4 fio is a tool that will spawn a number of threads or processes doing a
5 particular type of io action as specified by the user. fio takes a
6 number of global parameters, each inherited by the thread unless
7 otherwise parameters given to them overriding that setting is given.
8 The typical use of fio is to write a job file matching the io load
15 fio resides in a git repo, the canonical place is:
17 git://git.kernel.dk/fio.git
19 The http protocol also works, path is the same.
21 Snapshots are frequently generated and they include the git meta data as
22 well. You can download them here:
24 http://brick.kernel.dk/snaps/
31 Starting with Debian "Squeeze", fio packages are part of the official
32 Debian repository. http://packages.debian.org/search?keywords=fio
35 Starting with Ubuntu 10.04 LTS (aka "Lucid Lynx"), fio packages are part
36 of the Ubuntu "universe" repository.
37 http://packages.ubuntu.com/search?keywords=fio
40 Pascal Bleser <guru@unixtech.be> has fio RPMs in his repository for SUSE
41 variants, you can find them here:
42 http://linux01.gwdg.de/~pbleser/rpm-navigation.php?cat=System/fio
45 Dag Wieƫrs has RPMs for Red Hat related distros, find them here:
46 http://dag.wieers.com/rpm/packages/fio/
49 Mandriva has integrated fio into their package repository, so installing
50 on that distro should be as easy as typing 'urpmi fio'.
53 Packages for Solaris are available from OpenCSW. Install their pkgutil
54 tool (http://www.opencsw.org/get-it/pkgutil/) and then install fio via
58 Bruce Cran <bruce@cran.org.uk> has fio packages for Windows at
59 http://www.bluestop.org/fio .
65 There's a mailing list associated with fio. It's meant for general
66 discussion, bug reporting, questions, and development - basically anything
67 that has to do with fio. An automated mail detailing recent commits is
68 automatically sent to the list at most daily. The list address is
69 fio@vger.kernel.org, subscribe by sending an email to
70 majordomo@vger.kernel.org with
74 in the body of the email. Archives can be found here:
76 http://www.spinics.net/lists/fio/
78 and archives for the old list can be found here:
80 http://maillist.kernel.dk/fio-devel/
86 Just type 'make' and 'make install'.
88 Note that GNU make is required. On BSD it's available from devel/gmake;
89 on Solaris it's in the SUNWgmake package. On platforms where GNU make
90 isn't the default, type 'gmake' instead of 'make'.
92 If your compile fails with an error like this:
95 In file included from fio.h:23,
97 os/os.h:15:20: error: libaio.h: No such file or directory
98 In file included from gettime.c:8:
99 fio.h:119: error: field 'iocb' has incomplete type
100 make: *** [gettime.o] Error 1
102 Check that you have the libaio development package installed. On RPM
103 based distros, it's typically called libaio-devel.
109 On Windows Cygwin (http://www.cygwin.com) is required with at least
110 devel/gcc4 and devel/make installed in order to build fio, and
111 admin/cygrunsrv to run it. You can also install devel/git to fetch/update
112 the source files. To create an MSI installer package put a copy of Cygwin
113 in os\windows\fio, install WiX 3.6 from http://wix.sourceforge.net/releases/
114 and run dobuild.cmd from the os/windows directory.
116 Before running fio you'll need to have a copy of cygserver running. Run
117 "/usr/bin/cygserver-config" from an elevated Cygwin shell (i.e. launch the
118 Cygwin shell under the Administrator account) to configure it. Once
119 configured, run "net start cygserver" to start it, or type
120 "/usr/sbin/cygserver &" in the Cygwin shell to start a local copy.
122 If fio exits with the message "Bad system call" it normally means that
123 Cygserver isn't running.
130 --debug Enable some debugging options (see below)
131 --output Write output to file
132 --timeout Runtime in seconds
133 --latency-log Generate per-job latency logs
134 --bandwidth-log Generate per-job bandwidth logs
135 --minimal Minimal (terse) output
136 --version Print version info and exit
137 --help Print this page
138 --cmdhelp=cmd Print command help, "all" for all of them
139 --showcmd Turn a job file into command line options
140 --readonly Turn on safety read-only checks, preventing
142 --eta=when When ETA estimate should be printed
143 May be "always", "never" or "auto"
144 --section=name Only run specified section in job file. Multiple
145 sections can be specified.
146 --alloc-size=kb Set smalloc pool to this size in kb (def 1024)
147 --warnings-fatal Fio parser warnings are fatal
148 --max-jobs Maximum number of threads/processes to support
151 Any parameters following the options will be assumed to be job files,
152 unless they match a job file parameter. You can add as many as you want,
153 each job file will be regarded as a separate group and fio will stonewall
156 The --readonly switch is an extra safety guard to prevent accidentally
157 turning on a write setting when that is not desired. Fio will only write
158 if rw=write/randwrite/rw/randrw is given, but this extra safety net can
159 be used as an extra precaution. It will also enable a write check in the
160 io engine core to prevent an accidental write due to a fio bug.
162 The debug switch allows adding options that trigger certain logging
163 options in fio. Currently the options are:
165 process Dump info related to processes
166 file Dump info related to file actions
167 io Dump info related to IO queuing
168 mem Dump info related to memory allocations
169 blktrace Dump info related to blktrace setup
170 verify Dump info related to IO verification
171 all Enable all debug options
172 random Dump info related to random offset generation
173 parse Dump info related to option matching and parsing
174 diskutil Dump info related to disk utilization updates
175 job:x Dump info only related to job number x
176 mutex Dump info only related to mutex up/down ops
177 profile Dump info related to profile extensions
178 time Dump info related to internal time keeping
179 ? or help Show available debug options.
181 You can specify as many as you want, eg --debug=file,mem will enable
182 file and memory debugging.
184 The section switch is meant to make it easier to ship a bigger job file
185 instead of several smaller ones. Say you define a job file with light,
186 moderate, and heavy parts. Then you can ask fio to run the given part
187 only by giving it a --section=heavy command line option. The section
188 option only applies to job sections, the reserved 'global' section is
189 always parsed and taken into account.
191 Fio has an internal allocator for shared memory called smalloc. It
192 allocates shared structures from this pool. The pool defaults to 1024k
193 in size, and can grow to 128 pools. If running large jobs with randommap
194 enabled it can run out of memory, in which case the --alloc-size switch
195 is handy for starting with a larger pool size. The backing store is
196 files in /tmp. Fio cleans up after itself, while it is running you
197 may see .fio_smalloc.* files in /tmp.
203 See the HOWTO file for a more detailed description of parameters and what
204 they mean. This file contains the terse version. You can describe big and
205 complex setups with the command line, but generally it's a lot easier to
206 just write a simple job file to describe the workload. The job file format
207 is in the ini style format, as that is easy to read and write for the user.
209 The job file parameters are:
211 name=x Use 'x' as the identifier for this job.
212 description=x 'x' is a text description of the job.
213 directory=x Use 'x' as the top level directory for storing files
214 filename=x Force the use of 'x' as the filename for all files
215 in this thread. If not given, fio will make up
216 a suitable filename based on the thread and file
218 rw=x 'x' may be: read, randread, write, randwrite,
219 rw (read-write mix), randrw (read-write random mix)
220 rwmixcycle=x Base cycle for switching between read and write
222 rwmixread=x 'x' percentage of rw mix ios will be reads. If
223 rwmixwrite is also given, the last of the two will
224 be used if they don't add up to 100%.
225 rwmixwrite=x 'x' percentage of rw mix ios will be writes. See
227 rand_repeatable=x The sequence of random io blocks can be repeatable
228 across runs, if 'x' is 1.
229 size=x Set file size to x bytes (x string can include k/m/g)
230 ioengine=x 'x' may be: aio/libaio/linuxaio for Linux aio,
231 posixaio for POSIX aio, solarisaio for Solaris
232 native async IO, windowsaio for Windows native async IO,
233 sync for regular read/write io,
234 psync for regular pread/pwrite io, vsync for regular
235 readv/writev (with queuing emulation) mmap for mmap'ed
236 io, syslet-rw for syslet driven read/write, splice for
237 using splice/vmsplice, sg for direct SG_IO io, net
238 for network io, or cpuio for a cycler burner load. sg
239 only works on Linux on SCSI (or SCSI-like devices, such
240 as usb-storage or sata/libata driven) devices. Fio also
241 has a null io engine, which is mainly used for testing
244 iodepth=x For async io, allow 'x' ios in flight
245 overwrite=x If 'x', layout a write file first.
246 nrfiles=x Spread io load over 'x' number of files per job,
248 prio=x Run io at prio X, 0-7 is the kernel allowed range
249 prioclass=x Run io at prio class X
250 bs=x Use 'x' for thread blocksize. May include k/m postfix.
251 bsrange=x-y Mix thread block sizes randomly between x and y. May
252 also include k/m postfix.
253 direct=x 1 for direct IO, 0 for buffered IO
254 thinktime=x "Think" x usec after each io
255 rate=x Throttle rate to x KB/sec
256 ratemin=x Quit if rate of x KB/sec can't be met
257 ratecycle=x ratemin averaged over x msecs
258 cpumask=x Only allow job to run on CPUs defined by mask.
259 cpus_allowed=x Like 'cpumask', but allow text setting of CPU affinity.
260 fsync=x If writing with buffered IO, fsync after every
261 'x' blocks have been written.
262 end_fsync=x If 'x', run fsync() after end-of-job.
263 startdelay=x Start this thread x seconds after startup
264 runtime=x Terminate x seconds after startup. Can include a
265 normal time suffix if not given in seconds, such as
266 'm' for minutes, 'h' for hours, and 'd' for days.
267 offset=x Start io at offset x (x string can include k/m/g)
268 invalidate=x Invalidate page cache for file prior to doing io
269 sync=x Use sync writes if x and writing buffered IO.
270 mem=x If x == malloc, use malloc for buffers. If x == shm,
271 use shared memory for buffers. If x == mmap, use
273 exitall When one thread quits, terminate the others
274 bwavgtime=x Average bandwidth stats over an x msec window.
275 create_serialize=x If 'x', serialize file creation.
276 create_fsync=x If 'x', run fsync() after file creation.
277 unlink If set, unlink files when done.
278 loops=x Run the job 'x' number of times.
279 verify=x If 'x' == md5, use md5 for verifies. If 'x' == crc32,
280 use crc32 for verifies. md5 is 'safer', but crc32 is
281 a lot faster. Only makes sense for writing to a file.
282 For other types of checksumming, see HOWTO.
283 stonewall Wait for preceeding jobs to end before running.
284 numjobs=x Create 'x' similar entries for this job
285 thread Use pthreads instead of forked jobs
287 zoneskip=y Zone options must be paired. If given, the job
288 will skip y bytes for every x read/written. This
289 can be used to gauge hard drive speed over the entire
290 platter, without reading everything. Both x/y can
291 include k/m/g suffix.
292 iolog=x Open and read io pattern from file 'x'. The file must
293 contain one io action per line in the following format:
295 where with rw=0/1 for read/write, and the offset
296 and length entries being in bytes.
297 write_iolog=x Write an iolog to file 'x' in the same format as iolog.
298 The iolog options are exclusive, if both given the
299 read iolog will be performed. Specify a separate file
300 for each job, otherwise the iologs will be interspersed
301 and the file may be corrupt.
302 write_bw_log Write a bandwidth log.
303 write_lat_log Write a latency log.
304 lockmem=x Lock down x amount of memory on the machine, to
305 simulate a machine with less memory available. x can
306 include k/m/g suffix.
307 nice=x Run job at given nice value.
308 exec_prerun=x Run 'x' before job io is begun.
309 exec_postrun=x Run 'x' after job io has finished.
310 ioscheduler=x Use ioscheduler 'x' for this job.
311 cpuload=x For a CPU io thread, percentage of CPU time to attempt
313 cpuchunks=x Split burn cycles into pieces of x usecs.
320 Fio works on (at least) Linux, Solaris, AIX, HP-UX, OSX, NetBSD, Windows
321 and FreeBSD. Some features and/or options may only be available on some of
322 the platforms, typically because those features only apply to that platform
323 (like the solarisaio engine, or the splice engine on Linux).
325 Some features are not available on FreeBSD/Solaris even if they could be
326 implemented, I'd be happy to take patches for that. An example of that is
327 disk utility statistics and (I think) huge page support, support for that
328 does exist in FreeBSD/Solaris.
330 Fio uses pthread mutexes for signalling and locking and FreeBSD does not
331 support process shared pthread mutexes. As a result, only threads are
332 supported on FreeBSD. This could be fixed with sysv ipc locking or
333 other locking alternatives.
335 Other *BSD platforms are untested, but fio should work there almost out
336 of the box. Since I don't do test runs or even compiles on those platforms,
337 your mileage may vary. Sending me patches for other platforms is greatly
338 appreciated. There's a lot of value in having the same test/benchmark tool
339 available on all platforms.
341 Note that POSIX aio is not enabled by default on AIX. If you get messages like:
343 Symbol resolution failed for /usr/lib/libc.a(posix_aio.o) because:
344 Symbol _posix_kaio_rdwr (number 2) is not exported from dependent module /unix.
346 you need to enable POSIX aio. Run the following commands as root:
348 # lsdev -C -l posix_aio0
349 posix_aio0 Defined Posix Asynchronous I/O
350 # cfgmgr -l posix_aio0
351 # lsdev -C -l posix_aio0
352 posix_aio0 Available Posix Asynchronous I/O
354 POSIX aio should work now. To make the change permanent:
356 # chdev -l posix_aio0 -P -a autoconfig='available'
363 Fio was written by Jens Axboe <axboe@kernel.dk> to enable flexible testing
364 of the Linux IO subsystem and schedulers. He got tired of writing
365 specific test applications to simulate a given workload, and found that
366 the existing io benchmark/test tools out there weren't flexible enough
367 to do what he wanted.
369 Jens Axboe <axboe@kernel.dk> 20060905