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`. `auto` is the default, it prints ETA
177 when requested if the output is a TTY. `always` disregards the output
178 type, and prints ETA when requested. `never` never prints ETA.
180 .. option:: --eta-interval=time
182 By default, fio requests client ETA status roughly every second. With
183 this option, the interval is configurable. Fio imposes a minimum
184 allowed time to avoid flooding the console, less than 250 msec is
187 .. option:: --eta-newline=time
189 Force a new line for every `time` period passed. When the unit is omitted,
190 the value is interpreted in seconds.
192 .. option:: --status-interval=time
194 Force a full status dump of cumulative (from job start) values at `time`
195 intervals. This option does *not* provide per-period measurements. So
196 values such as bandwidth are running averages. When the time unit is omitted,
197 `time` is interpreted in seconds.
199 .. option:: --section=name
201 Only run specified section `name` in job file. Multiple sections can be specified.
202 The ``--section`` option allows one to combine related jobs into one file.
203 E.g. one job file could define light, moderate, and heavy sections. Tell
204 fio to run only the "heavy" section by giving ``--section=heavy``
205 command line option. One can also specify the "write" operations in one
206 section and "verify" operation in another section. The ``--section`` option
207 only applies to job sections. The reserved *global* section is always
210 .. option:: --alloc-size=kb
212 Set the internal smalloc pool size to `kb` in KiB. The
213 ``--alloc-size`` switch allows one to use a larger pool size for smalloc.
214 If running large jobs with randommap enabled, fio can run out of memory.
215 Smalloc is an internal allocator for shared structures from a fixed size
216 memory pool and can grow to 16 pools. The pool size defaults to 16MiB.
218 NOTE: While running :file:`.fio_smalloc.*` backing store files are visible
221 .. option:: --warnings-fatal
223 All fio parser warnings are fatal, causing fio to exit with an
226 .. option:: --max-jobs=nr
228 Set the maximum number of threads/processes to support to `nr`.
229 NOTE: On Linux, it may be necessary to increase the shared-memory
230 limit (:file:`/proc/sys/kernel/shmmax`) if fio runs into errors while
233 .. option:: --server=args
235 Start a backend server, with `args` specifying what to listen to.
236 See `Client/Server`_ section.
238 .. option:: --daemonize=pidfile
240 Background a fio server, writing the pid to the given `pidfile` file.
242 .. option:: --client=hostname
244 Instead of running the jobs locally, send and run them on the given `hostname`
245 or set of `hostname`\s. See `Client/Server`_ section.
247 .. option:: --remote-config=file
249 Tell fio server to load this local `file`.
251 .. option:: --idle-prof=option
253 Report CPU idleness. `option` is one of the following:
256 Run unit work calibration only and exit.
259 Show aggregate system idleness and unit work.
262 As **system** but also show per CPU idleness.
264 .. option:: --inflate-log=log
266 Inflate and output compressed `log`.
268 .. option:: --trigger-file=file
270 Execute trigger command when `file` exists.
272 .. option:: --trigger-timeout=time
274 Execute trigger at this `time`.
276 .. option:: --trigger=command
278 Set this `command` as local trigger.
280 .. option:: --trigger-remote=command
282 Set this `command` as remote trigger.
284 .. option:: --aux-path=path
286 Use this `path` for fio state generated files.
288 Any parameters following the options will be assumed to be job files, unless
289 they match a job file parameter. Multiple job files can be listed and each job
290 file will be regarded as a separate group. Fio will :option:`stonewall`
291 execution between each group.
297 As previously described, fio accepts one or more job files describing what it is
298 supposed to do. The job file format is the classic ini file, where the names
299 enclosed in [] brackets define the job name. You are free to use any ASCII name
300 you want, except *global* which has special meaning. Following the job name is
301 a sequence of zero or more parameters, one per line, that define the behavior of
302 the job. If the first character in a line is a ';' or a '#', the entire line is
303 discarded as a comment.
305 A *global* section sets defaults for the jobs described in that file. A job may
306 override a *global* section parameter, and a job file may even have several
307 *global* sections if so desired. A job is only affected by a *global* section
310 The :option:`--cmdhelp` option also lists all options. If used with a `command`
311 argument, :option:`--cmdhelp` will detail the given `command`.
313 See the `examples/` directory for inspiration on how to write job files. Note
314 the copyright and license requirements currently apply to `examples/` files.
316 So let's look at a really simple job file that defines two processes, each
317 randomly reading from a 128MiB file:
321 ; -- start job file --
332 As you can see, the job file sections themselves are empty as all the described
333 parameters are shared. As no :option:`filename` option is given, fio makes up a
334 `filename` for each of the jobs as it sees fit. On the command line, this job
335 would look as follows::
337 $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2
340 Let's look at an example that has a number of processes writing randomly to
345 ; -- start job file --
356 Here we have no *global* section, as we only have one job defined anyway. We
357 want to use async I/O here, with a depth of 4 for each file. We also increased
358 the buffer size used to 32KiB and define numjobs to 4 to fork 4 identical
359 jobs. The result is 4 processes each randomly writing to their own 64MiB
360 file. Instead of using the above job file, you could have given the parameters
361 on the command line. For this case, you would specify::
363 $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4
365 When fio is utilized as a basis of any reasonably large test suite, it might be
366 desirable to share a set of standardized settings across multiple job files.
367 Instead of copy/pasting such settings, any section may pull in an external
368 :file:`filename.fio` file with *include filename* directive, as in the following
371 ; -- start job file including.fio --
375 include glob-include.fio
382 include test-include.fio
383 ; -- end job file including.fio --
387 ; -- start job file glob-include.fio --
390 ; -- end job file glob-include.fio --
394 ; -- start job file test-include.fio --
397 ; -- end job file test-include.fio --
399 Settings pulled into a section apply to that section only (except *global*
400 section). Include directives may be nested in that any included file may contain
401 further include directive(s). Include files may not contain [] sections.
404 Environment variables
405 ~~~~~~~~~~~~~~~~~~~~~
407 Fio also supports environment variable expansion in job files. Any sub-string of
408 the form ``${VARNAME}`` as part of an option value (in other words, on the right
409 of the '='), will be expanded to the value of the environment variable called
410 `VARNAME`. If no such environment variable is defined, or `VARNAME` is the
411 empty string, the empty string will be substituted.
413 As an example, let's look at a sample fio invocation and job file::
415 $ SIZE=64m NUMJOBS=4 fio jobfile.fio
419 ; -- start job file --
426 This will expand to the following equivalent job file at runtime:
430 ; -- start job file --
437 Fio ships with a few example job files, you can also look there for inspiration.
442 Additionally, fio has a set of reserved keywords that will be replaced
443 internally with the appropriate value. Those keywords are:
447 The architecture page size of the running system.
451 Megabytes of total memory in the system.
455 Number of online available CPUs.
457 These can be used on the command line or in the job file, and will be
458 automatically substituted with the current system values when the job is
459 run. Simple math is also supported on these keywords, so you can perform actions
464 and get that properly expanded to 8 times the size of memory in the machine.
470 This section describes in details each parameter associated with a job. Some
471 parameters take an option of a given type, such as an integer or a
472 string. Anywhere a numeric value is required, an arithmetic expression may be
473 used, provided it is surrounded by parentheses. Supported operators are:
482 For time values in expressions, units are microseconds by default. This is
483 different than for time values not in expressions (not enclosed in
484 parentheses). The following types are used:
491 String: A sequence of alphanumeric characters.
494 Integer with possible time suffix. Without a unit value is interpreted as
495 seconds unless otherwise specified. Accepts a suffix of 'd' for days, 'h' for
496 hours, 'm' for minutes, 's' for seconds, 'ms' (or 'msec') for milliseconds and
497 'us' (or 'usec') for microseconds. For example, use 10m for 10 minutes.
502 Integer. A whole number value, which may contain an integer prefix
503 and an integer suffix:
505 [*integer prefix*] **number** [*integer suffix*]
507 The optional *integer prefix* specifies the number's base. The default
508 is decimal. *0x* specifies hexadecimal.
510 The optional *integer suffix* specifies the number's units, and includes an
511 optional unit prefix and an optional unit. For quantities of data, the
512 default unit is bytes. For quantities of time, the default unit is seconds
513 unless otherwise specified.
515 With :option:`kb_base`\=1000, fio follows international standards for unit
516 prefixes. To specify power-of-10 decimal values defined in the
517 International System of Units (SI):
519 * *K* -- means kilo (K) or 1000
520 * *M* -- means mega (M) or 1000**2
521 * *G* -- means giga (G) or 1000**3
522 * *T* -- means tera (T) or 1000**4
523 * *P* -- means peta (P) or 1000**5
525 To specify power-of-2 binary values defined in IEC 80000-13:
527 * *Ki* -- means kibi (Ki) or 1024
528 * *Mi* -- means mebi (Mi) or 1024**2
529 * *Gi* -- means gibi (Gi) or 1024**3
530 * *Ti* -- means tebi (Ti) or 1024**4
531 * *Pi* -- means pebi (Pi) or 1024**5
533 With :option:`kb_base`\=1024 (the default), the unit prefixes are opposite
534 from those specified in the SI and IEC 80000-13 standards to provide
535 compatibility with old scripts. For example, 4k means 4096.
537 For quantities of data, an optional unit of 'B' may be included
538 (e.g., 'kB' is the same as 'k').
540 The *integer suffix* is not case sensitive (e.g., m/mi mean mebi/mega,
541 not milli). 'b' and 'B' both mean byte, not bit.
543 Examples with :option:`kb_base`\=1000:
545 * *4 KiB*: 4096, 4096b, 4096B, 4ki, 4kib, 4kiB, 4Ki, 4KiB
546 * *1 MiB*: 1048576, 1mi, 1024ki
547 * *1 MB*: 1000000, 1m, 1000k
548 * *1 TiB*: 1099511627776, 1ti, 1024gi, 1048576mi
549 * *1 TB*: 1000000000, 1t, 1000m, 1000000k
551 Examples with :option:`kb_base`\=1024 (default):
553 * *4 KiB*: 4096, 4096b, 4096B, 4k, 4kb, 4kB, 4K, 4KB
554 * *1 MiB*: 1048576, 1m, 1024k
555 * *1 MB*: 1000000, 1mi, 1000ki
556 * *1 TiB*: 1099511627776, 1t, 1024g, 1048576m
557 * *1 TB*: 1000000000, 1ti, 1000mi, 1000000ki
559 To specify times (units are not case sensitive):
563 * *M* -- means minutes
564 * *s* -- or sec means seconds (default)
565 * *ms* -- or *msec* means milliseconds
566 * *us* -- or *usec* means microseconds
568 If the option accepts an upper and lower range, use a colon ':' or
569 minus '-' to separate such values. See :ref:`irange <irange>`.
570 If the lower value specified happens to be larger than the upper value
571 the two values are swapped.
576 Boolean. Usually parsed as an integer, however only defined for
577 true and false (1 and 0).
582 Integer range with suffix. Allows value range to be given, such as
583 1024-4096. A colon may also be used as the separator, e.g. 1k:4k. If the
584 option allows two sets of ranges, they can be specified with a ',' or '/'
585 delimiter: 1k-4k/8k-32k. Also see :ref:`int <int>`.
588 A list of floating point numbers, separated by a ':' character.
590 With the above in mind, here follows the complete list of fio job parameters.
596 .. option:: kb_base=int
598 Select the interpretation of unit prefixes in input parameters.
601 Inputs comply with IEC 80000-13 and the International
602 System of Units (SI). Use:
604 - power-of-2 values with IEC prefixes (e.g., KiB)
605 - power-of-10 values with SI prefixes (e.g., kB)
608 Compatibility mode (default). To avoid breaking old scripts:
610 - power-of-2 values with SI prefixes
611 - power-of-10 values with IEC prefixes
613 See :option:`bs` for more details on input parameters.
615 Outputs always use correct prefixes. Most outputs include both
618 bw=2383.3kB/s (2327.4KiB/s)
620 If only one value is reported, then kb_base selects the one to use:
622 **1000** -- SI prefixes
624 **1024** -- IEC prefixes
626 .. option:: unit_base=int
628 Base unit for reporting. Allowed values are:
631 Use auto-detection (default).
643 ASCII name of the job. This may be used to override the name printed by fio
644 for this job. Otherwise the job name is used. On the command line this
645 parameter has the special purpose of also signaling the start of a new job.
647 .. option:: description=str
649 Text description of the job. Doesn't do anything except dump this text
650 description when this job is run. It's not parsed.
652 .. option:: loops=int
654 Run the specified number of iterations of this job. Used to repeat the same
655 workload a given number of times. Defaults to 1.
657 .. option:: numjobs=int
659 Create the specified number of clones of this job. Each clone of job
660 is spawned as an independent thread or process. May be used to setup a
661 larger number of threads/processes doing the same thing. Each thread is
662 reported separately; to see statistics for all clones as a whole, use
663 :option:`group_reporting` in conjunction with :option:`new_group`.
664 See :option:`--max-jobs`. Default: 1.
667 Time related parameters
668 ~~~~~~~~~~~~~~~~~~~~~~~
670 .. option:: runtime=time
672 Tell fio to terminate processing after the specified period of time. It
673 can be quite hard to determine for how long a specified job will run, so
674 this parameter is handy to cap the total runtime to a given time. When
675 the unit is omitted, the value is interpreted in seconds.
677 .. option:: time_based
679 If set, fio will run for the duration of the :option:`runtime` specified
680 even if the file(s) are completely read or written. It will simply loop over
681 the same workload as many times as the :option:`runtime` allows.
683 .. option:: startdelay=irange(time)
685 Delay the start of job for the specified amount of time. Can be a single
686 value or a range. When given as a range, each thread will choose a value
687 randomly from within the range. Value is in seconds if a unit is omitted.
689 .. option:: ramp_time=time
691 If set, fio will run the specified workload for this amount of time before
692 logging any performance numbers. Useful for letting performance settle
693 before logging results, thus minimizing the runtime required for stable
694 results. Note that the ``ramp_time`` is considered lead in time for a job,
695 thus it will increase the total runtime if a special timeout or
696 :option:`runtime` is specified. When the unit is omitted, the value is
699 .. option:: clocksource=str
701 Use the given clocksource as the base of timing. The supported options are:
704 :manpage:`gettimeofday(2)`
707 :manpage:`clock_gettime(2)`
710 Internal CPU clock source
712 cpu is the preferred clocksource if it is reliable, as it is very fast (and
713 fio is heavy on time calls). Fio will automatically use this clocksource if
714 it's supported and considered reliable on the system it is running on,
715 unless another clocksource is specifically set. For x86/x86-64 CPUs, this
716 means supporting TSC Invariant.
718 .. option:: gtod_reduce=bool
720 Enable all of the :manpage:`gettimeofday(2)` reducing options
721 (:option:`disable_clat`, :option:`disable_slat`, :option:`disable_bw_measurement`) plus
722 reduce precision of the timeout somewhat to really shrink the
723 :manpage:`gettimeofday(2)` call count. With this option enabled, we only do
724 about 0.4% of the :manpage:`gettimeofday(2)` calls we would have done if all
725 time keeping was enabled.
727 .. option:: gtod_cpu=int
729 Sometimes it's cheaper to dedicate a single thread of execution to just
730 getting the current time. Fio (and databases, for instance) are very
731 intensive on :manpage:`gettimeofday(2)` calls. With this option, you can set
732 one CPU aside for doing nothing but logging current time to a shared memory
733 location. Then the other threads/processes that run I/O workloads need only
734 copy that segment, instead of entering the kernel with a
735 :manpage:`gettimeofday(2)` call. The CPU set aside for doing these time
736 calls will be excluded from other uses. Fio will manually clear it from the
737 CPU mask of other jobs.
743 .. option:: directory=str
745 Prefix filenames with this directory. Used to place files in a different
746 location than :file:`./`. You can specify a number of directories by
747 separating the names with a ':' character. These directories will be
748 assigned equally distributed to job clones created by :option:`numjobs` as
749 long as they are using generated filenames. If specific `filename(s)` are
750 set fio will use the first listed directory, and thereby matching the
751 `filename` semantic which generates a file each clone if not specified, but
752 let all clones use the same if set.
754 See the :option:`filename` option for information on how to escape "``:``" and
755 "``\``" characters within the directory path itself.
757 .. option:: filename=str
759 Fio normally makes up a `filename` based on the job name, thread number, and
760 file number (see :option:`filename_format`). If you want to share files
761 between threads in a job or several
762 jobs with fixed file paths, specify a `filename` for each of them to override
763 the default. If the ioengine is file based, you can specify a number of files
764 by separating the names with a ':' colon. So if you wanted a job to open
765 :file:`/dev/sda` and :file:`/dev/sdb` as the two working files, you would use
766 ``filename=/dev/sda:/dev/sdb``. This also means that whenever this option is
767 specified, :option:`nrfiles` is ignored. The size of regular files specified
768 by this option will be :option:`size` divided by number of files unless an
769 explicit size is specified by :option:`filesize`.
771 Each colon and backslash in the wanted path must be escaped with a ``\``
772 character. For instance, if the path is :file:`/dev/dsk/foo@3,0:c` then you
773 would use ``filename=/dev/dsk/foo@3,0\:c`` and if the path is
774 :file:`F:\\filename` then you would use ``filename=F\:\\filename``.
776 On Windows, disk devices are accessed as :file:`\\\\.\\PhysicalDrive0` for
777 the first device, :file:`\\\\.\\PhysicalDrive1` for the second etc.
778 Note: Windows and FreeBSD prevent write access to areas
779 of the disk containing in-use data (e.g. filesystems).
781 The filename "`-`" is a reserved name, meaning *stdin* or *stdout*. Which
782 of the two depends on the read/write direction set.
784 .. option:: filename_format=str
786 If sharing multiple files between jobs, it is usually necessary to have fio
787 generate the exact names that you want. By default, fio will name a file
788 based on the default file format specification of
789 :file:`jobname.jobnumber.filenumber`. With this option, that can be
790 customized. Fio will recognize and replace the following keywords in this
794 The name of the worker thread or process.
796 The incremental number of the worker thread or process.
798 The incremental number of the file for that worker thread or
801 To have dependent jobs share a set of files, this option can be set to have
802 fio generate filenames that are shared between the two. For instance, if
803 :file:`testfiles.$filenum` is specified, file number 4 for any job will be
804 named :file:`testfiles.4`. The default of :file:`$jobname.$jobnum.$filenum`
805 will be used if no other format specifier is given.
807 If you specify a path then the directories will be created up to the
808 main directory for the file. So for example if you specify
809 ``filename_format=a/b/c/$jobnum`` then the directories a/b/c will be
810 created before the file setup part of the job. If you specify
811 :option:`directory` then the path will be relative that directory,
812 otherwise it is treated as the absolute path.
814 .. option:: unique_filename=bool
816 To avoid collisions between networked clients, fio defaults to prefixing any
817 generated filenames (with a directory specified) with the source of the
818 client connecting. To disable this behavior, set this option to 0.
820 .. option:: opendir=str
822 Recursively open any files below directory `str`.
824 .. option:: lockfile=str
826 Fio defaults to not locking any files before it does I/O to them. If a file
827 or file descriptor is shared, fio can serialize I/O to that file to make the
828 end result consistent. This is usual for emulating real workloads that share
829 files. The lock modes are:
832 No locking. The default.
834 Only one thread or process may do I/O at a time, excluding all
837 Read-write locking on the file. Many readers may
838 access the file at the same time, but writes get exclusive access.
840 .. option:: nrfiles=int
842 Number of files to use for this job. Defaults to 1. The size of files
843 will be :option:`size` divided by this unless explicit size is specified by
844 :option:`filesize`. Files are created for each thread separately, and each
845 file will have a file number within its name by default, as explained in
846 :option:`filename` section.
849 .. option:: openfiles=int
851 Number of files to keep open at the same time. Defaults to the same as
852 :option:`nrfiles`, can be set smaller to limit the number simultaneous
855 .. option:: file_service_type=str
857 Defines how fio decides which file from a job to service next. The following
861 Choose a file at random.
864 Round robin over opened files. This is the default.
867 Finish one file before moving on to the next. Multiple files can
868 still be open depending on :option:`openfiles`.
871 Use a *Zipf* distribution to decide what file to access.
874 Use a *Pareto* distribution to decide what file to access.
877 Use a *Gaussian* (normal) distribution to decide what file to
883 For *random*, *roundrobin*, and *sequential*, a postfix can be appended to
884 tell fio how many I/Os to issue before switching to a new file. For example,
885 specifying ``file_service_type=random:8`` would cause fio to issue
886 8 I/Os before selecting a new file at random. For the non-uniform
887 distributions, a floating point postfix can be given to influence how the
888 distribution is skewed. See :option:`random_distribution` for a description
889 of how that would work.
891 .. option:: ioscheduler=str
893 Attempt to switch the device hosting the file to the specified I/O scheduler
896 .. option:: create_serialize=bool
898 If true, serialize the file creation for the jobs. This may be handy to
899 avoid interleaving of data files, which may greatly depend on the filesystem
900 used and even the number of processors in the system. Default: true.
902 .. option:: create_fsync=bool
904 :manpage:`fsync(2)` the data file after creation. This is the default.
906 .. option:: create_on_open=bool
908 If true, don't pre-create files but allow the job's open() to create a file
909 when it's time to do I/O. Default: false -- pre-create all necessary files
912 .. option:: create_only=bool
914 If true, fio will only run the setup phase of the job. If files need to be
915 laid out or updated on disk, only that will be done -- the actual job contents
916 are not executed. Default: false.
918 .. option:: allow_file_create=bool
920 If true, fio is permitted to create files as part of its workload. If this
921 option is false, then fio will error out if
922 the files it needs to use don't already exist. Default: true.
924 .. option:: allow_mounted_write=bool
926 If this isn't set, fio will abort jobs that are destructive (e.g. that write)
927 to what appears to be a mounted device or partition. This should help catch
928 creating inadvertently destructive tests, not realizing that the test will
929 destroy data on the mounted file system. Note that some platforms don't allow
930 writing against a mounted device regardless of this option. Default: false.
932 .. option:: pre_read=bool
934 If this is given, files will be pre-read into memory before starting the
935 given I/O operation. This will also clear the :option:`invalidate` flag,
936 since it is pointless to pre-read and then drop the cache. This will only
937 work for I/O engines that are seek-able, since they allow you to read the
938 same data multiple times. Thus it will not work on non-seekable I/O engines
939 (e.g. network, splice). Default: false.
941 .. option:: unlink=bool
943 Unlink the job files when done. Not the default, as repeated runs of that
944 job would then waste time recreating the file set again and again. Default:
947 .. option:: unlink_each_loop=bool
949 Unlink job files after each iteration or loop. Default: false.
951 .. option:: zonesize=int
953 Divide a file into zones of the specified size. See :option:`zoneskip`.
955 .. option:: zonerange=int
957 Give size of an I/O zone. See :option:`zoneskip`.
959 .. option:: zoneskip=int
961 Skip the specified number of bytes when :option:`zonesize` data has been
962 read. The two zone options can be used to only do I/O on zones of a file.
968 .. option:: direct=bool
970 If value is true, use non-buffered I/O. This is usually O_DIRECT. Note that
971 OpenBSD and ZFS on Solaris don't support direct I/O. On Windows the synchronous
972 ioengines don't support direct I/O. Default: false.
974 .. option:: atomic=bool
976 If value is true, attempt to use atomic direct I/O. Atomic writes are
977 guaranteed to be stable once acknowledged by the operating system. Only
978 Linux supports O_ATOMIC right now.
980 .. option:: buffered=bool
982 If value is true, use buffered I/O. This is the opposite of the
983 :option:`direct` option. Defaults to true.
985 .. option:: readwrite=str, rw=str
987 Type of I/O pattern. Accepted values are:
994 Sequential trims (Linux block devices only).
1000 Random trims (Linux block devices only).
1002 Sequential mixed reads and writes.
1004 Random mixed reads and writes.
1006 Sequential trim+write sequences. Blocks will be trimmed first,
1007 then the same blocks will be written to.
1009 Fio defaults to read if the option is not specified. For the mixed I/O
1010 types, the default is to split them 50/50. For certain types of I/O the
1011 result may still be skewed a bit, since the speed may be different.
1013 It is possible to specify the number of I/Os to do before getting a new
1014 offset by appending ``:<nr>`` to the end of the string given. For a
1015 random read, it would look like ``rw=randread:8`` for passing in an offset
1016 modifier with a value of 8. If the suffix is used with a sequential I/O
1017 pattern, then the *<nr>* value specified will be **added** to the generated
1018 offset for each I/O turning sequential I/O into sequential I/O with holes.
1019 For instance, using ``rw=write:4k`` will skip 4k for every write. Also see
1020 the :option:`rw_sequencer` option.
1022 .. option:: rw_sequencer=str
1024 If an offset modifier is given by appending a number to the ``rw=<str>``
1025 line, then this option controls how that number modifies the I/O offset
1026 being generated. Accepted values are:
1029 Generate sequential offset.
1031 Generate the same offset.
1033 ``sequential`` is only useful for random I/O, where fio would normally
1034 generate a new random offset for every I/O. If you append e.g. 8 to randread,
1035 you would get a new random offset for every 8 I/Os. The result would be a
1036 seek for only every 8 I/Os, instead of for every I/O. Use ``rw=randread:8``
1037 to specify that. As sequential I/O is already sequential, setting
1038 ``sequential`` for that would not result in any differences. ``identical``
1039 behaves in a similar fashion, except it sends the same offset 8 number of
1040 times before generating a new offset.
1042 .. option:: unified_rw_reporting=bool
1044 Fio normally reports statistics on a per data direction basis, meaning that
1045 reads, writes, and trims are accounted and reported separately. If this
1046 option is set fio sums the results and report them as "mixed" instead.
1048 .. option:: randrepeat=bool
1050 Seed the random number generator used for random I/O patterns in a
1051 predictable way so the pattern is repeatable across runs. Default: true.
1053 .. option:: allrandrepeat=bool
1055 Seed all random number generators in a predictable way so results are
1056 repeatable across runs. Default: false.
1058 .. option:: randseed=int
1060 Seed the random number generators based on this seed value, to be able to
1061 control what sequence of output is being generated. If not set, the random
1062 sequence depends on the :option:`randrepeat` setting.
1064 .. option:: fallocate=str
1066 Whether pre-allocation is performed when laying down files.
1067 Accepted values are:
1070 Do not pre-allocate space.
1073 Use a platform's native pre-allocation call but fall back to
1074 **none** behavior if it fails/is not implemented.
1077 Pre-allocate via :manpage:`posix_fallocate(3)`.
1080 Pre-allocate via :manpage:`fallocate(2)` with
1081 FALLOC_FL_KEEP_SIZE set.
1084 Backward-compatible alias for **none**.
1087 Backward-compatible alias for **posix**.
1089 May not be available on all supported platforms. **keep** is only available
1090 on Linux. If using ZFS on Solaris this cannot be set to **posix**
1091 because ZFS doesn't support pre-allocation. Default: **native** if any
1092 pre-allocation methods are available, **none** if not.
1094 .. option:: fadvise_hint=str
1096 Use :manpage:`posix_fadvise(2)` or :manpage:`posix_fadvise(2)` to
1097 advise the kernel on what I/O patterns are likely to be issued.
1098 Accepted values are:
1101 Backwards-compatible hint for "no hint".
1104 Backwards compatible hint for "advise with fio workload type". This
1105 uses **FADV_RANDOM** for a random workload, and **FADV_SEQUENTIAL**
1106 for a sequential workload.
1109 Advise using **FADV_SEQUENTIAL**.
1112 Advise using **FADV_RANDOM**.
1114 .. option:: write_hint=str
1116 Use :manpage:`fcntl(2)` to advise the kernel what life time to expect
1117 from a write. Only supported on Linux, as of version 4.13. Accepted
1121 No particular life time associated with this file.
1124 Data written to this file has a short life time.
1127 Data written to this file has a medium life time.
1130 Data written to this file has a long life time.
1133 Data written to this file has a very long life time.
1135 The values are all relative to each other, and no absolute meaning
1136 should be associated with them.
1138 .. option:: offset=int
1140 Start I/O at the provided offset in the file, given as either a fixed size in
1141 bytes or a percentage. If a percentage is given, the generated offset will be
1142 aligned to the minimum ``blocksize`` or to the value of ``offset_align`` if
1143 provided. Data before the given offset will not be touched. This
1144 effectively caps the file size at `real_size - offset`. Can be combined with
1145 :option:`size` to constrain the start and end range of the I/O workload.
1146 A percentage can be specified by a number between 1 and 100 followed by '%',
1147 for example, ``offset=20%`` to specify 20%.
1149 .. option:: offset_align=int
1151 If set to non-zero value, the byte offset generated by a percentage ``offset``
1152 is aligned upwards to this value. Defaults to 0 meaning that a percentage
1153 offset is aligned to the minimum block size.
1155 .. option:: offset_increment=int
1157 If this is provided, then the real offset becomes `offset + offset_increment
1158 * thread_number`, where the thread number is a counter that starts at 0 and
1159 is incremented for each sub-job (i.e. when :option:`numjobs` option is
1160 specified). This option is useful if there are several jobs which are
1161 intended to operate on a file in parallel disjoint segments, with even
1162 spacing between the starting points.
1164 .. option:: number_ios=int
1166 Fio will normally perform I/Os until it has exhausted the size of the region
1167 set by :option:`size`, or if it exhaust the allocated time (or hits an error
1168 condition). With this setting, the range/size can be set independently of
1169 the number of I/Os to perform. When fio reaches this number, it will exit
1170 normally and report status. Note that this does not extend the amount of I/O
1171 that will be done, it will only stop fio if this condition is met before
1172 other end-of-job criteria.
1174 .. option:: fsync=int
1176 If writing to a file, issue an :manpage:`fsync(2)` (or its equivalent) of
1177 the dirty data for every number of blocks given. For example, if you give 32
1178 as a parameter, fio will sync the file after every 32 writes issued. If fio is
1179 using non-buffered I/O, we may not sync the file. The exception is the sg
1180 I/O engine, which synchronizes the disk cache anyway. Defaults to 0, which
1181 means fio does not periodically issue and wait for a sync to complete. Also
1182 see :option:`end_fsync` and :option:`fsync_on_close`.
1184 .. option:: fdatasync=int
1186 Like :option:`fsync` but uses :manpage:`fdatasync(2)` to only sync data and
1187 not metadata blocks. In Windows, FreeBSD, and DragonFlyBSD there is no
1188 :manpage:`fdatasync(2)` so this falls back to using :manpage:`fsync(2)`.
1189 Defaults to 0, which means fio does not periodically issue and wait for a
1190 data-only sync to complete.
1192 .. option:: write_barrier=int
1194 Make every `N-th` write a barrier write.
1196 .. option:: sync_file_range=str:int
1198 Use :manpage:`sync_file_range(2)` for every `int` number of write
1199 operations. Fio will track range of writes that have happened since the last
1200 :manpage:`sync_file_range(2)` call. `str` can currently be one or more of:
1203 SYNC_FILE_RANGE_WAIT_BEFORE
1205 SYNC_FILE_RANGE_WRITE
1207 SYNC_FILE_RANGE_WAIT_AFTER
1209 So if you do ``sync_file_range=wait_before,write:8``, fio would use
1210 ``SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE`` for every 8
1211 writes. Also see the :manpage:`sync_file_range(2)` man page. This option is
1214 .. option:: overwrite=bool
1216 If true, writes to a file will always overwrite existing data. If the file
1217 doesn't already exist, it will be created before the write phase begins. If
1218 the file exists and is large enough for the specified write phase, nothing
1219 will be done. Default: false.
1221 .. option:: end_fsync=bool
1223 If true, :manpage:`fsync(2)` file contents when a write stage has completed.
1226 .. option:: fsync_on_close=bool
1228 If true, fio will :manpage:`fsync(2)` a dirty file on close. This differs
1229 from :option:`end_fsync` in that it will happen on every file close, not
1230 just at the end of the job. Default: false.
1232 .. option:: rwmixread=int
1234 Percentage of a mixed workload that should be reads. Default: 50.
1236 .. option:: rwmixwrite=int
1238 Percentage of a mixed workload that should be writes. If both
1239 :option:`rwmixread` and :option:`rwmixwrite` is given and the values do not
1240 add up to 100%, the latter of the two will be used to override the
1241 first. This may interfere with a given rate setting, if fio is asked to
1242 limit reads or writes to a certain rate. If that is the case, then the
1243 distribution may be skewed. Default: 50.
1245 .. option:: random_distribution=str:float[,str:float][,str:float]
1247 By default, fio will use a completely uniform random distribution when asked
1248 to perform random I/O. Sometimes it is useful to skew the distribution in
1249 specific ways, ensuring that some parts of the data is more hot than others.
1250 fio includes the following distribution models:
1253 Uniform random distribution
1262 Normal (Gaussian) distribution
1265 Zoned random distribution
1268 Zone absolute random distribution
1270 When using a **zipf** or **pareto** distribution, an input value is also
1271 needed to define the access pattern. For **zipf**, this is the `Zipf
1272 theta`. For **pareto**, it's the `Pareto power`. Fio includes a test
1273 program, :command:`fio-genzipf`, that can be used visualize what the given input
1274 values will yield in terms of hit rates. If you wanted to use **zipf** with
1275 a `theta` of 1.2, you would use ``random_distribution=zipf:1.2`` as the
1276 option. If a non-uniform model is used, fio will disable use of the random
1277 map. For the **normal** distribution, a normal (Gaussian) deviation is
1278 supplied as a value between 0 and 100.
1280 For a **zoned** distribution, fio supports specifying percentages of I/O
1281 access that should fall within what range of the file or device. For
1282 example, given a criteria of:
1284 * 60% of accesses should be to the first 10%
1285 * 30% of accesses should be to the next 20%
1286 * 8% of accesses should be to the next 30%
1287 * 2% of accesses should be to the next 40%
1289 we can define that through zoning of the random accesses. For the above
1290 example, the user would do::
1292 random_distribution=zoned:60/10:30/20:8/30:2/40
1294 A **zoned_abs** distribution works exactly like the **zoned**, except
1295 that it takes absolute sizes. For example, let's say you wanted to
1296 define access according to the following criteria:
1298 * 60% of accesses should be to the first 20G
1299 * 30% of accesses should be to the next 100G
1300 * 10% of accesses should be to the next 500G
1302 we can define an absolute zoning distribution with:
1304 random_distribution=zoned_abs=60/20G:30/100G:10/500g
1306 For both **zoned** and **zoned_abs**, fio supports defining up to
1309 Similarly to how :option:`bssplit` works for setting ranges and
1310 percentages of block sizes. Like :option:`bssplit`, it's possible to
1311 specify separate zones for reads, writes, and trims. If just one set
1312 is given, it'll apply to all of them. This goes for both **zoned**
1313 **zoned_abs** distributions.
1315 .. option:: percentage_random=int[,int][,int]
1317 For a random workload, set how big a percentage should be random. This
1318 defaults to 100%, in which case the workload is fully random. It can be set
1319 from anywhere from 0 to 100. Setting it to 0 would make the workload fully
1320 sequential. Any setting in between will result in a random mix of sequential
1321 and random I/O, at the given percentages. Comma-separated values may be
1322 specified for reads, writes, and trims as described in :option:`blocksize`.
1324 .. option:: norandommap
1326 Normally fio will cover every block of the file when doing random I/O. If
1327 this option is given, fio will just get a new random offset without looking
1328 at past I/O history. This means that some blocks may not be read or written,
1329 and that some blocks may be read/written more than once. If this option is
1330 used with :option:`verify` and multiple blocksizes (via :option:`bsrange`),
1331 only intact blocks are verified, i.e., partially-overwritten blocks are
1334 .. option:: softrandommap=bool
1336 See :option:`norandommap`. If fio runs with the random block map enabled and
1337 it fails to allocate the map, if this option is set it will continue without
1338 a random block map. As coverage will not be as complete as with random maps,
1339 this option is disabled by default.
1341 .. option:: random_generator=str
1343 Fio supports the following engines for generating I/O offsets for random I/O:
1346 Strong 2^88 cycle random number generator.
1348 Linear feedback shift register generator.
1350 Strong 64-bit 2^258 cycle random number generator.
1352 **tausworthe** is a strong random number generator, but it requires tracking
1353 on the side if we want to ensure that blocks are only read or written
1354 once. **lfsr** guarantees that we never generate the same offset twice, and
1355 it's also less computationally expensive. It's not a true random generator,
1356 however, though for I/O purposes it's typically good enough. **lfsr** only
1357 works with single block sizes, not with workloads that use multiple block
1358 sizes. If used with such a workload, fio may read or write some blocks
1359 multiple times. The default value is **tausworthe**, unless the required
1360 space exceeds 2^32 blocks. If it does, then **tausworthe64** is
1361 selected automatically.
1367 .. option:: blocksize=int[,int][,int], bs=int[,int][,int]
1369 The block size in bytes used for I/O units. Default: 4096. A single value
1370 applies to reads, writes, and trims. Comma-separated values may be
1371 specified for reads, writes, and trims. A value not terminated in a comma
1372 applies to subsequent types.
1377 means 256k for reads, writes and trims.
1380 means 8k for reads, 32k for writes and trims.
1383 means 8k for reads, 32k for writes, and default for trims.
1386 means default for reads, 8k for writes and trims.
1389 means default for reads, 8k for writes, and default for trims.
1391 .. option:: blocksize_range=irange[,irange][,irange], bsrange=irange[,irange][,irange]
1393 A range of block sizes in bytes for I/O units. The issued I/O unit will
1394 always be a multiple of the minimum size, unless
1395 :option:`blocksize_unaligned` is set.
1397 Comma-separated ranges may be specified for reads, writes, and trims as
1398 described in :option:`blocksize`.
1400 Example: ``bsrange=1k-4k,2k-8k``.
1402 .. option:: bssplit=str[,str][,str]
1404 Sometimes you want even finer grained control of the block sizes
1405 issued, not just an even split between them. This option allows you to
1406 weight various block sizes, so that you are able to define a specific
1407 amount of block sizes issued. The format for this option is::
1409 bssplit=blocksize/percentage:blocksize/percentage
1411 for as many block sizes as needed. So if you want to define a workload
1412 that has 50% 64k blocks, 10% 4k blocks, and 40% 32k blocks, you would
1415 bssplit=4k/10:64k/50:32k/40
1417 Ordering does not matter. If the percentage is left blank, fio will
1418 fill in the remaining values evenly. So a bssplit option like this one::
1420 bssplit=4k/50:1k/:32k/
1422 would have 50% 4k ios, and 25% 1k and 32k ios. The percentages always
1423 add up to 100, if bssplit is given a range that adds up to more, it
1426 Comma-separated values may be specified for reads, writes, and trims as
1427 described in :option:`blocksize`.
1429 If you want a workload that has 50% 2k reads and 50% 4k reads, while
1430 having 90% 4k writes and 10% 8k writes, you would specify::
1432 bssplit=2k/50:4k/50,4k/90,8k/10
1434 Fio supports defining up to 64 different weights for each data
1437 .. option:: blocksize_unaligned, bs_unaligned
1439 If set, fio will issue I/O units with any size within
1440 :option:`blocksize_range`, not just multiples of the minimum size. This
1441 typically won't work with direct I/O, as that normally requires sector
1444 .. option:: bs_is_seq_rand=bool
1446 If this option is set, fio will use the normal read,write blocksize settings
1447 as sequential,random blocksize settings instead. Any random read or write
1448 will use the WRITE blocksize settings, and any sequential read or write will
1449 use the READ blocksize settings.
1451 .. option:: blockalign=int[,int][,int], ba=int[,int][,int]
1453 Boundary to which fio will align random I/O units. Default:
1454 :option:`blocksize`. Minimum alignment is typically 512b for using direct
1455 I/O, though it usually depends on the hardware block size. This option is
1456 mutually exclusive with using a random map for files, so it will turn off
1457 that option. Comma-separated values may be specified for reads, writes, and
1458 trims as described in :option:`blocksize`.
1464 .. option:: zero_buffers
1466 Initialize buffers with all zeros. Default: fill buffers with random data.
1468 .. option:: refill_buffers
1470 If this option is given, fio will refill the I/O buffers on every
1471 submit. Only makes sense if :option:`zero_buffers` isn't specified,
1472 naturally. Defaults to being unset i.e., the buffer is only filled at
1473 init time and the data in it is reused when possible but if any of
1474 :option:`verify`, :option:`buffer_compress_percentage` or
1475 :option:`dedupe_percentage` are enabled then `refill_buffers` is also
1476 automatically enabled.
1478 .. option:: scramble_buffers=bool
1480 If :option:`refill_buffers` is too costly and the target is using data
1481 deduplication, then setting this option will slightly modify the I/O buffer
1482 contents to defeat normal de-dupe attempts. This is not enough to defeat
1483 more clever block compression attempts, but it will stop naive dedupe of
1484 blocks. Default: true.
1486 .. option:: buffer_compress_percentage=int
1488 If this is set, then fio will attempt to provide I/O buffer content
1489 (on WRITEs) that compresses to the specified level. Fio does this by
1490 providing a mix of random data followed by fixed pattern data. The
1491 fixed pattern is either zeros, or the pattern specified by
1492 :option:`buffer_pattern`. If the `buffer_pattern` option is used, it
1493 might skew the compression ratio slightly. Setting
1494 `buffer_compress_percentage` to a value other than 100 will also
1495 enable :option:`refill_buffers` in order to reduce the likelihood that
1496 adjacent blocks are so similar that they over compress when seen
1497 together. See :option:`buffer_compress_chunk` for how to set a finer or
1498 coarser granularity for the random/fixed data region. Defaults to unset
1499 i.e., buffer data will not adhere to any compression level.
1501 .. option:: buffer_compress_chunk=int
1503 This setting allows fio to manage how big the random/fixed data region
1504 is when using :option:`buffer_compress_percentage`. When
1505 `buffer_compress_chunk` is set to some non-zero value smaller than the
1506 block size, fio can repeat the random/fixed region throughout the I/O
1507 buffer at the specified interval (which particularly useful when
1508 bigger block sizes are used for a job). When set to 0, fio will use a
1509 chunk size that matches the block size resulting in a single
1510 random/fixed region within the I/O buffer. Defaults to 512. When the
1511 unit is omitted, the value is interpreted in bytes.
1513 .. option:: buffer_pattern=str
1515 If set, fio will fill the I/O buffers with this pattern or with the contents
1516 of a file. If not set, the contents of I/O buffers are defined by the other
1517 options related to buffer contents. The setting can be any pattern of bytes,
1518 and can be prefixed with 0x for hex values. It may also be a string, where
1519 the string must then be wrapped with ``""``. Or it may also be a filename,
1520 where the filename must be wrapped with ``''`` in which case the file is
1521 opened and read. Note that not all the file contents will be read if that
1522 would cause the buffers to overflow. So, for example::
1524 buffer_pattern='filename'
1528 buffer_pattern="abcd"
1536 buffer_pattern=0xdeadface
1538 Also you can combine everything together in any order::
1540 buffer_pattern=0xdeadface"abcd"-12'filename'
1542 .. option:: dedupe_percentage=int
1544 If set, fio will generate this percentage of identical buffers when
1545 writing. These buffers will be naturally dedupable. The contents of the
1546 buffers depend on what other buffer compression settings have been set. It's
1547 possible to have the individual buffers either fully compressible, or not at
1548 all -- this option only controls the distribution of unique buffers. Setting
1549 this option will also enable :option:`refill_buffers` to prevent every buffer
1552 .. option:: invalidate=bool
1554 Invalidate the buffer/page cache parts of the files to be used prior to
1555 starting I/O if the platform and file type support it. Defaults to true.
1556 This will be ignored if :option:`pre_read` is also specified for the
1559 .. option:: sync=bool
1561 Use synchronous I/O for buffered writes. For the majority of I/O engines,
1562 this means using O_SYNC. Default: false.
1564 .. option:: iomem=str, mem=str
1566 Fio can use various types of memory as the I/O unit buffer. The allowed
1570 Use memory from :manpage:`malloc(3)` as the buffers. Default memory
1574 Use shared memory as the buffers. Allocated through
1575 :manpage:`shmget(2)`.
1578 Same as shm, but use huge pages as backing.
1581 Use :manpage:`mmap(2)` to allocate buffers. May either be anonymous memory, or can
1582 be file backed if a filename is given after the option. The format
1583 is `mem=mmap:/path/to/file`.
1586 Use a memory mapped huge file as the buffer backing. Append filename
1587 after mmaphuge, ala `mem=mmaphuge:/hugetlbfs/file`.
1590 Same as mmap, but use a MMAP_SHARED mapping.
1593 Use GPU memory as the buffers for GPUDirect RDMA benchmark.
1594 The :option:`ioengine` must be `rdma`.
1596 The area allocated is a function of the maximum allowed bs size for the job,
1597 multiplied by the I/O depth given. Note that for **shmhuge** and
1598 **mmaphuge** to work, the system must have free huge pages allocated. This
1599 can normally be checked and set by reading/writing
1600 :file:`/proc/sys/vm/nr_hugepages` on a Linux system. Fio assumes a huge page
1601 is 4MiB in size. So to calculate the number of huge pages you need for a
1602 given job file, add up the I/O depth of all jobs (normally one unless
1603 :option:`iodepth` is used) and multiply by the maximum bs set. Then divide
1604 that number by the huge page size. You can see the size of the huge pages in
1605 :file:`/proc/meminfo`. If no huge pages are allocated by having a non-zero
1606 number in `nr_hugepages`, using **mmaphuge** or **shmhuge** will fail. Also
1607 see :option:`hugepage-size`.
1609 **mmaphuge** also needs to have hugetlbfs mounted and the file location
1610 should point there. So if it's mounted in :file:`/huge`, you would use
1611 `mem=mmaphuge:/huge/somefile`.
1613 .. option:: iomem_align=int, mem_align=int
1615 This indicates the memory alignment of the I/O memory buffers. Note that
1616 the given alignment is applied to the first I/O unit buffer, if using
1617 :option:`iodepth` the alignment of the following buffers are given by the
1618 :option:`bs` used. In other words, if using a :option:`bs` that is a
1619 multiple of the page sized in the system, all buffers will be aligned to
1620 this value. If using a :option:`bs` that is not page aligned, the alignment
1621 of subsequent I/O memory buffers is the sum of the :option:`iomem_align` and
1624 .. option:: hugepage-size=int
1626 Defines the size of a huge page. Must at least be equal to the system
1627 setting, see :file:`/proc/meminfo`. Defaults to 4MiB. Should probably
1628 always be a multiple of megabytes, so using ``hugepage-size=Xm`` is the
1629 preferred way to set this to avoid setting a non-pow-2 bad value.
1631 .. option:: lockmem=int
1633 Pin the specified amount of memory with :manpage:`mlock(2)`. Can be used to
1634 simulate a smaller amount of memory. The amount specified is per worker.
1640 .. option:: size=int
1642 The total size of file I/O for each thread of this job. Fio will run until
1643 this many bytes has been transferred, unless runtime is limited by other options
1644 (such as :option:`runtime`, for instance, or increased/decreased by :option:`io_size`).
1645 Fio will divide this size between the available files determined by options
1646 such as :option:`nrfiles`, :option:`filename`, unless :option:`filesize` is
1647 specified by the job. If the result of division happens to be 0, the size is
1648 set to the physical size of the given files or devices if they exist.
1649 If this option is not specified, fio will use the full size of the given
1650 files or devices. If the files do not exist, size must be given. It is also
1651 possible to give size as a percentage between 1 and 100. If ``size=20%`` is
1652 given, fio will use 20% of the full size of the given files or devices.
1653 Can be combined with :option:`offset` to constrain the start and end range
1654 that I/O will be done within.
1656 .. option:: io_size=int, io_limit=int
1658 Normally fio operates within the region set by :option:`size`, which means
1659 that the :option:`size` option sets both the region and size of I/O to be
1660 performed. Sometimes that is not what you want. With this option, it is
1661 possible to define just the amount of I/O that fio should do. For instance,
1662 if :option:`size` is set to 20GiB and :option:`io_size` is set to 5GiB, fio
1663 will perform I/O within the first 20GiB but exit when 5GiB have been
1664 done. The opposite is also possible -- if :option:`size` is set to 20GiB,
1665 and :option:`io_size` is set to 40GiB, then fio will do 40GiB of I/O within
1666 the 0..20GiB region.
1668 .. option:: filesize=irange(int)
1670 Individual file sizes. May be a range, in which case fio will select sizes
1671 for files at random within the given range and limited to :option:`size` in
1672 total (if that is given). If not given, each created file is the same size.
1673 This option overrides :option:`size` in terms of file size, which means
1674 this value is used as a fixed size or possible range of each file.
1676 .. option:: file_append=bool
1678 Perform I/O after the end of the file. Normally fio will operate within the
1679 size of a file. If this option is set, then fio will append to the file
1680 instead. This has identical behavior to setting :option:`offset` to the size
1681 of a file. This option is ignored on non-regular files.
1683 .. option:: fill_device=bool, fill_fs=bool
1685 Sets size to something really large and waits for ENOSPC (no space left on
1686 device) as the terminating condition. Only makes sense with sequential
1687 write. For a read workload, the mount point will be filled first then I/O
1688 started on the result. This option doesn't make sense if operating on a raw
1689 device node, since the size of that is already known by the file system.
1690 Additionally, writing beyond end-of-device will not return ENOSPC there.
1696 .. option:: ioengine=str
1698 Defines how the job issues I/O to the file. The following types are defined:
1701 Basic :manpage:`read(2)` or :manpage:`write(2)`
1702 I/O. :manpage:`lseek(2)` is used to position the I/O location.
1703 See :option:`fsync` and :option:`fdatasync` for syncing write I/Os.
1706 Basic :manpage:`pread(2)` or :manpage:`pwrite(2)` I/O. Default on
1707 all supported operating systems except for Windows.
1710 Basic :manpage:`readv(2)` or :manpage:`writev(2)` I/O. Will emulate
1711 queuing by coalescing adjacent I/Os into a single submission.
1714 Basic :manpage:`preadv(2)` or :manpage:`pwritev(2)` I/O.
1717 Basic :manpage:`preadv2(2)` or :manpage:`pwritev2(2)` I/O.
1720 Linux native asynchronous I/O. Note that Linux may only support
1721 queued behavior with non-buffered I/O (set ``direct=1`` or
1723 This engine defines engine specific options.
1726 POSIX asynchronous I/O using :manpage:`aio_read(3)` and
1727 :manpage:`aio_write(3)`.
1730 Solaris native asynchronous I/O.
1733 Windows native asynchronous I/O. Default on Windows.
1736 File is memory mapped with :manpage:`mmap(2)` and data copied
1737 to/from using :manpage:`memcpy(3)`.
1740 :manpage:`splice(2)` is used to transfer the data and
1741 :manpage:`vmsplice(2)` to transfer data from user space to the
1745 SCSI generic sg v3 I/O. May either be synchronous using the SG_IO
1746 ioctl, or if the target is an sg character device we use
1747 :manpage:`read(2)` and :manpage:`write(2)` for asynchronous
1748 I/O. Requires :option:`filename` option to specify either block or
1750 The sg engine includes engine specific options.
1753 Doesn't transfer any data, just pretends to. This is mainly used to
1754 exercise fio itself and for debugging/testing purposes.
1757 Transfer over the network to given ``host:port``. Depending on the
1758 :option:`protocol` used, the :option:`hostname`, :option:`port`,
1759 :option:`listen` and :option:`filename` options are used to specify
1760 what sort of connection to make, while the :option:`protocol` option
1761 determines which protocol will be used. This engine defines engine
1765 Like **net**, but uses :manpage:`splice(2)` and
1766 :manpage:`vmsplice(2)` to map data and send/receive.
1767 This engine defines engine specific options.
1770 Doesn't transfer any data, but burns CPU cycles according to the
1771 :option:`cpuload` and :option:`cpuchunks` options. Setting
1772 :option:`cpuload`\=85 will cause that job to do nothing but burn 85%
1773 of the CPU. In case of SMP machines, use :option:`numjobs`\=<nr_of_cpu>
1774 to get desired CPU usage, as the cpuload only loads a
1775 single CPU at the desired rate. A job never finishes unless there is
1776 at least one non-cpuio job.
1779 The GUASI I/O engine is the Generic Userspace Asynchronous Syscall
1780 Interface approach to async I/O. See
1782 http://www.xmailserver.org/guasi-lib.html
1784 for more info on GUASI.
1787 The RDMA I/O engine supports both RDMA memory semantics
1788 (RDMA_WRITE/RDMA_READ) and channel semantics (Send/Recv) for the
1789 InfiniBand, RoCE and iWARP protocols. This engine defines engine
1793 I/O engine that does regular fallocate to simulate data transfer as
1797 does fallocate(,mode = FALLOC_FL_KEEP_SIZE,).
1800 does fallocate(,mode = 0).
1803 does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE).
1806 I/O engine that sends :manpage:`ftruncate(2)` operations in response
1807 to write (DDIR_WRITE) events. Each ftruncate issued sets the file's
1808 size to the current block offset. :option:`blocksize` is ignored.
1811 I/O engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate
1812 defragment activity in request to DDIR_WRITE event.
1815 I/O engine supporting direct access to Ceph Reliable Autonomic
1816 Distributed Object Store (RADOS) via librados. This ioengine
1817 defines engine specific options.
1820 I/O engine supporting direct access to Ceph Rados Block Devices
1821 (RBD) via librbd without the need to use the kernel rbd driver. This
1822 ioengine defines engine specific options.
1825 Using GlusterFS libgfapi sync interface to direct access to
1826 GlusterFS volumes without having to go through FUSE. This ioengine
1827 defines engine specific options.
1830 Using GlusterFS libgfapi async interface to direct access to
1831 GlusterFS volumes without having to go through FUSE. This ioengine
1832 defines engine specific options.
1835 Read and write through Hadoop (HDFS). The :option:`filename` option
1836 is used to specify host,port of the hdfs name-node to connect. This
1837 engine interprets offsets a little differently. In HDFS, files once
1838 created cannot be modified so random writes are not possible. To
1839 imitate this the libhdfs engine expects a bunch of small files to be
1840 created over HDFS and will randomly pick a file from them
1841 based on the offset generated by fio backend (see the example
1842 job file to create such files, use ``rw=write`` option). Please
1843 note, it may be necessary to set environment variables to work
1844 with HDFS/libhdfs properly. Each job uses its own connection to
1848 Read, write and erase an MTD character device (e.g.,
1849 :file:`/dev/mtd0`). Discards are treated as erases. Depending on the
1850 underlying device type, the I/O may have to go in a certain pattern,
1851 e.g., on NAND, writing sequentially to erase blocks and discarding
1852 before overwriting. The `trimwrite` mode works well for this
1856 Read and write using filesystem DAX to a file on a filesystem
1857 mounted with DAX on a persistent memory device through the NVML
1861 Read and write using device DAX to a persistent memory device (e.g.,
1862 /dev/dax0.0) through the NVML libpmem library.
1865 Prefix to specify loading an external I/O engine object file. Append
1866 the engine filename, e.g. ``ioengine=external:/tmp/foo.o`` to load
1867 ioengine :file:`foo.o` in :file:`/tmp`. The path can be either
1868 absolute or relative. See :file:`engines/skeleton_external.c` for
1869 details of writing an external I/O engine.
1872 Simply create the files and do no I/O to them. You still need to
1873 set `filesize` so that all the accounting still occurs, but no
1874 actual I/O will be done other than creating the file.
1877 Read and write using mmap I/O to a file on a filesystem
1878 mounted with DAX on a persistent memory device through the NVML
1881 I/O engine specific parameters
1882 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1884 In addition, there are some parameters which are only valid when a specific
1885 :option:`ioengine` is in use. These are used identically to normal parameters,
1886 with the caveat that when used on the command line, they must come after the
1887 :option:`ioengine` that defines them is selected.
1889 .. option:: userspace_reap : [libaio]
1891 Normally, with the libaio engine in use, fio will use the
1892 :manpage:`io_getevents(2)` system call to reap newly returned events. With
1893 this flag turned on, the AIO ring will be read directly from user-space to
1894 reap events. The reaping mode is only enabled when polling for a minimum of
1895 0 events (e.g. when :option:`iodepth_batch_complete` `=0`).
1897 .. option:: hipri : [pvsync2]
1899 Set RWF_HIPRI on I/O, indicating to the kernel that it's of higher priority
1902 .. option:: hipri_percentage : [pvsync2]
1904 When hipri is set this determines the probability of a pvsync2 I/O being high
1905 priority. The default is 100%.
1907 .. option:: cpuload=int : [cpuio]
1909 Attempt to use the specified percentage of CPU cycles. This is a mandatory
1910 option when using cpuio I/O engine.
1912 .. option:: cpuchunks=int : [cpuio]
1914 Split the load into cycles of the given time. In microseconds.
1916 .. option:: exit_on_io_done=bool : [cpuio]
1918 Detect when I/O threads are done, then exit.
1920 .. option:: namenode=str : [libhdfs]
1922 The hostname or IP address of a HDFS cluster namenode to contact.
1924 .. option:: port=int
1928 The listening port of the HFDS cluster namenode.
1932 The TCP or UDP port to bind to or connect to. If this is used with
1933 :option:`numjobs` to spawn multiple instances of the same job type, then
1934 this will be the starting port number since fio will use a range of
1939 The port to use for RDMA-CM communication. This should be the same value
1940 on the client and the server side.
1942 .. option:: hostname=str : [netsplice] [net] [rdma]
1944 The hostname or IP address to use for TCP, UDP or RDMA-CM based I/O. If the job
1945 is a TCP listener or UDP reader, the hostname is not used and must be omitted
1946 unless it is a valid UDP multicast address.
1948 .. option:: interface=str : [netsplice] [net]
1950 The IP address of the network interface used to send or receive UDP
1953 .. option:: ttl=int : [netsplice] [net]
1955 Time-to-live value for outgoing UDP multicast packets. Default: 1.
1957 .. option:: nodelay=bool : [netsplice] [net]
1959 Set TCP_NODELAY on TCP connections.
1961 .. option:: protocol=str, proto=str : [netsplice] [net]
1963 The network protocol to use. Accepted values are:
1966 Transmission control protocol.
1968 Transmission control protocol V6.
1970 User datagram protocol.
1972 User datagram protocol V6.
1976 When the protocol is TCP or UDP, the port must also be given, as well as the
1977 hostname if the job is a TCP listener or UDP reader. For unix sockets, the
1978 normal :option:`filename` option should be used and the port is invalid.
1980 .. option:: listen : [netsplice] [net]
1982 For TCP network connections, tell fio to listen for incoming connections
1983 rather than initiating an outgoing connection. The :option:`hostname` must
1984 be omitted if this option is used.
1986 .. option:: pingpong : [netsplice] [net]
1988 Normally a network writer will just continue writing data, and a network
1989 reader will just consume packages. If ``pingpong=1`` is set, a writer will
1990 send its normal payload to the reader, then wait for the reader to send the
1991 same payload back. This allows fio to measure network latencies. The
1992 submission and completion latencies then measure local time spent sending or
1993 receiving, and the completion latency measures how long it took for the
1994 other end to receive and send back. For UDP multicast traffic
1995 ``pingpong=1`` should only be set for a single reader when multiple readers
1996 are listening to the same address.
1998 .. option:: window_size : [netsplice] [net]
2000 Set the desired socket buffer size for the connection.
2002 .. option:: mss : [netsplice] [net]
2004 Set the TCP maximum segment size (TCP_MAXSEG).
2006 .. option:: donorname=str : [e4defrag]
2008 File will be used as a block donor (swap extents between files).
2010 .. option:: inplace=int : [e4defrag]
2012 Configure donor file blocks allocation strategy:
2015 Default. Preallocate donor's file on init.
2017 Allocate space immediately inside defragment event, and free right
2020 .. option:: clustername=str : [rbd,rados]
2022 Specifies the name of the Ceph cluster.
2024 .. option:: rbdname=str : [rbd]
2026 Specifies the name of the RBD.
2028 .. option:: pool=str : [rbd,rados]
2030 Specifies the name of the Ceph pool containing RBD or RADOS data.
2032 .. option:: clientname=str : [rbd,rados]
2034 Specifies the username (without the 'client.' prefix) used to access the
2035 Ceph cluster. If the *clustername* is specified, the *clientname* shall be
2036 the full *type.id* string. If no type. prefix is given, fio will add
2037 'client.' by default.
2039 .. option:: busy_poll=bool : [rbd,rados]
2041 Poll store instead of waiting for completion. Usually this provides better
2042 throughput at cost of higher(up to 100%) CPU utilization.
2044 .. option:: skip_bad=bool : [mtd]
2046 Skip operations against known bad blocks.
2048 .. option:: hdfsdirectory : [libhdfs]
2050 libhdfs will create chunk in this HDFS directory.
2052 .. option:: chunk_size : [libhdfs]
2054 The size of the chunk to use for each file.
2056 .. option:: verb=str : [rdma]
2058 The RDMA verb to use on this side of the RDMA ioengine connection. Valid
2059 values are write, read, send and recv. These correspond to the equivalent
2060 RDMA verbs (e.g. write = rdma_write etc.). Note that this only needs to be
2061 specified on the client side of the connection. See the examples folder.
2063 .. option:: bindname=str : [rdma]
2065 The name to use to bind the local RDMA-CM connection to a local RDMA device.
2066 This could be a hostname or an IPv4 or IPv6 address. On the server side this
2067 will be passed into the rdma_bind_addr() function and on the client site it
2068 will be used in the rdma_resolve_add() function. This can be useful when
2069 multiple paths exist between the client and the server or in certain loopback
2072 .. option:: readfua=bool : [sg]
2074 With readfua option set to 1, read operations include
2075 the force unit access (fua) flag. Default is 0.
2077 .. option:: writefua=bool : [sg]
2079 With writefua option set to 1, write operations include
2080 the force unit access (fua) flag. Default is 0.
2086 .. option:: iodepth=int
2088 Number of I/O units to keep in flight against the file. Note that
2089 increasing *iodepth* beyond 1 will not affect synchronous ioengines (except
2090 for small degrees when :option:`verify_async` is in use). Even async
2091 engines may impose OS restrictions causing the desired depth not to be
2092 achieved. This may happen on Linux when using libaio and not setting
2093 :option:`direct`\=1, since buffered I/O is not async on that OS. Keep an
2094 eye on the I/O depth distribution in the fio output to verify that the
2095 achieved depth is as expected. Default: 1.
2097 .. option:: iodepth_batch_submit=int, iodepth_batch=int
2099 This defines how many pieces of I/O to submit at once. It defaults to 1
2100 which means that we submit each I/O as soon as it is available, but can be
2101 raised to submit bigger batches of I/O at the time. If it is set to 0 the
2102 :option:`iodepth` value will be used.
2104 .. option:: iodepth_batch_complete_min=int, iodepth_batch_complete=int
2106 This defines how many pieces of I/O to retrieve at once. It defaults to 1
2107 which means that we'll ask for a minimum of 1 I/O in the retrieval process
2108 from the kernel. The I/O retrieval will go on until we hit the limit set by
2109 :option:`iodepth_low`. If this variable is set to 0, then fio will always
2110 check for completed events before queuing more I/O. This helps reduce I/O
2111 latency, at the cost of more retrieval system calls.
2113 .. option:: iodepth_batch_complete_max=int
2115 This defines maximum pieces of I/O to retrieve at once. This variable should
2116 be used along with :option:`iodepth_batch_complete_min`\=int variable,
2117 specifying the range of min and max amount of I/O which should be
2118 retrieved. By default it is equal to the :option:`iodepth_batch_complete_min`
2123 iodepth_batch_complete_min=1
2124 iodepth_batch_complete_max=<iodepth>
2126 which means that we will retrieve at least 1 I/O and up to the whole
2127 submitted queue depth. If none of I/O has been completed yet, we will wait.
2131 iodepth_batch_complete_min=0
2132 iodepth_batch_complete_max=<iodepth>
2134 which means that we can retrieve up to the whole submitted queue depth, but
2135 if none of I/O has been completed yet, we will NOT wait and immediately exit
2136 the system call. In this example we simply do polling.
2138 .. option:: iodepth_low=int
2140 The low water mark indicating when to start filling the queue
2141 again. Defaults to the same as :option:`iodepth`, meaning that fio will
2142 attempt to keep the queue full at all times. If :option:`iodepth` is set to
2143 e.g. 16 and *iodepth_low* is set to 4, then after fio has filled the queue of
2144 16 requests, it will let the depth drain down to 4 before starting to fill
2147 .. option:: serialize_overlap=bool
2149 Serialize in-flight I/Os that might otherwise cause or suffer from data races.
2150 When two or more I/Os are submitted simultaneously, there is no guarantee that
2151 the I/Os will be processed or completed in the submitted order. Further, if
2152 two or more of those I/Os are writes, any overlapping region between them can
2153 become indeterminate/undefined on certain storage. These issues can cause
2154 verification to fail erratically when at least one of the racing I/Os is
2155 changing data and the overlapping region has a non-zero size. Setting
2156 ``serialize_overlap`` tells fio to avoid provoking this behavior by explicitly
2157 serializing in-flight I/Os that have a non-zero overlap. Note that setting
2158 this option can reduce both performance and the :option:`iodepth` achieved.
2159 Additionally this option does not work when :option:`io_submit_mode` is set to
2160 offload. Default: false.
2162 .. option:: io_submit_mode=str
2164 This option controls how fio submits the I/O to the I/O engine. The default
2165 is `inline`, which means that the fio job threads submit and reap I/O
2166 directly. If set to `offload`, the job threads will offload I/O submission
2167 to a dedicated pool of I/O threads. This requires some coordination and thus
2168 has a bit of extra overhead, especially for lower queue depth I/O where it
2169 can increase latencies. The benefit is that fio can manage submission rates
2170 independently of the device completion rates. This avoids skewed latency
2171 reporting if I/O gets backed up on the device side (the coordinated omission
2178 .. option:: thinktime=time
2180 Stall the job for the specified period of time after an I/O has completed before issuing the
2181 next. May be used to simulate processing being done by an application.
2182 When the unit is omitted, the value is interpreted in microseconds. See
2183 :option:`thinktime_blocks` and :option:`thinktime_spin`.
2185 .. option:: thinktime_spin=time
2187 Only valid if :option:`thinktime` is set - pretend to spend CPU time doing
2188 something with the data received, before falling back to sleeping for the
2189 rest of the period specified by :option:`thinktime`. When the unit is
2190 omitted, the value is interpreted in microseconds.
2192 .. option:: thinktime_blocks=int
2194 Only valid if :option:`thinktime` is set - control how many blocks to issue,
2195 before waiting :option:`thinktime` usecs. If not set, defaults to 1 which will make
2196 fio wait :option:`thinktime` usecs after every block. This effectively makes any
2197 queue depth setting redundant, since no more than 1 I/O will be queued
2198 before we have to complete it and do our :option:`thinktime`. In other words, this
2199 setting effectively caps the queue depth if the latter is larger.
2201 .. option:: rate=int[,int][,int]
2203 Cap the bandwidth used by this job. The number is in bytes/sec, the normal
2204 suffix rules apply. Comma-separated values may be specified for reads,
2205 writes, and trims as described in :option:`blocksize`.
2207 For example, using `rate=1m,500k` would limit reads to 1MiB/sec and writes to
2208 500KiB/sec. Capping only reads or writes can be done with `rate=,500k` or
2209 `rate=500k,` where the former will only limit writes (to 500KiB/sec) and the
2210 latter will only limit reads.
2212 .. option:: rate_min=int[,int][,int]
2214 Tell fio to do whatever it can to maintain at least this bandwidth. Failing
2215 to meet this requirement will cause the job to exit. Comma-separated values
2216 may be specified for reads, writes, and trims as described in
2217 :option:`blocksize`.
2219 .. option:: rate_iops=int[,int][,int]
2221 Cap the bandwidth to this number of IOPS. Basically the same as
2222 :option:`rate`, just specified independently of bandwidth. If the job is
2223 given a block size range instead of a fixed value, the smallest block size
2224 is used as the metric. Comma-separated values may be specified for reads,
2225 writes, and trims as described in :option:`blocksize`.
2227 .. option:: rate_iops_min=int[,int][,int]
2229 If fio doesn't meet this rate of I/O, it will cause the job to exit.
2230 Comma-separated values may be specified for reads, writes, and trims as
2231 described in :option:`blocksize`.
2233 .. option:: rate_process=str
2235 This option controls how fio manages rated I/O submissions. The default is
2236 `linear`, which submits I/O in a linear fashion with fixed delays between
2237 I/Os that gets adjusted based on I/O completion rates. If this is set to
2238 `poisson`, fio will submit I/O based on a more real world random request
2239 flow, known as the Poisson process
2240 (https://en.wikipedia.org/wiki/Poisson_point_process). The lambda will be
2241 10^6 / IOPS for the given workload.
2243 .. option:: rate_ignore_thinktime=bool
2245 By default, fio will attempt to catch up to the specified rate setting,
2246 if any kind of thinktime setting was used. If this option is set, then
2247 fio will ignore the thinktime and continue doing IO at the specified
2248 rate, instead of entering a catch-up mode after thinktime is done.
2254 .. option:: latency_target=time
2256 If set, fio will attempt to find the max performance point that the given
2257 workload will run at while maintaining a latency below this target. When
2258 the unit is omitted, the value is interpreted in microseconds. See
2259 :option:`latency_window` and :option:`latency_percentile`.
2261 .. option:: latency_window=time
2263 Used with :option:`latency_target` to specify the sample window that the job
2264 is run at varying queue depths to test the performance. When the unit is
2265 omitted, the value is interpreted in microseconds.
2267 .. option:: latency_percentile=float
2269 The percentage of I/Os that must fall within the criteria specified by
2270 :option:`latency_target` and :option:`latency_window`. If not set, this
2271 defaults to 100.0, meaning that all I/Os must be equal or below to the value
2272 set by :option:`latency_target`.
2274 .. option:: max_latency=time
2276 If set, fio will exit the job with an ETIMEDOUT error if it exceeds this
2277 maximum latency. When the unit is omitted, the value is interpreted in
2280 .. option:: rate_cycle=int
2282 Average bandwidth for :option:`rate` and :option:`rate_min` over this number
2283 of milliseconds. Defaults to 1000.
2289 .. option:: write_iolog=str
2291 Write the issued I/O patterns to the specified file. See
2292 :option:`read_iolog`. Specify a separate file for each job, otherwise the
2293 iologs will be interspersed and the file may be corrupt.
2295 .. option:: read_iolog=str
2297 Open an iolog with the specified filename and replay the I/O patterns it
2298 contains. This can be used to store a workload and replay it sometime
2299 later. The iolog given may also be a blktrace binary file, which allows fio
2300 to replay a workload captured by :command:`blktrace`. See
2301 :manpage:`blktrace(8)` for how to capture such logging data. For blktrace
2302 replay, the file needs to be turned into a blkparse binary data file first
2303 (``blkparse <device> -o /dev/null -d file_for_fio.bin``).
2305 .. option:: replay_no_stall=bool
2307 When replaying I/O with :option:`read_iolog` the default behavior is to
2308 attempt to respect the timestamps within the log and replay them with the
2309 appropriate delay between IOPS. By setting this variable fio will not
2310 respect the timestamps and attempt to replay them as fast as possible while
2311 still respecting ordering. The result is the same I/O pattern to a given
2312 device, but different timings.
2314 .. option:: replay_time_scale=int
2316 When replaying I/O with :option:`read_iolog`, fio will honor the
2317 original timing in the trace. With this option, it's possible to scale
2318 the time. It's a percentage option, if set to 50 it means run at 50%
2319 the original IO rate in the trace. If set to 200, run at twice the
2320 original IO rate. Defaults to 100.
2322 .. option:: replay_redirect=str
2324 While replaying I/O patterns using :option:`read_iolog` the default behavior
2325 is to replay the IOPS onto the major/minor device that each IOP was recorded
2326 from. This is sometimes undesirable because on a different machine those
2327 major/minor numbers can map to a different device. Changing hardware on the
2328 same system can also result in a different major/minor mapping.
2329 ``replay_redirect`` causes all I/Os to be replayed onto the single specified
2330 device regardless of the device it was recorded
2331 from. i.e. :option:`replay_redirect`\= :file:`/dev/sdc` would cause all I/O
2332 in the blktrace or iolog to be replayed onto :file:`/dev/sdc`. This means
2333 multiple devices will be replayed onto a single device, if the trace
2334 contains multiple devices. If you want multiple devices to be replayed
2335 concurrently to multiple redirected devices you must blkparse your trace
2336 into separate traces and replay them with independent fio invocations.
2337 Unfortunately this also breaks the strict time ordering between multiple
2340 .. option:: replay_align=int
2342 Force alignment of I/O offsets and lengths in a trace to this power of 2
2345 .. option:: replay_scale=int
2347 Scale sector offsets down by this factor when replaying traces.
2350 Threads, processes and job synchronization
2351 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2355 Fio defaults to creating jobs by using fork, however if this option is
2356 given, fio will create jobs by using POSIX Threads' function
2357 :manpage:`pthread_create(3)` to create threads instead.
2359 .. option:: wait_for=str
2361 If set, the current job won't be started until all workers of the specified
2362 waitee job are done.
2364 ``wait_for`` operates on the job name basis, so there are a few
2365 limitations. First, the waitee must be defined prior to the waiter job
2366 (meaning no forward references). Second, if a job is being referenced as a
2367 waitee, it must have a unique name (no duplicate waitees).
2369 .. option:: nice=int
2371 Run the job with the given nice value. See man :manpage:`nice(2)`.
2373 On Windows, values less than -15 set the process class to "High"; -1 through
2374 -15 set "Above Normal"; 1 through 15 "Below Normal"; and above 15 "Idle"
2377 .. option:: prio=int
2379 Set the I/O priority value of this job. Linux limits us to a positive value
2380 between 0 and 7, with 0 being the highest. See man
2381 :manpage:`ionice(1)`. Refer to an appropriate manpage for other operating
2382 systems since meaning of priority may differ.
2384 .. option:: prioclass=int
2386 Set the I/O priority class. See man :manpage:`ionice(1)`.
2388 .. option:: cpus_allowed=str
2390 Controls the same options as :option:`cpumask`, but accepts a textual
2391 specification of the permitted CPUs instead and CPUs are indexed from 0. So
2392 to use CPUs 0 and 5 you would specify ``cpus_allowed=0,5``. This option also
2393 allows a range of CPUs to be specified -- say you wanted a binding to CPUs
2394 0, 5, and 8 to 15, you would set ``cpus_allowed=0,5,8-15``.
2396 On Windows, when ``cpus_allowed`` is unset only CPUs from fio's current
2397 processor group will be used and affinity settings are inherited from the
2398 system. An fio build configured to target Windows 7 makes options that set
2399 CPUs processor group aware and values will set both the processor group
2400 and a CPU from within that group. For example, on a system where processor
2401 group 0 has 40 CPUs and processor group 1 has 32 CPUs, ``cpus_allowed``
2402 values between 0 and 39 will bind CPUs from processor group 0 and
2403 ``cpus_allowed`` values between 40 and 71 will bind CPUs from processor
2404 group 1. When using ``cpus_allowed_policy=shared`` all CPUs specified by a
2405 single ``cpus_allowed`` option must be from the same processor group. For
2406 Windows fio builds not built for Windows 7, CPUs will only be selected from
2407 (and be relative to) whatever processor group fio happens to be running in
2408 and CPUs from other processor groups cannot be used.
2410 .. option:: cpus_allowed_policy=str
2412 Set the policy of how fio distributes the CPUs specified by
2413 :option:`cpus_allowed` or :option:`cpumask`. Two policies are supported:
2416 All jobs will share the CPU set specified.
2418 Each job will get a unique CPU from the CPU set.
2420 **shared** is the default behavior, if the option isn't specified. If
2421 **split** is specified, then fio will will assign one cpu per job. If not
2422 enough CPUs are given for the jobs listed, then fio will roundrobin the CPUs
2425 .. option:: cpumask=int
2427 Set the CPU affinity of this job. The parameter given is a bit mask of
2428 allowed CPUs the job may run on. So if you want the allowed CPUs to be 1
2429 and 5, you would pass the decimal value of (1 << 1 | 1 << 5), or 34. See man
2430 :manpage:`sched_setaffinity(2)`. This may not work on all supported
2431 operating systems or kernel versions. This option doesn't work well for a
2432 higher CPU count than what you can store in an integer mask, so it can only
2433 control cpus 1-32. For boxes with larger CPU counts, use
2434 :option:`cpus_allowed`.
2436 .. option:: numa_cpu_nodes=str
2438 Set this job running on specified NUMA nodes' CPUs. The arguments allow
2439 comma delimited list of cpu numbers, A-B ranges, or `all`. Note, to enable
2440 NUMA options support, fio must be built on a system with libnuma-dev(el)
2443 .. option:: numa_mem_policy=str
2445 Set this job's memory policy and corresponding NUMA nodes. Format of the
2450 ``mode`` is one of the following memory policies: ``default``, ``prefer``,
2451 ``bind``, ``interleave`` or ``local``. For ``default`` and ``local`` memory
2452 policies, no node needs to be specified. For ``prefer``, only one node is
2453 allowed. For ``bind`` and ``interleave`` the ``nodelist`` may be as
2454 follows: a comma delimited list of numbers, A-B ranges, or `all`.
2456 .. option:: cgroup=str
2458 Add job to this control group. If it doesn't exist, it will be created. The
2459 system must have a mounted cgroup blkio mount point for this to work. If
2460 your system doesn't have it mounted, you can do so with::
2462 # mount -t cgroup -o blkio none /cgroup
2464 .. option:: cgroup_weight=int
2466 Set the weight of the cgroup to this value. See the documentation that comes
2467 with the kernel, allowed values are in the range of 100..1000.
2469 .. option:: cgroup_nodelete=bool
2471 Normally fio will delete the cgroups it has created after the job
2472 completion. To override this behavior and to leave cgroups around after the
2473 job completion, set ``cgroup_nodelete=1``. This can be useful if one wants
2474 to inspect various cgroup files after job completion. Default: false.
2476 .. option:: flow_id=int
2478 The ID of the flow. If not specified, it defaults to being a global
2479 flow. See :option:`flow`.
2481 .. option:: flow=int
2483 Weight in token-based flow control. If this value is used, then there is a
2484 'flow counter' which is used to regulate the proportion of activity between
2485 two or more jobs. Fio attempts to keep this flow counter near zero. The
2486 ``flow`` parameter stands for how much should be added or subtracted to the
2487 flow counter on each iteration of the main I/O loop. That is, if one job has
2488 ``flow=8`` and another job has ``flow=-1``, then there will be a roughly 1:8
2489 ratio in how much one runs vs the other.
2491 .. option:: flow_watermark=int
2493 The maximum value that the absolute value of the flow counter is allowed to
2494 reach before the job must wait for a lower value of the counter.
2496 .. option:: flow_sleep=int
2498 The period of time, in microseconds, to wait after the flow watermark has
2499 been exceeded before retrying operations.
2501 .. option:: stonewall, wait_for_previous
2503 Wait for preceding jobs in the job file to exit, before starting this
2504 one. Can be used to insert serialization points in the job file. A stone
2505 wall also implies starting a new reporting group, see
2506 :option:`group_reporting`.
2510 By default, fio will continue running all other jobs when one job finishes
2511 but sometimes this is not the desired action. Setting ``exitall`` will
2512 instead make fio terminate all other jobs when one job finishes.
2514 .. option:: exec_prerun=str
2516 Before running this job, issue the command specified through
2517 :manpage:`system(3)`. Output is redirected in a file called
2518 :file:`jobname.prerun.txt`.
2520 .. option:: exec_postrun=str
2522 After the job completes, issue the command specified though
2523 :manpage:`system(3)`. Output is redirected in a file called
2524 :file:`jobname.postrun.txt`.
2528 Instead of running as the invoking user, set the user ID to this value
2529 before the thread/process does any work.
2533 Set group ID, see :option:`uid`.
2539 .. option:: verify_only
2541 Do not perform specified workload, only verify data still matches previous
2542 invocation of this workload. This option allows one to check data multiple
2543 times at a later date without overwriting it. This option makes sense only
2544 for workloads that write data, and does not support workloads with the
2545 :option:`time_based` option set.
2547 .. option:: do_verify=bool
2549 Run the verify phase after a write phase. Only valid if :option:`verify` is
2552 .. option:: verify=str
2554 If writing to a file, fio can verify the file contents after each iteration
2555 of the job. Each verification method also implies verification of special
2556 header, which is written to the beginning of each block. This header also
2557 includes meta information, like offset of the block, block number, timestamp
2558 when block was written, etc. :option:`verify` can be combined with
2559 :option:`verify_pattern` option. The allowed values are:
2562 Use an md5 sum of the data area and store it in the header of
2566 Use an experimental crc64 sum of the data area and store it in the
2567 header of each block.
2570 Use a crc32c sum of the data area and store it in the header of
2571 each block. This will automatically use hardware acceleration
2572 (e.g. SSE4.2 on an x86 or CRC crypto extensions on ARM64) but will
2573 fall back to software crc32c if none is found. Generally the
2574 fastest checksum fio supports when hardware accelerated.
2580 Use a crc32 sum of the data area and store it in the header of each
2584 Use a crc16 sum of the data area and store it in the header of each
2588 Use a crc7 sum of the data area and store it in the header of each
2592 Use xxhash as the checksum function. Generally the fastest software
2593 checksum that fio supports.
2596 Use sha512 as the checksum function.
2599 Use sha256 as the checksum function.
2602 Use optimized sha1 as the checksum function.
2605 Use optimized sha3-224 as the checksum function.
2608 Use optimized sha3-256 as the checksum function.
2611 Use optimized sha3-384 as the checksum function.
2614 Use optimized sha3-512 as the checksum function.
2617 This option is deprecated, since now meta information is included in
2618 generic verification header and meta verification happens by
2619 default. For detailed information see the description of the
2620 :option:`verify` setting. This option is kept because of
2621 compatibility's sake with old configurations. Do not use it.
2624 Verify a strict pattern. Normally fio includes a header with some
2625 basic information and checksumming, but if this option is set, only
2626 the specific pattern set with :option:`verify_pattern` is verified.
2629 Only pretend to verify. Useful for testing internals with
2630 :option:`ioengine`\=null, not for much else.
2632 This option can be used for repeated burn-in tests of a system to make sure
2633 that the written data is also correctly read back. If the data direction
2634 given is a read or random read, fio will assume that it should verify a
2635 previously written file. If the data direction includes any form of write,
2636 the verify will be of the newly written data.
2638 .. option:: verifysort=bool
2640 If true, fio will sort written verify blocks when it deems it faster to read
2641 them back in a sorted manner. This is often the case when overwriting an
2642 existing file, since the blocks are already laid out in the file system. You
2643 can ignore this option unless doing huge amounts of really fast I/O where
2644 the red-black tree sorting CPU time becomes significant. Default: true.
2646 .. option:: verifysort_nr=int
2648 Pre-load and sort verify blocks for a read workload.
2650 .. option:: verify_offset=int
2652 Swap the verification header with data somewhere else in the block before
2653 writing. It is swapped back before verifying.
2655 .. option:: verify_interval=int
2657 Write the verification header at a finer granularity than the
2658 :option:`blocksize`. It will be written for chunks the size of
2659 ``verify_interval``. :option:`blocksize` should divide this evenly.
2661 .. option:: verify_pattern=str
2663 If set, fio will fill the I/O buffers with this pattern. Fio defaults to
2664 filling with totally random bytes, but sometimes it's interesting to fill
2665 with a known pattern for I/O verification purposes. Depending on the width
2666 of the pattern, fio will fill 1/2/3/4 bytes of the buffer at the time (it can
2667 be either a decimal or a hex number). The ``verify_pattern`` if larger than
2668 a 32-bit quantity has to be a hex number that starts with either "0x" or
2669 "0X". Use with :option:`verify`. Also, ``verify_pattern`` supports %o
2670 format, which means that for each block offset will be written and then
2671 verified back, e.g.::
2675 Or use combination of everything::
2677 verify_pattern=0xff%o"abcd"-12
2679 .. option:: verify_fatal=bool
2681 Normally fio will keep checking the entire contents before quitting on a
2682 block verification failure. If this option is set, fio will exit the job on
2683 the first observed failure. Default: false.
2685 .. option:: verify_dump=bool
2687 If set, dump the contents of both the original data block and the data block
2688 we read off disk to files. This allows later analysis to inspect just what
2689 kind of data corruption occurred. Off by default.
2691 .. option:: verify_async=int
2693 Fio will normally verify I/O inline from the submitting thread. This option
2694 takes an integer describing how many async offload threads to create for I/O
2695 verification instead, causing fio to offload the duty of verifying I/O
2696 contents to one or more separate threads. If using this offload option, even
2697 sync I/O engines can benefit from using an :option:`iodepth` setting higher
2698 than 1, as it allows them to have I/O in flight while verifies are running.
2699 Defaults to 0 async threads, i.e. verification is not asynchronous.
2701 .. option:: verify_async_cpus=str
2703 Tell fio to set the given CPU affinity on the async I/O verification
2704 threads. See :option:`cpus_allowed` for the format used.
2706 .. option:: verify_backlog=int
2708 Fio will normally verify the written contents of a job that utilizes verify
2709 once that job has completed. In other words, everything is written then
2710 everything is read back and verified. You may want to verify continually
2711 instead for a variety of reasons. Fio stores the meta data associated with
2712 an I/O block in memory, so for large verify workloads, quite a bit of memory
2713 would be used up holding this meta data. If this option is enabled, fio will
2714 write only N blocks before verifying these blocks.
2716 .. option:: verify_backlog_batch=int
2718 Control how many blocks fio will verify if :option:`verify_backlog` is
2719 set. If not set, will default to the value of :option:`verify_backlog`
2720 (meaning the entire queue is read back and verified). If
2721 ``verify_backlog_batch`` is less than :option:`verify_backlog` then not all
2722 blocks will be verified, if ``verify_backlog_batch`` is larger than
2723 :option:`verify_backlog`, some blocks will be verified more than once.
2725 .. option:: verify_state_save=bool
2727 When a job exits during the write phase of a verify workload, save its
2728 current state. This allows fio to replay up until that point, if the verify
2729 state is loaded for the verify read phase. The format of the filename is,
2732 <type>-<jobname>-<jobindex>-verify.state.
2734 <type> is "local" for a local run, "sock" for a client/server socket
2735 connection, and "ip" (192.168.0.1, for instance) for a networked
2736 client/server connection. Defaults to true.
2738 .. option:: verify_state_load=bool
2740 If a verify termination trigger was used, fio stores the current write state
2741 of each thread. This can be used at verification time so that fio knows how
2742 far it should verify. Without this information, fio will run a full
2743 verification pass, according to the settings in the job file used. Default
2746 .. option:: trim_percentage=int
2748 Number of verify blocks to discard/trim.
2750 .. option:: trim_verify_zero=bool
2752 Verify that trim/discarded blocks are returned as zeros.
2754 .. option:: trim_backlog=int
2756 Trim after this number of blocks are written.
2758 .. option:: trim_backlog_batch=int
2760 Trim this number of I/O blocks.
2762 .. option:: experimental_verify=bool
2764 Enable experimental verification.
2769 .. option:: steadystate=str:float, ss=str:float
2771 Define the criterion and limit for assessing steady state performance. The
2772 first parameter designates the criterion whereas the second parameter sets
2773 the threshold. When the criterion falls below the threshold for the
2774 specified duration, the job will stop. For example, `iops_slope:0.1%` will
2775 direct fio to terminate the job when the least squares regression slope
2776 falls below 0.1% of the mean IOPS. If :option:`group_reporting` is enabled
2777 this will apply to all jobs in the group. Below is the list of available
2778 steady state assessment criteria. All assessments are carried out using only
2779 data from the rolling collection window. Threshold limits can be expressed
2780 as a fixed value or as a percentage of the mean in the collection window.
2783 Collect IOPS data. Stop the job if all individual IOPS measurements
2784 are within the specified limit of the mean IOPS (e.g., ``iops:2``
2785 means that all individual IOPS values must be within 2 of the mean,
2786 whereas ``iops:0.2%`` means that all individual IOPS values must be
2787 within 0.2% of the mean IOPS to terminate the job).
2790 Collect IOPS data and calculate the least squares regression
2791 slope. Stop the job if the slope falls below the specified limit.
2794 Collect bandwidth data. Stop the job if all individual bandwidth
2795 measurements are within the specified limit of the mean bandwidth.
2798 Collect bandwidth data and calculate the least squares regression
2799 slope. Stop the job if the slope falls below the specified limit.
2801 .. option:: steadystate_duration=time, ss_dur=time
2803 A rolling window of this duration will be used to judge whether steady state
2804 has been reached. Data will be collected once per second. The default is 0
2805 which disables steady state detection. When the unit is omitted, the
2806 value is interpreted in seconds.
2808 .. option:: steadystate_ramp_time=time, ss_ramp=time
2810 Allow the job to run for the specified duration before beginning data
2811 collection for checking the steady state job termination criterion. The
2812 default is 0. When the unit is omitted, the value is interpreted in seconds.
2815 Measurements and reporting
2816 ~~~~~~~~~~~~~~~~~~~~~~~~~~
2818 .. option:: per_job_logs=bool
2820 If set, this generates bw/clat/iops log with per file private filenames. If
2821 not set, jobs with identical names will share the log filename. Default:
2824 .. option:: group_reporting
2826 It may sometimes be interesting to display statistics for groups of jobs as
2827 a whole instead of for each individual job. This is especially true if
2828 :option:`numjobs` is used; looking at individual thread/process output
2829 quickly becomes unwieldy. To see the final report per-group instead of
2830 per-job, use :option:`group_reporting`. Jobs in a file will be part of the
2831 same reporting group, unless if separated by a :option:`stonewall`, or by
2832 using :option:`new_group`.
2834 .. option:: new_group
2836 Start a new reporting group. See: :option:`group_reporting`. If not given,
2837 all jobs in a file will be part of the same reporting group, unless
2838 separated by a :option:`stonewall`.
2840 .. option:: stats=bool
2842 By default, fio collects and shows final output results for all jobs
2843 that run. If this option is set to 0, then fio will ignore it in
2844 the final stat output.
2846 .. option:: write_bw_log=str
2848 If given, write a bandwidth log for this job. Can be used to store data of
2849 the bandwidth of the jobs in their lifetime.
2851 If no str argument is given, the default filename of
2852 :file:`jobname_type.x.log` is used. Even when the argument is given, fio
2853 will still append the type of log. So if one specifies::
2857 The actual log name will be :file:`foo_bw.x.log` where `x` is the index
2858 of the job (`1..N`, where `N` is the number of jobs). If
2859 :option:`per_job_logs` is false, then the filename will not include the
2862 The included :command:`fio_generate_plots` script uses :command:`gnuplot` to turn these
2863 text files into nice graphs. See `Log File Formats`_ for how data is
2864 structured within the file.
2866 .. option:: write_lat_log=str
2868 Same as :option:`write_bw_log`, except this option creates I/O
2869 submission (e.g., :file:`name_slat.x.log`), completion (e.g.,
2870 :file:`name_clat.x.log`), and total (e.g., :file:`name_lat.x.log`)
2871 latency files instead. See :option:`write_bw_log` for details about
2872 the filename format and `Log File Formats`_ for how data is structured
2875 .. option:: write_hist_log=str
2877 Same as :option:`write_bw_log` but writes an I/O completion latency
2878 histogram file (e.g., :file:`name_hist.x.log`) instead. Note that this
2879 file will be empty unless :option:`log_hist_msec` has also been set.
2880 See :option:`write_bw_log` for details about the filename format and
2881 `Log File Formats`_ for how data is structured within the file.
2883 .. option:: write_iops_log=str
2885 Same as :option:`write_bw_log`, but writes an IOPS file (e.g.
2886 :file:`name_iops.x.log`) instead. See :option:`write_bw_log` for
2887 details about the filename format and `Log File Formats`_ for how data
2888 is structured within the file.
2890 .. option:: log_avg_msec=int
2892 By default, fio will log an entry in the iops, latency, or bw log for every
2893 I/O that completes. When writing to the disk log, that can quickly grow to a
2894 very large size. Setting this option makes fio average the each log entry
2895 over the specified period of time, reducing the resolution of the log. See
2896 :option:`log_max_value` as well. Defaults to 0, logging all entries.
2897 Also see `Log File Formats`_.
2899 .. option:: log_hist_msec=int
2901 Same as :option:`log_avg_msec`, but logs entries for completion latency
2902 histograms. Computing latency percentiles from averages of intervals using
2903 :option:`log_avg_msec` is inaccurate. Setting this option makes fio log
2904 histogram entries over the specified period of time, reducing log sizes for
2905 high IOPS devices while retaining percentile accuracy. See
2906 :option:`log_hist_coarseness` and :option:`write_hist_log` as well.
2907 Defaults to 0, meaning histogram logging is disabled.
2909 .. option:: log_hist_coarseness=int
2911 Integer ranging from 0 to 6, defining the coarseness of the resolution of
2912 the histogram logs enabled with :option:`log_hist_msec`. For each increment
2913 in coarseness, fio outputs half as many bins. Defaults to 0, for which
2914 histogram logs contain 1216 latency bins. See :option:`write_hist_log`
2915 and `Log File Formats`_.
2917 .. option:: log_max_value=bool
2919 If :option:`log_avg_msec` is set, fio logs the average over that window. If
2920 you instead want to log the maximum value, set this option to 1. Defaults to
2921 0, meaning that averaged values are logged.
2923 .. option:: log_offset=bool
2925 If this is set, the iolog options will include the byte offset for the I/O
2926 entry as well as the other data values. Defaults to 0 meaning that
2927 offsets are not present in logs. Also see `Log File Formats`_.
2929 .. option:: log_compression=int
2931 If this is set, fio will compress the I/O logs as it goes, to keep the
2932 memory footprint lower. When a log reaches the specified size, that chunk is
2933 removed and compressed in the background. Given that I/O logs are fairly
2934 highly compressible, this yields a nice memory savings for longer runs. The
2935 downside is that the compression will consume some background CPU cycles, so
2936 it may impact the run. This, however, is also true if the logging ends up
2937 consuming most of the system memory. So pick your poison. The I/O logs are
2938 saved normally at the end of a run, by decompressing the chunks and storing
2939 them in the specified log file. This feature depends on the availability of
2942 .. option:: log_compression_cpus=str
2944 Define the set of CPUs that are allowed to handle online log compression for
2945 the I/O jobs. This can provide better isolation between performance
2946 sensitive jobs, and background compression work. See
2947 :option:`cpus_allowed` for the format used.
2949 .. option:: log_store_compressed=bool
2951 If set, fio will store the log files in a compressed format. They can be
2952 decompressed with fio, using the :option:`--inflate-log` command line
2953 parameter. The files will be stored with a :file:`.fz` suffix.
2955 .. option:: log_unix_epoch=bool
2957 If set, fio will log Unix timestamps to the log files produced by enabling
2958 write_type_log for each log type, instead of the default zero-based
2961 .. option:: block_error_percentiles=bool
2963 If set, record errors in trim block-sized units from writes and trims and
2964 output a histogram of how many trims it took to get to errors, and what kind
2965 of error was encountered.
2967 .. option:: bwavgtime=int
2969 Average the calculated bandwidth over the given time. Value is specified in
2970 milliseconds. If the job also does bandwidth logging through
2971 :option:`write_bw_log`, then the minimum of this option and
2972 :option:`log_avg_msec` will be used. Default: 500ms.
2974 .. option:: iopsavgtime=int
2976 Average the calculated IOPS over the given time. Value is specified in
2977 milliseconds. If the job also does IOPS logging through
2978 :option:`write_iops_log`, then the minimum of this option and
2979 :option:`log_avg_msec` will be used. Default: 500ms.
2981 .. option:: disk_util=bool
2983 Generate disk utilization statistics, if the platform supports it.
2986 .. option:: disable_lat=bool
2988 Disable measurements of total latency numbers. Useful only for cutting back
2989 the number of calls to :manpage:`gettimeofday(2)`, as that does impact
2990 performance at really high IOPS rates. Note that to really get rid of a
2991 large amount of these calls, this option must be used with
2992 :option:`disable_slat` and :option:`disable_bw_measurement` as well.
2994 .. option:: disable_clat=bool
2996 Disable measurements of completion latency numbers. See
2997 :option:`disable_lat`.
2999 .. option:: disable_slat=bool
3001 Disable measurements of submission latency numbers. See
3002 :option:`disable_lat`.
3004 .. option:: disable_bw_measurement=bool, disable_bw=bool
3006 Disable measurements of throughput/bandwidth numbers. See
3007 :option:`disable_lat`.
3009 .. option:: clat_percentiles=bool
3011 Enable the reporting of percentiles of completion latencies. This
3012 option is mutually exclusive with :option:`lat_percentiles`.
3014 .. option:: lat_percentiles=bool
3016 Enable the reporting of percentiles of I/O latencies. This is similar
3017 to :option:`clat_percentiles`, except that this includes the
3018 submission latency. This option is mutually exclusive with
3019 :option:`clat_percentiles`.
3021 .. option:: percentile_list=float_list
3023 Overwrite the default list of percentiles for completion latencies and
3024 the block error histogram. Each number is a floating number in the
3025 range (0,100], and the maximum length of the list is 20. Use ``:`` to
3026 separate the numbers, and list the numbers in ascending order. For
3027 example, ``--percentile_list=99.5:99.9`` will cause fio to report the
3028 values of completion latency below which 99.5% and 99.9% of the observed
3029 latencies fell, respectively.
3031 .. option:: significant_figures=int
3033 If using :option:`--output-format` of `normal`, set the significant
3034 figures to this value. Higher values will yield more precise IOPS and
3035 throughput units, while lower values will round. Requires a minimum
3036 value of 1 and a maximum value of 10. Defaults to 4.
3042 .. option:: exitall_on_error
3044 When one job finishes in error, terminate the rest. The default is to wait
3045 for each job to finish.
3047 .. option:: continue_on_error=str
3049 Normally fio will exit the job on the first observed failure. If this option
3050 is set, fio will continue the job when there is a 'non-fatal error' (EIO or
3051 EILSEQ) until the runtime is exceeded or the I/O size specified is
3052 completed. If this option is used, there are two more stats that are
3053 appended, the total error count and the first error. The error field given
3054 in the stats is the first error that was hit during the run.
3056 The allowed values are:
3059 Exit on any I/O or verify errors.
3062 Continue on read errors, exit on all others.
3065 Continue on write errors, exit on all others.
3068 Continue on any I/O error, exit on all others.
3071 Continue on verify errors, exit on all others.
3074 Continue on all errors.
3077 Backward-compatible alias for 'none'.
3080 Backward-compatible alias for 'all'.
3082 .. option:: ignore_error=str
3084 Sometimes you want to ignore some errors during test in that case you can
3085 specify error list for each error type, instead of only being able to
3086 ignore the default 'non-fatal error' using :option:`continue_on_error`.
3087 ``ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST`` errors for
3088 given error type is separated with ':'. Error may be symbol ('ENOSPC',
3089 'ENOMEM') or integer. Example::
3091 ignore_error=EAGAIN,ENOSPC:122
3093 This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from
3094 WRITE. This option works by overriding :option:`continue_on_error` with
3095 the list of errors for each error type if any.
3097 .. option:: error_dump=bool
3099 If set dump every error even if it is non fatal, true by default. If
3100 disabled only fatal error will be dumped.
3102 Running predefined workloads
3103 ----------------------------
3105 Fio includes predefined profiles that mimic the I/O workloads generated by
3108 .. option:: profile=str
3110 The predefined workload to run. Current profiles are:
3113 Threaded I/O bench (tiotest/tiobench) like workload.
3116 Aerospike Certification Tool (ACT) like workload.
3118 To view a profile's additional options use :option:`--cmdhelp` after specifying
3119 the profile. For example::
3121 $ fio --profile=act --cmdhelp
3126 .. option:: device-names=str
3131 .. option:: load=int
3134 ACT load multiplier. Default: 1.
3136 .. option:: test-duration=time
3139 How long the entire test takes to run. When the unit is omitted, the value
3140 is given in seconds. Default: 24h.
3142 .. option:: threads-per-queue=int
3145 Number of read I/O threads per device. Default: 8.
3147 .. option:: read-req-num-512-blocks=int
3150 Number of 512B blocks to read at the time. Default: 3.
3152 .. option:: large-block-op-kbytes=int
3155 Size of large block ops in KiB (writes). Default: 131072.
3160 Set to run ACT prep phase.
3162 Tiobench profile options
3163 ~~~~~~~~~~~~~~~~~~~~~~~~
3165 .. option:: size=str
3170 .. option:: block=int
3173 Block size in bytes. Default: 4096.
3175 .. option:: numruns=int
3185 .. option:: threads=int
3190 Interpreting the output
3191 -----------------------
3194 Example output was based on the following:
3195 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --time_based \
3196 --rate=1256k --bs=14K --name=quick --runtime=1s --name=mixed \
3197 --runtime=2m --rw=rw
3199 Fio spits out a lot of output. While running, fio will display the status of the
3200 jobs created. An example of that would be::
3202 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]
3204 The characters inside the first set of square brackets denote the current status of
3205 each thread. The first character is the first job defined in the job file, and so
3206 forth. The possible values (in typical life cycle order) are:
3208 +------+-----+-----------------------------------------------------------+
3210 +======+=====+===========================================================+
3211 | P | | Thread setup, but not started. |
3212 +------+-----+-----------------------------------------------------------+
3213 | C | | Thread created. |
3214 +------+-----+-----------------------------------------------------------+
3215 | I | | Thread initialized, waiting or generating necessary data. |
3216 +------+-----+-----------------------------------------------------------+
3217 | | p | Thread running pre-reading file(s). |
3218 +------+-----+-----------------------------------------------------------+
3219 | | / | Thread is in ramp period. |
3220 +------+-----+-----------------------------------------------------------+
3221 | | R | Running, doing sequential reads. |
3222 +------+-----+-----------------------------------------------------------+
3223 | | r | Running, doing random reads. |
3224 +------+-----+-----------------------------------------------------------+
3225 | | W | Running, doing sequential writes. |
3226 +------+-----+-----------------------------------------------------------+
3227 | | w | Running, doing random writes. |
3228 +------+-----+-----------------------------------------------------------+
3229 | | M | Running, doing mixed sequential reads/writes. |
3230 +------+-----+-----------------------------------------------------------+
3231 | | m | Running, doing mixed random reads/writes. |
3232 +------+-----+-----------------------------------------------------------+
3233 | | D | Running, doing sequential trims. |
3234 +------+-----+-----------------------------------------------------------+
3235 | | d | Running, doing random trims. |
3236 +------+-----+-----------------------------------------------------------+
3237 | | F | Running, currently waiting for :manpage:`fsync(2)`. |
3238 +------+-----+-----------------------------------------------------------+
3239 | | V | Running, doing verification of written data. |
3240 +------+-----+-----------------------------------------------------------+
3241 | f | | Thread finishing. |
3242 +------+-----+-----------------------------------------------------------+
3243 | E | | Thread exited, not reaped by main thread yet. |
3244 +------+-----+-----------------------------------------------------------+
3245 | _ | | Thread reaped. |
3246 +------+-----+-----------------------------------------------------------+
3247 | X | | Thread reaped, exited with an error. |
3248 +------+-----+-----------------------------------------------------------+
3249 | K | | Thread reaped, exited due to signal. |
3250 +------+-----+-----------------------------------------------------------+
3253 Example output was based on the following:
3254 TZ=UTC fio --iodepth=8 --ioengine=null --size=100M --runtime=58m \
3255 --time_based --rate=2512k --bs=256K --numjobs=10 \
3256 --name=readers --rw=read --name=writers --rw=write
3258 Fio will condense the thread string as not to take up more space on the command
3259 line than needed. For instance, if you have 10 readers and 10 writers running,
3260 the output would look like this::
3262 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]
3264 Note that the status string is displayed in order, so it's possible to tell which of
3265 the jobs are currently doing what. In the example above this means that jobs 1--10
3266 are readers and 11--20 are writers.
3268 The other values are fairly self explanatory -- number of threads currently
3269 running and doing I/O, the number of currently open files (f=), the estimated
3270 completion percentage, the rate of I/O since last check (read speed listed first,
3271 then write speed and optionally trim speed) in terms of bandwidth and IOPS,
3272 and time to completion for the current running group. It's impossible to estimate
3273 runtime of the following groups (if any).
3276 Example output was based on the following:
3277 TZ=UTC fio --iodepth=16 --ioengine=posixaio --filename=/tmp/fiofile \
3278 --direct=1 --size=100M --time_based --runtime=50s --rate_iops=89 \
3279 --bs=7K --name=Client1 --rw=write
3281 When fio is done (or interrupted by :kbd:`Ctrl-C`), it will show the data for
3282 each thread, group of threads, and disks in that order. For each overall thread (or
3283 group) the output looks like::
3285 Client1: (groupid=0, jobs=1): err= 0: pid=16109: Sat Jun 24 12:07:54 2017
3286 write: IOPS=88, BW=623KiB/s (638kB/s)(30.4MiB/50032msec)
3287 slat (nsec): min=500, max=145500, avg=8318.00, stdev=4781.50
3288 clat (usec): min=170, max=78367, avg=4019.02, stdev=8293.31
3289 lat (usec): min=174, max=78375, avg=4027.34, stdev=8291.79
3290 clat percentiles (usec):
3291 | 1.00th=[ 302], 5.00th=[ 326], 10.00th=[ 343], 20.00th=[ 363],
3292 | 30.00th=[ 392], 40.00th=[ 404], 50.00th=[ 416], 60.00th=[ 445],
3293 | 70.00th=[ 816], 80.00th=[ 6718], 90.00th=[12911], 95.00th=[21627],
3294 | 99.00th=[43779], 99.50th=[51643], 99.90th=[68682], 99.95th=[72877],
3296 bw ( KiB/s): min= 532, max= 686, per=0.10%, avg=622.87, stdev=24.82, samples= 100
3297 iops : min= 76, max= 98, avg=88.98, stdev= 3.54, samples= 100
3298 lat (usec) : 250=0.04%, 500=64.11%, 750=4.81%, 1000=2.79%
3299 lat (msec) : 2=4.16%, 4=1.84%, 10=4.90%, 20=11.33%, 50=5.37%
3300 lat (msec) : 100=0.65%
3301 cpu : usr=0.27%, sys=0.18%, ctx=12072, majf=0, minf=21
3302 IO depths : 1=85.0%, 2=13.1%, 4=1.8%, 8=0.1%, 16=0.0%, 32=0.0%, >=64=0.0%
3303 submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
3304 complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
3305 issued rwt: total=0,4450,0, short=0,0,0, dropped=0,0,0
3306 latency : target=0, window=0, percentile=100.00%, depth=8
3308 The job name (or first job's name when using :option:`group_reporting`) is printed,
3309 along with the group id, count of jobs being aggregated, last error id seen (which
3310 is 0 when there are no errors), pid/tid of that thread and the time the job/group
3311 completed. Below are the I/O statistics for each data direction performed (showing
3312 writes in the example above). In the order listed, they denote:
3315 The string before the colon shows the I/O direction the statistics
3316 are for. **IOPS** is the average I/Os performed per second. **BW**
3317 is the average bandwidth rate shown as: value in power of 2 format
3318 (value in power of 10 format). The last two values show: (**total
3319 I/O performed** in power of 2 format / **runtime** of that thread).
3322 Submission latency (**min** being the minimum, **max** being the
3323 maximum, **avg** being the average, **stdev** being the standard
3324 deviation). This is the time it took to submit the I/O. For
3325 sync I/O this row is not displayed as the slat is really the
3326 completion latency (since queue/complete is one operation there).
3327 This value can be in nanoseconds, microseconds or milliseconds ---
3328 fio will choose the most appropriate base and print that (in the
3329 example above nanoseconds was the best scale). Note: in :option:`--minimal` mode
3330 latencies are always expressed in microseconds.
3333 Completion latency. Same names as slat, this denotes the time from
3334 submission to completion of the I/O pieces. For sync I/O, clat will
3335 usually be equal (or very close) to 0, as the time from submit to
3336 complete is basically just CPU time (I/O has already been done, see slat
3340 Total latency. Same names as slat and clat, this denotes the time from
3341 when fio created the I/O unit to completion of the I/O operation.
3344 Bandwidth statistics based on samples. Same names as the xlat stats,
3345 but also includes the number of samples taken (**samples**) and an
3346 approximate percentage of total aggregate bandwidth this thread
3347 received in its group (**per**). This last value is only really
3348 useful if the threads in this group are on the same disk, since they
3349 are then competing for disk access.
3352 IOPS statistics based on samples. Same names as bw.
3354 **lat (nsec/usec/msec)**
3355 The distribution of I/O completion latencies. This is the time from when
3356 I/O leaves fio and when it gets completed. Unlike the separate
3357 read/write/trim sections above, the data here and in the remaining
3358 sections apply to all I/Os for the reporting group. 250=0.04% means that
3359 0.04% of the I/Os completed in under 250us. 500=64.11% means that 64.11%
3360 of the I/Os required 250 to 499us for completion.
3363 CPU usage. User and system time, along with the number of context
3364 switches this thread went through, usage of system and user time, and
3365 finally the number of major and minor page faults. The CPU utilization
3366 numbers are averages for the jobs in that reporting group, while the
3367 context and fault counters are summed.
3370 The distribution of I/O depths over the job lifetime. The numbers are
3371 divided into powers of 2 and each entry covers depths from that value
3372 up to those that are lower than the next entry -- e.g., 16= covers
3373 depths from 16 to 31. Note that the range covered by a depth
3374 distribution entry can be different to the range covered by the
3375 equivalent submit/complete distribution entry.
3378 How many pieces of I/O were submitting in a single submit call. Each
3379 entry denotes that amount and below, until the previous entry -- e.g.,
3380 16=100% means that we submitted anywhere between 9 to 16 I/Os per submit
3381 call. Note that the range covered by a submit distribution entry can
3382 be different to the range covered by the equivalent depth distribution
3386 Like the above submit number, but for completions instead.
3389 The number of read/write/trim requests issued, and how many of them were
3393 These values are for :option:`latency_target` and related options. When
3394 these options are engaged, this section describes the I/O depth required
3395 to meet the specified latency target.
3398 Example output was based on the following:
3399 TZ=UTC fio --ioengine=null --iodepth=2 --size=100M --numjobs=2 \
3400 --rate_process=poisson --io_limit=32M --name=read --bs=128k \
3401 --rate=11M --name=write --rw=write --bs=2k --rate=700k
3403 After each client has been listed, the group statistics are printed. They
3404 will look like this::
3406 Run status group 0 (all jobs):
3407 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
3408 WRITE: bw=1231KiB/s (1261kB/s), 616KiB/s-621KiB/s (630kB/s-636kB/s), io=64.0MiB (67.1MB), run=52747-53223msec
3410 For each data direction it prints:
3413 Aggregate bandwidth of threads in this group followed by the
3414 minimum and maximum bandwidth of all the threads in this group.
3415 Values outside of brackets are power-of-2 format and those
3416 within are the equivalent value in a power-of-10 format.
3418 Aggregate I/O performed of all threads in this group. The
3419 format is the same as bw.
3421 The smallest and longest runtimes of the threads in this group.
3423 And finally, the disk statistics are printed. This is Linux specific. They will look like this::
3425 Disk stats (read/write):
3426 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
3428 Each value is printed for both reads and writes, with reads first. The
3432 Number of I/Os performed by all groups.
3434 Number of merges performed by the I/O scheduler.
3436 Number of ticks we kept the disk busy.
3438 Total time spent in the disk queue.
3440 The disk utilization. A value of 100% means we kept the disk
3441 busy constantly, 50% would be a disk idling half of the time.
3443 It is also possible to get fio to dump the current output while it is running,
3444 without terminating the job. To do that, send fio the **USR1** signal. You can
3445 also get regularly timed dumps by using the :option:`--status-interval`
3446 parameter, or by creating a file in :file:`/tmp` named
3447 :file:`fio-dump-status`. If fio sees this file, it will unlink it and dump the
3448 current output status.
3454 For scripted usage where you typically want to generate tables or graphs of the
3455 results, fio can output the results in a semicolon separated format. The format
3456 is one long line of values, such as::
3458 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%
3459 A description of this job goes here.
3461 The job description (if provided) follows on a second line.
3463 To enable terse output, use the :option:`--minimal` or
3464 :option:`--output-format`\=terse command line options. The
3465 first value is the version of the terse output format. If the output has to be
3466 changed for some reason, this number will be incremented by 1 to signify that
3469 Split up, the format is as follows (comments in brackets denote when a
3470 field was introduced or whether it's specific to some terse version):
3474 terse version, fio version [v3], jobname, groupid, error
3478 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
3479 Submission latency: min, max, mean, stdev (usec)
3480 Completion latency: min, max, mean, stdev (usec)
3481 Completion latency percentiles: 20 fields (see below)
3482 Total latency: min, max, mean, stdev (usec)
3483 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
3484 IOPS [v5]: min, max, mean, stdev, number of samples
3490 Total IO (KiB), bandwidth (KiB/sec), IOPS, runtime (msec)
3491 Submission latency: min, max, mean, stdev (usec)
3492 Completion latency: min, max, mean, stdev (usec)
3493 Completion latency percentiles: 20 fields (see below)
3494 Total latency: min, max, mean, stdev (usec)
3495 Bw (KiB/s): min, max, aggregate percentage of total, mean, stdev, number of samples [v5]
3496 IOPS [v5]: min, max, mean, stdev, number of samples
3498 TRIM status [all but version 3]:
3500 Fields are similar to READ/WRITE status.
3504 user, system, context switches, major faults, minor faults
3508 <=1, 2, 4, 8, 16, 32, >=64
3510 I/O latencies microseconds::
3512 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000
3514 I/O latencies milliseconds::
3516 <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000
3518 Disk utilization [v3]::
3520 disk name, read ios, write ios, read merges, write merges, read ticks, write ticks,
3521 time spent in queue, disk utilization percentage
3523 Additional Info (dependent on continue_on_error, default off)::
3525 total # errors, first error code
3527 Additional Info (dependent on description being set)::
3531 Completion latency percentiles can be a grouping of up to 20 sets, so for the
3532 terse output fio writes all of them. Each field will look like this::
3536 which is the Xth percentile, and the `usec` latency associated with it.
3538 For `Disk utilization`, all disks used by fio are shown. So for each disk there
3539 will be a disk utilization section.
3541 Below is a single line containing short names for each of the fields in the
3542 minimal output v3, separated by semicolons::
3544 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
3550 The `json` output format is intended to be both human readable and convenient
3551 for automated parsing. For the most part its sections mirror those of the
3552 `normal` output. The `runtime` value is reported in msec and the `bw` value is
3553 reported in 1024 bytes per second units.
3559 The `json+` output format is identical to the `json` output format except that it
3560 adds a full dump of the completion latency bins. Each `bins` object contains a
3561 set of (key, value) pairs where keys are latency durations and values count how
3562 many I/Os had completion latencies of the corresponding duration. For example,
3565 "bins" : { "87552" : 1, "89600" : 1, "94720" : 1, "96768" : 1, "97792" : 1, "99840" : 1, "100864" : 2, "103936" : 6, "104960" : 534, "105984" : 5995, "107008" : 7529, ... }
3567 This data indicates that one I/O required 87,552ns to complete, two I/Os required
3568 100,864ns to complete, and 7529 I/Os required 107,008ns to complete.
3570 Also included with fio is a Python script `fio_jsonplus_clat2csv` that takes
3571 json+ output and generates CSV-formatted latency data suitable for plotting.
3573 The latency durations actually represent the midpoints of latency intervals.
3574 For details refer to :file:`stat.h`.
3580 There are two trace file format that you can encounter. The older (v1) format is
3581 unsupported since version 1.20-rc3 (March 2008). It will still be described
3582 below in case that you get an old trace and want to understand it.
3584 In any case the trace is a simple text file with a single action per line.
3587 Trace file format v1
3588 ~~~~~~~~~~~~~~~~~~~~
3590 Each line represents a single I/O action in the following format::
3594 where `rw=0/1` for read/write, and the `offset` and `length` entries being in bytes.
3596 This format is not supported in fio versions >= 1.20-rc3.
3599 Trace file format v2
3600 ~~~~~~~~~~~~~~~~~~~~
3602 The second version of the trace file format was added in fio version 1.17. It
3603 allows to access more then one file per trace and has a bigger set of possible
3606 The first line of the trace file has to be::
3610 Following this can be lines in two different formats, which are described below.
3612 The file management format::
3616 The `filename` is given as an absolute path. The `action` can be one of these:
3619 Add the given `filename` to the trace.
3621 Open the file with the given `filename`. The `filename` has to have
3622 been added with the **add** action before.
3624 Close the file with the given `filename`. The file has to have been
3628 The file I/O action format::
3630 filename action offset length
3632 The `filename` is given as an absolute path, and has to have been added and
3633 opened before it can be used with this format. The `offset` and `length` are
3634 given in bytes. The `action` can be one of these:
3637 Wait for `offset` microseconds. Everything below 100 is discarded.
3638 The time is relative to the previous `wait` statement.
3640 Read `length` bytes beginning from `offset`.
3642 Write `length` bytes beginning from `offset`.
3644 :manpage:`fsync(2)` the file.
3646 :manpage:`fdatasync(2)` the file.
3648 Trim the given file from the given `offset` for `length` bytes.
3650 CPU idleness profiling
3651 ----------------------
3653 In some cases, we want to understand CPU overhead in a test. For example, we
3654 test patches for the specific goodness of whether they reduce CPU usage.
3655 Fio implements a balloon approach to create a thread per CPU that runs at idle
3656 priority, meaning that it only runs when nobody else needs the cpu.
3657 By measuring the amount of work completed by the thread, idleness of each CPU
3658 can be derived accordingly.
3660 An unit work is defined as touching a full page of unsigned characters. Mean and
3661 standard deviation of time to complete an unit work is reported in "unit work"
3662 section. Options can be chosen to report detailed percpu idleness or overall
3663 system idleness by aggregating percpu stats.
3666 Verification and triggers
3667 -------------------------
3669 Fio is usually run in one of two ways, when data verification is done. The first
3670 is a normal write job of some sort with verify enabled. When the write phase has
3671 completed, fio switches to reads and verifies everything it wrote. The second
3672 model is running just the write phase, and then later on running the same job
3673 (but with reads instead of writes) to repeat the same I/O patterns and verify
3674 the contents. Both of these methods depend on the write phase being completed,
3675 as fio otherwise has no idea how much data was written.
3677 With verification triggers, fio supports dumping the current write state to
3678 local files. Then a subsequent read verify workload can load this state and know
3679 exactly where to stop. This is useful for testing cases where power is cut to a
3680 server in a managed fashion, for instance.
3682 A verification trigger consists of two things:
3684 1) Storing the write state of each job.
3685 2) Executing a trigger command.
3687 The write state is relatively small, on the order of hundreds of bytes to single
3688 kilobytes. It contains information on the number of completions done, the last X
3691 A trigger is invoked either through creation ('touch') of a specified file in
3692 the system, or through a timeout setting. If fio is run with
3693 :option:`--trigger-file`\= :file:`/tmp/trigger-file`, then it will continually
3694 check for the existence of :file:`/tmp/trigger-file`. When it sees this file, it
3695 will fire off the trigger (thus saving state, and executing the trigger
3698 For client/server runs, there's both a local and remote trigger. If fio is
3699 running as a server backend, it will send the job states back to the client for
3700 safe storage, then execute the remote trigger, if specified. If a local trigger
3701 is specified, the server will still send back the write state, but the client
3702 will then execute the trigger.
3704 Verification trigger example
3705 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
3707 Let's say we want to run a powercut test on the remote Linux machine 'server'.
3708 Our write workload is in :file:`write-test.fio`. We want to cut power to 'server' at
3709 some point during the run, and we'll run this test from the safety or our local
3710 machine, 'localbox'. On the server, we'll start the fio backend normally::
3712 server# fio --server
3714 and on the client, we'll fire off the workload::
3716 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger-remote="bash -c \"echo b > /proc/sysrq-triger\""
3718 We set :file:`/tmp/my-trigger` as the trigger file, and we tell fio to execute::
3720 echo b > /proc/sysrq-trigger
3722 on the server once it has received the trigger and sent us the write state. This
3723 will work, but it's not **really** cutting power to the server, it's merely
3724 abruptly rebooting it. If we have a remote way of cutting power to the server
3725 through IPMI or similar, we could do that through a local trigger command
3726 instead. Let's assume we have a script that does IPMI reboot of a given hostname,
3727 ipmi-reboot. On localbox, we could then have run fio with a local trigger
3730 localbox$ fio --client=server --trigger-file=/tmp/my-trigger --trigger="ipmi-reboot server"
3732 For this case, fio would wait for the server to send us the write state, then
3733 execute ``ipmi-reboot server`` when that happened.
3735 Loading verify state
3736 ~~~~~~~~~~~~~~~~~~~~
3738 To load stored write state, a read verification job file must contain the
3739 :option:`verify_state_load` option. If that is set, fio will load the previously
3740 stored state. For a local fio run this is done by loading the files directly,
3741 and on a client/server run, the server backend will ask the client to send the
3742 files over and load them from there.
3748 Fio supports a variety of log file formats, for logging latencies, bandwidth,
3749 and IOPS. The logs share a common format, which looks like this:
3751 *time* (`msec`), *value*, *data direction*, *block size* (`bytes`),
3754 *Time* for the log entry is always in milliseconds. The *value* logged depends
3755 on the type of log, it will be one of the following:
3758 Value is latency in nsecs
3764 *Data direction* is one of the following:
3773 The entry's *block size* is always in bytes. The *offset* is the offset, in bytes,
3774 from the start of the file, for that particular I/O. The logging of the offset can be
3775 toggled with :option:`log_offset`.
3777 Fio defaults to logging every individual I/O. When IOPS are logged for individual
3778 I/Os the *value* entry will always be 1. If windowed logging is enabled through
3779 :option:`log_avg_msec`, fio logs the average values over the specified period of time.
3780 If windowed logging is enabled and :option:`log_max_value` is set, then fio logs
3781 maximum values in that window instead of averages. Since *data direction*, *block
3782 size* and *offset* are per-I/O values, if windowed logging is enabled they
3783 aren't applicable and will be 0.
3788 Normally fio is invoked as a stand-alone application on the machine where the
3789 I/O workload should be generated. However, the backend and frontend of fio can
3790 be run separately i.e., the fio server can generate an I/O workload on the "Device
3791 Under Test" while being controlled by a client on another machine.
3793 Start the server on the machine which has access to the storage DUT::
3797 where `args` defines what fio listens to. The arguments are of the form
3798 ``type,hostname`` or ``IP,port``. *type* is either ``ip`` (or ip4) for TCP/IP
3799 v4, ``ip6`` for TCP/IP v6, or ``sock`` for a local unix domain socket.
3800 *hostname* is either a hostname or IP address, and *port* is the port to listen
3801 to (only valid for TCP/IP, not a local socket). Some examples:
3805 Start a fio server, listening on all interfaces on the default port (8765).
3807 2) ``fio --server=ip:hostname,4444``
3809 Start a fio server, listening on IP belonging to hostname and on port 4444.
3811 3) ``fio --server=ip6:::1,4444``
3813 Start a fio server, listening on IPv6 localhost ::1 and on port 4444.
3815 4) ``fio --server=,4444``
3817 Start a fio server, listening on all interfaces on port 4444.
3819 5) ``fio --server=1.2.3.4``
3821 Start a fio server, listening on IP 1.2.3.4 on the default port.
3823 6) ``fio --server=sock:/tmp/fio.sock``
3825 Start a fio server, listening on the local socket :file:`/tmp/fio.sock`.
3827 Once a server is running, a "client" can connect to the fio server with::
3829 fio <local-args> --client=<server> <remote-args> <job file(s)>
3831 where `local-args` are arguments for the client where it is running, `server`
3832 is the connect string, and `remote-args` and `job file(s)` are sent to the
3833 server. The `server` string follows the same format as it does on the server
3834 side, to allow IP/hostname/socket and port strings.
3836 Fio can connect to multiple servers this way::
3838 fio --client=<server1> <job file(s)> --client=<server2> <job file(s)>
3840 If the job file is located on the fio server, then you can tell the server to
3841 load a local file as well. This is done by using :option:`--remote-config` ::
3843 fio --client=server --remote-config /path/to/file.fio
3845 Then fio will open this local (to the server) job file instead of being passed
3846 one from the client.
3848 If you have many servers (example: 100 VMs/containers), you can input a pathname
3849 of a file containing host IPs/names as the parameter value for the
3850 :option:`--client` option. For example, here is an example :file:`host.list`
3851 file containing 2 hostnames::
3853 host1.your.dns.domain
3854 host2.your.dns.domain
3856 The fio command would then be::
3858 fio --client=host.list <job file(s)>
3860 In this mode, you cannot input server-specific parameters or job files -- all
3861 servers receive the same job file.
3863 In order to let ``fio --client`` runs use a shared filesystem from multiple
3864 hosts, ``fio --client`` now prepends the IP address of the server to the
3865 filename. For example, if fio is using the directory :file:`/mnt/nfs/fio` and is
3866 writing filename :file:`fileio.tmp`, with a :option:`--client` `hostfile`
3867 containing two hostnames ``h1`` and ``h2`` with IP addresses 192.168.10.120 and
3868 192.168.10.121, then fio will create two files::
3870 /mnt/nfs/fio/192.168.10.120.fileio.tmp
3871 /mnt/nfs/fio/192.168.10.121.fileio.tmp