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://brick.kernel.dk/data/git/fio.git
19 Snapshots are frequently generated and they include the git meta data as
20 well. You can download them here:
22 http://brick.kernel.dk/snaps/
24 Pascal Bleser <guru@unixtech.be> has fio RPMs in his repository, you
27 http://linux01.gwdg.de/~pbleser/rpm-navigation.php?cat=System/fio
33 There's a mailing list associated with fio. It's meant for general
34 discussion, bug reporting, questions - basically anything that has to
35 do with fio. An automated mail detailing recent commits is automatically
36 sent to the list at most daily. The list address is fio-devel@kernel.dk,
37 subscribe by sending an empty email to fio-devel+subscribe@kernel.dk.
43 Just type 'make' and 'make install'. If on FreeBSD, for now you have to
44 specify the FreeBSD Makefile with -f, eg:
46 $ make -f Makefile.Freebsd && make -f Makefile.FreeBSD install
48 Likewise with OpenSolaris, use the Makefile.solaris to compile there.
49 This might change in the future if I opt for an autoconf type setup.
56 --output Write output to file
57 --runtime Runtime in seconds
58 --latency-log Generate per-job latency logs
59 --bandwidth-log Generate per-job bandwidth logs
60 --minimal Minimal (terse) output
61 --version Print version info and exit
62 --help Print this page
63 --cmdhelp=cmd Print command help, "all" for all of them
65 Any parameters following the options will be assumed to be job files,
66 unless they match a job file parameter. You can add as many as you want,
67 each job file will be regarded as a separate group and fio will stonewall
74 See the HOWTO file for a more detailed description of parameters and what
75 they mean. This file contains the terse version. Only a few options can
76 be controlled with command line parameters, generally it's a lot easier to
77 just write a simple job file to describe the workload. The job file format
78 is in the ini style format, as it's easy to read and write for the user.
80 The job file parameters are:
82 name=x Use 'x' as the identifier for this job.
83 directory=x Use 'x' as the top level directory for storing files
84 filename=x Force the use of 'x' as the filename for all files
85 in this thread. If not given, fio will make up
86 a suitable filename based on the thread and file
88 rw=x 'x' may be: read, randread, write, randwrite,
89 rw (read-write mix), randrw (read-write random mix)
90 rwmixcycle=x Base cycle for switching between read and write
92 rwmixread=x 'x' percentage of rw mix ios will be reads. If
93 rwmixwrite is also given, the last of the two will
94 be used if they don't add up to 100%.
95 rwmixwrite=x 'x' percentage of rw mix ios will be writes. See
97 rand_repeatable=x The sequence of random io blocks can be repeatable
98 across runs, if 'x' is 1.
99 size=x Set file size to x bytes (x string can include k/m/g)
100 ioengine=x 'x' may be: aio/libaio/linuxaio for Linux aio,
101 posixaio for POSIX aio, sync for regular read/write io,
102 mmap for mmap'ed io, splice for using splice/vmsplice,
103 or sgio for direct SG_IO io. The latter only works on
104 Linux on SCSI (or SCSI-like devices, such as
105 usb-storage or sata/libata driven) devices. Fio also
106 has a null io engine, which is mainly used for testing
108 iodepth=x For async io, allow 'x' ios in flight
109 overwrite=x If 'x', layout a write file first.
110 nrfiles=x Spread io load over 'x' number of files per job,
112 prio=x Run io at prio X, 0-7 is the kernel allowed range
113 prioclass=x Run io at prio class X
114 bs=x Use 'x' for thread blocksize. May include k/m postfix.
115 bsrange=x-y Mix thread block sizes randomly between x and y. May
116 also include k/m postfix.
117 direct=x 1 for direct IO, 0 for buffered IO
118 thinktime=x "Think" x usec after each io
119 rate=x Throttle rate to x KiB/sec
120 ratemin=x Quit if rate of x KiB/sec can't be met
121 ratecycle=x ratemin averaged over x msecs
122 cpumask=x Only allow job to run on CPUs defined by mask.
123 fsync=x If writing with buffered IO, fsync after every
124 'x' blocks have been written.
125 end_fsync=x If 'x', run fsync() after end-of-job.
126 startdelay=x Start this thread x seconds after startup
127 runtime=x Terminate x seconds after startup. Can include a
128 normal time suffix if not given in seconds, such as
129 'm' for minutes, 'h' for hours, and 'd' for days.
130 offset=x Start io at offset x (x string can include k/m/g)
131 invalidate=x Invalidate page cache for file prior to doing io
132 sync=x Use sync writes if x and writing buffered IO.
133 mem=x If x == malloc, use malloc for buffers. If x == shm,
134 use shared memory for buffers. If x == mmap, use
136 exitall When one thread quits, terminate the others
137 bwavgtime=x Average bandwidth stats over an x msec window.
138 create_serialize=x If 'x', serialize file creation.
139 create_fsync=x If 'x', run fsync() after file creation.
140 unlink If set, unlink files when done.
141 loops=x Run the job 'x' number of times.
142 verify=x If 'x' == md5, use md5 for verifies. If 'x' == crc32,
143 use crc32 for verifies. md5 is 'safer', but crc32 is
144 a lot faster. Only makes sense for writing to a file.
145 stonewall Wait for preceeding jobs to end before running.
146 numjobs=x Create 'x' similar entries for this job
147 thread Use pthreads instead of forked jobs
149 zoneskip=y Zone options must be paired. If given, the job
150 will skip y bytes for every x read/written. This
151 can be used to gauge hard drive speed over the entire
152 platter, without reading everything. Both x/y can
153 include k/m/g suffix.
154 iolog=x Open and read io pattern from file 'x'. The file must
155 contain one io action per line in the following format:
157 where with rw=0/1 for read/write, and the offset
158 and length entries being in bytes.
159 write_iolog=x Write an iolog to file 'x' in the same format as iolog.
160 The iolog options are exclusive, if both given the
161 read iolog will be performed.
162 write_bw_log Write a bandwidth log.
163 write_lat_log Write a latency log.
164 lockmem=x Lock down x amount of memory on the machine, to
165 simulate a machine with less memory available. x can
166 include k/m/g suffix.
167 nice=x Run job at given nice value.
168 exec_prerun=x Run 'x' before job io is begun.
169 exec_postrun=x Run 'x' after job io has finished.
170 ioscheduler=x Use ioscheduler 'x' for this job.
171 cpuload=x For a CPU io thread, percentage of CPU time to attempt
173 cpuchunks=x Split burn cycles into pieces of x.
179 Fio was written by Jens Axboe <axboe@kernel.dk> to enable flexible testing
180 of the Linux IO subsystem and schedulers. He got tired of writing
181 specific test applications to simulate a given workload, and found that
182 the existing io benchmark/test tools out there weren't flexible enough
183 to do what he wanted.
185 Jens Axboe <axboe@kernel.dk> 20060905