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 Show available debug options.
99 .. option:: --parse-only
101 Parse options only, don't start any I/O.
103 .. option:: --output=filename
105 Write output to file `filename`.
107 .. option:: --output-format=format
109 Set the reporting `format` to `normal`, `terse`, `json`, or `json+`. Multiple
110 formats can be selected, separated by a comma. `terse` is a CSV based
111 format. `json+` is like `json`, except it adds a full dump of the latency
114 .. option:: --bandwidth-log
116 Generate aggregate bandwidth logs.
118 .. option:: --minimal
120 Print statistics in a terse, semicolon-delimited format.
122 .. option:: --append-terse
124 Print statistics in selected mode AND terse, semicolon-delimited format.
125 **Deprecated**, use :option:`--output-format` instead to select multiple
128 .. option:: --terse-version=version
130 Set terse `version` output format (default 3, or 2 or 4 or 5).
132 .. option:: --version
134 Print version information and exit.
138 Print a summary of the command line options and exit.
140 .. option:: --cpuclock-test
142 Perform test and validation of internal CPU clock.
144 .. option:: --crctest=[test]
146 Test the speed of the built-in checksumming functions. If no argument is
147 given, all of them are tested. Alternatively, a comma separated list can
148 be passed, in which case the given ones are tested.
150 .. option:: --cmdhelp=command
152 Print help information for `command`. May be ``all`` for all commands.
154 .. option:: --enghelp=[ioengine[,command]]
156 List all commands defined by `ioengine`, or print help for `command`
157 defined by `ioengine`. If no `ioengine` is given, list all
160 .. option:: --showcmd=jobfile
162 Convert `jobfile` to a set of command-line options.
164 .. option:: --readonly
166 Turn on safety read-only checks, preventing writes. The ``--readonly``
167 option is an extra safety guard to prevent users from accidentally starting
168 a write workload when that is not desired. Fio will only write if
169 `rw=write/randwrite/rw/randrw` is given. This extra safety net can be used
170 as an extra precaution as ``--readonly`` will also enable a write check in
171 the I/O engine core to prevent writes due to unknown user space bug(s).
173 .. option:: --eta=when
175 Specifies when real-time ETA estimate should be printed. `when` may be
176 `always`, `never` or `auto`.
178 .. option:: --eta-newline=time
180 Force a new line for every `time` period passed. When the unit is omitted,
181 the value is interpreted in seconds.
183 .. option:: --status-interval=time
185 Force a full status dump of cumulative (from job start) values at `time`
186 intervals. This option does *not* provide per-period measurements. So
187 values such as bandwidth are running averages. When the time unit is omitted,
188 `time` is interpreted in seconds.
190 .. option:: --section=name
192 Only run specified section `name` in job file. Multiple sections can be specified.
193 The ``--section`` option allows one to combine related jobs into one file.
194 E.g. one job file could define light, moderate, and heavy sections. Tell
195 fio to run only the "heavy" section by giving ``--section=heavy``
196 command line option. One can also specify the "write" operations in one
197 section and "verify" operation in another section. The ``--section`` option
198 only applies to job sections. The reserved *global* section is always
201 .. option:: --alloc-size=kb
203 Set the internal smalloc pool size to `kb` in KiB. The
204 ``--alloc-size`` switch allows one to use a larger pool size for smalloc.
205 If running large jobs with randommap enabled, fio can run out of memory.
206 Smalloc is an internal allocator for shared structures from a fixed size
207 memory pool and can grow to 16 pools. The pool size defaults to 16MiB.
209 NOTE: While running :file:`.fio_smalloc.*` backing store files are visible
212 .. option:: --warnings-fatal
214 All fio parser warnings are fatal, causing fio to exit with an
217 .. option:: --max-jobs=nr
219 Set the maximum number of threads/processes to support to `nr`.
220 NOTE: On Linux, it may be necessary to increase the shared-memory
221 limit (:file:`/proc/sys/kernel/shmmax`) if fio runs into errors while
224 .. option:: --server=args
226 Start a backend server, with `args` specifying what to listen to.
227 See `Client/Server`_ section.
229 .. option:: --daemonize=pidfile
231 Background a fio server, writing the pid to the given `pidfile` file.
233 .. option:: --client=hostname
235 Instead of running the jobs locally, send and run them on the given `hostname`
236 or set of `hostname`\s. See `Client/Server`_ section.
238 .. option:: --remote-config=file
240 Tell fio server to load this local `file`.
242 .. option:: --idle-prof=option
244 Report CPU idleness. `option` is one of the following:
247 Run unit work calibration only and exit.
250 Show aggregate system idleness and unit work.
253 As **system** but also show per CPU idleness.
255 .. option:: --inflate-log=log
257 Inflate and output compressed `log`.
259 .. option:: --trigger-file=file
261 Execute trigger command when `file` exists.
263 .. option:: --trigger-timeout=time
265 Execute trigger at this `time`.
267 .. option:: --trigger=command
269 Set this `command` as local trigger.
271 .. option:: --trigger-remote=command
273 Set this `command` as remote trigger.
275 .. option:: --aux-path=path
277 Use this `path` for fio state generated files.
279 Any parameters following the options will be assumed to be job files, unless
280 they match a job file parameter. Multiple job files can be listed and each job
281 file will be regarded as a separate group. Fio will :option:`stonewall`
282 execution between each group.
288 As previously described, fio accepts one or more job files describing what it is
289 supposed to do. The job file format is the classic ini file, where the names
290 enclosed in [] brackets define the job name. You are free to use any ASCII name
291 you want, except *global* which has special meaning. Following the job name is
292 a sequence of zero or more parameters, one per line, that define the behavior of
293 the job. If the first character in a line is a ';' or a '#', the entire line is
294 discarded as a comment.
296 A *global* section sets defaults for the jobs described in that file. A job may
297 override a *global* section parameter, and a job file may even have several
298 *global* sections if so desired. A job is only affected by a *global* section
301 The :option:`--cmdhelp` option also lists all options. If used with a `command`
302 argument, :option:`--cmdhelp` will detail the given `command`.
304 See the `examples/` directory for inspiration on how to write job files. Note
305 the copyright and license requirements currently apply to `examples/` files.
307 So let's look at a really simple job file that defines two processes, each
308 randomly reading from a 128MiB file:
312 ; -- start job file --
323 As you can see, the job file sections themselves are empty as all the described
324 parameters are shared. As no :option:`filename` option is given, fio makes up a
325 `filename` for each of the jobs as it sees fit. On the command line, this job
326 would look as follows::
328 $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2
331 Let's look at an example that has a number of processes writing randomly to
336 ; -- start job file --
347 Here we have no *global* section, as we only have one job defined anyway. We
348 want to use async I/O here, with a depth of 4 for each file. We also increased
349 the buffer size used to 32KiB and define numjobs to 4 to fork 4 identical
350 jobs. The result is 4 processes each randomly writing to their own 64MiB
351 file. Instead of using the above job file, you could have given the parameters
352 on the command line. For this case, you would specify::
354 $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4
356 When fio is utilized as a basis of any reasonably large test suite, it might be
357 desirable to share a set of standardized settings across multiple job files.
358 Instead of copy/pasting such settings, any section may pull in an external
359 :file:`filename.fio` file with *include filename* directive, as in the following
362 ; -- start job file including.fio --
366 include glob-include.fio
373 include test-include.fio
374 ; -- end job file including.fio --
378 ; -- start job file glob-include.fio --
381 ; -- end job file glob-include.fio --
385 ; -- start job file test-include.fio --
388 ; -- end job file test-include.fio --
390 Settings pulled into a section apply to that section only (except *global*
391 section). Include directives may be nested in that any included file may contain
392 further include directive(s). Include files may not contain [] sections.
395 Environment variables
396 ~~~~~~~~~~~~~~~~~~~~~
398 Fio also supports environment variable expansion in job files. Any sub-string of
399 the form ``${VARNAME}`` as part of an option value (in other words, on the right
400 of the '='), will be expanded to the value of the environment variable called
401 `VARNAME`. If no such environment variable is defined, or `VARNAME` is the
402 empty string, the empty string will be substituted.
404 As an example, let's look at a sample fio invocation and job file::
406 $ SIZE=64m NUMJOBS=4 fio jobfile.fio
410 ; -- start job file --
417 This will expand to the following equivalent job file at runtime:
421 ; -- start job file --
428 Fio ships with a few example job files, you can also look there for inspiration.
433 Additionally, fio has a set of reserved keywords that will be replaced
434 internally with the appropriate value. Those keywords are:
438 The architecture page size of the running system.
442 Megabytes of total memory in the system.
446 Number of online available CPUs.
448 These can be used on the command line or in the job file, and will be
449 automatically substituted with the current system values when the job is
450 run. Simple math is also supported on these keywords, so you can perform actions
455 and get that properly expanded to 8 times the size of memory in the machine.
461 This section describes in details each parameter associated with a job. Some
462 parameters take an option of a given type, such as an integer or a
463 string. Anywhere a numeric value is required, an arithmetic expression may be
464 used, provided it is surrounded by parentheses. Supported operators are:
473 For time values in expressions, units are microseconds by default. This is
474 different than for time values not in expressions (not enclosed in
475 parentheses). The following types are used:
482 String: A sequence of alphanumeric characters.
485 Integer with possible time suffix. Without a unit value is interpreted as
486 seconds unless otherwise specified. Accepts a suffix of 'd' for days, 'h' for
487 hours, 'm' for minutes, 's' for seconds, 'ms' (or 'msec') for milliseconds and
488 'us' (or 'usec') for microseconds. For example, use 10m for 10 minutes.
493 Integer. A whole number value, which may contain an integer prefix
494 and an integer suffix:
496 [*integer prefix*] **number** [*integer suffix*]
498 The optional *integer prefix* specifies the number's base. The default
499 is decimal. *0x* specifies hexadecimal.
501 The optional *integer suffix* specifies the number's units, and includes an
502 optional unit prefix and an optional unit. For quantities of data, the
503 default unit is bytes. For quantities of time, the default unit is seconds
504 unless otherwise specified.
506 With :option:`kb_base`\=1000, fio follows international standards for unit
507 prefixes. To specify power-of-10 decimal values defined in the
508 International System of Units (SI):
510 * *K* -- means kilo (K) or 1000
511 * *M* -- means mega (M) or 1000**2
512 * *G* -- means giga (G) or 1000**3
513 * *T* -- means tera (T) or 1000**4
514 * *P* -- means peta (P) or 1000**5
516 To specify power-of-2 binary values defined in IEC 80000-13:
518 * *Ki* -- means kibi (Ki) or 1024
519 * *Mi* -- means mebi (Mi) or 1024**2
520 * *Gi* -- means gibi (Gi) or 1024**3
521 * *Ti* -- means tebi (Ti) or 1024**4
522 * *Pi* -- means pebi (Pi) or 1024**5
524 With :option:`kb_base`\=1024 (the default), the unit prefixes are opposite
525 from those specified in the SI and IEC 80000-13 standards to provide
526 compatibility with old scripts. For example, 4k means 4096.
528 For quantities of data, an optional unit of 'B' may be included
529 (e.g., 'kB' is the same as 'k').
531 The *integer suffix* is not case sensitive (e.g., m/mi mean mebi/mega,
532 not milli). 'b' and 'B' both mean byte, not bit.
534 Examples with :option:`kb_base`\=1000:
536 * *4 KiB*: 4096, 4096b, 4096B, 4ki, 4kib, 4kiB, 4Ki, 4KiB
537 * *1 MiB*: 1048576, 1mi, 1024ki
538 * *1 MB*: 1000000, 1m, 1000k
539 * *1 TiB*: 1099511627776, 1ti, 1024gi, 1048576mi
540 * *1 TB*: 1000000000, 1t, 1000m, 1000000k
542 Examples with :option:`kb_base`\=1024 (default):
544 * *4 KiB*: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB
545 * *1 MiB*: 1048576, 1m, 1024k
546 * *1 MB*: 1000000, 1mi, 1000ki
547 * *1 TiB*: 1099511627776, 1t, 1024g, 1048576m
548 * *1 TB*: 1000000000, 1ti, 1000mi, 1000000ki
550 To specify times (units are not case sensitive):
554 * *M* -- means minutes
555 * *s* -- or sec means seconds (default)
556 * *ms* -- or *msec* means milliseconds
557 * *us* -- or *usec* means microseconds
559 If the option accepts an upper and lower range, use a colon ':' or
560 minus '-' to separate such values. See :ref:`irange <irange>`.
561 If the lower value specified happens to be larger than the upper value
562 the two values are swapped.
567 Boolean. Usually parsed as an integer, however only defined for
568 true and false (1 and 0).
573 Integer range with suffix. Allows value range to be given, such as
574 1024-4096. A colon may also be used as the separator, e.g. 1k:4k. If the
575 option allows two sets of ranges, they can be specified with a ',' or '/'
576 delimiter: 1k-4k/8k-32k. Also see :ref:`int <int>`.
579 A list of floating point numbers, separated by a ':' character.
581 With the above in mind, here follows the complete list of fio job parameters.
587 .. option:: kb_base=int
589 Select the interpretation of unit prefixes in input parameters.
592 Inputs comply with IEC 80000-13 and the International
593 System of Units (SI). Use:
595 - power-of-2 values with IEC prefixes (e.g., KiB)
596 - power-of-10 values with SI prefixes (e.g., kB)
599 Compatibility mode (default). To avoid breaking old scripts:
601 - power-of-2 values with SI prefixes
602 - power-of-10 values with IEC prefixes
604 See :option:`bs` for more details on input parameters.
606 Outputs always use correct prefixes. Most outputs include both
609 bw=2383.3kB/s (2327.4KiB/s)
611 If only one value is reported, then kb_base selects the one to use:
613 **1000** -- SI prefixes
615 **1024** -- IEC prefixes
617 .. option:: unit_base=int
619 Base unit for reporting. Allowed values are:
622 Use auto-detection (default).
634 ASCII name of the job. This may be used to override the name printed by fio
635 for this job. Otherwise the job name is used. On the command line this
636 parameter has the special purpose of also signaling the start of a new job.
638 .. option:: description=str
640 Text description of the job. Doesn't do anything except dump this text
641 description when this job is run. It's not parsed.
643 .. option:: loops=int
645 Run the specified number of iterations of this job. Used to repeat the same
646 workload a given number of times. Defaults to 1.
648 .. option:: numjobs=int
650 Create the specified number of clones of this job. Each clone of job
651 is spawned as an independent thread or process. May be used to setup a
652 larger number of threads/processes doing the same thing. Each thread is
653 reported separately; to see statistics for all clones as a whole, use
654 :option:`group_reporting` in conjunction with :option:`new_group`.
655 See :option:`--max-jobs`. Default: 1.
658 Time related parameters
659 ~~~~~~~~~~~~~~~~~~~~~~~
661 .. option:: runtime=time
663 Tell fio to terminate processing after the specified period of time. It
664 can be quite hard to determine for how long a specified job will run, so
665 this parameter is handy to cap the total runtime to a given time. When
666 the unit is omitted, the value is intepreted in seconds.
668 .. option:: time_based
670 If set, fio will run for the duration of the :option:`runtime` specified
671 even if the file(s) are completely read or written. It will simply loop over
672 the same workload as many times as the :option:`runtime` allows.
674 .. option:: startdelay=irange(time)
676 Delay the start of job for the specified amount of time. Can be a single
677 value or a range. When given as a range, each thread will choose a value
678 randomly from within the range. Value is in seconds if a unit is omitted.
680 .. option:: ramp_time=time
682 If set, fio will run the specified workload for this amount of time before
683 logging any performance numbers. Useful for letting performance settle
684 before logging results, thus minimizing the runtime required for stable
685 results. Note that the ``ramp_time`` is considered lead in time for a job,
686 thus it will increase the total runtime if a special timeout or
687 :option:`runtime` is specified. When the unit is omitted, the value is
690 .. option:: clocksource=str
692 Use the given clocksource as the base of timing. The supported options are:
695 :manpage:`gettimeofday(2)`
698 :manpage:`clock_gettime(2)`
701 Internal CPU clock source
703 cpu is the preferred clocksource if it is reliable, as it is very fast (and
704 fio is heavy on time calls). Fio will automatically use this clocksource if
705 it's supported and considered reliable on the system it is running on,
706 unless another clocksource is specifically set. For x86/x86-64 CPUs, this
707 means supporting TSC Invariant.
709 .. option:: gtod_reduce=bool
711 Enable all of the :manpage:`gettimeofday(2)` reducing options
712 (:option:`disable_clat`, :option:`disable_slat`, :option:`disable_bw_measurement`) plus
713 reduce precision of the timeout somewhat to really shrink the
714 :manpage:`gettimeofday(2)` call count. With this option enabled, we only do
715 about 0.4% of the :manpage:`gettimeofday(2)` calls we would have done if all
716 time keeping was enabled.
718 .. option:: gtod_cpu=int
720 Sometimes it's cheaper to dedicate a single thread of execution to just
721 getting the current time. Fio (and databases, for instance) are very
722 intensive on :manpage:`gettimeofday(2)` calls. With this option, you can set
723 one CPU aside for doing nothing but logging current time to a shared memory
724 location. Then the other threads/processes that run I/O workloads need only
725 copy that segment, instead of entering the kernel with a
726 :manpage:`gettimeofday(2)` call. The CPU set aside for doing these time
727 calls will be excluded from other uses. Fio will manually clear it from the
728 CPU mask of other jobs.
734 .. option:: directory=str
736 Prefix filenames with this directory. Used to place files in a different
737 location than :file:`./`. You can specify a number of directories by
738 separating the names with a ':' character. These directories will be
739 assigned equally distributed to job clones created by :option:`numjobs` as
740 long as they are using generated filenames. If specific `filename(s)` are
741 set fio will use the first listed directory, and thereby matching the
742 `filename` semantic which generates a file each clone if not specified, but
743 let all clones use the same if set.
745 See the :option:`filename` option for information on how to escape "``:``" and
746 "``\``" characters within the directory path itself.
748 .. option:: filename=str
750 Fio normally makes up a `filename` based on the job name, thread number, and
751 file number (see :option:`filename_format`). If you want to share files
752 between threads in a job or several
753 jobs with fixed file paths, specify a `filename` for each of them to override
754 the default. If the ioengine is file based, you can specify a number of files
755 by separating the names with a ':' colon. So if you wanted a job to open
756 :file:`/dev/sda` and :file:`/dev/sdb` as the two working files, you would use
757 ``filename=/dev/sda:/dev/sdb``. This also means that whenever this option is
758 specified, :option:`nrfiles` is ignored. The size of regular files specified
759 by this option will be :option:`size` divided by number of files unless an
760 explicit size is specified by :option:`filesize`.
762 Each colon and backslash in the wanted path must be escaped with a ``\``
763 character. For instance, if the path is :file:`/dev/dsk/foo@3,0:c` then you
764 would use ``filename=/dev/dsk/foo@3,0\:c`` and if the path is
765 :file:`F:\\filename` then you would use ``filename=F\:\\filename``.
767 On Windows, disk devices are accessed as :file:`\\\\.\\PhysicalDrive0` for
768 the first device, :file:`\\\\.\\PhysicalDrive1` for the second etc.
769 Note: Windows and FreeBSD prevent write access to areas
770 of the disk containing in-use data (e.g. filesystems).
772 The filename "`-`" is a reserved name, meaning *stdin* or *stdout*. Which
773 of the two depends on the read/write direction set.
775 .. option:: filename_format=str
777 If sharing multiple files between jobs, it is usually necessary to have fio
778 generate the exact names that you want. By default, fio will name a file
779 based on the default file format specification of
780 :file:`jobname.jobnumber.filenumber`. With this option, that can be
781 customized. Fio will recognize and replace the following keywords in this
785 The name of the worker thread or process.
787 The incremental number of the worker thread or process.
789 The incremental number of the file for that worker thread or
792 To have dependent jobs share a set of files, this option can be set to have
793 fio generate filenames that are shared between the two. For instance, if
794 :file:`testfiles.$filenum` is specified, file number 4 for any job will be
795 named :file:`testfiles.4`. The default of :file:`$jobname.$jobnum.$filenum`
796 will be used if no other format specifier is given.
798 If you specify a path then the directories will be created up to the
799 main directory for the file. So for example if you specify
800 ``filename_format=a/b/c/$jobnum`` then the directories a/b/c will be
801 created before the file setup part of the job. If you specify
802 :option:`directory` then the path will be relative that directory,
803 otherwise it is treated as the absolute path.
805 .. option:: unique_filename=bool
807 To avoid collisions between networked clients, fio defaults to prefixing any
808 generated filenames (with a directory specified) with the source of the
809 client connecting. To disable this behavior, set this option to 0.
811 .. option:: opendir=str
813 Recursively open any files below directory `str`.
815 .. option:: lockfile=str
817 Fio defaults to not locking any files before it does I/O to them. If a file
818 or file descriptor is shared, fio can serialize I/O to that file to make the
819 end result consistent. This is usual for emulating real workloads that share
820 files. The lock modes are:
823 No locking. The default.
825 Only one thread or process may do I/O at a time, excluding all
828 Read-write locking on the file. Many readers may
829 access the file at the same time, but writes get exclusive access.
831 .. option:: nrfiles=int
833 Number of files to use for this job. Defaults to 1. The size of files
834 will be :option:`size` divided by this unless explicit size is specified by
835 :option:`filesize`. Files are created for each thread separately, and each
836 file will have a file number within its name by default, as explained in
837 :option:`filename` section.
840 .. option:: openfiles=int
842 Number of files to keep open at the same time. Defaults to the same as
843 :option:`nrfiles`, can be set smaller to limit the number simultaneous
846 .. option:: file_service_type=str
848 Defines how fio decides which file from a job to service next. The following
852 Choose a file at random.
855 Round robin over opened files. This is the default.
858 Finish one file before moving on to the next. Multiple files can
859 still be open depending on :option:`openfiles`.
862 Use a *Zipf* distribution to decide what file to access.
865 Use a *Pareto* distribution to decide what file to access.
868 Use a *Gaussian* (normal) distribution to decide what file to
874 For *random*, *roundrobin*, and *sequential*, a postfix can be appended to
875 tell fio how many I/Os to issue before switching to a new file. For example,
876 specifying ``file_service_type=random:8`` would cause fio to issue
877 8 I/Os before selecting a new file at random. For the non-uniform
878 distributions, a floating point postfix can be given to influence how the
879 distribution is skewed. See :option:`random_distribution` for a description
880 of how that would work.
882 .. option:: ioscheduler=str
884 Attempt to switch the device hosting the file to the specified I/O scheduler
887 .. option:: create_serialize=bool
889 If true, serialize the file creation for the jobs. This may be handy to
890 avoid interleaving of data files, which may greatly depend on the filesystem
891 used and even the number of processors in the system. Default: true.
893 .. option:: create_fsync=bool
895 :manpage:`fsync(2)` the data file after creation. This is the default.
897 .. option:: create_on_open=bool
899 If true, don't pre-create files but allow the job's open() to create a file
900 when it's time to do I/O. Default: false -- pre-create all necessary files
903 .. option:: create_only=bool
905 If true, fio will only run the setup phase of the job. If files need to be
906 laid out or updated on disk, only that will be done -- the actual job contents
907 are not executed. Default: false.
909 .. option:: allow_file_create=bool
911 If true, fio is permitted to create files as part of its workload. If this
912 option is false, then fio will error out if
913 the files it needs to use don't already exist. Default: true.
915 .. option:: allow_mounted_write=bool
917 If this isn't set, fio will abort jobs that are destructive (e.g. that write)
918 to what appears to be a mounted device or partition. This should help catch
919 creating inadvertently destructive tests, not realizing that the test will
920 destroy data on the mounted file system. Note that some platforms don't allow
921 writing against a mounted device regardless of this option. Default: false.
923 .. option:: pre_read=bool
925 If this is given, files will be pre-read into memory before starting the
926 given I/O operation. This will also clear the :option:`invalidate` flag,
927 since it is pointless to pre-read and then drop the cache. This will only
928 work for I/O engines that are seek-able, since they allow you to read the
929 same data multiple times. Thus it will not work on non-seekable I/O engines
930 (e.g. network, splice). Default: false.
932 .. option:: unlink=bool
934 Unlink the job files when done. Not the default, as repeated runs of that
935 job would then waste time recreating the file set again and again. Default:
938 .. option:: unlink_each_loop=bool
940 Unlink job files after each iteration or loop. Default: false.
942 .. option:: zonesize=int
944 Divide a file into zones of the specified size. See :option:`zoneskip`.
946 .. option:: zonerange=int
948 Give size of an I/O zone. See :option:`zoneskip`.
950 .. option:: zoneskip=int
952 Skip the specified number of bytes when :option:`zonesize` data has been
953 read. The two zone options can be used to only do I/O on zones of a file.
959 .. option:: direct=bool
961 If value is true, use non-buffered I/O. This is usually O_DIRECT. Note that
962 OpenBSD and ZFS on Solaris don't support direct I/O. On Windows the synchronous
963 ioengines don't support direct I/O. Default: false.
965 .. option:: atomic=bool
967 If value is true, attempt to use atomic direct I/O. Atomic writes are
968 guaranteed to be stable once acknowledged by the operating system. Only
969 Linux supports O_ATOMIC right now.
971 .. option:: buffered=bool
973 If value is true, use buffered I/O. This is the opposite of the
974 :option:`direct` option. Defaults to true.
976 .. option:: readwrite=str, rw=str
978 Type of I/O pattern. Accepted values are:
985 Sequential trims (Linux block devices only).
991 Random trims (Linux block devices only).
993 Sequential mixed reads and writes.
995 Random mixed reads and writes.
997 Sequential trim+write sequences. Blocks will be trimmed first,
998 then the same blocks will be written to.
1000 Fio defaults to read if the option is not specified. For the mixed I/O
1001 types, the default is to split them 50/50. For certain types of I/O the
1002 result may still be skewed a bit, since the speed may be different.
1004 It is possible to specify the number of I/Os to do before getting a new
1005 offset by appending ``:<nr>`` to the end of the string given. For a
1006 random read, it would look like ``rw=randread:8`` for passing in an offset
1007 modifier with a value of 8. If the suffix is used with a sequential I/O
1008 pattern, then the *<nr>* value specified will be **added** to the generated
1009 offset for each I/O turning sequential I/O into sequential I/O with holes.
1010 For instance, using ``rw=write:4k`` will skip 4k for every write. Also see
1011 the :option:`rw_sequencer` option.
1013 .. option:: rw_sequencer=str
1015 If an offset modifier is given by appending a number to the ``rw=<str>``
1016 line, then this option controls how that number modifies the I/O offset
1017 being generated. Accepted values are:
1020 Generate sequential offset.
1022 Generate the same offset.
1024 ``sequential`` is only useful for random I/O, where fio would normally
1025 generate a new random offset for every I/O. If you append e.g. 8 to randread,
1026 you would get a new random offset for every 8 I/Os. The result would be a
1027 seek for only every 8 I/Os, instead of for every I/O. Use ``rw=randread:8``
1028 to specify that. As sequential I/O is already sequential, setting
1029 ``sequential`` for that would not result in any differences. ``identical``
1030 behaves in a similar fashion, except it sends the same offset 8 number of
1031 times before generating a new offset.
1033 .. option:: unified_rw_reporting=bool
1035 Fio normally reports statistics on a per data direction basis, meaning that
1036 reads, writes, and trims are accounted and reported separately. If this
1037 option is set fio sums the results and report them as "mixed" instead.
1039 .. option:: randrepeat=bool
1041 Seed the random number generator used for random I/O patterns in a
1042 predictable way so the pattern is repeatable across runs. Default: true.
1044 .. option:: allrandrepeat=bool
1046 Seed all random number generators in a predictable way so results are
1047 repeatable across runs. Default: false.
1049 .. option:: randseed=int
1051 Seed the random number generators based on this seed value, to be able to
1052 control what sequence of output is being generated. If not set, the random
1053 sequence depends on the :option:`randrepeat` setting.
1055 .. option:: fallocate=str
1057 Whether pre-allocation is performed when laying down files.
1058 Accepted values are:
1061 Do not pre-allocate space.
1064 Use a platform's native pre-allocation call but fall back to
1065 **none** behavior if it fails/is not implemented.
1068 Pre-allocate via :manpage:`posix_fallocate(3)`.
1071 Pre-allocate via :manpage:`fallocate(2)` with
1072 FALLOC_FL_KEEP_SIZE set.
1075 Backward-compatible alias for **none**.
1078 Backward-compatible alias for **posix**.
1080 May not be available on all supported platforms. **keep** is only available
1081 on Linux. If using ZFS on Solaris this cannot be set to **posix**
1082 because ZFS doesn't support pre-allocation. Default: **native** if any
1083 pre-allocation methods are available, **none** if not.
1085 .. option:: fadvise_hint=str
1087 Use :manpage:`posix_fadvise(2)` to advise the kernel on what I/O patterns
1088 are likely to be issued. Accepted values are:
1091 Backwards-compatible hint for "no hint".
1094 Backwards compatible hint for "advise with fio workload type". This
1095 uses **FADV_RANDOM** for a random workload, and **FADV_SEQUENTIAL**
1096 for a sequential workload.
1099 Advise using **FADV_SEQUENTIAL**.
1102 Advise using **FADV_RANDOM**.
1104 .. option:: write_hint=str
1106 Use :manpage:`fcntl(2)` to advise the kernel what life time to expect
1107 from a write. Only supported on Linux, as of version 4.13. Accepted
1111 No particular life time associated with this file.
1114 Data written to this file has a short life time.
1117 Data written to this file has a medium life time.
1120 Data written to this file has a long life time.
1123 Data written to this file has a very long life time.
1125 The values are all relative to each other, and no absolute meaning
1126 should be associated with them.
1128 .. option:: offset=int
1130 Start I/O at the provided offset in the file, given as either a fixed size in
1131 bytes or a percentage. If a percentage is given, the generated offset will be
1132 aligned to the minimum ``blocksize`` or to the value of ``offset_align`` if
1133 provided. Data before the given offset will not be touched. This
1134 effectively caps the file size at `real_size - offset`. Can be combined with
1135 :option:`size` to constrain the start and end range of the I/O workload.
1136 A percentage can be specified by a number between 1 and 100 followed by '%',
1137 for example, ``offset=20%`` to specify 20%.
1139 .. option:: offset_align=int
1141 If set to non-zero value, the byte offset generated by a percentage ``offset``
1142 is aligned upwards to this value. Defaults to 0 meaning that a percentage
1143 offset is aligned to the minimum block size.
1145 .. option:: offset_increment=int
1147 If this is provided, then the real offset becomes `offset + offset_increment
1148 * thread_number`, where the thread number is a counter that starts at 0 and
1149 is incremented for each sub-job (i.e. when :option:`numjobs` option is
1150 specified). This option is useful if there are several jobs which are
1151 intended to operate on a file in parallel disjoint segments, with even
1152 spacing between the starting points.
1154 .. option:: number_ios=int
1156 Fio will normally perform I/Os until it has exhausted the size of the region
1157 set by :option:`size`, or if it exhaust the allocated time (or hits an error
1158 condition). With this setting, the range/size can be set independently of
1159 the number of I/Os to perform. When fio reaches this number, it will exit
1160 normally and report status. Note that this does not extend the amount of I/O
1161 that will be done, it will only stop fio if this condition is met before
1162 other end-of-job criteria.
1164 .. option:: fsync=int
1166 If writing to a file, issue an :manpage:`fsync(2)` (or its equivalent) of
1167 the dirty data for every number of blocks given. For example, if you give 32
1168 as a parameter, fio will sync the file after every 32 writes issued. If fio is
1169 using non-buffered I/O, we may not sync the file. The exception is the sg
1170 I/O engine, which synchronizes the disk cache anyway. Defaults to 0, which
1171 means fio does not periodically issue and wait for a sync to complete. Also
1172 see :option:`end_fsync` and :option:`fsync_on_close`.
1174 .. option:: fdatasync=int
1176 Like :option:`fsync` but uses :manpage:`fdatasync(2)` to only sync data and
1177 not metadata blocks. In Windows, FreeBSD, and DragonFlyBSD there is no
1178 :manpage:`fdatasync(2)` so this falls back to using :manpage:`fsync(2)`.
1179 Defaults to 0, which means fio does not periodically issue and wait for a
1180 data-only sync to complete.
1182 .. option:: write_barrier=int
1184 Make every `N-th` write a barrier write.
1186 .. option:: sync_file_range=str:int
1188 Use :manpage:`sync_file_range(2)` for every `int` number of write
1189 operations. Fio will track range of writes that have happened since the last
1190 :manpage:`sync_file_range(2)` call. `str` can currently be one or more of:
1193 SYNC_FILE_RANGE_WAIT_BEFORE
1195 SYNC_FILE_RANGE_WRITE
1197 SYNC_FILE_RANGE_WAIT_AFTER
1199 So if you do ``sync_file_range=wait_before,write:8``, fio would use
1200 ``SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE`` for every 8
1201 writes. Also see the :manpage:`sync_file_range(2)` man page. This option is
1204 .. option:: overwrite=bool
1206 If true, writes to a file will always overwrite existing data. If the file
1207 doesn't already exist, it will be created before the write phase begins. If
1208 the file exists and is large enough for the specified write phase, nothing
1209 will be done. Default: false.
1211 .. option:: end_fsync=bool
1213 If true, :manpage:`fsync(2)` file contents when a write stage has completed.
1216 .. option:: fsync_on_close=bool
1218 If true, fio will :manpage:`fsync(2)` a dirty file on close. This differs
1219 from :option:`end_fsync` in that it will happen on every file close, not
1220 just at the end of the job. Default: false.
1222 .. option:: rwmixread=int
1224 Percentage of a mixed workload that should be reads. Default: 50.
1226 .. option:: rwmixwrite=int
1228 Percentage of a mixed workload that should be writes. If both
1229 :option:`rwmixread` and :option:`rwmixwrite` is given and the values do not
1230 add up to 100%, the latter of the two will be used to override the
1231 first. This may interfere with a given rate setting, if fio is asked to
1232 limit reads or writes to a certain rate. If that is the case, then the
1233 distribution may be skewed. Default: 50.
1235 .. option:: random_distribution=str:float[,str:float][,str:float]
1237 By default, fio will use a completely uniform random distribution when asked
1238 to perform random I/O. Sometimes it is useful to skew the distribution in
1239 specific ways, ensuring that some parts of the data is more hot than others.
1240 fio includes the following distribution models:
1243 Uniform random distribution
1252 Normal (Gaussian) distribution
1255 Zoned random distribution
1258 Zone absolute random distribution
1260 When using a **zipf** or **pareto** distribution, an input value is also
1261 needed to define the access pattern. For **zipf**, this is the `Zipf
1262 theta`. For **pareto**, it's the `Pareto power`. Fio includes a test
1263 program, :command:`fio-genzipf`, that can be used visualize what the given input
1264 values will yield in terms of hit rates. If you wanted to use **zipf** with
1265 a `theta` of 1.2, you would use ``random_distribution=zipf:1.2`` as the
1266 option. If a non-uniform model is used, fio will disable use of the random
1267 map. For the **normal** distribution, a normal (Gaussian) deviation is
1268 supplied as a value between 0 and 100.
1270 For a **zoned** distribution, fio supports specifying percentages of I/O
1271 access that should fall within what range of the file or device. For
1272 example, given a criteria of:
1274 * 60% of accesses should be to the first 10%
1275 * 30% of accesses should be to the next 20%
1276 * 8% of accesses should be to the next 30%
1277 * 2% of accesses should be to the next 40%
1279 we can define that through zoning of the random accesses. For the above
1280 example, the user would do::
1282 random_distribution=zoned:60/10:30/20:8/30:2/40
1284 A **zoned_abs** distribution works exactly like the **zoned**, except
1285 that it takes absolute sizes. For example, let's say you wanted to
1286 define access according to the following criteria:
1288 * 60% of accesses should be to the first 20G
1289 * 30% of accesses should be to the next 100G
1290 * 10% of accesses should be to the next 500G
1292 we can define an absolute zoning distribution with:
1294 random_distribution=zoned_abs=60/20G:30/100G:10/500g
1296 For both **zoned** and **zoned_abs**, fio supports defining up to
1299 Similarly to how :option:`bssplit` works for setting ranges and
1300 percentages of block sizes. Like :option:`bssplit`, it's possible to
1301 specify separate zones for reads, writes, and trims. If just one set
1302 is given, it'll apply to all of them. This goes for both **zoned**
1303 **zoned_abs** distributions.
1305 .. option:: percentage_random=int[,int][,int]
1307 For a random workload, set how big a percentage should be random. This
1308 defaults to 100%, in which case the workload is fully random. It can be set
1309 from anywhere from 0 to 100. Setting it to 0 would make the workload fully
1310 sequential. Any setting in between will result in a random mix of sequential
1311 and random I/O, at the given percentages. Comma-separated values may be
1312 specified for reads, writes, and trims as described in :option:`blocksize`.
1314 .. option:: norandommap
1316 Normally fio will cover every block of the file when doing random I/O. If
1317 this option is given, fio will just get a new random offset without looking
1318 at past I/O history. This means that some blocks may not be read or written,
1319 and that some blocks may be read/written more than once. If this option is
1320 used with :option:`verify` and multiple blocksizes (via :option:`bsrange`),
1321 only intact blocks are verified, i.e., partially-overwritten blocks are
1324 .. option:: softrandommap=bool
1326 See :option:`norandommap`. If fio runs with the random block map enabled and
1327 it fails to allocate the map, if this option is set it will continue without
1328 a random block map. As coverage will not be as complete as with random maps,
1329 this option is disabled by default.
1331 .. option:: random_generator=str
1333 Fio supports the following engines for generating I/O offsets for random I/O:
1336 Strong 2^88 cycle random number generator.
1338 Linear feedback shift register generator.
1340 Strong 64-bit 2^258 cycle random number generator.
1342 **tausworthe** is a strong random number generator, but it requires tracking
1343 on the side if we want to ensure that blocks are only read or written
1344 once. **lfsr** guarantees that we never generate the same offset twice, and
1345 it's also less computationally expensive. It's not a true random generator,
1346 however, though for I/O purposes it's typically good enough. **lfsr** only
1347 works with single block sizes, not with workloads that use multiple block
1348 sizes. If used with such a workload, fio may read or write some blocks
1349 multiple times. The default value is **tausworthe**, unless the required
1350 space exceeds 2^32 blocks. If it does, then **tausworthe64** is
1351 selected automatically.
1357 .. option:: blocksize=int[,int][,int], bs=int[,int][,int]
1359 The block size in bytes used for I/O units. Default: 4096. A single value
1360 applies to reads, writes, and trims. Comma-separated values may be
1361 specified for reads, writes, and trims. A value not terminated in a comma
1362 applies to subsequent types.
1367 means 256k for reads, writes and trims.
1370 means 8k for reads, 32k for writes and trims.
1373 means 8k for reads, 32k for writes, and default for trims.
1376 means default for reads, 8k for writes and trims.
1379 means default for reads, 8k for writes, and default for trims.
1381 .. option:: blocksize_range=irange[,irange][,irange], bsrange=irange[,irange][,irange]
1383 A range of block sizes in bytes for I/O units. The issued I/O unit will
1384 always be a multiple of the minimum size, unless
1385 :option:`blocksize_unaligned` is set.
1387 Comma-separated ranges may be specified for reads, writes, and trims as
1388 described in :option:`blocksize`.
1390 Example: ``bsrange=1k-4k,2k-8k``.
1392 .. option:: bssplit=str[,str][,str]
1394 Sometimes you want even finer grained control of the block sizes
1395 issued, not just an even split between them. This option allows you to
1396 weight various block sizes, so that you are able to define a specific
1397 amount of block sizes issued. The format for this option is::
1399 bssplit=blocksize/percentage:blocksize/percentage
1401 for as many block sizes as needed. So if you want to define a workload
1402 that has 50% 64k blocks, 10% 4k blocks, and 40% 32k blocks, you would
1405 bssplit=4k/10:64k/50:32k/40
1407 Ordering does not matter. If the percentage is left blank, fio will
1408 fill in the remaining values evenly. So a bssplit option like this one::
1410 bssplit=4k/50:1k/:32k/
1412 would have 50% 4k ios, and 25% 1k and 32k ios. The percentages always
1413 add up to 100, if bssplit is given a range that adds up to more, it
1416 Comma-separated values may be specified for reads, writes, and trims as
1417 described in :option:`blocksize`.
1419 If you want a workload that has 50% 2k reads and 50% 4k reads, while
1420 having 90% 4k writes and 10% 8k writes, you would specify::
1422 bssplit=2k/50:4k/50,4k/90,8k/10
1424 Fio supports defining up to 64 different weights for each data
1427 .. option:: blocksize_unaligned, bs_unaligned
1429 If set, fio will issue I/O units with any size within
1430 :option:`blocksize_range`, not just multiples of the minimum size. This
1431 typically won't work with direct I/O, as that normally requires sector
1434 .. option:: bs_is_seq_rand=bool
1436 If this option is set, fio will use the normal read,write blocksize settings
1437 as sequential,random blocksize settings instead. Any random read or write
1438 will use the WRITE blocksize settings, and any sequential read or write will
1439 use the READ blocksize settings.
1441 .. option:: blockalign=int[,int][,int], ba=int[,int][,int]
1443 Boundary to which fio will align random I/O units. Default:
1444 :option:`blocksize`. Minimum alignment is typically 512b for using direct
1445 I/O, though it usually depends on the hardware block size. This option is
1446 mutually exclusive with using a random map for files, so it will turn off
1447 that option. Comma-separated values may be specified for reads, writes, and
1448 trims as described in :option:`blocksize`.
1454 .. option:: zero_buffers
1456 Initialize buffers with all zeros. Default: fill buffers with random data.
1458 .. option:: refill_buffers
1460 If this option is given, fio will refill the I/O buffers on every
1461 submit. Only makes sense if :option:`zero_buffers` isn't specified,
1462 naturally. Defaults to being unset i.e., the buffer is only filled at
1463 init time and the data in it is reused when possible but if any of
1464 :option:`verify`, :option:`buffer_compress_percentage` or
1465 :option:`dedupe_percentage` are enabled then `refill_buffers` is also
1466 automatically enabled.
1468 .. option:: scramble_buffers=bool
1470 If :option:`refill_buffers` is too costly and the target is using data
1471 deduplication, then setting this option will slightly modify the I/O buffer
1472 contents to defeat normal de-dupe attempts. This is not enough to defeat
1473 more clever block compression attempts, but it will stop naive dedupe of
1474 blocks. Default: true.
1476 .. option:: buffer_compress_percentage=int
1478 If this is set, then fio will attempt to provide I/O buffer content
1479 (on WRITEs) that compresses to the specified level. Fio does this by
1480 providing a mix of random data followed by fixed pattern data. The
1481 fixed pattern is either zeros, or the pattern specified by
1482 :option:`buffer_pattern`. If the `buffer_pattern` option is used, it
1483 might skew the compression ratio slightly. Setting
1484 `buffer_compress_percentage` to a value other than 100 will also
1485 enable :option:`refill_buffers` in order to reduce the likelihood that
1486 adjacent blocks are so similar that they over compress when seen
1487 together. See :option:`buffer_compress_chunk` for how to set a finer or
1488 coarser granularity for the random/fixed data region. Defaults to unset
1489 i.e., buffer data will not adhere to any compression level.
1491 .. option:: buffer_compress_chunk=int
1493 This setting allows fio to manage how big the random/fixed data region
1494 is when using :option:`buffer_compress_percentage`. When
1495 `buffer_compress_chunk` is set to some non-zero value smaller than the
1496 block size, fio can repeat the random/fixed region throughout the I/O
1497 buffer at the specified interval (which particularly useful when
1498 bigger block sizes are used for a job). When set to 0, fio will use a
1499 chunk size that matches the block size resulting in a single
1500 random/fixed region within the I/O buffer. Defaults to 512. When the
1501 unit is omitted, the value is interpreted in bytes.
1503 .. option:: buffer_pattern=str
1505 If set, fio will fill the I/O buffers with this pattern or with the contents
1506 of a file. If not set, the contents of I/O buffers are defined by the other
1507 options related to buffer contents. The setting can be any pattern of bytes,
1508 and can be prefixed with 0x for hex values. It may also be a string, where
1509 the string must then be wrapped with ``""``. Or it may also be a filename,
1510 where the filename must be wrapped with ``''`` in which case the file is
1511 opened and read. Note that not all the file contents will be read if that
1512 would cause the buffers to overflow. So, for example::
1514 buffer_pattern='filename'
1518 buffer_pattern="abcd"
1526 buffer_pattern=0xdeadface
1528 Also you can combine everything together in any order::
1530 buffer_pattern=0xdeadface"abcd"-12'filename'
1532 .. option:: dedupe_percentage=int
1534 If set, fio will generate this percentage of identical buffers when
1535 writing. These buffers will be naturally dedupable. The contents of the
1536 buffers depend on what other buffer compression settings have been set. It's
1537 possible to have the individual buffers either fully compressible, or not at
1538 all -- this option only controls the distribution of unique buffers. Setting
1539 this option will also enable :option:`refill_buffers` to prevent every buffer
1542 .. option:: invalidate=bool
1544 Invalidate the buffer/page cache parts of the files to be used prior to
1545 starting I/O if the platform and file type support it. Defaults to true.
1546 This will be ignored if :option:`pre_read` is also specified for the
1549 .. option:: sync=bool
1551 Use synchronous I/O for buffered writes. For the majority of I/O engines,
1552 this means using O_SYNC. Default: false.
1554 .. option:: iomem=str, mem=str
1556 Fio can use various types of memory as the I/O unit buffer. The allowed
1560 Use memory from :manpage:`malloc(3)` as the buffers. Default memory
1564 Use shared memory as the buffers. Allocated through
1565 :manpage:`shmget(2)`.
1568 Same as shm, but use huge pages as backing.
1571 Use :manpage:`mmap(2)` to allocate buffers. May either be anonymous memory, or can
1572 be file backed if a filename is given after the option. The format
1573 is `mem=mmap:/path/to/file`.
1576 Use a memory mapped huge file as the buffer backing. Append filename
1577 after mmaphuge, ala `mem=mmaphuge:/hugetlbfs/file`.
1580 Same as mmap, but use a MMAP_SHARED mapping.
1583 Use GPU memory as the buffers for GPUDirect RDMA benchmark.
1584 The :option:`ioengine` must be `rdma`.
1586 The area allocated is a function of the maximum allowed bs size for the job,
1587 multiplied by the I/O depth given. Note that for **shmhuge** and
1588 **mmaphuge** to work, the system must have free huge pages allocated. This
1589 can normally be checked and set by reading/writing
1590 :file:`/proc/sys/vm/nr_hugepages` on a Linux system. Fio assumes a huge page
1591 is 4MiB in size. So to calculate the number of huge pages you need for a
1592 given job file, add up the I/O depth of all jobs (normally one unless
1593 :option:`iodepth` is used) and multiply by the maximum bs set. Then divide
1594 that number by the huge page size. You can see the size of the huge pages in
1595 :file:`/proc/meminfo`. If no huge pages are allocated by having a non-zero
1596 number in `nr_hugepages`, using **mmaphuge** or **shmhuge** will fail. Also
1597 see :option:`hugepage-size`.
1599 **mmaphuge** also needs to have hugetlbfs mounted and the file location
1600 should point there. So if it's mounted in :file:`/huge`, you would use
1601 `mem=mmaphuge:/huge/somefile`.
1603 .. option:: iomem_align=int, mem_align=int
1605 This indicates the memory alignment of the I/O memory buffers. Note that
1606 the given alignment is applied to the first I/O unit buffer, if using
1607 :option:`iodepth` the alignment of the following buffers are given by the
1608 :option:`bs` used. In other words, if using a :option:`bs` that is a
1609 multiple of the page sized in the system, all buffers will be aligned to
1610 this value. If using a :option:`bs` that is not page aligned, the alignment
1611 of subsequent I/O memory buffers is the sum of the :option:`iomem_align` and
1614 .. option:: hugepage-size=int
1616 Defines the size of a huge page. Must at least be equal to the system
1617 setting, see :file:`/proc/meminfo`. Defaults to 4MiB. Should probably
1618 always be a multiple of megabytes, so using ``hugepage-size=Xm`` is the
1619 preferred way to set this to avoid setting a non-pow-2 bad value.
1621 .. option:: lockmem=int
1623 Pin the specified amount of memory with :manpage:`mlock(2)`. Can be used to
1624 simulate a smaller amount of memory. The amount specified is per worker.
1630 .. option:: size=int
1632 The total size of file I/O for each thread of this job. Fio will run until
1633 this many bytes has been transferred, unless runtime is limited by other options
1634 (such as :option:`runtime`, for instance, or increased/decreased by :option:`io_size`).
1635 Fio will divide this size between the available files determined by options
1636 such as :option:`nrfiles`, :option:`filename`, unless :option:`filesize` is
1637 specified by the job. If the result of division happens to be 0, the size is
1638 set to the physical size of the given files or devices if they exist.
1639 If this option is not specified, fio will use the full size of the given
1640 files or devices. If the files do not exist, size must be given. It is also
1641 possible to give size as a percentage between 1 and 100. If ``size=20%`` is
1642 given, fio will use 20% of the full size of the given files or devices.
1643 Can be combined with :option:`offset` to constrain the start and end range
1644 that I/O will be done within.
1646 .. option:: io_size=int, io_limit=int
1648 Normally fio operates within the region set by :option:`size`, which means
1649 that the :option:`size` option sets both the region and size of I/O to be
1650 performed. Sometimes that is not what you want. With this option, it is
1651 possible to define just the amount of I/O that fio should do. For instance,
1652 if :option:`size` is set to 20GiB and :option:`io_size` is set to 5GiB, fio
1653 will perform I/O within the first 20GiB but exit when 5GiB have been
1654 done. The opposite is also possible -- if :option:`size` is set to 20GiB,
1655 and :option:`io_size` is set to 40GiB, then fio will do 40GiB of I/O within
1656 the 0..20GiB region.
1658 .. option:: filesize=irange(int)
1660 Individual file sizes. May be a range, in which case fio will select sizes
1661 for files at random within the given range and limited to :option:`size` in
1662 total (if that is given). If not given, each created file is the same size.
1663 This option overrides :option:`size` in terms of file size, which means
1664 this value is used as a fixed size or possible range of each file.
1666 .. option:: file_append=bool
1668 Perform I/O after the end of the file. Normally fio will operate within the
1669 size of a file. If this option is set, then fio will append to the file
1670 instead. This has identical behavior to setting :option:`offset` to the size
1671 of a file. This option is ignored on non-regular files.
1673 .. option:: fill_device=bool, fill_fs=bool
1675 Sets size to something really large and waits for ENOSPC (no space left on
1676 device) as the terminating condition. Only makes sense with sequential
1677 write. For a read workload, the mount point will be filled first then I/O
1678 started on the result. This option doesn't make sense if operating on a raw
1679 device node, since the size of that is already known by the file system.
1680 Additionally, writing beyond end-of-device will not return ENOSPC there.
1686 .. option:: ioengine=str
1688 Defines how the job issues I/O to the file. The following types are defined:
1691 Basic :manpage:`read(2)` or :manpage:`write(2)`
1692 I/O. :manpage:`lseek(2)` is used to position the I/O location.
1693 See :option:`fsync` and :option:`fdatasync` for syncing write I/Os.
1696 Basic :manpage:`pread(2)` or :manpage:`pwrite(2)` I/O. Default on
1697 all supported operating systems except for Windows.
1700 Basic :manpage:`readv(2)` or :manpage:`writev(2)` I/O. Will emulate
1701 queuing by coalescing adjacent I/Os into a single submission.
1704 Basic :manpage:`preadv(2)` or :manpage:`pwritev(2)` I/O.
1707 Basic :manpage:`preadv2(2)` or :manpage:`pwritev2(2)` I/O.
1710 Linux native asynchronous I/O. Note that Linux may only support
1711 queued behavior with non-buffered I/O (set ``direct=1`` or
1713 This engine defines engine specific options.
1716 POSIX asynchronous I/O using :manpage:`aio_read(3)` and
1717 :manpage:`aio_write(3)`.
1720 Solaris native asynchronous I/O.
1723 Windows native asynchronous I/O. Default on Windows.
1726 File is memory mapped with :manpage:`mmap(2)` and data copied
1727 to/from using :manpage:`memcpy(3)`.
1730 :manpage:`splice(2)` is used to transfer the data and
1731 :manpage:`vmsplice(2)` to transfer data from user space to the
1735 SCSI generic sg v3 I/O. May either be synchronous using the SG_IO
1736 ioctl, or if the target is an sg character device we use
1737 :manpage:`read(2)` and :manpage:`write(2)` for asynchronous
1738 I/O. Requires :option:`filename` option to specify either block or
1742 Doesn't transfer any data, just pretends to. This is mainly used to
1743 exercise fio itself and for debugging/testing purposes.
1746 Transfer over the network to given ``host:port``. Depending on the
1747 :option:`protocol` used, the :option:`hostname`, :option:`port`,
1748 :option:`listen` and :option:`filename` options are used to specify
1749 what sort of connection to make, while the :option:`protocol` option
1750 determines which protocol will be used. This engine defines engine
1754 Like **net**, but uses :manpage:`splice(2)` and
1755 :manpage:`vmsplice(2)` to map data and send/receive.
1756 This engine defines engine specific options.
1759 Doesn't transfer any data, but burns CPU cycles according to the
1760 :option:`cpuload` and :option:`cpuchunks` options. Setting
1761 :option:`cpuload`\=85 will cause that job to do nothing but burn 85%
1762 of the CPU. In case of SMP machines, use :option:`numjobs`\=<nr_of_cpu>
1763 to get desired CPU usage, as the cpuload only loads a
1764 single CPU at the desired rate. A job never finishes unless there is
1765 at least one non-cpuio job.
1768 The GUASI I/O engine is the Generic Userspace Asyncronous Syscall
1769 Interface approach to async I/O. See
1771 http://www.xmailserver.org/guasi-lib.html
1773 for more info on GUASI.
1776 The RDMA I/O engine supports both RDMA memory semantics
1777 (RDMA_WRITE/RDMA_READ) and channel semantics (Send/Recv) for the
1778 InfiniBand, RoCE and iWARP protocols. This engine defines engine
1782 I/O engine that does regular fallocate to simulate data transfer as
1786 does fallocate(,mode = FALLOC_FL_KEEP_SIZE,).
1789 does fallocate(,mode = 0).
1792 does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE).
1795 I/O engine that sends :manpage:`ftruncate(2)` operations in response
1796 to write (DDIR_WRITE) events. Each ftruncate issued sets the file's
1797 size to the current block offset. :option:`blocksize` is ignored.
1800 I/O engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate
1801 defragment activity in request to DDIR_WRITE event.
1804 I/O engine supporting direct access to Ceph Rados Block Devices
1805 (RBD) via librbd without the need to use the kernel rbd driver. This
1806 ioengine defines engine specific options.
1809 Using GlusterFS libgfapi sync interface to direct access to
1810 GlusterFS volumes without having to go through FUSE. This ioengine
1811 defines engine specific options.
1814 Using GlusterFS libgfapi async interface to direct access to
1815 GlusterFS volumes without having to go through FUSE. This ioengine
1816 defines engine specific options.
1819 Read and write through Hadoop (HDFS). The :option:`filename` option
1820 is used to specify host,port of the hdfs name-node to connect. This
1821 engine interprets offsets a little differently. In HDFS, files once
1822 created cannot be modified so random writes are not possible. To
1823 imitate this the libhdfs engine expects a bunch of small files to be
1824 created over HDFS and will randomly pick a file from them
1825 based on the offset generated by fio backend (see the example
1826 job file to create such files, use ``rw=write`` option). Please
1827 note, it may be necessary to set environment variables to work
1828 with HDFS/libhdfs properly. Each job uses its own connection to
1832 Read, write and erase an MTD character device (e.g.,
1833 :file:`/dev/mtd0`). Discards are treated as erases. Depending on the
1834 underlying device type, the I/O may have to go in a certain pattern,
1835 e.g., on NAND, writing sequentially to erase blocks and discarding
1836 before overwriting. The `trimwrite` mode works well for this
1840 Read and write using filesystem DAX to a file on a filesystem
1841 mounted with DAX on a persistent memory device through the NVML
1845 Read and write using device DAX to a persistent memory device (e.g.,
1846 /dev/dax0.0) through the NVML libpmem library.
1849 Prefix to specify loading an external I/O engine object file. Append
1850 the engine filename, e.g. ``ioengine=external:/tmp/foo.o`` to load
1851 ioengine :file:`foo.o` in :file:`/tmp`. The path can be either
1852 absolute or relative. See :file:`engines/skeleton_external.c` for
1853 details of writing an external I/O engine.
1856 Simply create the files and do no I/O to them. You still need to
1857 set `filesize` so that all the accounting still occurs, but no
1858 actual I/O will be done other than creating the file.
1861 Read and write using mmap I/O to a file on a filesystem
1862 mounted with DAX on a persistent memory device through the NVML
1865 I/O engine specific parameters
1866 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1868 In addition, there are some parameters which are only valid when a specific
1869 :option:`ioengine` is in use. These are used identically to normal parameters,
1870 with the caveat that when used on the command line, they must come after the
1871 :option:`ioengine` that defines them is selected.
1873 .. option:: userspace_reap : [libaio]
1875 Normally, with the libaio engine in use, fio will use the
1876 :manpage:`io_getevents(2)` system call to reap newly returned events. With
1877 this flag turned on, the AIO ring will be read directly from user-space to
1878 reap events. The reaping mode is only enabled when polling for a minimum of
1879 0 events (e.g. when :option:`iodepth_batch_complete` `=0`).
1881 .. option:: hipri : [pvsync2]
1883 Set RWF_HIPRI on I/O, indicating to the kernel that it's of higher priority
1886 .. option:: hipri_percentage : [pvsync2]
1888 When hipri is set this determines the probability of a pvsync2 I/O being high
1889 priority. The default is 100%.
1891 .. option:: cpuload=int : [cpuio]
1893 Attempt to use the specified percentage of CPU cycles. This is a mandatory
1894 option when using cpuio I/O engine.
1896 .. option:: cpuchunks=int : [cpuio]
1898 Split the load into cycles of the given time. In microseconds.
1900 .. option:: exit_on_io_done=bool : [cpuio]
1902 Detect when I/O threads are done, then exit.
1904 .. option:: namenode=str : [libhdfs]
1906 The hostname or IP address of a HDFS cluster namenode to contact.
1908 .. option:: port=int
1912 The listening port of the HFDS cluster namenode.
1916 The TCP or UDP port to bind to or connect to. If this is used with
1917 :option:`numjobs` to spawn multiple instances of the same job type, then
1918 this will be the starting port number since fio will use a range of
1923 The port to use for RDMA-CM communication. This should be the same value
1924 on the client and the server side.
1926 .. option:: hostname=str : [netsplice] [net] [rdma]
1928 The hostname or IP address to use for TCP, UDP or RDMA-CM based I/O. If the job
1929 is a TCP listener or UDP reader, the hostname is not used and must be omitted
1930 unless it is a valid UDP multicast address.
1932 .. option:: interface=str : [netsplice] [net]
1934 The IP address of the network interface used to send or receive UDP
1937 .. option:: ttl=int : [netsplice] [net]
1939 Time-to-live value for outgoing UDP multicast packets. Default: 1.
1941 .. option:: nodelay=bool : [netsplice] [net]
1943 Set TCP_NODELAY on TCP connections.
1945 .. option:: protocol=str, proto=str : [netsplice] [net]
1947 The network protocol to use. Accepted values are:
1950 Transmission control protocol.
1952 Transmission control protocol V6.
1954 User datagram protocol.
1956 User datagram protocol V6.
1960 When the protocol is TCP or UDP, the port must also be given, as well as the
1961 hostname if the job is a TCP listener or UDP reader. For unix sockets, the
1962 normal :option:`filename` option should be used and the port is invalid.
1964 .. option:: listen : [netsplice] [net]
1966 For TCP network connections, tell fio to listen for incoming connections
1967 rather than initiating an outgoing connection. The :option:`hostname` must
1968 be omitted if this option is used.
1970 .. option:: pingpong : [netsplice] [net]
1972 Normally a network writer will just continue writing data, and a network
1973 reader will just consume packages. If ``pingpong=1`` is set, a writer will
1974 send its normal payload to the reader, then wait for the reader to send the
1975 same payload back. This allows fio to measure network latencies. The
1976 submission and completion latencies then measure local time spent sending or
1977 receiving, and the completion latency measures how long it took for the
1978 other end to receive and send back. For UDP multicast traffic
1979 ``pingpong=1`` should only be set for a single reader when multiple readers
1980 are listening to the same address.
1982 .. option:: window_size : [netsplice] [net]
1984 Set the desired socket buffer size for the connection.
1986 .. option:: mss : [netsplice] [net]
1988 Set the TCP maximum segment size (TCP_MAXSEG).
1990 .. option:: donorname=str : [e4defrag]
1992 File will be used as a block donor (swap extents between files).
1994 .. option:: inplace=int : [e4defrag]
1996 Configure donor file blocks allocation strategy:
1999 Default. Preallocate donor's file on init.
2001 Allocate space immediately inside defragment event, and free right
2004 .. option:: clustername=str : [rbd]
2006 Specifies the name of the Ceph cluster.
2008 .. option:: rbdname=str : [rbd]
2010 Specifies the name of the RBD.
2012 .. option:: pool=str : [rbd]
2014 Specifies the name of the Ceph pool containing RBD.
2016 .. option:: clientname=str : [rbd]
2018 Specifies the username (without the 'client.' prefix) used to access the
2019 Ceph cluster. If the *clustername* is specified, the *clientname* shall be
2020 the full *type.id* string. If no type. prefix is given, fio will add
2021 'client.' by default.
2023 .. option:: skip_bad=bool : [mtd]
2025 Skip operations against known bad blocks.
2027 .. option:: hdfsdirectory : [libhdfs]
2029 libhdfs will create chunk in this HDFS directory.
2031 .. option:: chunk_size : [libhdfs]
2033 The size of the chunk to use for each file.
2035 .. option:: verb=str : [rdma]
2037 The RDMA verb to use on this side of the RDMA ioengine connection. Valid
2038 values are write, read, send and recv. These correspond to the equivalent
2039 RDMA verbs (e.g. write = rdma_write etc.). Note that this only needs to be
2040 specified on the client side of the connection. See the examples folder.
2042 .. option:: bindname=str : [rdma]
2044 The name to use to bind the local RDMA-CM connection to a local RDMA device.
2045 This could be a hostname or an IPv4 or IPv6 address. On the server side this
2046 will be passed into the rdma_bind_addr() function and on the client site it
2047 will be used in the rdma_resolve_add() function. This can be useful when
2048 multiple paths exist between the client and the server or in certain loopback
2054 .. option:: iodepth=int
2056 Number of I/O units to keep in flight against the file. Note that
2057 increasing *iodepth* beyond 1 will not affect synchronous ioengines (except
2058 for small degrees when :option:`verify_async` is in use). Even async
2059 engines may impose OS restrictions causing the desired depth not to be
2060 achieved. This may happen on Linux when using libaio and not setting
2061 :option:`direct`\=1, since buffered I/O is not async on that OS. Keep an
2062 eye on the I/O depth distribution in the fio output to verify that the
2063 achieved depth is as expected. Default: 1.
2065 .. option:: iodepth_batch_submit=int, iodepth_batch=int
2067 This defines how many pieces of I/O to submit at once. It defaults to 1
2068 which means that we submit each I/O as soon as it is available, but can be
2069 raised to submit bigger batches of I/O at the time. If it is set to 0 the
2070 :option:`iodepth` value will be used.
2072 .. option:: iodepth_batch_complete_min=int, iodepth_batch_complete=int
2074 This defines how many pieces of I/O to retrieve at once. It defaults to 1
2075 which means that we'll ask for a minimum of 1 I/O in the retrieval process
2076 from the kernel. The I/O retrieval will go on until we hit the limit set by
2077 :option:`iodepth_low`. If this variable is set to 0, then fio will always
2078 check for completed events before queuing more I/O. This helps reduce I/O
2079 latency, at the cost of more retrieval system calls.
2081 .. option:: iodepth_batch_complete_max=int
2083 This defines maximum pieces of I/O to retrieve at once. This variable should
2084 be used along with :option:`iodepth_batch_complete_min`\=int variable,
2085 specifying the range of min and max amount of I/O which should be
2086 retrieved. By default it is equal to the :option:`iodepth_batch_complete_min`
2091 iodepth_batch_complete_min=1
2092 iodepth_batch_complete_max=<iodepth>
2094 which means that we will retrieve at least 1 I/O and up to the whole
2095 submitted queue depth. If none of I/O has been completed yet, we will wait.
2099 iodepth_batch_complete_min=0
2100 iodepth_batch_complete_max=<iodepth>
2102 which means that we can retrieve up to the whole submitted queue depth, but
2103 if none of I/O has been completed yet, we will NOT wait and immediately exit
2104 the system call. In this example we simply do polling.
2106 .. option:: iodepth_low=int
2108 The low water mark indicating when to start filling the queue
2109 again. Defaults to the same as :option:`iodepth`, meaning that fio will
2110 attempt to keep the queue full at all times. If :option:`iodepth` is set to
2111 e.g. 16 and *iodepth_low* is set to 4, then after fio has filled the queue of
2112 16 requests, it will let the depth drain down to 4 before starting to fill
2115 .. option:: serialize_overlap=bool
2117 Serialize in-flight I/Os that might otherwise cause or suffer from data races.
2118 When two or more I/Os are submitted simultaneously, there is no guarantee that
2119 the I/Os will be processed or completed in the submitted order. Further, if
2120 two or more of those I/Os are writes, any overlapping region between them can
2121 become indeterminate/undefined on certain storage. These issues can cause
2122 verification to fail erratically when at least one of the racing I/Os is
2123 changing data and the overlapping region has a non-zero size. Setting
2124 ``serialize_overlap`` tells fio to avoid provoking this behavior by explicitly
2125 serializing in-flight I/Os that have a non-zero overlap. Note that setting
2126 this option can reduce both performance and the :option:`iodepth` achieved.
2127 Additionally this option does not work when :option:`io_submit_mode` is set to
2128 offload. Default: false.
2130 .. option:: io_submit_mode=str
2132 This option controls how fio submits the I/O to the I/O engine. The default
2133 is `inline`, which means that the fio job threads submit and reap I/O
2134 directly. If set to `offload`, the job threads will offload I/O submission
2135 to a dedicated pool of I/O threads. This requires some coordination and thus
2136 has a bit of extra overhead, especially for lower queue depth I/O where it
2137 can increase latencies. The benefit is that fio can manage submission rates
2138 independently of the device completion rates. This avoids skewed latency
2139 reporting if I/O gets backed up on the device side (the coordinated omission
2146 .. option:: thinktime=time
2148 Stall the job for the specified period of time after an I/O has completed before issuing the
2149 next. May be used to simulate processing being done by an application.
2150 When the unit is omitted, the value is interpreted in microseconds. See
2151 :option:`thinktime_blocks` and :option:`thinktime_spin`.
2153 .. option:: thinktime_spin=time
2155 Only valid if :option:`thinktime` is set - pretend to spend CPU time doing
2156 something with the data received, before falling back to sleeping for the
2157 rest of the period specified by :option:`thinktime`. When the unit is
2158 omitted, the value is interpreted in microseconds.
2160 .. option:: thinktime_blocks=int
2162 Only valid if :option:`thinktime` is set - control how many blocks to issue,
2163 before waiting :option:`thinktime` usecs. If not set, defaults to 1 which will make
2164 fio wait :option:`thinktime` usecs after every block. This effectively makes any
2165 queue depth setting redundant, since no more than 1 I/O will be queued
2166 before we have to complete it and do our :option:`thinktime`. In other words, this
2167 setting effectively caps the queue depth if the latter is larger.
2169 .. option:: rate=int[,int][,int]
2171 Cap the bandwidth used by this job. The number is in bytes/sec, the normal
2172 suffix rules apply. Comma-separated values may be specified for reads,
2173 writes, and trims as described in :option:`blocksize`.
2175 For example, using `rate=1m,500k` would limit reads to 1MiB/sec and writes to
2176 500KiB/sec. Capping only reads or writes can be done with `rate=,500k` or
2177 `rate=500k,` where the former will only limit writes (to 500KiB/sec) and the
2178 latter will only limit reads.
2180 .. option:: rate_min=int[,int][,int]
2182 Tell fio to do whatever it can to maintain at least this bandwidth. Failing
2183 to meet this requirement will cause the job to exit. Comma-separated values
2184 may be specified for reads, writes, and trims as described in
2185 :option:`blocksize`.
2187 .. option:: rate_iops=int[,int][,int]
2189 Cap the bandwidth to this number of IOPS. Basically the same as
2190 :option:`rate`, just specified independently of bandwidth. If the job is
2191 given a block size range instead of a fixed value, the smallest block size
2192 is used as the metric. Comma-separated values may be specified for reads,
2193 writes, and trims as described in :option:`blocksize`.
2195 .. option:: rate_iops_min=int[,int][,int]
2197 If fio doesn't meet this rate of I/O, it will cause the job to exit.
2198 Comma-separated values may be specified for reads, writes, and trims as
2199 described in :option:`blocksize`.
2201 .. option:: rate_process=str
2203 This option controls how fio manages rated I/O submissions. The default is
2204 `linear`, which submits I/O in a linear fashion with fixed delays between
2205 I/Os that gets adjusted based on I/O completion rates. If this is set to
2206 `poisson`, fio will submit I/O based on a more real world random request
2207 flow, known as the Poisson process
2208 (https://en.wikipedia.org/wiki/Poisson_point_process). The lambda will be
2209 10^6 / IOPS for the given workload.
2215 .. option:: latency_target=time
2217 If set, fio will attempt to find the max performance point that the given
2218 workload will run at while maintaining a latency below this target. When
2219 the unit is omitted, the value is interpreted in microseconds. See
2220 :option:`latency_window` and :option:`latency_percentile`.
2222 .. option:: latency_window=time
2224 Used with :option:`latency_target` to specify the sample window that the job
2225 is run at varying queue depths to test the performance. When the unit is
2226 omitted, the value is interpreted in microseconds.
2228 .. option:: latency_percentile=float
2230 The percentage of I/Os that must fall within the criteria specified by
2231 :option:`latency_target` and :option:`latency_window`. If not set, this
2232 defaults to 100.0, meaning that all I/Os must be equal or below to the value
2233 set by :option:`latency_target`.
2235 .. option:: max_latency=time
2237 If set, fio will exit the job with an ETIMEDOUT error if it exceeds this
2238 maximum latency. When the unit is omitted, the value is interpreted in
2241 .. option:: rate_cycle=int
2243 Average bandwidth for :option:`rate` and :option:`rate_min` over this number
2244 of milliseconds. Defaults to 1000.
2250 .. option:: write_iolog=str
2252 Write the issued I/O patterns to the specified file. See
2253 :option:`read_iolog`. Specify a separate file for each job, otherwise the
2254 iologs will be interspersed and the file may be corrupt.
2256 .. option:: read_iolog=str
2258 Open an iolog with the specified filename and replay the I/O patterns it
2259 contains. This can be used to store a workload and replay it sometime
2260 later. The iolog given may also be a blktrace binary file, which allows fio
2261 to replay a workload captured by :command:`blktrace`. See
2262 :manpage:`blktrace(8)` for how to capture such logging data. For blktrace
2263 replay, the file needs to be turned into a blkparse binary data file first
2264 (``blkparse <device> -o /dev/null -d file_for_fio.bin``).
2266 .. option:: replay_no_stall=bool
2268 When replaying I/O with :option:`read_iolog` the default behavior is to
2269 attempt to respect the timestamps within the log and replay them with the
2270 appropriate delay between IOPS. By setting this variable fio will not
2271 respect the timestamps and attempt to replay them as fast as possible while
2272 still respecting ordering. The result is the same I/O pattern to a given
2273 device, but different timings.
2275 .. option:: replay_redirect=str
2277 While replaying I/O patterns using :option:`read_iolog` the default behavior
2278 is to replay the IOPS onto the major/minor device that each IOP was recorded
2279 from. This is sometimes undesirable because on a different machine those
2280 major/minor numbers can map to a different device. Changing hardware on the
2281 same system can also result in a different major/minor mapping.
2282 ``replay_redirect`` causes all I/Os to be replayed onto the single specified
2283 device regardless of the device it was recorded
2284 from. i.e. :option:`replay_redirect`\= :file:`/dev/sdc` would cause all I/O
2285 in the blktrace or iolog to be replayed onto :file:`/dev/sdc`. This means
2286 multiple devices will be replayed onto a single device, if the trace
2287 contains multiple devices. If you want multiple devices to be replayed
2288 concurrently to multiple redirected devices you must blkparse your trace
2289 into separate traces and replay them with independent fio invocations.
2290 Unfortunately this also breaks the strict time ordering between multiple
2293 .. option:: replay_align=int
2295 Force alignment of I/O offsets and lengths in a trace to this power of 2
2298 .. option:: replay_scale=int
2300 Scale sector offsets down by this factor when replaying traces.
2303 Threads, processes and job synchronization
2304 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2308 Fio defaults to creating jobs by using fork, however if this option is
2309 given, fio will create jobs by using POSIX Threads' function
2310 :manpage:`pthread_create(3)` to create threads instead.
2312 .. option:: wait_for=str
2314 If set, the current job won't be started until all workers of the specified
2315 waitee job are done.
2317 ``wait_for`` operates on the job name basis, so there are a few
2318 limitations. First, the waitee must be defined prior to the waiter job
2319 (meaning no forward references). Second, if a job is being referenced as a
2320 waitee, it must have a unique name (no duplicate waitees).
2322 .. option:: nice=int
2324 Run the job with the given nice value. See man :manpage:`nice(2)`.
2326 On Windows, values less than -15 set the process class to "High"; -1 through
2327 -15 set "Above Normal"; 1 through 15 "Below Normal"; and above 15 "Idle"
2330 .. option:: prio=int
2332 Set the I/O priority value of this job. Linux limits us to a positive value
2333 between 0 and 7, with 0 being the highest. See man
2334 :manpage:`ionice(1)`. Refer to an appropriate manpage for other operating
2335 systems since meaning of priority may differ.
2337 .. option:: prioclass=int
2339 Set the I/O priority class. See man :manpage:`ionice(1)`.
2341 .. option:: cpumask=int
2343 Set the CPU affinity of this job. The parameter given is a bit mask of
2344 allowed CPUs the job may run on. So if you want the allowed CPUs to be 1
2345 and 5, you would pass the decimal value of (1 << 1 | 1 << 5), or 34. See man
2346 :manpage:`sched_setaffinity(2)`. This may not work on all supported
2347 operating systems or kernel versions. This option doesn't work well for a
2348 higher CPU count than what you can store in an integer mask, so it can only
2349 control cpus 1-32. For boxes with larger CPU counts, use
2350 :option:`cpus_allowed`.
2352 .. option:: cpus_allowed=str
2354 Controls the same options as :option:`cpumask`, but accepts a textual
2355 specification of the permitted CPUs instead. So to use CPUs 1 and 5 you
2356 would specify ``cpus_allowed=1,5``. This option also allows a range of CPUs
2357 to be specified -- say you wanted a binding to CPUs 1, 5, and 8 to 15, you
2358 would set ``cpus_allowed=1,5,8-15``.
2360 .. option:: cpus_allowed_policy=str
2362 Set the policy of how fio distributes the CPUs specified by
2363 :option:`cpus_allowed` or :option:`cpumask`. Two policies are supported:
2366 All jobs will share the CPU set specified.
2368 Each job will get a unique CPU from the CPU set.
2370 **shared** is the default behavior, if the option isn't specified. If
2371 **split** is specified, then fio will will assign one cpu per job. If not
2372 enough CPUs are given for the jobs listed, then fio will roundrobin the CPUs
2375 .. option:: numa_cpu_nodes=str
2377 Set this job running on specified NUMA nodes' CPUs. The arguments allow
2378 comma delimited list of cpu numbers, A-B ranges, or `all`. Note, to enable
2379 NUMA options support, fio must be built on a system with libnuma-dev(el)
2382 .. option:: numa_mem_policy=str
2384 Set this job's memory policy and corresponding NUMA nodes. Format of the
2389 ``mode`` is one of the following memory poicies: ``default``, ``prefer``,
2390 ``bind``, ``interleave`` or ``local``. For ``default`` and ``local`` memory
2391 policies, no node needs to be specified. For ``prefer``, only one node is
2392 allowed. For ``bind`` and ``interleave`` the ``nodelist`` may be as
2393 follows: a comma delimited list of numbers, A-B ranges, or `all`.
2395 .. option:: cgroup=str
2397 Add job to this control group. If it doesn't exist, it will be created. The
2398 system must have a mounted cgroup blkio mount point for this to work. If
2399 your system doesn't have it mounted, you can do so with::
2401 # mount -t cgroup -o blkio none /cgroup
2403 .. option:: cgroup_weight=int
2405 Set the weight of the cgroup to this value. See the documentation that comes
2406 with the kernel, allowed values are in the range of 100..1000.
2408 .. option:: cgroup_nodelete=bool
2410 Normally fio will delete the cgroups it has created after the job
2411 completion. To override this behavior and to leave cgroups around after the
2412 job completion, set ``cgroup_nodelete=1``. This can be useful if one wants
2413 to inspect various cgroup files after job completion. Default: false.
2415 .. option:: flow_id=int
2417 The ID of the flow. If not specified, it defaults to being a global
2418 flow. See :option:`flow`.
2420 .. option:: flow=int
2422 Weight in token-based flow control. If this value is used, then there is a
2423 'flow counter' which is used to regulate the proportion of activity between
2424 two or more jobs. Fio attempts to keep this flow counter near zero. The
2425 ``flow`` parameter stands for how much should be added or subtracted to the
2426 flow counter on each iteration of the main I/O loop. That is, if one job has
2427 ``flow=8`` and another job has ``flow=-1``, then there will be a roughly 1:8
2428 ratio in how much one runs vs the other.
2430 .. option:: flow_watermark=int
2432 The maximum value that the absolute value of the flow counter is allowed to
2433 reach before the job must wait for a lower value of the counter.
2435 .. option:: flow_sleep=int
2437 The period of time, in microseconds, to wait after the flow watermark has
2438 been exceeded before retrying operations.
2440 .. option:: stonewall, wait_for_previous
2442 Wait for preceding jobs in the job file to exit, before starting this
2443 one. Can be used to insert serialization points in the job file. A stone
2444 wall also implies starting a new reporting group, see
2445 :option:`group_reporting`.
2449 By default, fio will continue running all other jobs when one job finishes
2450 but sometimes this is not the desired action. Setting ``exitall`` will
2451 instead make fio terminate all other jobs when one job finishes.
2453 .. option:: exec_prerun=str
2455 Before running this job, issue the command specified through
2456 :manpage:`system(3)`. Output is redirected in a file called
2457 :file:`jobname.prerun.txt`.
2459 .. option:: exec_postrun=str
2461 After the job completes, issue the command specified though
2462 :manpage:`system(3)`. Output is redirected in a file called
2463 :file:`jobname.postrun.txt`.
2467 Instead of running as the invoking user, set the user ID to this value
2468 before the thread/process does any work.
2472 Set group ID, see :option:`uid`.
2478 .. option:: verify_only
2480 Do not perform specified workload, only verify data still matches previous
2481 invocation of this workload. This option allows one to check data multiple
2482 times at a later date without overwriting it. This option makes sense only
2483 for workloads that write data, and does not support workloads with the
2484 :option:`time_based` option set.
2486 .. option:: do_verify=bool
2488 Run the verify phase after a write phase. Only valid if :option:`verify` is
2491 .. option:: verify=str
2493 If writing to a file, fio can verify the file contents after each iteration
2494 of the job. Each verification method also implies verification of special
2495 header, which is written to the beginning of each block. This header also
2496 includes meta information, like offset of the block, block number, timestamp
2497 when block was written, etc. :option:`verify` can be combined with
2498 :option:`verify_pattern` option. The allowed values are:
2501 Use an md5 sum of the data area and store it in the header of
2505 Use an experimental crc64 sum of the data area and store it in the
2506 header of each block.
2509 Use a crc32c sum of the data area and store it in the header of
2510 each block. This will automatically use hardware acceleration
2511 (e.g. SSE4.2 on an x86 or CRC crypto extensions on ARM64) but will
2512 fall back to software crc32c if none is found. Generally the
2513 fatest checksum fio supports when hardware accelerated.
2519 Use a crc32 sum of the data area and store it in the header of each
2523 Use a crc16 sum of the data area and store it in the header of each
2527 Use a crc7 sum of the data area and store it in the header of each
2531 Use xxhash as the checksum function. Generally the fastest software
2532 checksum that fio supports.
2535 Use sha512 as the checksum function.
2538 Use sha256 as the checksum function.
2541 Use optimized sha1 as the checksum function.
2544 Use optimized sha3-224 as the checksum function.
2547 Use optimized sha3-256 as the checksum function.
2550 Use optimized sha3-384 as the checksum function.
2553 Use optimized sha3-512 as the checksum function.
2556 This option is deprecated, since now meta information is included in
2557 generic verification header and meta verification happens by
2558 default. For detailed information see the description of the
2559 :option:`verify` setting. This option is kept because of
2560 compatibility's sake with old configurations. Do not use it.
2563 Verify a strict pattern. Normally fio includes a header with some
2564 basic information and checksumming, but if this option is set, only
2565 the specific pattern set with :option:`verify_pattern` is verified.
2568 Only pretend to verify. Useful for testing internals with
2569 :option:`ioengine`\=null, not for much else.
2571 This option can be used for repeated burn-in tests of a system to make sure
2572 that the written data is also correctly read back. If the data direction
2573 given is a read or random read, fio will assume that it should verify a
2574 previously written file. If the data direction includes any form of write,
2575 the verify will be of the newly written data.
2577 .. option:: verifysort=bool
2579 If true, fio will sort written verify blocks when it deems it faster to read
2580 them back in a sorted manner. This is often the case when overwriting an
2581 existing file, since the blocks are already laid out in the file system. You
2582 can ignore this option unless doing huge amounts of really fast I/O where
2583 the red-black tree sorting CPU time becomes significant. Default: true.
2585 .. option:: verifysort_nr=int
2587 Pre-load and sort verify blocks for a read workload.
2589 .. option:: verify_offset=int
2591 Swap the verification header with data somewhere else in the block before
2592 writing. It is swapped back before verifying.
2594 .. option:: verify_interval=int
2596 Write the verification header at a finer granularity than the
2597 :option:`blocksize`. It will be written for chunks the size of
2598 ``verify_interval``. :option:`blocksize` should divide this evenly.
2600 .. option:: verify_pattern=str
2602 If set, fio will fill the I/O buffers with this pattern. Fio defaults to
2603 filling with totally random bytes, but sometimes it's interesting to fill
2604 with a known pattern for I/O verification purposes. Depending on the width
2605 of the pattern, fio will fill 1/2/3/4 bytes of the buffer at the time (it can
2606 be either a decimal or a hex number). The ``verify_pattern`` if larger than
2607 a 32-bit quantity has to be a hex number that starts with either "0x" or
2608 "0X". Use with :option:`verify`. Also, ``verify_pattern`` supports %o
2609 format, which means that for each block offset will be written and then
2610 verified back, e.g.::
2614 Or use combination of everything::
2616 verify_pattern=0xff%o"abcd"-12
2618 .. option:: verify_fatal=bool
2620 Normally fio will keep checking the entire contents before quitting on a
2621 block verification failure. If this option is set, fio will exit the job on
2622 the first observed failure. Default: false.
2624 .. option:: verify_dump=bool
2626 If set, dump the contents of both the original data block and the data block
2627 we read off disk to files. This allows later analysis to inspect just what
2628 kind of data corruption occurred. Off by default.
2630 .. option:: verify_async=int
2632 Fio will normally verify I/O inline from the submitting thread. This option
2633 takes an integer describing how many async offload threads to create for I/O
2634 verification instead, causing fio to offload the duty of verifying I/O
2635 contents to one or more separate threads. If using this offload option, even
2636 sync I/O engines can benefit from using an :option:`iodepth` setting higher
2637 than 1, as it allows them to have I/O in flight while verifies are running.
2638 Defaults to 0 async threads, i.e. verification is not asynchronous.
2640 .. option:: verify_async_cpus=str
2642 Tell fio to set the given CPU affinity on the async I/O verification
2643 threads. See :option:`cpus_allowed` for the format used.
2645 .. option:: verify_backlog=int
2647 Fio will normally verify the written contents of a job that utilizes verify
2648 once that job has completed. In other words, everything is written then
2649 everything is read back and verified. You may want to verify continually
2650 instead for a variety of reasons. Fio stores the meta data associated with
2651 an I/O block in memory, so for large verify workloads, quite a bit of memory
2652 would be used up holding this meta data. If this option is enabled, fio will
2653 write only N blocks before verifying these blocks.
2655 .. option:: verify_backlog_batch=int
2657 Control how many blocks fio will verify if :option:`verify_backlog` is
2658 set. If not set, will default to the value of :option:`verify_backlog`
2659 (meaning the entire queue is read back and verified). If
2660 ``verify_backlog_batch`` is less than :option:`verify_backlog` then not all
2661 blocks will be verified, if ``verify_backlog_batch`` is larger than
2662 :option:`verify_backlog`, some blocks will be verified more than once.
2664 .. option:: verify_state_save=bool
2666 When a job exits during the write phase of a verify workload, save its
2667 current state. This allows fio to replay up until that point, if the verify
2668 state is loaded for the verify read phase. The format of the filename is,
2671 <type>-<jobname>-<jobindex>-verify.state.
2673 <type> is "local" for a local run, "sock" for a client/server socket
2674 connection, and "ip" (192.168.0.1, for instance) for a networked
2675 client/server connection. Defaults to true.
2677 .. option:: verify_state_load=bool
2679 If a verify termination trigger was used, fio stores the current write state
2680 of each thread. This can be used at verification time so that fio knows how
2681 far it should verify. Without this information, fio will run a full
2682 verification pass, according to the settings in the job file used. Default
2685 .. option:: trim_percentage=int
2687 Number of verify blocks to discard/trim.
2689 .. option:: trim_verify_zero=bool
2691 Verify that trim/discarded blocks are returned as zeros.
2693 .. option:: trim_backlog=int
2695 Trim after this number of blocks are written.
2697 .. option:: trim_backlog_batch=int
2699 Trim this number of I/O blocks.
2701 .. option:: experimental_verify=bool
2703 Enable experimental verification.
2708 .. option:: steadystate=str:float, ss=str:float
2710 Define the criterion and limit for assessing steady state performance. The
2711 first parameter designates the criterion whereas the second parameter sets
2712 the threshold. When the criterion falls below the threshold for the
2713 specified duration, the job will stop. For example, `iops_slope:0.1%` will
2714 direct fio to terminate the job when the least squares regression slope
2715 falls below 0.1% of the mean IOPS. If :option:`group_reporting` is enabled
2716 this will apply to all jobs in the group. Below is the list of available
2717 steady state assessment criteria. All assessments are carried out using only
2718 data from the rolling collection window. Threshold limits can be expressed
2719 as a fixed value or as a percentage of the mean in the collection window.
2722 Collect IOPS data. Stop the job if all individual IOPS measurements
2723 are within the specified limit of the mean IOPS (e.g., ``iops:2``
2724 means that all individual IOPS values must be within 2 of the mean,
2725 whereas ``iops:0.2%`` means that all individual IOPS values must be
2726 within 0.2% of the mean IOPS to terminate the job).
2729 Collect IOPS data and calculate the least squares regression
2730 slope. Stop the job if the slope falls below the specified limit.
2733 Collect bandwidth data. Stop the job if all individual bandwidth
2734 measurements are within the specified limit of the mean bandwidth.
2737 Collect bandwidth data and calculate the least squares regression
2738 slope. Stop the job if the slope falls below the specified limit.
2740 .. option:: steadystate_duration=time, ss_dur=time
2742 A rolling window of this duration will be used to judge whether steady state
2743 has been reached. Data will be collected once per second. The default is 0
2744 which disables steady state detection. When the unit is omitted, the
2745 value is interpreted in seconds.
2747 .. option:: steadystate_ramp_time=time, ss_ramp=time
2749 Allow the job to run for the specified duration before beginning data
2750 collection for checking the steady state job termination criterion. The
2751 default is 0. When the unit is omitted, the value is interpreted in seconds.
2754 Measurements and reporting
2755 ~~~~~~~~~~~~~~~~~~~~~~~~~~
2757 .. option:: per_job_logs=bool
2759 If set, this generates bw/clat/iops log with per file private filenames. If
2760 not set, jobs with identical names will share the log filename. Default:
2763 .. option:: group_reporting
2765 It may sometimes be interesting to display statistics for groups of jobs as
2766 a whole instead of for each individual job. This is especially true if
2767 :option:`numjobs` is used; looking at individual thread/process output
2768 quickly becomes unwieldy. To see the final report per-group instead of
2769 per-job, use :option:`group_reporting`. Jobs in a file will be part of the
2770 same reporting group, unless if separated by a :option:`stonewall`, or by
2771 using :option:`new_group`.
2773 .. option:: new_group
2775 Start a new reporting group. See: :option:`group_reporting`. If not given,
2776 all jobs in a file will be part of the same reporting group, unless
2777 separated by a :option:`stonewall`.
2779 .. option:: stats=bool
2781 By default, fio collects and shows final output results for all jobs
2782 that run. If this option is set to 0, then fio will ignore it in
2783 the final stat output.
2785 .. option:: write_bw_log=str
2787 If given, write a bandwidth log for this job. Can be used to store data of
2788 the bandwidth of the jobs in their lifetime.
2790 If no str argument is given, the default filename of
2791 :file:`jobname_type.x.log` is used. Even when the argument is given, fio
2792 will still append the type of log. So if one specifies::
2796 The actual log name will be :file:`foo_bw.x.log` where `x` is the index
2797 of the job (`1..N`, where `N` is the number of jobs). If
2798 :option:`per_job_logs` is false, then the filename will not include the
2801 The included :command:`fio_generate_plots` script uses :command:`gnuplot` to turn these
2802 text files into nice graphs. See `Log File Formats`_ for how data is
2803 structured within the file.
2805 .. option:: write_lat_log=str
2807 Same as :option:`write_bw_log`, except this option creates I/O
2808 submission (e.g., :file:`name_slat.x.log`), completion (e.g.,
2809 :file:`name_clat.x.log`), and total (e.g., :file:`name_lat.x.log`)
2810 latency files instead. See :option:`write_bw_log` for details about
2811 the filename format and `Log File Formats`_ for how data is structured
2814 .. option:: write_hist_log=str
2816 Same as :option:`write_bw_log` but writes an I/O completion latency
2817 histogram file (e.g., :file:`name_hist.x.log`) instead. Note that this
2818 file will be empty unless :option:`log_hist_msec` has also been set.
2819 See :option:`write_bw_log` for details about the filename format and
2820 `Log File Formats`_ for how data is structured within the file.
2822 .. option:: write_iops_log=str
2824 Same as :option:`write_bw_log`, but writes an IOPS file (e.g.
2825 :file:`name_iops.x.log`) instead. See :option:`write_bw_log` for
2826 details about the filename format and `Log File Formats`_ for how data
2827 is structured within the file.
2829 .. option:: log_avg_msec=int
2831 By default, fio will log an entry in the iops, latency, or bw log for every
2832 I/O that completes. When writing to the disk log, that can quickly grow to a
2833 very large size. Setting this option makes fio average the each log entry
2834 over the specified period of time, reducing the resolution of the log. See
2835 :option:`log_max_value` as well. Defaults to 0, logging all entries.
2836 Also see `Log File Formats`_.
2838 .. option:: log_hist_msec=int
2840 Same as :option:`log_avg_msec`, but logs entries for completion latency
2841 histograms. Computing latency percentiles from averages of intervals using
2842 :option:`log_avg_msec` is inaccurate. Setting this option makes fio log
2843 histogram entries over the specified period of time, reducing log sizes for
2844 high IOPS devices while retaining percentile accuracy. See
2845 :option:`log_hist_coarseness` and :option:`write_hist_log` as well.
2846 Defaults to 0, meaning histogram logging is disabled.
2848 .. option:: log_hist_coarseness=int
2850 Integer ranging from 0 to 6, defining the coarseness of the resolution of
2851 the histogram logs enabled with :option:`log_hist_msec`. For each increment
2852 in coarseness, fio outputs half as many bins. Defaults to 0, for which
2853 histogram logs contain 1216 latency bins. See :option:`write_hist_log`
2854 and `Log File Formats`_.
2856 .. option:: log_max_value=bool
2858 If :option:`log_avg_msec` is set, fio logs the average over that window. If
2859 you instead want to log the maximum value, set this option to 1. Defaults to
2860 0, meaning that averaged values are logged.
2862 .. option:: log_offset=bool
2864 If this is set, the iolog options will include the byte offset for the I/O
2865 entry as well as the other data values. Defaults to 0 meaning that
2866 offsets are not present in logs. Also see `Log File Formats`_.
2868 .. option:: log_compression=int
2870 If this is set, fio will compress the I/O logs as it goes, to keep the
2871 memory footprint lower. When a log reaches the specified size, that chunk is
2872 removed and compressed in the background. Given that I/O logs are fairly
2873 highly compressible, this yields a nice memory savings for longer runs. The
2874 downside is that the compression will consume some background CPU cycles, so
2875 it may impact the run. This, however, is also true if the logging ends up
2876 consuming most of the system memory. So pick your poison. The I/O logs are
2877 saved normally at the end of a run, by decompressing the chunks and storing
2878 them in the specified log file. This feature depends on the availability of
2881 .. option:: log_compression_cpus=str
2883 Define the set of CPUs that are allowed to handle online log compression for
2884 the I/O jobs. This can provide better isolation between performance
2885 sensitive jobs, and background compression work.
2887 .. option:: log_store_compressed=bool
2889 If set, fio will store the log files in a compressed format. They can be
2890 decompressed with fio, using the :option:`--inflate-log` command line
2891 parameter. The files will be stored with a :file:`.fz` suffix.
2893 .. option:: log_unix_epoch=bool
2895 If set, fio will log Unix timestamps to the log files produced by enabling
2896 write_type_log for each log type, instead of the default zero-based
2899 .. option:: block_error_percentiles=bool
2901 If set, record errors in trim block-sized units from writes and trims and
2902 output a histogram of how many trims it took to get to errors, and what kind
2903 of error was encountered.
2905 .. option:: bwavgtime=int
2907 Average the calculated bandwidth over the given time. Value is specified in
2908 milliseconds. If the job also does bandwidth logging through
2909 :option:`write_bw_log`, then the minimum of this option and
2910 :option:`log_avg_msec` will be used. Default: 500ms.
2912 .. option:: iopsavgtime=int
2914 Average the calculated IOPS over the given time. Value is specified in
2915 milliseconds. If the job also does IOPS logging through
2916 :option:`write_iops_log`, then the minimum of this option and
2917 :option:`log_avg_msec` will be used. Default: 500ms.
2919 .. option:: disk_util=bool
2921 Generate disk utilization statistics, if the platform supports it.
2924 .. option:: disable_lat=bool
2926 Disable measurements of total latency numbers. Useful only for cutting back
2927 the number of calls to :manpage:`gettimeofday(2)`, as that does impact
2928 performance at really high IOPS rates. Note that to really get rid of a
2929 large amount of these calls, this option must be used with
2930 :option:`disable_slat` and :option:`disable_bw_measurement` as well.
2932 .. option:: disable_clat=bool
2934 Disable measurements of completion latency numbers. See
2935 :option:`disable_lat`.
2937 .. option:: disable_slat=bool
2939 Disable measurements of submission latency numbers. See
2940 :option:`disable_lat`.
2942 .. option:: disable_bw_measurement=bool, disable_bw=bool
2944 Disable measurements of throughput/bandwidth numbers. See
2945 :option:`disable_lat`.
2947 .. option:: clat_percentiles=bool
2949 Enable the reporting of percentiles of completion latencies. This
2950 option is mutually exclusive with :option:`lat_percentiles`.
2952 .. option:: lat_percentiles=bool
2954 Enable the reporting of percentiles of I/O latencies. This is similar
2955 to :option:`clat_percentiles`, except that this includes the
2956 submission latency. This option is mutually exclusive with
2957 :option:`clat_percentiles`.
2959 .. option:: percentile_list=float_list
2961 Overwrite the default list of percentiles for completion latencies and
2962 the block error histogram. Each number is a floating number in the
2963 range (0,100], and the maximum length of the list is 20. Use ``:`` to
2964 separate the numbers, and list the numbers in ascending order. For
2965 example, ``--percentile_list=99.5:99.9`` will cause fio to report the
2966 values of completion latency below which 99.5% and 99.9% of the observed
2967 latencies fell, respectively.
2969 .. option:: significant_figures=int
2971 If using :option:`--output-format` of `normal`, set the significant
2972 figures to this value. Higher values will yield more precise IOPS and
2973 throughput units, while lower values will round. Requires a minimum
2974 value of 1 and a maximum value of 10. Defaults to 4.
2980 .. option:: exitall_on_error
2982 When one job finishes in error, terminate the rest. The default is to wait
2983 for each job to finish.
2985 .. option:: continue_on_error=str
2987 Normally fio will exit the job on the first observed failure. If this option
2988 is set, fio will continue the job when there is a 'non-fatal error' (EIO or
2989 EILSEQ) until the runtime is exceeded or the I/O size specified is
2990 completed. If this option is used, there are two more stats that are
2991 appended, the total error count and the first error. The error field given
2992 in the stats is the first error that was hit during the run.
2994 The allowed values are:
2997 Exit on any I/O or verify errors.
3000 Continue on read errors, exit on all others.
3003 Continue on write errors, exit on all others.
3006 Continue on any I/O error, exit on all others.
3009 Continue on verify errors, exit on all others.
3012 Continue on all errors.
3015 Backward-compatible alias for 'none'.
3018 Backward-compatible alias for 'all'.
3020 .. option:: ignore_error=str
3022 Sometimes you want to ignore some errors during test in that case you can
3023 specify error list for each error type, instead of only being able to
3024 ignore the default 'non-fatal error' using :option:`continue_on_error`.
3025 ``ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST`` errors for
3026 given error type is separated with ':'. Error may be symbol ('ENOSPC',
3027 'ENOMEM') or integer. Example::
3029 ignore_error=EAGAIN,ENOSPC:122
3031 This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from
3032 WRITE. This option works by overriding :option:`continue_on_error` with
3033 the list of errors for each error type if any.
3035 .. option:: error_dump=bool
3037 If set dump every error even if it is non fatal, true by default. If
3038 disabled only fatal error will be dumped.
3040 Running predefined workloads
3041 ----------------------------
3043 Fio includes predefined profiles that mimic the I/O workloads generated by
3046 .. option:: profile=str
3048 The predefined workload to run. Current profiles are:
3051 Threaded I/O bench (tiotest/tiobench) like workload.
3054 Aerospike Certification Tool (ACT) like workload.
3056 To view a profile's additional options use :option:`--cmdhelp` after specifying
3057 the profile. For example::
3059 $ fio --profile=act --cmdhelp
3064 .. option:: device-names=str
3069 .. option:: load=int
3072 ACT load multiplier. Default: 1.
3074 .. option:: test-duration=time
3077 How long the entire test takes to run. When the unit is omitted, the value
3078 is given in seconds. Default: 24h.
3080 .. option:: threads-per-queue=int
3083 Number of read I/O threads per device. Default: 8.
3085 .. option:: read-req-num-512-blocks=int
3088 Number of 512B blocks to read at the time. Default: 3.
3090 .. option:: large-block-op-kbytes=int
3093 Size of large block ops in KiB (writes). Default: 131072.
3098 Set to run ACT prep phase.
3100 Tiobench profile options
3101 ~~~~~~~~~~~~~~~~~~~~~~~~
3103 .. option:: size=str
3108 .. option:: block=int
3111 Block size in bytes. Default: 4096.
3113 .. option:: numruns=int
3123 .. option:: threads=int
3128 Interpreting the output
3129 -----------------------
3132 Example output was based on the following:
3133 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --time_based \
3134 --rate=1256k --bs=14K --name=quick --runtime=1s --name=mixed \
3135 --runtime=2m --rw=rw
3137 Fio spits out a lot of output. While running, fio will display the status of the
3138 jobs created. An example of that would be::
3140 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]
3142 The characters inside the first set of square brackets denote the current status of
3143 each thread. The first character is the first job defined in the job file, and so
3144 forth. The possible values (in typical life cycle order) are:
3146 +------+-----+-----------------------------------------------------------+
3148 +======+=====+===========================================================+
3149 | P | | Thread setup, but not started. |
3150 +------+-----+-----------------------------------------------------------+
3151 | C | | Thread created. |
3152 +------+-----+-----------------------------------------------------------+
3153 | I | | Thread initialized, waiting or generating necessary data. |
3154 +------+-----+-----------------------------------------------------------+
3155 | | p | Thread running pre-reading file(s). |
3156 +------+-----+-----------------------------------------------------------+
3157 | | / | Thread is in ramp period. |
3158 +------+-----+-----------------------------------------------------------+
3159 | | R | Running, doing sequential reads. |
3160 +------+-----+-----------------------------------------------------------+
3161 | | r | Running, doing random reads. |
3162 +------+-----+-----------------------------------------------------------+
3163 | | W | Running, doing sequential writes. |
3164 +------+-----+-----------------------------------------------------------+
3165 | | w | Running, doing random writes. |
3166 +------+-----+-----------------------------------------------------------+
3167 | | M | Running, doing mixed sequential reads/writes. |
3168 +------+-----+-----------------------------------------------------------+
3169 | | m | Running, doing mixed random reads/writes. |
3170 +------+-----+-----------------------------------------------------------+
3171 | | D | Running, doing sequential trims. |
3172 +------+-----+-----------------------------------------------------------+
3173 | | d | Running, doing random trims. |
3174 +------+-----+-----------------------------------------------------------+
3175 | | F | Running, currently waiting for :manpage:`fsync(2)`. |
3176 +------+-----+-----------------------------------------------------------+
3177 | | V | Running, doing verification of written data. |
3178 +------+-----+-----------------------------------------------------------+
3179 | f | | Thread finishing. |
3180 +------+-----+-----------------------------------------------------------+
3181 | E | | Thread exited, not reaped by main thread yet. |
3182 +------+-----+-----------------------------------------------------------+
3183 | _ | | Thread reaped. |
3184 +------+-----+-----------------------------------------------------------+
3185 | X | | Thread reaped, exited with an error. |
3186 +------+-----+-----------------------------------------------------------+
3187 | K | | Thread reaped, exited due to signal. |
3188 +------+-----+-----------------------------------------------------------+
3191 Example output was based on the following:
3192 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --runtime=58m \
3193 --time_based --rate=2512k --bs=256K --numjobs=10 \
3194 --name=readers --rw=read --name=writers --rw=write
3196 Fio will condense the thread string as not to take up more space on the command
3197 line than needed. For instance, if you have 10 readers and 10 writers running,
3198 the output would look like this::
3200 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]
3202 Note that the status string is displayed in order, so it's possible to tell which of
3203 the jobs are currently doing what. In the example above this means that jobs 1--10
3204 are readers and 11--20 are writers.
3206 The other values are fairly self explanatory -- number of threads currently
3207 running and doing I/O, the number of currently open files (f=), the estimated
3208 completion percentage, the rate of I/O since last check (read speed listed first,
3209 then write speed and optionally trim speed) in terms of bandwidth and IOPS,
3210 and time to completion for the current running group. It's impossible to estimate
3211 runtime of the following groups (if any).
3214 Example output was based on the following:
3215 TZ=UTC fio --iodepth=16 --ioengine=posixaio --filename=/tmp/fiofile \
3216 --direct=1 --size=100M --time_based --runtime=50s --rate_iops=89 \
3217 --bs=7K --name=Client1 --rw=write
3219 When fio is done (or interrupted by :kbd:`Ctrl-C`), it will show the data for
3220 each thread, group of threads, and disks in that order. For each overall thread (or
3221 group) the output looks like::
3223 Client1: (groupid=0, jobs=1): err= 0: pid=16109: Sat Jun 24 12:07:54 2017
3224 write: IOPS=88, BW=623KiB/s (638kB/s)(30.4MiB/50032msec)
3225 slat (nsec): min=500, max=145500, avg=8318.00, stdev=4781.50
3226 clat (usec): min=170, max=78367, avg=4019.02, stdev=8293.31
3227 lat (usec): min=174, max=78375, avg=4027.34, stdev=8291.79
3228 clat percentiles (usec):
3229 | 1.00th=[ 302], 5.00th=[ 326], 10.00th=[ 343], 20.00th=[ 363],
3230 | 30.00th=[ 392], 40.00th=[ 404], 50.00th=[ 416], 60.00th=[ 445],
3231 | 70.00th=[ 816], 80.00th=[ 6718], 90.00th=[12911], 95.00th=[21627],
3232 | 99.00th=[43779], 99.50th=[51643], 99.90th=[68682], 99.95th=[72877],
3234 bw ( KiB/s): min= 532, max= 686, per=0.10%, avg=622.87, stdev=24.82, samples= 100
3235 iops : min= 76, max= 98, avg=88.98, stdev= 3.54, samples= 100
3236 lat (usec) : 250=0.04%, 500=64.11%, 750=4.81%, 1000=2.79%
3237 lat (msec) : 2=4.16%, 4=1.84%, 10=4.90%, 20=11.33%, 50=5.37%
3238 lat (msec) : 100=0.65%
3239 cpu : usr=0.27%, sys=0.18%, ctx=12072, majf=0, minf=21
3240 IO depths : 1=85.0%, 2=13.1%, 4=1.8%, 8=0.1%, 16=0.0%, 32=0.0%, >=64=0.0%
3241 submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
3242 complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
3243 issued rwt: total=0,4450,0, short=0,0,0, dropped=0,0,0
3244 latency : target=0, window=0, percentile=100.00%, depth=8
3246 The job name (or first job's name when using :option:`group_reporting`) is printed,
3247 along with the group id, count of jobs being aggregated, last error id seen (which
3248 is 0 when there are no errors), pid/tid of that thread and the time the job/group
3249 completed. Below are the I/O statistics for each data direction performed (showing
3250 writes in the example above). In the order listed, they denote:
3253 The string before the colon shows the I/O direction the statistics
3254 are for. **IOPS** is the average I/Os performed per second. **BW**
3255 is the average bandwidth rate shown as: value in power of 2 format
3256 (value in power of 10 format). The last two values show: (**total
3257 I/O performed** in power of 2 format / **runtime** of that thread).
3260 Submission latency (**min** being the minimum, **max** being the
3261 maximum, **avg** being the average, **stdev** being the standard
3262 deviation). This is the time it took to submit the I/O. For
3263 sync I/O this row is not displayed as the slat is really the
3264 completion latency (since queue/complete is one operation there).
3265 This value can be in nanoseconds, microseconds or milliseconds ---
3266 fio will choose the most appropriate base and print that (in the
3267 example above nanoseconds was the best scale). Note: in :option:`--minimal` mode
3268 latencies are always expressed in microseconds.
3271 Completion latency. Same names as slat, this denotes the time from
3272 submission to completion of the I/O pieces. For sync I/O, clat will
3273 usually be equal (or very close) to 0, as the time from submit to
3274 complete is basically just CPU time (I/O has already been done, see slat
3278 Total latency. Same names as slat and clat, this denotes the time from
3279 when fio created the I/O unit to completion of the I/O operation.
3282 Bandwidth statistics based on samples. Same names as the xlat stats,
3283 but also includes the number of samples taken (**samples**) and an
3284 approximate percentage of total aggregate bandwidth this thread
3285 received in its group (**per**). This last value is only really
3286 useful if the threads in this group are on the same disk, since they
3287 are then competing for disk access.
3290 IOPS statistics based on samples. Same names as bw.
3292 **lat (nsec/usec/msec)**
3293 The distribution of I/O completion latencies. This is the time from when
3294 I/O leaves fio and when it gets completed. Unlike the separate
3295 read/write/trim sections above, the data here and in the remaining
3296 sections apply to all I/Os for the reporting group. 250=0.04% means that
3297 0.04% of the I/Os completed in under 250us. 500=64.11% means that 64.11%
3298 of the I/Os required 250 to 499us for completion.
3301 CPU usage. User and system time, along with the number of context
3302 switches this thread went through, usage of system and user time, and
3303 finally the number of major and minor page faults. The CPU utilization
3304 numbers are averages for the jobs in that reporting group, while the
3305 context and fault counters are summed.
3308 The distribution of I/O depths over the job lifetime. The numbers are
3309 divided into powers of 2 and each entry covers depths from that value
3310 up to those that are lower than the next entry -- e.g., 16= covers
3311 depths from 16 to 31. Note that the range covered by a depth
3312 distribution entry can be different to the range covered by the
3313 equivalent submit/complete distribution entry.
3316 How many pieces of I/O were submitting in a single submit call. Each
3317 entry denotes that amount and below, until the previous entry -- e.g.,
3318 16=100% means that we submitted anywhere between 9 to 16 I/Os per submit
3319 call. Note that the range covered by a submit distribution entry can
3320 be different to the range covered by the equivalent depth distribution
3324 Like the above submit number, but for completions instead.
3327 The number of read/write/trim requests issued, and how many of them were
3331 These values are for :option:`latency_target` and related options. When
3332 these options are engaged, this section describes the I/O depth required
3333 to meet the specified latency target.
3336 Example output was based on the following:
3337 TZ=UTC fio --ioengine=null --iodepth=2 --size=100M --numjobs=2 \
3338 --rate_process=poisson --io_limit=32M --name=read --bs=128k \
3339 --rate=11M --name=write --rw=write --bs=2k --rate=700k
3341 After each client has been listed, the group statistics are printed. They
3342 will look like this::
3344 Run status group 0 (all jobs):
3345 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
3346 WRITE: bw=1231KiB/s (1261kB/s), 616KiB/s-621KiB/s (630kB/s-636kB/s), io=64.0MiB (67.1MB), run=52747-53223msec
3348 For each data direction it prints:
3351 Aggregate bandwidth of threads in this group followed by the
3352 minimum and maximum bandwidth of all the threads in this group.
3353 Values outside of brackets are power-of-2 format and those
3354 within are the equivalent value in a power-of-10 format.
3356 Aggregate I/O performed of all threads in this group. The
3357 format is the same as bw.
3359 The smallest and longest runtimes of the threads in this group.
3361 And finally, the disk statistics are printed. This is Linux specific. They will look like this::
3363 Disk stats (read/write):
3364 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
3366 Each value is printed for both reads and writes, with reads first. The
3370 Number of I/Os performed by all groups.
3372 Number of merges performed by the I/O scheduler.
3374 Number of ticks we kept the disk busy.
3376 Total time spent in the disk queue.
3378 The disk utilization. A value of 100% means we kept the disk
3379 busy constantly, 50% would be a disk idling half of the time.
3381 It is also possible to get fio to dump the current output while it is running,
3382 without terminating the job. To do that, send fio the **USR1** signal. You can
3383 also get regularly timed dumps by using the :option:`--status-interval`
3384 parameter, or by creating a file in :file:`/tmp` named
3385 :file:`fio-dump-status`. If fio sees this file, it will unlink it and dump the
3386 current output status.
3392 For scripted usage where you typically want to generate tables or graphs of the
3393 results, fio can output the results in a semicolon separated format. The format
3394 is one long line of values, such as::
3396 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%
3397 A description of this job goes here.
3399 The job description (if provided) follows on a second line.
3401 To enable terse output, use the :option:`--minimal` or
3402 :option:`--output-format`\=terse command line options. The
3403 first value is the version of the terse output format. If the output has to be
3404 changed for some reason, this number will be incremented by 1 to signify that
3407 Split up, the format is as follows (comments in brackets denote when a
3408 field was introduced or whether it's specific to some terse version):
3412 terse version, fio version [v3], jobname, groupid, error
3416 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
3417 Submission latency: min, max, mean, stdev (usec)
3418 Completion latency: min, max, mean, stdev (usec)
3419 Completion latency percentiles: 20 fields (see below)
3420 Total latency: min, max, mean, stdev (usec)
3421 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
3422 IOPS [v5]: min, max, mean, stdev, number of samples
3428 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
3429 Submission latency: min, max, mean, stdev (usec)
3430 Completion latency: min, max, mean, stdev (usec)
3431 Completion latency percentiles: 20 fields (see below)
3432 Total latency: min, max, mean, stdev (usec)
3433 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
3434 IOPS [v5]: min, max, mean, stdev, number of samples
3436 TRIM status [all but version 3]:
3438 Fields are similar to READ/WRITE status.
3442 user, system, context switches, major faults, minor faults
3446 <=1, 2, 4, 8, 16, 32, >=64
3448 I/O latencies microseconds::
3450 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000
3452 I/O latencies milliseconds::
3454 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000
3456 Disk utilization [v3]::
3458 disk name, read ios, write ios, read merges, write merges, read ticks, write ticks,
3459 time spent in queue, disk utilization percentage
3461 Additional Info (dependent on continue_on_error, default off)::
3463 total # errors, first error code
3465 Additional Info (dependent on description being set)::
3469 Completion latency percentiles can be a grouping of up to 20 sets, so for the
3470 terse output fio writes all of them. Each field will look like this::
3474 which is the Xth percentile, and the `usec` latency associated with it.
3476 For `Disk utilization`, all disks used by fio are shown. So for each disk there
3477 will be a disk utilization section.
3479 Below is a single line containing short names for each of the fields in the
3480 minimal output v3, separated by semicolons::
3482 terse_version_3;fio_version;jobname;groupid;error;read_kb;read_bandwidth;read_iops;read_runtime_ms;read_slat_min;read_slat_max;read_slat_mean;read_slat_dev;read_clat_min;read_clat_max;read_clat_mean;read_clat_dev;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;read_lat_max;read_lat_mean;read_lat_dev;read_bw_min;read_bw_max;read_bw_agg_pct;read_bw_mean;read_bw_dev;write_kb;write_bandwidth;write_iops;write_runtime_ms;write_slat_min;write_slat_max;write_slat_mean;write_slat_dev;write_clat_min;write_clat_max;write_clat_mean;write_clat_dev;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;write_lat_max;write_lat_mean;write_lat_dev;write_bw_min;write_bw_max;write_bw_agg_pct;write_bw_mean;write_bw_dev;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
3488 The `json` output format is intended to be both human readable and convenient
3489 for automated parsing. For the most part its sections mirror those of the
3490 `normal` output. The `runtime` value is reported in msec and the `bw` value is
3491 reported in 1024 bytes per second units.
3497 The `json+` output format is identical to the `json` output format except that it
3498 adds a full dump of the completion latency bins. Each `bins` object contains a
3499 set of (key, value) pairs where keys are latency durations and values count how
3500 many I/Os had completion latencies of the corresponding duration. For example,
3503 "bins" : { "87552" : 1, "89600" : 1, "94720" : 1, "96768" : 1, "97792" : 1, "99840" : 1, "100864" : 2, "103936" : 6, "104960" : 534, "105984" : 5995, "107008" : 7529, ... }
3505 This data indicates that one I/O required 87,552ns to complete, two I/Os required
3506 100,864ns to complete, and 7529 I/Os required 107,008ns to complete.
3508 Also included with fio is a Python script `fio_jsonplus_clat2csv` that takes
3509 json+ output and generates CSV-formatted latency data suitable for plotting.
3511 The latency durations actually represent the midpoints of latency intervals.
3512 For details refer to :file:`stat.h`.
3518 There are two trace file format that you can encounter. The older (v1) format is
3519 unsupported since version 1.20-rc3 (March 2008). It will still be described
3520 below in case that you get an old trace and want to understand it.
3522 In any case the trace is a simple text file with a single action per line.
3525 Trace file format v1
3526 ~~~~~~~~~~~~~~~~~~~~
3528 Each line represents a single I/O action in the following format::
3532 where `rw=0/1` for read/write, and the `offset` and `length` entries being in bytes.
3534 This format is not supported in fio versions >= 1.20-rc3.
3537 Trace file format v2
3538 ~~~~~~~~~~~~~~~~~~~~
3540 The second version of the trace file format was added in fio version 1.17. It
3541 allows to access more then one file per trace and has a bigger set of possible
3544 The first line of the trace file has to be::
3548 Following this can be lines in two different formats, which are described below.
3550 The file management format::
3554 The `filename` is given as an absolute path. The `action` can be one of these:
3557 Add the given `filename` to the trace.
3559 Open the file with the given `filename`. The `filename` has to have
3560 been added with the **add** action before.
3562 Close the file with the given `filename`. The file has to have been
3566 The file I/O action format::
3568 filename action offset length
3570 The `filename` is given as an absolute path, and has to have been added and
3571 opened before it can be used with this format. The `offset` and `length` are
3572 given in bytes. The `action` can be one of these:
3575 Wait for `offset` microseconds. Everything below 100 is discarded.
3576 The time is relative to the previous `wait` statement.
3578 Read `length` bytes beginning from `offset`.
3580 Write `length` bytes beginning from `offset`.
3582 :manpage:`fsync(2)` the file.
3584 :manpage:`fdatasync(2)` the file.
3586 Trim the given file from the given `offset` for `length` bytes.
3588 CPU idleness profiling
3589 ----------------------
3591 In some cases, we want to understand CPU overhead in a test. For example, we
3592 test patches for the specific goodness of whether they reduce CPU usage.
3593 Fio implements a balloon approach to create a thread per CPU that runs at idle
3594 priority, meaning that it only runs when nobody else needs the cpu.
3595 By measuring the amount of work completed by the thread, idleness of each CPU
3596 can be derived accordingly.
3598 An unit work is defined as touching a full page of unsigned characters. Mean and
3599 standard deviation of time to complete an unit work is reported in "unit work"
3600 section. Options can be chosen to report detailed percpu idleness or overall
3601 system idleness by aggregating percpu stats.
3604 Verification and triggers
3605 -------------------------
3607 Fio is usually run in one of two ways, when data verification is done. The first
3608 is a normal write job of some sort with verify enabled. When the write phase has
3609 completed, fio switches to reads and verifies everything it wrote. The second
3610 model is running just the write phase, and then later on running the same job
3611 (but with reads instead of writes) to repeat the same I/O patterns and verify
3612 the contents. Both of these methods depend on the write phase being completed,
3613 as fio otherwise has no idea how much data was written.
3615 With verification triggers, fio supports dumping the current write state to
3616 local files. Then a subsequent read verify workload can load this state and know
3617 exactly where to stop. This is useful for testing cases where power is cut to a
3618 server in a managed fashion, for instance.
3620 A verification trigger consists of two things:
3622 1) Storing the write state of each job.
3623 2) Executing a trigger command.
3625 The write state is relatively small, on the order of hundreds of bytes to single
3626 kilobytes. It contains information on the number of completions done, the last X
3629 A trigger is invoked either through creation ('touch') of a specified file in
3630 the system, or through a timeout setting. If fio is run with
3631 :option:`--trigger-file`\= :file:`/tmp/trigger-file`, then it will continually
3632 check for the existence of :file:`/tmp/trigger-file`. When it sees this file, it
3633 will fire off the trigger (thus saving state, and executing the trigger
3636 For client/server runs, there's both a local and remote trigger. If fio is
3637 running as a server backend, it will send the job states back to the client for
3638 safe storage, then execute the remote trigger, if specified. If a local trigger
3639 is specified, the server will still send back the write state, but the client
3640 will then execute the trigger.
3642 Verification trigger example
3643 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
3645 Let's say we want to run a powercut test on the remote Linux machine 'server'.
3646 Our write workload is in :file:`write-test.fio`. We want to cut power to 'server' at
3647 some point during the run, and we'll run this test from the safety or our local
3648 machine, 'localbox'. On the server, we'll start the fio backend normally::
3650 server# fio --server
3652 and on the client, we'll fire off the workload::
3654 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger-remote="bash -c \"echo b > /proc/sysrq-triger\""
3656 We set :file:`/tmp/my-trigger` as the trigger file, and we tell fio to execute::
3658 echo b > /proc/sysrq-trigger
3660 on the server once it has received the trigger and sent us the write state. This
3661 will work, but it's not **really** cutting power to the server, it's merely
3662 abruptly rebooting it. If we have a remote way of cutting power to the server
3663 through IPMI or similar, we could do that through a local trigger command
3664 instead. Let's assume we have a script that does IPMI reboot of a given hostname,
3665 ipmi-reboot. On localbox, we could then have run fio with a local trigger
3668 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger="ipmi-reboot server"
3670 For this case, fio would wait for the server to send us the write state, then
3671 execute ``ipmi-reboot server`` when that happened.
3673 Loading verify state
3674 ~~~~~~~~~~~~~~~~~~~~
3676 To load stored write state, a read verification job file must contain the
3677 :option:`verify_state_load` option. If that is set, fio will load the previously
3678 stored state. For a local fio run this is done by loading the files directly,
3679 and on a client/server run, the server backend will ask the client to send the
3680 files over and load them from there.
3686 Fio supports a variety of log file formats, for logging latencies, bandwidth,
3687 and IOPS. The logs share a common format, which looks like this:
3689 *time* (`msec`), *value*, *data direction*, *block size* (`bytes`),
3692 *Time* for the log entry is always in milliseconds. The *value* logged depends
3693 on the type of log, it will be one of the following:
3696 Value is latency in nsecs
3702 *Data direction* is one of the following:
3711 The entry's *block size* is always in bytes. The *offset* is the offset, in bytes,
3712 from the start of the file, for that particular I/O. The logging of the offset can be
3713 toggled with :option:`log_offset`.
3715 Fio defaults to logging every individual I/O. When IOPS are logged for individual
3716 I/Os the *value* entry will always be 1. If windowed logging is enabled through
3717 :option:`log_avg_msec`, fio logs the average values over the specified period of time.
3718 If windowed logging is enabled and :option:`log_max_value` is set, then fio logs
3719 maximum values in that window instead of averages. Since *data direction*, *block
3720 size* and *offset* are per-I/O values, if windowed logging is enabled they
3721 aren't applicable and will be 0.
3726 Normally fio is invoked as a stand-alone application on the machine where the
3727 I/O workload should be generated. However, the backend and frontend of fio can
3728 be run separately i.e., the fio server can generate an I/O workload on the "Device
3729 Under Test" while being controlled by a client on another machine.
3731 Start the server on the machine which has access to the storage DUT::
3735 where `args` defines what fio listens to. The arguments are of the form
3736 ``type,hostname`` or ``IP,port``. *type* is either ``ip`` (or ip4) for TCP/IP
3737 v4, ``ip6`` for TCP/IP v6, or ``sock`` for a local unix domain socket.
3738 *hostname* is either a hostname or IP address, and *port* is the port to listen
3739 to (only valid for TCP/IP, not a local socket). Some examples:
3743 Start a fio server, listening on all interfaces on the default port (8765).
3745 2) ``fio --server=ip:hostname,4444``
3747 Start a fio server, listening on IP belonging to hostname and on port 4444.
3749 3) ``fio --server=ip6:::1,4444``
3751 Start a fio server, listening on IPv6 localhost ::1 and on port 4444.
3753 4) ``fio --server=,4444``
3755 Start a fio server, listening on all interfaces on port 4444.
3757 5) ``fio --server=1.2.3.4``
3759 Start a fio server, listening on IP 1.2.3.4 on the default port.
3761 6) ``fio --server=sock:/tmp/fio.sock``
3763 Start a fio server, listening on the local socket :file:`/tmp/fio.sock`.
3765 Once a server is running, a "client" can connect to the fio server with::
3767 fio <local-args> --client=<server> <remote-args> <job file(s)>
3769 where `local-args` are arguments for the client where it is running, `server`
3770 is the connect string, and `remote-args` and `job file(s)` are sent to the
3771 server. The `server` string follows the same format as it does on the server
3772 side, to allow IP/hostname/socket and port strings.
3774 Fio can connect to multiple servers this way::
3776 fio --client=<server1> <job file(s)> --client=<server2> <job file(s)>
3778 If the job file is located on the fio server, then you can tell the server to
3779 load a local file as well. This is done by using :option:`--remote-config` ::
3781 fio --client=server --remote-config /path/to/file.fio
3783 Then fio will open this local (to the server) job file instead of being passed
3784 one from the client.
3786 If you have many servers (example: 100 VMs/containers), you can input a pathname
3787 of a file containing host IPs/names as the parameter value for the
3788 :option:`--client` option. For example, here is an example :file:`host.list`
3789 file containing 2 hostnames::
3791 host1.your.dns.domain
3792 host2.your.dns.domain
3794 The fio command would then be::
3796 fio --client=host.list <job file(s)>
3798 In this mode, you cannot input server-specific parameters or job files -- all
3799 servers receive the same job file.
3801 In order to let ``fio --client`` runs use a shared filesystem from multiple
3802 hosts, ``fio --client`` now prepends the IP address of the server to the
3803 filename. For example, if fio is using the directory :file:`/mnt/nfs/fio` and is
3804 writing filename :file:`fileio.tmp`, with a :option:`--client` `hostfile`
3805 containing two hostnames ``h1`` and ``h2`` with IP addresses 192.168.10.120 and
3806 192.168.10.121, then fio will create two files::
3808 /mnt/nfs/fio/192.168.10.120.fileio.tmp
3809 /mnt/nfs/fio/192.168.10.121.fileio.tmp