Failing
3074 to meet this requirement will cause the job to exit. Comma-separated values
3075 may be specified for reads, writes, and trims as described in
3076 :option:`blocksize`.
3078 .. option:: rate_iops=int[,int][,int]
3080 Cap the bandwidth to this number of IOPS. Basically the same as
3081 :option:`rate`, just specified independently of bandwidth. If the job is
3082 given a block size range instead of a fixed value, the smallest block size
3083 is used as the metric. Comma-separated values may be specified for reads,
3084 writes, and trims as described in :option:`blocksize`.
3086 .. option:: rate_iops_min=int[,int][,int]
3088 If fio doesn't meet this rate of I/O, it will cause the job to exit.
3089 Comma-separated values may be specified for reads, writes, and trims as
3090 described in :option:`blocksize`.
3092 .. option:: rate_process=str
3094 This option controls how fio manages rated I/O submissions. The default is
3095 `linear`, which submits I/O in a linear fashion with fixed delays between
3096 I/Os that gets adjusted based on I/O completion rates. If this is set to
3097 `poisson`, fio will submit I/O based on a more real world random request
3098 flow, known as the Poisson process
3099 (https://en.wikipedia.org/wiki/Poisson_point_process). The lambda will be
3100 10^6 / IOPS for the given workload.
3102 .. option:: rate_ignore_thinktime=bool
3104 By default, fio will attempt to catch up to the specified rate setting,
3105 if any kind of thinktime setting was used. If this option is set, then
3106 fio will ignore the thinktime and continue doing IO at the specified
3107 rate, instead of entering a catch-up mode after thinktime is done.
3113 .. option:: latency_target=time
3115 If set, fio will attempt to find the max performance point that the given
3116 workload will run at while maintaining a latency below this target. When
3117 the unit is omitted, the value is interpreted in microseconds. See
3118 :option:`latency_window` and :option:`latency_percentile`.
3120 .. option:: latency_window=time
3122 Used with :option:`latency_target` to specify the sample window that the job
3123 is run at varying queue depths to test the performance. When the unit is
3124 omitted, the value is interpreted in microseconds.
3126 .. option:: latency_percentile=float
3128 The percentage of I/Os that must fall within the criteria specified by
3129 :option:`latency_target` and :option:`latency_window`. If not set, this
3130 defaults to 100.0, meaning that all I/Os must be equal or below to the value
3131 set by :option:`latency_target`.
3133 .. option:: latency_run=bool
3135 Used with :option:`latency_target`. If false (default), fio will find
3136 the highest queue depth that meets :option:`latency_target` and exit. If
3137 true, fio will continue running and try to meet :option:`latency_target`
3138 by adjusting queue depth.
3140 .. option:: max_latency=time[,time][,time]
3142 If set, fio will exit the job with an ETIMEDOUT error if it exceeds this
3143 maximum latency. When the unit is omitted, the value is interpreted in
3144 microseconds. Comma-separated values may be specified for reads, writes,
3145 and trims as described in :option:`blocksize`.
3147 .. option:: rate_cycle=int
3149 Average bandwidth for :option:`rate` and :option:`rate_min` over this number
3150 of milliseconds. Defaults to 1000.
3156 .. option:: write_iolog=str
3158 Write the issued I/O patterns to the specified file. See
3159 :option:`read_iolog`. Specify a separate file for each job, otherwise the
3160 iologs will be interspersed and the file may be corrupt. This file will
3161 be opened in append mode.
3163 .. option:: read_iolog=str
3165 Open an iolog with the specified filename and replay the I/O patterns it
3166 contains. This can be used to store a workload and replay it sometime
3167 later. The iolog given may also be a blktrace binary file, which allows fio
3168 to replay a workload captured by :command:`blktrace`. See
3169 :manpage:`blktrace(8)` for how to capture such logging data. For blktrace
3170 replay, the file needs to be turned into a blkparse binary data file first
3171 (``blkparse <device> -o /dev/null -d file_for_fio.bin``).
3172 You can specify a number of files by separating the names with a ':'
3173 character. See the :option:`filename` option for information on how to
3174 escape ':' characters within the file names. These files will
3175 be sequentially assigned to job clones created by :option:`numjobs`.
3176 '-' is a reserved name, meaning read from stdin, notably if
3177 :option:`filename` is set to '-' which means stdin as well, then
3178 this flag can't be set to '-'.
3180 .. option:: read_iolog_chunked=bool
3182 Determines how iolog is read. If false(default) entire :option:`read_iolog`
3183 will be read at once. If selected true, input from iolog will be read
3184 gradually. Useful when iolog is very large, or it is generated.
3186 .. option:: merge_blktrace_file=str
3188 When specified, rather than replaying the logs passed to :option:`read_iolog`,
3189 the logs go through a merge phase which aggregates them into a single
3190 blktrace. The resulting file is then passed on as the :option:`read_iolog`
3191 parameter. The intention here is to make the order of events consistent.
3192 This limits the influence of the scheduler compared to replaying multiple
3193 blktraces via concurrent jobs.
3195 .. option:: merge_blktrace_scalars=float_list
3197 This is a percentage based option that is index paired with the list of
3198 files passed to :option:`read_iolog`. When merging is performed, scale
3199 the time of each event by the corresponding amount. For example,
3200 ``--merge_blktrace_scalars="50:100"`` runs the first trace in halftime
3201 and the second trace in realtime. This knob is separately tunable from
3202 :option:`replay_time_scale` which scales the trace during runtime and
3203 does not change the output of the merge unlike this option.
3205 .. option:: merge_blktrace_iters=float_list
3207 This is a whole number option that is index paired with the list of files
3208 passed to :option:`read_iolog`. When merging is performed, run each trace
3209 for the specified number of iterations. For example,
3210 ``--merge_blktrace_iters="2:1"`` runs the first trace for two iterations
3211 and the second trace for one iteration.
3213 .. option:: replay_no_stall=bool
3215 When replaying I/O with :option:`read_iolog` the default behavior is to
3216 attempt to respect the timestamps within the log and replay them with the
3217 appropriate delay between IOPS. By setting this variable fio will not
3218 respect the timestamps and attempt to replay them as fast as possible while
3219 still respecting ordering. The result is the same I/O pattern to a given
3220 device, but different timings.
3222 .. option:: replay_time_scale=int
3224 When replaying I/O with :option:`read_iolog`, fio will honor the
3225 original timing in the trace. With this option, it's possible to scale
3226 the time. It's a percentage option, if set to 50 it means run at 50%
3227 the original IO rate in the trace. If set to 200, run at twice the
3228 original IO rate. Defaults to 100.
3230 .. option:: replay_redirect=str
3232 While replaying I/O patterns using :option:`read_iolog` the default behavior
3233 is to replay the IOPS onto the major/minor device that each IOP was recorded
3234 from. This is sometimes undesirable because on a different machine those
3235 major/minor numbers can map to a different device. Changing hardware on the
3236 same system can also result in a different major/minor mapping.
3237 ``replay_redirect`` causes all I/Os to be replayed onto the single specified
3238 device regardless of the device it was recorded
3239 from. i.e. :option:`replay_redirect`\= :file:`/dev/sdc` would cause all I/O
3240 in the blktrace or iolog to be replayed onto :file:`/dev/sdc`. This means
3241 multiple devices will be replayed onto a single device, if the trace
3242 contains multiple devices. If you want multiple devices to be replayed
3243 concurrently to multiple redirected devices you must blkparse your trace
3244 into separate traces and replay them with independent fio invocations.
3245 Unfortunately this also breaks the strict time ordering between multiple
3248 .. option:: replay_align=int
3250 Force alignment of the byte offsets in a trace to this value. The value
3251 must be a power of 2.
3253 .. option:: replay_scale=int
3255 Scale byte offsets down by this factor when replaying traces. Should most
3256 likely use :option:`replay_align` as well.
3258 .. option:: replay_skip=str
3260 Sometimes it's useful to skip certain IO types in a replay trace.
3261 This could be, for instance, eliminating the writes in the trace.
3262 Or not replaying the trims/discards, if you are redirecting to
3263 a device that doesn't support them. This option takes a comma
3264 separated list of read, write, trim, sync.
3267 Threads, processes and job synchronization
3268 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
3272 Fio defaults to creating jobs by using fork, however if this option is
3273 given, fio will create jobs by using POSIX Threads' function
3274 :manpage:`pthread_create(3)` to create threads instead.
3276 .. option:: wait_for=str
3278 If set, the current job won't be started until all workers of the specified
3279 waitee job are done.
3281 ``wait_for`` operates on the job name basis, so there are a few
3282 limitations. First, the waitee must be defined prior to the waiter job
3283 (meaning no forward references). Second, if a job is being referenced as a
3284 waitee, it must have a unique name (no duplicate waitees).
3286 .. option:: nice=int
3288 Run the job with the given nice value. See man :manpage:`nice(2)`.
3290 On Windows, values less than -15 set the process class to "High"; -1 through
3291 -15 set "Above Normal"; 1 through 15 "Below Normal"; and above 15 "Idle"
3294 .. option:: prio=int
3296 Set the I/O priority value of this job. Linux limits us to a positive value
3297 between 0 and 7, with 0 being the highest. See man
3298 :manpage:`ionice(1)`. Refer to an appropriate manpage for other operating
3299 systems since meaning of priority may differ. For per-command priority
3300 setting, see I/O engine specific :option:`cmdprio_percentage` and
3301 :option:`cmdprio` options.
3303 .. option:: prioclass=int
3305 Set the I/O priority class. See man :manpage:`ionice(1)`. For per-command
3306 priority setting, see I/O engine specific :option:`cmdprio_percentage`
3307 and :option:`cmdprio_class` options.
3309 .. option:: cpus_allowed=str
3311 Controls the same options as :option:`cpumask`, but accepts a textual
3312 specification of the permitted CPUs instead and CPUs are indexed from 0. So
3313 to use CPUs 0 and 5 you would specify ``cpus_allowed=0,5``. This option also
3314 allows a range of CPUs to be specified -- say you wanted a binding to CPUs
3315 0, 5, and 8 to 15, you would set ``cpus_allowed=0,5,8-15``.
3317 On Windows, when ``cpus_allowed`` is unset only CPUs from fio's current
3318 processor group will be used and affinity settings are inherited from the
3319 system. An fio build configured to target Windows 7 makes options that set
3320 CPUs processor group aware and values will set both the processor group
3321 and a CPU from within that group. For example, on a system where processor
3322 group 0 has 40 CPUs and processor group 1 has 32 CPUs, ``cpus_allowed``
3323 values between 0 and 39 will bind CPUs from processor group 0 and
3324 ``cpus_allowed`` values between 40 and 71 will bind CPUs from processor
3325 group 1. When using ``cpus_allowed_policy=shared`` all CPUs specified by a
3326 single ``cpus_allowed`` option must be from the same processor group. For
3327 Windows fio builds not built for Windows 7, CPUs will only be selected from
3328 (and be relative to) whatever processor group fio happens to be running in
3329 and CPUs from other processor groups cannot be used.
3331 .. option:: cpus_allowed_policy=str
3333 Set the policy of how fio distributes the CPUs specified by
3334 :option:`cpus_allowed` or :option:`cpumask`. Two policies are supported:
3337 All jobs will share the CPU set specified.
3339 Each job will get a unique CPU from the CPU set.
3341 **shared** is the default behavior, if the option isn't specified. If
3342 **split** is specified, then fio will assign one cpu per job. If not
3343 enough CPUs are given for the jobs listed, then fio will roundrobin the CPUs
3346 .. option:: cpumask=int
3348 Set the CPU affinity of this job. The parameter given is a bit mask of
3349 allowed CPUs the job may run on. So if you want the allowed CPUs to be 1
3350 and 5, you would pass the decimal value of (1 << 1 | 1 << 5), or 34. See man
3351 :manpage:`sched_setaffinity(2)`. This may not work on all supported
3352 operating systems or kernel versions. This option doesn't work well for a
3353 higher CPU count than what you can store in an integer mask, so it can only
3354 control cpus 1-32. For boxes with larger CPU counts, use
3355 :option:`cpus_allowed`.
3357 .. option:: numa_cpu_nodes=str
3359 Set this job running on specified NUMA nodes' CPUs. The arguments allow
3360 comma delimited list of cpu numbers, A-B ranges, or `all`. Note, to enable
3361 NUMA options support, fio must be built on a system with libnuma-dev(el)
3364 .. option:: numa_mem_policy=str
3366 Set this job's memory policy and corresponding NUMA nodes. Format of the
3371 ``mode`` is one of the following memory policies: ``default``, ``prefer``,
3372 ``bind``, ``interleave`` or ``local``. For ``default`` and ``local`` memory
3373 policies, no node needs to be specified. For ``prefer``, only one node is
3374 allowed. For ``bind`` and ``interleave`` the ``nodelist`` may be as
3375 follows: a comma delimited list of numbers, A-B ranges, or `all`.
3377 .. option:: cgroup=str
3379 Add job to this control group. If it doesn't exist, it will be created. The
3380 system must have a mounted cgroup blkio mount point for this to work. If
3381 your system doesn't have it mounted, you can do so with::
3383 # mount -t cgroup -o blkio none /cgroup
3385 .. option:: cgroup_weight=int
3387 Set the weight of the cgroup to this value. See the documentation that comes
3388 with the kernel, allowed values are in the range of 100..1000.
3390 .. option:: cgroup_nodelete=bool
3392 Normally fio will delete the cgroups it has created after the job
3393 completion. To override this behavior and to leave cgroups around after the
3394 job completion, set ``cgroup_nodelete=1``. This can be useful if one wants
3395 to inspect various cgroup files after job completion. Default: false.
3397 .. option:: flow_id=int
3399 The ID of the flow. If not specified, it defaults to being a global
3400 flow. See :option:`flow`.
3402 .. option:: flow=int
3404 Weight in token-based flow control. If this value is used, then fio
3405 regulates the activity between two or more jobs sharing the same
3406 flow_id. Fio attempts to keep each job activity proportional to other
3407 jobs' activities in the same flow_id group, with respect to requested
3408 weight per job. That is, if one job has `flow=3', another job has
3409 `flow=2' and another with `flow=1`, then there will be a roughly 3:2:1
3410 ratio in how much one runs vs the others.
3412 .. option:: flow_sleep=int
3414 The period of time, in microseconds, to wait after the flow counter
3415 has exceeded its proportion before retrying operations.
3417 .. option:: stonewall, wait_for_previous
3419 Wait for preceding jobs in the job file to exit, before starting this
3420 one. Can be used to insert serialization points in the job file. A stone
3421 wall also implies starting a new reporting group, see
3422 :option:`group_reporting`.
3426 By default, fio will continue running all other jobs when one job finishes.
3427 Sometimes this is not the desired action. Setting ``exitall`` will instead
3428 make fio terminate all jobs in the same group, as soon as one job of that
3431 .. option:: exit_what=str
3433 By default, fio will continue running all other jobs when one job finishes.
3434 Sometimes this is not the desired action. Setting ``exitall`` will
3435 instead make fio terminate all jobs in the same group. The option
3436 ``exit_what`` allows to control which jobs get terminated when ``exitall`` is
3437 enabled. The default is ``group`` and does not change the behaviour of
3438 ``exitall``. The setting ``all`` terminates all jobs. The setting ``stonewall``
3439 terminates all currently running jobs across all groups and continues execution
3440 with the next stonewalled group.
3442 .. option:: exec_prerun=str
3444 Before running this job, issue the command specified through
3445 :manpage:`system(3)`. Output is redirected in a file called
3446 :file:`jobname.prerun.txt`.
3448 .. option:: exec_postrun=str
3450 After the job completes, issue the command specified though
3451 :manpage:`system(3)`. Output is redirected in a file called
3452 :file:`jobname.postrun.txt`.
3456 Instead of running as the invoking user, set the user ID to this value
3457 before the thread/process does any work.
3461 Set group ID, see :option:`uid`.
3467 .. option:: verify_only
3469 Do not perform specified workload, only verify data still matches previous
3470 invocation of this workload. This option allows one to check data multiple
3471 times at a later date without overwriting it. This option makes sense only
3472 for workloads that write data, and does not support workloads with the
3473 :option:`time_based` option set.
3475 .. option:: do_verify=bool
3477 Run the verify phase after a write phase. Only valid if :option:`verify` is
3480 .. option:: verify=str
3482 If writing to a file, fio can verify the file contents after each iteration
3483 of the job. Each verification method also implies verification of special
3484 header, which is written to the beginning of each block. This header also
3485 includes meta information, like offset of the block, block number, timestamp
3486 when block was written, etc. :option:`verify` can be combined with
3487 :option:`verify_pattern` option. The allowed values are:
3490 Use an md5 sum of the data area and store it in the header of
3494 Use an experimental crc64 sum of the data area and store it in the
3495 header of each block.
3498 Use a crc32c sum of the data area and store it in the header of
3499 each block. This will automatically use hardware acceleration
3500 (e.g. SSE4.2 on an x86 or CRC crypto extensions on ARM64) but will
3501 fall back to software crc32c if none is found. Generally the
3502 fastest checksum fio supports when hardware accelerated.
3508 Use a crc32 sum of the data area and store it in the header of each
3512 Use a crc16 sum of the data area and store it in the header of each
3516 Use a crc7 sum of the data area and store it in the header of each
3520 Use xxhash as the checksum function. Generally the fastest software
3521 checksum that fio supports.
3524 Use sha512 as the checksum function.
3527 Use sha256 as the checksum function.
3530 Use optimized sha1 as the checksum function.
3533 Use optimized sha3-224 as the checksum function.
3536 Use optimized sha3-256 as the checksum function.
3539 Use optimized sha3-384 as the checksum function.
3542 Use optimized sha3-512 as the checksum function.
3545 This option is deprecated, since now meta information is included in
3546 generic verification header and meta verification happens by
3547 default. For detailed information see the description of the
3548 :option:`verify` setting. This option is kept because of
3549 compatibility's sake with old configurations. Do not use it.
3552 Verify a strict pattern. Normally fio includes a header with some
3553 basic information and checksumming, but if this option is set, only
3554 the specific pattern set with :option:`verify_pattern` is verified.
3557 Only pretend to verify. Useful for testing internals with
3558 :option:`ioengine`\=null, not for much else.
3560 This option can be used for repeated burn-in tests of a system to make sure
3561 that the written data is also correctly read back. If the data direction
3562 given is a read or random read, fio will assume that it should verify a
3563 previously written file. If the data direction includes any form of write,
3564 the verify will be of the newly written data.
3566 To avoid false verification errors, do not use the norandommap option when
3567 verifying data with async I/O engines and I/O depths > 1. Or use the
3568 norandommap and the lfsr random generator together to avoid writing to the
3569 same offset with multiple outstanding I/Os.
3571 .. option:: verify_offset=int
3573 Swap the verification header with data somewhere else in the block before
3574 writing. It is swapped back before verifying.
3576 .. option:: verify_interval=int
3578 Write the verification header at a finer granularity than the
3579 :option:`blocksize`. It will be written for chunks the size of
3580 ``verify_interval``. :option:`blocksize` should divide this evenly.
3582 .. option:: verify_pattern=str
3584 If set, fio will fill the I/O buffers with this pattern. Fio defaults to
3585 filling with totally random bytes, but sometimes it's interesting to fill
3586 with a known pattern for I/O verification purposes. Depending on the width
3587 of the pattern, fio will fill 1/2/3/4 bytes of the buffer at the time (it can
3588 be either a decimal or a hex number). The ``verify_pattern`` if larger than
3589 a 32-bit quantity has to be a hex number that starts with either "0x" or
3590 "0X". Use with :option:`verify`. Also, ``verify_pattern`` supports %o
3591 format, which means that for each block offset will be written and then
3592 verified back, e.g.::
3596 Or use combination of everything::
3598 verify_pattern=0xff%o"abcd"-12
3600 .. option:: verify_fatal=bool
3602 Normally fio will keep checking the entire contents before quitting on a
3603 block verification failure. If this option is set, fio will exit the job on
3604 the first observed failure. Default: false.
3606 .. option:: verify_dump=bool
3608 If set, dump the contents of both the original data block and the data block
3609 we read off disk to files. This allows later analysis to inspect just what
3610 kind of data corruption occurred. Off by default.
3612 .. option:: verify_async=int
3614 Fio will normally verify I/O inline from the submitting thread. This option
3615 takes an integer describing how many async offload threads to create for I/O
3616 verification instead, causing fio to offload the duty of verifying I/O
3617 contents to one or more separate threads. If using this offload option, even
3618 sync I/O engines can benefit from using an :option:`iodepth` setting higher
3619 than 1, as it allows them to have I/O in flight while verifies are running.
3620 Defaults to 0 async threads, i.e. verification is not asynchronous.
3622 .. option:: verify_async_cpus=str
3624 Tell fio to set the given CPU affinity on the async I/O verification
3625 threads. See :option:`cpus_allowed` for the format used.
3627 .. option:: verify_backlog=int
3629 Fio will normally verify the written contents of a job that utilizes verify
3630 once that job has completed. In other words, everything is written then
3631 everything is read back and verified. You may want to verify continually
3632 instead for a variety of reasons. Fio stores the meta data associated with
3633 an I/O block in memory, so for large verify workloads, quite a bit of memory
3634 would be used up holding this meta data. If this option is enabled, fio will
3635 write only N blocks before verifying these blocks.
3637 .. option:: verify_backlog_batch=int
3639 Control how many blocks fio will verify if :option:`verify_backlog` is
3640 set. If not set, will default to the value of :option:`verify_backlog`
3641 (meaning the entire queue is read back and verified). If
3642 ``verify_backlog_batch`` is less than :option:`verify_backlog` then not all
3643 blocks will be verified, if ``verify_backlog_batch`` is larger than
3644 :option:`verify_backlog`, some blocks will be verified more than once.
3646 .. option:: verify_state_save=bool
3648 When a job exits during the write phase of a verify workload, save its
3649 current state. This allows fio to replay up until that point, if the verify
3650 state is loaded for the verify read phase. The format of the filename is,
3653 <type>-<jobname>-<jobindex>-verify.state.
3655 <type> is "local" for a local run, "sock" for a client/server socket
3656 connection, and "ip" (192.168.0.1, for instance) for a networked
3657 client/server connection. Defaults to true.
3659 .. option:: verify_state_load=bool
3661 If a verify termination trigger was used, fio stores the current write state
3662 of each thread. This can be used at verification time so that fio knows how
3663 far it should verify. Without this information, fio will run a full
3664 verification pass, according to the settings in the job file used. Default
3667 .. option:: trim_percentage=int
3669 Number of verify blocks to discard/trim.
3671 .. option:: trim_verify_zero=bool
3673 Verify that trim/discarded blocks are returned as zeros.
3675 .. option:: trim_backlog=int
3677 Trim after this number of blocks are written.
3679 .. option:: trim_backlog_batch=int
3681 Trim this number of I/O blocks.
3683 .. option:: experimental_verify=bool
3685 Enable experimental verification. Standard verify records I/O metadata
3686 for later use during the verification phase. Experimental verify
3687 instead resets the file after the write phase and then replays I/Os for
3688 the verification phase.
3693 .. option:: steadystate=str:float, ss=str:float
3695 Define the criterion and limit for assessing steady state performance. The
3696 first parameter designates the criterion whereas the second parameter sets
3697 the threshold. When the criterion falls below the threshold for the
3698 specified duration, the job will stop. For example, `iops_slope:0.1%` will
3699 direct fio to terminate the job when the least squares regression slope
3700 falls below 0.1% of the mean IOPS. If :option:`group_reporting` is enabled
3701 this will apply to all jobs in the group. Below is the list of available
3702 steady state assessment criteria. All assessments are carried out using only
3703 data from the rolling collection window. Threshold limits can be expressed
3704 as a fixed value or as a percentage of the mean in the collection window.
3706 When using this feature, most jobs should include the :option:`time_based`
3707 and :option:`runtime` options or the :option:`loops` option so that fio does not
3708 stop running after it has covered the full size of the specified file(s) or device(s).
3711 Collect IOPS data. Stop the job if all individual IOPS measurements
3712 are within the specified limit of the mean IOPS (e.g., ``iops:2``
3713 means that all individual IOPS values must be within 2 of the mean,
3714 whereas ``iops:0.2%`` means that all individual IOPS values must be
3715 within 0.2% of the mean IOPS to terminate the job).
3718 Collect IOPS data and calculate the least squares regression
3719 slope. Stop the job if the slope falls below the specified limit.
3722 Collect bandwidth data. Stop the job if all individual bandwidth
3723 measurements are within the specified limit of the mean bandwidth.
3726 Collect bandwidth data and calculate the least squares regression
3727 slope. Stop the job if the slope falls below the specified limit.
3729 .. option:: steadystate_duration=time, ss_dur=time
3731 A rolling window of this duration will be used to judge whether steady state
3732 has been reached. Data will be collected once per second. The default is 0
3733 which disables steady state detection. When the unit is omitted, the
3734 value is interpreted in seconds.
3736 .. option:: steadystate_ramp_time=time, ss_ramp=time
3738 Allow the job to run for the specified duration before beginning data
3739 collection for checking the steady state job termination criterion. The
3740 default is 0. When the unit is omitted, the value is interpreted in seconds.
3743 Measurements and reporting
3744 ~~~~~~~~~~~~~~~~~~~~~~~~~~
3746 .. option:: per_job_logs=bool
3748 If set, this generates bw/clat/iops log with per file private filenames. If
3749 not set, jobs with identical names will share the log filename. Default:
3752 .. option:: group_reporting
3754 It may sometimes be interesting to display statistics for groups of jobs as
3755 a whole instead of for each individual job. This is especially true if
3756 :option:`numjobs` is used; looking at individual thread/process output
3757 quickly becomes unwieldy. To see the final report per-group instead of
3758 per-job, use :option:`group_reporting`. Jobs in a file will be part of the
3759 same reporting group, unless if separated by a :option:`stonewall`, or by
3760 using :option:`new_group`.
3762 .. option:: new_group
3764 Start a new reporting group. See: :option:`group_reporting`. If not given,
3765 all jobs in a file will be part of the same reporting group, unless
3766 separated by a :option:`stonewall`.
3768 .. option:: stats=bool
3770 By default, fio collects and shows final output results for all jobs
3771 that run. If this option is set to 0, then fio will ignore it in
3772 the final stat output.
3774 .. option:: write_bw_log=str
3776 If given, write a bandwidth log for this job. Can be used to store data of
3777 the bandwidth of the jobs in their lifetime.
3779 If no str argument is given, the default filename of
3780 :file:`jobname_type.x.log` is used. Even when the argument is given, fio
3781 will still append the type of log. So if one specifies::
3785 The actual log name will be :file:`foo_bw.x.log` where `x` is the index
3786 of the job (`1..N`, where `N` is the number of jobs). If
3787 :option:`per_job_logs` is false, then the filename will not include the
3790 The included :command:`fio_generate_plots` script uses :command:`gnuplot` to turn these
3791 text files into nice graphs. See `Log File Formats`_ for how data is
3792 structured within the file.
3794 .. option:: write_lat_log=str
3796 Same as :option:`write_bw_log`, except this option creates I/O
3797 submission (e.g., :file:`name_slat.x.log`), completion (e.g.,
3798 :file:`name_clat.x.log`), and total (e.g., :file:`name_lat.x.log`)
3799 latency files instead. See :option:`write_bw_log` for details about
3800 the filename format and `Log File Formats`_ for how data is structured
3803 .. option:: write_hist_log=str
3805 Same as :option:`write_bw_log` but writes an I/O completion latency
3806 histogram file (e.g., :file:`name_hist.x.log`) instead. Note that this
3807 file will be empty unless :option:`log_hist_msec` has also been set.
3808 See :option:`write_bw_log` for details about the filename format and
3809 `Log File Formats`_ for how data is structured within the file.
3811 .. option:: write_iops_log=str
3813 Same as :option:`write_bw_log`, but writes an IOPS file (e.g.
3814 :file:`name_iops.x.log`) instead. Because fio defaults to individual
3815 I/O logging, the value entry in the IOPS log will be 1 unless windowed
3816 logging (see :option:`log_avg_msec`) has been enabled. See
3817 :option:`write_bw_log` for details about the filename format and `Log
3818 File Formats`_ for how data is structured within the file.
3820 .. option:: log_entries=int
3822 By default, fio will log an entry in the iops, latency, or bw log for
3823 every I/O that completes. The initial number of I/O log entries is 1024.
3824 When the log entries are all used, new log entries are dynamically
3825 allocated. This dynamic log entry allocation may negatively impact
3826 time-related statistics such as I/O tail latencies (e.g. 99.9th percentile
3827 completion latency). This option allows specifying a larger initial
3828 number of log entries to avoid run-time allocations of new log entries,
3829 resulting in more precise time-related I/O statistics.
3830 Also see :option:`log_avg_msec`. Defaults to 1024.
3832 .. option:: log_avg_msec=int
3834 By default, fio will log an entry in the iops, latency, or bw log for every
3835 I/O that completes. When writing to the disk log, that can quickly grow to a
3836 very large size. Setting this option makes fio average the each log entry
3837 over the specified period of time, reducing the resolution of the log. See
3838 :option:`log_max_value` as well. Defaults to 0, logging all entries.
3839 Also see `Log File Formats`_.
3841 .. option:: log_hist_msec=int
3843 Same as :option:`log_avg_msec`, but logs entries for completion latency
3844 histograms. Computing latency percentiles from averages of intervals using
3845 :option:`log_avg_msec` is inaccurate. Setting this option makes fio log
3846 histogram entries over the specified period of time, reducing log sizes for
3847 high IOPS devices while retaining percentile accuracy. See
3848 :option:`log_hist_coarseness` and :option:`write_hist_log` as well.
3849 Defaults to 0, meaning histogram logging is disabled.
3851 .. option:: log_hist_coarseness=int
3853 Integer ranging from 0 to 6, defining the coarseness of the resolution of
3854 the histogram logs enabled with :option:`log_hist_msec`. For each increment
3855 in coarseness, fio outputs half as many bins. Defaults to 0, for which
3856 histogram logs contain 1216 latency bins. See :option:`write_hist_log`
3857 and `Log File Formats`_.
3859 .. option:: log_max_value=bool
3861 If :option:`log_avg_msec` is set, fio logs the average over that window. If
3862 you instead want to log the maximum value, set this option to 1. Defaults to
3863 0, meaning that averaged values are logged.
3865 .. option:: log_offset=bool
3867 If this is set, the iolog options will include the byte offset for the I/O
3868 entry as well as the other data values. Defaults to 0 meaning that
3869 offsets are not present in logs. Also see `Log File Formats`_.
3871 .. option:: log_compression=int
3873 If this is set, fio will compress the I/O logs as it goes, to keep the
3874 memory footprint lower. When a log reaches the specified size, that chunk is
3875 removed and compressed in the background. Given that I/O logs are fairly
3876 highly compressible, this yields a nice memory savings for longer runs. The
3877 downside is that the compression will consume some background CPU cycles, so
3878 it may impact the run. This, however, is also true if the logging ends up
3879 consuming most of the system memory. So pick your poison. The I/O logs are
3880 saved normally at the end of a run, by decompressing the chunks and storing
3881 them in the specified log file. This feature depends on the availability of
3884 .. option:: log_compression_cpus=str
3886 Define the set of CPUs that are allowed to handle online log compression for
3887 the I/O jobs. This can provide better isolation between performance
3888 sensitive jobs, and background compression work. See
3889 :option:`cpus_allowed` for the format used.
3891 .. option:: log_store_compressed=bool
3893 If set, fio will store the log files in a compressed format. They can be
3894 decompressed with fio, using the :option:`--inflate-log` command line
3895 parameter. The files will be stored with a :file:`.fz` suffix.
3897 .. option:: log_unix_epoch=bool
3899 If set, fio will log Unix timestamps to the log files produced by enabling
3900 write_type_log for each log type, instead of the default zero-based
3903 .. option:: log_alternate_epoch=bool
3905 If set, fio will log timestamps based on the epoch used by the clock specified
3906 in the log_alternate_epoch_clock_id option, to the log files produced by
3907 enabling write_type_log for each log type, instead of the default zero-based
3910 .. option:: log_alternate_epoch_clock_id=int
3912 Specifies the clock_id to be used by clock_gettime to obtain the alternate epoch
3913 if either log_unix_epoch or log_alternate_epoch are true. Otherwise has no
3914 effect. Default value is 0, or CLOCK_REALTIME.
3916 .. option:: block_error_percentiles=bool
3918 If set, record errors in trim block-sized units from writes and trims and
3919 output a histogram of how many trims it took to get to errors, and what kind
3920 of error was encountered.
3922 .. option:: bwavgtime=int
3924 Average the calculated bandwidth over the given time. Value is specified in
3925 milliseconds. If the job also does bandwidth logging through
3926 :option:`write_bw_log`, then the minimum of this option and
3927 :option:`log_avg_msec` will be used. Default: 500ms.
3929 .. option:: iopsavgtime=int
3931 Average the calculated IOPS over the given time. Value is specified in
3932 milliseconds. If the job also does IOPS logging through
3933 :option:`write_iops_log`, then the minimum of this option and
3934 :option:`log_avg_msec` will be used. Default: 500ms.
3936 .. option:: disk_util=bool
3938 Generate disk utilization statistics, if the platform supports it.
3941 .. option:: disable_lat=bool
3943 Disable measurements of total latency numbers. Useful only for cutting back
3944 the number of calls to :manpage:`gettimeofday(2)`, as that does impact
3945 performance at really high IOPS rates. Note that to really get rid of a
3946 large amount of these calls, this option must be used with
3947 :option:`disable_slat` and :option:`disable_bw_measurement` as well.
3949 .. option:: disable_clat=bool
3951 Disable measurements of completion latency numbers. See
3952 :option:`disable_lat`.
3954 .. option:: disable_slat=bool
3956 Disable measurements of submission latency numbers. See
3957 :option:`disable_lat`.
3959 .. option:: disable_bw_measurement=bool, disable_bw=bool
3961 Disable measurements of throughput/bandwidth numbers. See
3962 :option:`disable_lat`.
3964 .. option:: slat_percentiles=bool
3966 Report submission latency percentiles. Submission latency is not recorded
3967 for synchronous ioengines.
3969 .. option:: clat_percentiles=bool
3971 Report completion latency percentiles.
3973 .. option:: lat_percentiles=bool
3975 Report total latency percentiles. Total latency is the sum of submission
3976 latency and completion latency.
3978 .. option:: percentile_list=float_list
3980 Overwrite the default list of percentiles for latencies and the block error
3981 histogram. Each number is a floating point number in the range (0,100], and
3982 the maximum length of the list is 20. Use ``:`` to separate the numbers. For
3983 example, ``--percentile_list=99.5:99.9`` will cause fio to report the
3984 latency durations below which 99.5% and 99.9% of the observed latencies fell,
3987 .. option:: significant_figures=int
3989 If using :option:`--output-format` of `normal`, set the significant
3990 figures to this value. Higher values will yield more precise IOPS and
3991 throughput units, while lower values will round. Requires a minimum
3992 value of 1 and a maximum value of 10. Defaults to 4.
3998 .. option:: exitall_on_error
4000 When one job finishes in error, terminate the rest. The default is to wait
4001 for each job to finish.
4003 .. option:: continue_on_error=str
4005 Normally fio will exit the job on the first observed failure. If this option
4006 is set, fio will continue the job when there is a 'non-fatal error' (EIO or
4007 EILSEQ) until the runtime is exceeded or the I/O size specified is
4008 completed. If this option is used, there are two more stats that are
4009 appended, the total error count and the first error. The error field given
4010 in the stats is the first error that was hit during the run.
4012 Note: a write error from the device may go unnoticed by fio when using
4013 buffered IO, as the write() (or similar) system call merely dirties the
4014 kernel pages, unless :option:`sync` or :option:`direct` is used. Device IO
4015 errors occur when the dirty data is actually written out to disk. If fully
4016 sync writes aren't desirable, :option:`fsync` or :option:`fdatasync` can be
4017 used as well. This is specific to writes, as reads are always synchronous.
4019 The allowed values are:
4022 Exit on any I/O or verify errors.
4025 Continue on read errors, exit on all others.
4028 Continue on write errors, exit on all others.
4031 Continue on any I/O error, exit on all others.
4034 Continue on verify errors, exit on all others.
4037 Continue on all errors.
4040 Backward-compatible alias for 'none'.
4043 Backward-compatible alias for 'all'.
4045 .. option:: ignore_error=str
4047 Sometimes you want to ignore some errors during test in that case you can
4048 specify error list for each error type, instead of only being able to
4049 ignore the default 'non-fatal error' using :option:`continue_on_error`.
4050 ``ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST`` errors for
4051 given error type is separated with ':'. Error may be symbol ('ENOSPC',
4052 'ENOMEM') or integer. Example::
4054 ignore_error=EAGAIN,ENOSPC:122
4056 This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from
4057 WRITE. This option works by overriding :option:`continue_on_error` with
4058 the list of errors for each error type if any.
4060 .. option:: error_dump=bool
4062 If set dump every error even if it is non fatal, true by default. If
4063 disabled only fatal error will be dumped.
4065 Running predefined workloads
4066 ----------------------------
4068 Fio includes predefined profiles that mimic the I/O workloads generated by
4071 .. option:: profile=str
4073 The predefined workload to run. Current profiles are:
4076 Threaded I/O bench (tiotest/tiobench) like workload.
4079 Aerospike Certification Tool (ACT) like workload.
4081 To view a profile's additional options use :option:`--cmdhelp` after specifying
4082 the profile. For example::
4084 $ fio --profile=act --cmdhelp
4089 .. option:: device-names=str
4094 .. option:: load=int
4097 ACT load multiplier. Default: 1.
4099 .. option:: test-duration=time
4102 How long the entire test takes to run. When the unit is omitted, the value
4103 is given in seconds. Default: 24h.
4105 .. option:: threads-per-queue=int
4108 Number of read I/O threads per device. Default: 8.
4110 .. option:: read-req-num-512-blocks=int
4113 Number of 512B blocks to read at the time. Default: 3.
4115 .. option:: large-block-op-kbytes=int
4118 Size of large block ops in KiB (writes). Default: 131072.
4123 Set to run ACT prep phase.
4125 Tiobench profile options
4126 ~~~~~~~~~~~~~~~~~~~~~~~~
4128 .. option:: size=str
4133 .. option:: block=int
4136 Block size in bytes. Default: 4096.
4138 .. option:: numruns=int
4148 .. option:: threads=int
4153 Interpreting the output
4154 -----------------------
4157 Example output was based on the following:
4158 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --time_based \
4159 --rate=1256k --bs=14K --name=quick --runtime=1s --name=mixed \
4160 --runtime=2m --rw=rw
4162 Fio spits out a lot of output. While running, fio will display the status of the
4163 jobs created. An example of that would be::
4165 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]
4167 The characters inside the first set of square brackets denote the current status of
4168 each thread. The first character is the first job defined in the job file, and so
4169 forth. The possible values (in typical life cycle order) are:
4171 +------+-----+-----------------------------------------------------------+
4173 +======+=====+===========================================================+
4174 | P | | Thread setup, but not started. |
4175 +------+-----+-----------------------------------------------------------+
4176 | C | | Thread created. |
4177 +------+-----+-----------------------------------------------------------+
4178 | I | | Thread initialized, waiting or generating necessary data. |
4179 +------+-----+-----------------------------------------------------------+
4180 | | p | Thread running pre-reading file(s). |
4181 +------+-----+-----------------------------------------------------------+
4182 | | / | Thread is in ramp period. |
4183 +------+-----+-----------------------------------------------------------+
4184 | | R | Running, doing sequential reads. |
4185 +------+-----+-----------------------------------------------------------+
4186 | | r | Running, doing random reads. |
4187 +------+-----+-----------------------------------------------------------+
4188 | | W | Running, doing sequential writes. |
4189 +------+-----+-----------------------------------------------------------+
4190 | | w | Running, doing random writes. |
4191 +------+-----+-----------------------------------------------------------+
4192 | | M | Running, doing mixed sequential reads/writes. |
4193 +------+-----+-----------------------------------------------------------+
4194 | | m | Running, doing mixed random reads/writes. |
4195 +------+-----+-----------------------------------------------------------+
4196 | | D | Running, doing sequential trims. |
4197 +------+-----+-----------------------------------------------------------+
4198 | | d | Running, doing random trims. |
4199 +------+-----+-----------------------------------------------------------+
4200 | | F | Running, currently waiting for :manpage:`fsync(2)`. |
4201 +------+-----+-----------------------------------------------------------+
4202 | | V | Running, doing verification of written data. |
4203 +------+-----+-----------------------------------------------------------+
4204 | f | | Thread finishing. |
4205 +------+-----+-----------------------------------------------------------+
4206 | E | | Thread exited, not reaped by main thread yet. |
4207 +------+-----+-----------------------------------------------------------+
4208 | _ | | Thread reaped. |
4209 +------+-----+-----------------------------------------------------------+
4210 | X | | Thread reaped, exited with an error. |
4211 +------+-----+-----------------------------------------------------------+
4212 | K | | Thread reaped, exited due to signal. |
4213 +------+-----+-----------------------------------------------------------+
4216 Example output was based on the following:
4217 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --runtime=58m \
4218 --time_based --rate=2512k --bs=256K --numjobs=10 \
4219 --name=readers --rw=read --name=writers --rw=write
4221 Fio will condense the thread string as not to take up more space on the command
4222 line than needed. For instance, if you have 10 readers and 10 writers running,
4223 the output would look like this::
4225 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]
4227 Note that the status string is displayed in order, so it's possible to tell which of
4228 the jobs are currently doing what. In the example above this means that jobs 1--10
4229 are readers and 11--20 are writers.
4231 The other values are fairly self explanatory -- number of threads currently
4232 running and doing I/O, the number of currently open files (f=), the estimated
4233 completion percentage, the rate of I/O since last check (read speed listed first,
4234 then write speed and optionally trim speed) in terms of bandwidth and IOPS,
4235 and time to completion for the current running group. It's impossible to estimate
4236 runtime of the following groups (if any).
4239 Example output was based on the following:
4240 TZ=UTC fio --iodepth=16 --ioengine=posixaio --filename=/tmp/fiofile \
4241 --direct=1 --size=100M --time_based --runtime=50s --rate_iops=89 \
4242 --bs=7K --name=Client1 --rw=write
4244 When fio is done (or interrupted by :kbd:`Ctrl-C`), it will show the data for
4245 each thread, group of threads, and disks in that order. For each overall thread (or
4246 group) the output looks like::
4248 Client1: (groupid=0, jobs=1): err= 0: pid=16109: Sat Jun 24 12:07:54 2017
4249 write: IOPS=88, BW=623KiB/s (638kB/s)(30.4MiB/50032msec)
4250 slat (nsec): min=500, max=145500, avg=8318.00, stdev=4781.50
4251 clat (usec): min=170, max=78367, avg=4019.02, stdev=8293.31
4252 lat (usec): min=174, max=78375, avg=4027.34, stdev=8291.79
4253 clat percentiles (usec):
4254 | 1.00th=[ 302], 5.00th=[ 326], 10.00th=[ 343], 20.00th=[ 363],
4255 | 30.00th=[ 392], 40.00th=[ 404], 50.00th=[ 416], 60.00th=[ 445],
4256 | 70.00th=[ 816], 80.00th=[ 6718], 90.00th=[12911], 95.00th=[21627],
4257 | 99.00th=[43779], 99.50th=[51643], 99.90th=[68682], 99.95th=[72877],
4259 bw ( KiB/s): min= 532, max= 686, per=0.10%, avg=622.87, stdev=24.82, samples= 100
4260 iops : min= 76, max= 98, avg=88.98, stdev= 3.54, samples= 100
4261 lat (usec) : 250=0.04%, 500=64.11%, 750=4.81%, 1000=2.79%
4262 lat (msec) : 2=4.16%, 4=1.84%, 10=4.90%, 20=11.33%, 50=5.37%
4263 lat (msec) : 100=0.65%
4264 cpu : usr=0.27%, sys=0.18%, ctx=12072, majf=0, minf=21
4265 IO depths : 1=85.0%, 2=13.1%, 4=1.8%, 8=0.1%, 16=0.0%, 32=0.0%, >=64=0.0%
4266 submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
4267 complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
4268 issued rwt: total=0,4450,0, short=0,0,0, dropped=0,0,0
4269 latency : target=0, window=0, percentile=100.00%, depth=8
4271 The job name (or first job's name when using :option:`group_reporting`) is printed,
4272 along with the group id, count of jobs being aggregated, last error id seen (which
4273 is 0 when there are no errors), pid/tid of that thread and the time the job/group
4274 completed. Below are the I/O statistics for each data direction performed (showing
4275 writes in the example above). In the order listed, they denote:
4278 The string before the colon shows the I/O direction the statistics
4279 are for. **IOPS** is the average I/Os performed per second. **BW**
4280 is the average bandwidth rate shown as: value in power of 2 format
4281 (value in power of 10 format). The last two values show: (**total
4282 I/O performed** in power of 2 format / **runtime** of that thread).
4285 Submission latency (**min** being the minimum, **max** being the
4286 maximum, **avg** being the average, **stdev** being the standard
4287 deviation). This is the time from when fio initialized the I/O
4288 to submission. For synchronous ioengines this includes the time
4289 up until just before the ioengine's queue function is called.
4290 For asynchronous ioengines this includes the time up through the
4291 completion of the ioengine's queue function (and commit function
4292 if it is defined). For sync I/O this row is not displayed as the
4293 slat is negligible. This value can be in nanoseconds,
4294 microseconds or milliseconds --- fio will choose the most
4295 appropriate base and print that (in the example above
4296 nanoseconds was the best scale). Note: in :option:`--minimal`
4297 mode latencies are always expressed in microseconds.
4300 Completion latency. Same names as slat, this denotes the time from
4301 submission to completion of the I/O pieces. For sync I/O, this
4302 represents the time from when the I/O was submitted to the
4303 operating system to when it was completed. For asynchronous
4304 ioengines this is the time from when the ioengine's queue (and
4305 commit if available) functions were completed to when the I/O's
4306 completion was reaped by fio.
4309 Total latency. Same names as slat and clat, this denotes the time from
4310 when fio created the I/O unit to completion of the I/O operation.
4311 It is the sum of submission and completion latency.
4314 Bandwidth statistics based on samples. Same names as the xlat stats,
4315 but also includes the number of samples taken (**samples**) and an
4316 approximate percentage of total aggregate bandwidth this thread
4317 received in its group (**per**). This last value is only really
4318 useful if the threads in this group are on the same disk, since they
4319 are then competing for disk access.
4322 IOPS statistics based on samples. Same names as bw.
4324 **lat (nsec/usec/msec)**
4325 The distribution of I/O completion latencies. This is the time from when
4326 I/O leaves fio and when it gets completed. Unlike the separate
4327 read/write/trim sections above, the data here and in the remaining
4328 sections apply to all I/Os for the reporting group. 250=0.04% means that
4329 0.04% of the I/Os completed in under 250us. 500=64.11% means that 64.11%
4330 of the I/Os required 250 to 499us for completion.
4333 CPU usage. User and system time, along with the number of context
4334 switches this thread went through, usage of system and user time, and
4335 finally the number of major and minor page faults. The CPU utilization
4336 numbers are averages for the jobs in that reporting group, while the
4337 context and fault counters are summed.
4340 The distribution of I/O depths over the job lifetime. The numbers are
4341 divided into powers of 2 and each entry covers depths from that value
4342 up to those that are lower than the next entry -- e.g., 16= covers
4343 depths from 16 to 31. Note that the range covered by a depth
4344 distribution entry can be different to the range covered by the
4345 equivalent submit/complete distribution entry.
4348 How many pieces of I/O were submitting in a single submit call. Each
4349 entry denotes that amount and below, until the previous entry -- e.g.,
4350 16=100% means that we submitted anywhere between 9 to 16 I/Os per submit
4351 call. Note that the range covered by a submit distribution entry can
4352 be different to the range covered by the equivalent depth distribution
4356 Like the above submit number, but for completions instead.
4359 The number of read/write/trim requests issued, and how many of them were
4363 These values are for :option:`latency_target` and related options. When
4364 these options are engaged, this section describes the I/O depth required
4365 to meet the specified latency target.
4368 Example output was based on the following:
4369 TZ=UTC fio --ioengine=null --iodepth=2 --size=100M --numjobs=2 \
4370 --rate_process=poisson --io_limit=32M --name=read --bs=128k \
4371 --rate=11M --name=write --rw=write --bs=2k --rate=700k
4373 After each client has been listed, the group statistics are printed. They
4374 will look like this::
4376 Run status group 0 (all jobs):
4377 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
4378 WRITE: bw=1231KiB/s (1261kB/s), 616KiB/s-621KiB/s (630kB/s-636kB/s), io=64.0MiB (67.1MB), run=52747-53223msec
4380 For each data direction it prints:
4383 Aggregate bandwidth of threads in this group followed by the
4384 minimum and maximum bandwidth of all the threads in this group.
4385 Values outside of brackets are power-of-2 format and those
4386 within are the equivalent value in a power-of-10 format.
4388 Aggregate I/O performed of all threads in this group. The
4389 format is the same as bw.
4391 The smallest and longest runtimes of the threads in this group.
4393 And finally, the disk statistics are printed. This is Linux specific. They will look like this::
4395 Disk stats (read/write):
4396 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
4398 Each value is printed for both reads and writes, with reads first. The
4402 Number of I/Os performed by all groups.
4404 Number of merges performed by the I/O scheduler.
4406 Number of ticks we kept the disk busy.
4408 Total time spent in the disk queue.
4410 The disk utilization. A value of 100% means we kept the disk
4411 busy constantly, 50% would be a disk idling half of the time.
4413 It is also possible to get fio to dump the current output while it is running,
4414 without terminating the job. To do that, send fio the **USR1** signal. You can
4415 also get regularly timed dumps by using the :option:`--status-interval`
4416 parameter, or by creating a file in :file:`/tmp` named
4417 :file:`fio-dump-status`. If fio sees this file, it will unlink it and dump the
4418 current output status.
4424 For scripted usage where you typically want to generate tables or graphs of the
4425 results, fio can output the results in a semicolon separated format. The format
4426 is one long line of values, such as::
4428 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%
4429 A description of this job goes here.
4431 The job description (if provided) follows on a second line for terse v2.
4432 It appears on the same line for other terse versions.
4434 To enable terse output, use the :option:`--minimal` or
4435 :option:`--output-format`\=terse command line options. The
4436 first value is the version of the terse output format. If the output has to be
4437 changed for some reason, this number will be incremented by 1 to signify that
4440 Split up, the format is as follows (comments in brackets denote when a
4441 field was introduced or whether it's specific to some terse version):
4445 terse version, fio version [v3], jobname, groupid, error
4449 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
4450 Submission latency: min, max, mean, stdev (usec)
4451 Completion latency: min, max, mean, stdev (usec)
4452 Completion latency percentiles: 20 fields (see below)
4453 Total latency: min, max, mean, stdev (usec)
4454 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
4455 IOPS [v5]: min, max, mean, stdev, number of samples
4461 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
4462 Submission latency: min, max, mean, stdev (usec)
4463 Completion latency: min, max, mean, stdev (usec)
4464 Completion latency percentiles: 20 fields (see below)
4465 Total latency: min, max, mean, stdev (usec)
4466 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
4467 IOPS [v5]: min, max, mean, stdev, number of samples
4469 TRIM status [all but version 3]:
4471 Fields are similar to READ/WRITE status.
4475 user, system, context switches, major faults, minor faults
4479 <=1, 2, 4, 8, 16, 32, >=64
4481 I/O latencies microseconds::
4483 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000
4485 I/O latencies milliseconds::
4487 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000
4489 Disk utilization [v3]::
4491 disk name, read ios, write ios, read merges, write merges, read ticks, write ticks,
4492 time spent in queue, disk utilization percentage
4494 Additional Info (dependent on continue_on_error, default off)::
4496 total # errors, first error code
4498 Additional Info (dependent on description being set)::
4502 Completion latency percentiles can be a grouping of up to 20 sets, so for the
4503 terse output fio writes all of them. Each field will look like this::
4507 which is the Xth percentile, and the `usec` latency associated with it.
4509 For `Disk utilization`, all disks used by fio are shown. So for each disk there
4510 will be a disk utilization section.
4512 Below is a single line containing short names for each of the fields in the
4513 minimal output v3, separated by semicolons::
4515 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
4517 In client/server mode terse output differs from what appears when jobs are run
4518 locally. Disk utilization data is omitted from the standard terse output and
4519 for v3 and later appears on its own separate line at the end of each terse
4526 The `json` output format is intended to be both human readable and convenient
4527 for automated parsing. For the most part its sections mirror those of the
4528 `normal` output. The `runtime` value is reported in msec and the `bw` value is
4529 reported in 1024 bytes per second units.
4535 The `json+` output format is identical to the `json` output format except that it
4536 adds a full dump of the completion latency bins. Each `bins` object contains a
4537 set of (key, value) pairs where keys are latency durations and values count how
4538 many I/Os had completion latencies of the corresponding duration. For example,
4541 "bins" : { "87552" : 1, "89600" : 1, "94720" : 1, "96768" : 1, "97792" : 1, "99840" : 1, "100864" : 2, "103936" : 6, "104960" : 534, "105984" : 5995, "107008" : 7529, ... }
4543 This data indicates that one I/O required 87,552ns to complete, two I/Os required
4544 100,864ns to complete, and 7529 I/Os required 107,008ns to complete.
4546 Also included with fio is a Python script `fio_jsonplus_clat2csv` that takes
4547 json+ output and generates CSV-formatted latency data suitable for plotting.
4549 The latency durations actually represent the midpoints of latency intervals.
4550 For details refer to :file:`stat.h`.
4556 There are two trace file format that you can encounter. The older (v1) format is
4557 unsupported since version 1.20-rc3 (March 2008). It will still be described
4558 below in case that you get an old trace and want to understand it.
4560 In any case the trace is a simple text file with a single action per line.
4563 Trace file format v1
4564 ~~~~~~~~~~~~~~~~~~~~
4566 Each line represents a single I/O action in the following format::
4570 where `rw=0/1` for read/write, and the `offset` and `length` entries being in bytes.
4572 This format is not supported in fio versions >= 1.20-rc3.
4575 Trace file format v2
4576 ~~~~~~~~~~~~~~~~~~~~
4578 The second version of the trace file format was added in fio version 1.17. It
4579 allows one to access more than one file per trace and has a bigger set of possible
4582 The first line of the trace file has to be::
4586 Following this can be lines in two different formats, which are described below.
4588 The file management format::
4592 The `filename` is given as an absolute path. The `action` can be one of these:
4595 Add the given `filename` to the trace.
4597 Open the file with the given `filename`. The `filename` has to have
4598 been added with the **add** action before.
4600 Close the file with the given `filename`. The file has to have been
4604 The file I/O action format::
4606 filename action offset length
4608 The `filename` is given as an absolute path, and has to have been added and
4609 opened before it can be used with this format. The `offset` and `length` are
4610 given in bytes. The `action` can be one of these:
4613 Wait for `offset` microseconds. Everything below 100 is discarded.
4614 The time is relative to the previous `wait` statement. Note that
4615 action `wait` is not allowed as of version 3, as the same behavior
4616 can be achieved using timestamps.
4618 Read `length` bytes beginning from `offset`.
4620 Write `length` bytes beginning from `offset`.
4622 :manpage:`fsync(2)` the file.
4624 :manpage:`fdatasync(2)` the file.
4626 Trim the given file from the given `offset` for `length` bytes.
4629 Trace file format v3
4630 ~~~~~~~~~~~~~~~~~~~~
4632 The third version of the trace file format was added in fio version 3.31. It
4633 forces each action to have a timestamp associated with it.
4635 The first line of the trace file has to be::
4639 Following this can be lines in two different formats, which are described below.
4641 The file management format::
4643 timestamp filename action
4645 The file I/O action format::
4647 timestamp filename action offset length
4649 The `timestamp` is relative to the beginning of the run (ie starts at 0). The
4650 `filename`, `action`, `offset` and `length` are identical to version 2, except
4651 that version 3 does not allow the `wait` action.
4654 I/O Replay - Merging Traces
4655 ---------------------------
4657 Colocation is a common practice used to get the most out of a machine.
4658 Knowing which workloads play nicely with each other and which ones don't is
4659 a much harder task. While fio can replay workloads concurrently via multiple
4660 jobs, it leaves some variability up to the scheduler making results harder to
4661 reproduce. Merging is a way to make the order of events consistent.
4663 Merging is integrated into I/O replay and done when a
4664 :option:`merge_blktrace_file` is specified. The list of files passed to
4665 :option:`read_iolog` go through the merge process and output a single file
4666 stored to the specified file. The output file is passed on as if it were the
4667 only file passed to :option:`read_iolog`. An example would look like::
4669 $ fio --read_iolog="<file1>:<file2>" --merge_blktrace_file="<output_file>"
4671 Creating only the merged file can be done by passing the command line argument
4672 :option:`--merge-blktrace-only`.
4674 Scaling traces can be done to see the relative impact of any particular trace
4675 being slowed down or sped up. :option:`merge_blktrace_scalars` takes in a colon
4676 separated list of percentage scalars. It is index paired with the files passed
4677 to :option:`read_iolog`.
4679 With scaling, it may be desirable to match the running time of all traces.
4680 This can be done with :option:`merge_blktrace_iters`. It is index paired with
4681 :option:`read_iolog` just like :option:`merge_blktrace_scalars`.
4683 In an example, given two traces, A and B, each 60s long. If we want to see
4684 the impact of trace A issuing IOs twice as fast and repeat trace A over the
4685 runtime of trace B, the following can be done::
4687 $ fio --read_iolog="<trace_a>:"<trace_b>" --merge_blktrace_file"<output_file>" --merge_blktrace_scalars="50:100" --merge_blktrace_iters="2:1"
4689 This runs trace A at 2x the speed twice for approximately the same runtime as
4690 a single run of trace B.
4693 CPU idleness profiling
4694 ----------------------
4696 In some cases, we want to understand CPU overhead in a test. For example, we
4697 test patches for the specific goodness of whether they reduce CPU usage.
4698 Fio implements a balloon approach to create a thread per CPU that runs at idle
4699 priority, meaning that it only runs when nobody else needs the cpu.
4700 By measuring the amount of work completed by the thread, idleness of each CPU
4701 can be derived accordingly.
4703 An unit work is defined as touching a full page of unsigned characters. Mean and
4704 standard deviation of time to complete an unit work is reported in "unit work"
4705 section. Options can be chosen to report detailed percpu idleness or overall
4706 system idleness by aggregating percpu stats.
4709 Verification and triggers
4710 -------------------------
4712 Fio is usually run in one of two ways, when data verification is done. The first
4713 is a normal write job of some sort with verify enabled. When the write phase has
4714 completed, fio switches to reads and verifies everything it wrote. The second
4715 model is running just the write phase, and then later on running the same job
4716 (but with reads instead of writes) to repeat the same I/O patterns and verify
4717 the contents. Both of these methods depend on the write phase being completed,
4718 as fio otherwise has no idea how much data was written.
4720 With verification triggers, fio supports dumping the current write state to
4721 local files. Then a subsequent read verify workload can load this state and know
4722 exactly where to stop. This is useful for testing cases where power is cut to a
4723 server in a managed fashion, for instance.
4725 A verification trigger consists of two things:
4727 1) Storing the write state of each job.
4728 2) Executing a trigger command.
4730 The write state is relatively small, on the order of hundreds of bytes to single
4731 kilobytes. It contains information on the number of completions done, the last X
4734 A trigger is invoked either through creation ('touch') of a specified file in
4735 the system, or through a timeout setting. If fio is run with
4736 :option:`--trigger-file`\= :file:`/tmp/trigger-file`, then it will continually
4737 check for the existence of :file:`/tmp/trigger-file`. When it sees this file, it
4738 will fire off the trigger (thus saving state, and executing the trigger
4741 For client/server runs, there's both a local and remote trigger. If fio is
4742 running as a server backend, it will send the job states back to the client for
4743 safe storage, then execute the remote trigger, if specified. If a local trigger
4744 is specified, the server will still send back the write state, but the client
4745 will then execute the trigger.
4747 Verification trigger example
4748 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
4750 Let's say we want to run a powercut test on the remote Linux machine 'server'.
4751 Our write workload is in :file:`write-test.fio`. We want to cut power to 'server' at
4752 some point during the run, and we'll run this test from the safety or our local
4753 machine, 'localbox'. On the server, we'll start the fio backend normally::
4755 server# fio --server
4757 and on the client, we'll fire off the workload::
4759 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger-remote="bash -c \"echo b > /proc/sysrq-triger\""
4761 We set :file:`/tmp/my-trigger` as the trigger file, and we tell fio to execute::
4763 echo b > /proc/sysrq-trigger
4765 on the server once it has received the trigger and sent us the write state. This
4766 will work, but it's not **really** cutting power to the server, it's merely
4767 abruptly rebooting it. If we have a remote way of cutting power to the server
4768 through IPMI or similar, we could do that through a local trigger command
4769 instead. Let's assume we have a script that does IPMI reboot of a given hostname,
4770 ipmi-reboot. On localbox, we could then have run fio with a local trigger
4773 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger="ipmi-reboot server"
4775 For this case, fio would wait for the server to send us the write state, then
4776 execute ``ipmi-reboot server`` when that happened.
4778 Loading verify state
4779 ~~~~~~~~~~~~~~~~~~~~
4781 To load stored write state, a read verification job file must contain the
4782 :option:`verify_state_load` option. If that is set, fio will load the previously
4783 stored state. For a local fio run this is done by loading the files directly,
4784 and on a client/server run, the server backend will ask the client to send the
4785 files over and load them from there.
4791 Fio supports a variety of log file formats, for logging latencies, bandwidth,
4792 and IOPS. The logs share a common format, which looks like this:
4794 *time* (`msec`), *value*, *data direction*, *block size* (`bytes`),
4795 *offset* (`bytes`), *command priority*
4797 *Time* for the log entry is always in milliseconds. The *value* logged depends
4798 on the type of log, it will be one of the following:
4801 Value is latency in nsecs
4807 *Data direction* is one of the following:
4816 The entry's *block size* is always in bytes. The *offset* is the position in bytes
4817 from the start of the file for that particular I/O. The logging of the offset can be
4818 toggled with :option:`log_offset`.
4820 *Command priority* is 0 for normal priority and 1 for high priority. This is controlled
4821 by the ioengine specific :option:`cmdprio_percentage`.
4823 Fio defaults to logging every individual I/O but when windowed logging is set
4824 through :option:`log_avg_msec`, either the average (by default) or the maximum
4825 (:option:`log_max_value` is set) *value* seen over the specified period of time
4826 is recorded. Each *data direction* seen within the window period will aggregate
4827 its values in a separate row. Further, when using windowed logging the *block
4828 size* and *offset* entries will always contain 0.
4834 Normally fio is invoked as a stand-alone application on the machine where the
4835 I/O workload should be generated. However, the backend and frontend of fio can
4836 be run separately i.e., the fio server can generate an I/O workload on the "Device
4837 Under Test" while being controlled by a client on another machine.
4839 Start the server on the machine which has access to the storage DUT::
4843 where `args` defines what fio listens to. The arguments are of the form
4844 ``type,hostname`` or ``IP,port``. *type* is either ``ip`` (or ip4) for TCP/IP
4845 v4, ``ip6`` for TCP/IP v6, or ``sock`` for a local unix domain socket.
4846 *hostname* is either a hostname or IP address, and *port* is the port to listen
4847 to (only valid for TCP/IP, not a local socket). Some examples:
4851 Start a fio server, listening on all interfaces on the default port (8765).
4853 2) ``fio --server=ip:hostname,4444``
4855 Start a fio server, listening on IP belonging to hostname and on port 4444.
4857 3) ``fio --server=ip6:::1,4444``
4859 Start a fio server, listening on IPv6 localhost ::1 and on port 4444.
4861 4) ``fio --server=,4444``
4863 Start a fio server, listening on all interfaces on port 4444.
4865 5) ``fio --server=1.2.3.4``
4867 Start a fio server, listening on IP 1.2.3.4 on the default port.
4869 6) ``fio --server=sock:/tmp/fio.sock``
4871 Start a fio server, listening on the local socket :file:`/tmp/fio.sock`.
4873 Once a server is running, a "client" can connect to the fio server with::
4875 fio <local-args> --client=<server> <remote-args> <job file(s)>
4877 where `local-args` are arguments for the client where it is running, `server`
4878 is the connect string, and `remote-args` and `job file(s)` are sent to the
4879 server. The `server` string follows the same format as it does on the server
4880 side, to allow IP/hostname/socket and port strings.
4882 Fio can connect to multiple servers this way::
4884 fio --client=<server1> <job file(s)> --client=<server2> <job file(s)>
4886 If the job file is located on the fio server, then you can tell the server to
4887 load a local file as well. This is done by using :option:`--remote-config` ::
4889 fio --client=server --remote-config /path/to/file.fio
4891 Then fio will open this local (to the server) job file instead of being passed
4892 one from the client.
4894 If you have many servers (example: 100 VMs/containers), you can input a pathname
4895 of a file containing host IPs/names as the parameter value for the
4896 :option:`--client` option. For example, here is an example :file:`host.list`
4897 file containing 2 hostnames::
4899 host1.your.dns.domain
4900 host2.your.dns.domain
4902 The fio command would then be::
4904 fio --client=host.list <job file(s)>
4906 In this mode, you cannot input server-specific parameters or job files -- all
4907 servers receive the same job file.
4909 In order to let ``fio --client`` runs use a shared filesystem from multiple
4910 hosts, ``fio --client`` now prepends the IP address of the server to the
4911 filename. For example, if fio is using the directory :file:`/mnt/nfs/fio` and is
4912 writing filename :file:`fileio.tmp`, with a :option:`--client` `hostfile`
4913 containing two hostnames ``h1`` and ``h2`` with IP addresses 192.168.10.120 and
4914 192.168.10.121, then fio will create two files::
4916 /mnt/nfs/fio/192.168.10.120.fileio.tmp
4917 /mnt/nfs/fio/192.168.10.121.fileio.tmp
4919 Terse output in client/server mode will differ slightly from what is produced
4920 when fio is run in stand-alone mode. See the terse output section for details.