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