blob: cdfe80aa9fc4f1908ecf504a9ba5dae1b7a11071 [file] [log] [blame]
Jens Axboe71bfa162006-10-25 11:08:19 +02001Table of contents
2-----------------
3
41. Overview
52. How fio works
63. Running fio
74. Job file format
85. Detailed list of parameters
96. Normal output
107. Terse output
11
12
131.0 Overview and history
14------------------------
15fio was originally written to save me the hassle of writing special test
16case programs when I wanted to test a specific workload, either for
17performance reasons or to find/reproduce a bug. The process of writing
18such a test app can be tiresome, especially if you have to do it often.
19Hence I needed a tool that would be able to simulate a given io workload
20without resorting to writing a tailored test case again and again.
21
22A test work load is difficult to define, though. There can be any number
23of processes or threads involved, and they can each be using their own
24way of generating io. You could have someone dirtying large amounts of
25memory in an memory mapped file, or maybe several threads issuing
26reads using asynchronous io. fio needed to be flexible enough to
27simulate both of these cases, and many more.
28
292.0 How fio works
30-----------------
31The first step in getting fio to simulate a desired io workload, is
32writing a job file describing that specific setup. A job file may contain
33any number of threads and/or files - the typical contents of the job file
34is a global section defining shared parameters, and one or more job
35sections describing the jobs involved. When run, fio parses this file
36and sets everything up as described. If we break down a job from top to
37bottom, it contains the following basic parameters:
38
39 IO type Defines the io pattern issued to the file(s).
40 We may only be reading sequentially from this
41 file(s), or we may be writing randomly. Or even
42 mixing reads and writes, sequentially or randomly.
43
44 Block size In how large chunks are we issuing io? This may be
45 a single value, or it may describe a range of
46 block sizes.
47
48 IO size How much data are we going to be reading/writing.
49
50 IO engine How do we issue io? We could be memory mapping the
51 file, we could be using regular read/write, we
Jens Axboed0ff85d2007-02-14 01:19:41 +010052 could be using splice, async io, syslet, or even
Jens Axboe71bfa162006-10-25 11:08:19 +020053 SG (SCSI generic sg).
54
Jens Axboe6c219762006-11-03 15:51:45 +010055 IO depth If the io engine is async, how large a queuing
Jens Axboe71bfa162006-10-25 11:08:19 +020056 depth do we want to maintain?
57
58 IO type Should we be doing buffered io, or direct/raw io?
59
60 Num files How many files are we spreading the workload over.
61
62 Num threads How many threads or processes should we spread
63 this workload over.
64
65The above are the basic parameters defined for a workload, in addition
66there's a multitude of parameters that modify other aspects of how this
67job behaves.
68
69
703.0 Running fio
71---------------
72See the README file for command line parameters, there are only a few
73of them.
74
75Running fio is normally the easiest part - you just give it the job file
76(or job files) as parameters:
77
78$ fio job_file
79
80and it will start doing what the job_file tells it to do. You can give
81more than one job file on the command line, fio will serialize the running
82of those files. Internally that is the same as using the 'stonewall'
83parameter described the the parameter section.
84
Jens Axboeb4692822006-10-27 13:43:22 +020085If the job file contains only one job, you may as well just give the
86parameters on the command line. The command line parameters are identical
87to the job parameters, with a few extra that control global parameters
88(see README). For example, for the job file parameter iodepth=2, the
Jens Axboec2b1e752006-10-30 09:03:13 +010089mirror command line option would be --iodepth 2 or --iodepth=2. You can
90also use the command line for giving more than one job entry. For each
91--name option that fio sees, it will start a new job with that name.
92Command line entries following a --name entry will apply to that job,
93until there are no more entries or a new --name entry is seen. This is
94similar to the job file options, where each option applies to the current
95job until a new [] job entry is seen.
Jens Axboeb4692822006-10-27 13:43:22 +020096
Jens Axboe71bfa162006-10-25 11:08:19 +020097fio does not need to run as root, except if the files or devices specified
98in the job section requires that. Some other options may also be restricted,
Jens Axboe6c219762006-11-03 15:51:45 +010099such as memory locking, io scheduler switching, and decreasing the nice value.
Jens Axboe71bfa162006-10-25 11:08:19 +0200100
101
1024.0 Job file format
103-------------------
104As previously described, fio accepts one or more job files describing
105what it is supposed to do. The job file format is the classic ini file,
106where the names enclosed in [] brackets define the job name. You are free
107to use any ascii name you want, except 'global' which has special meaning.
108A global section sets defaults for the jobs described in that file. A job
109may override a global section parameter, and a job file may even have
110several global sections if so desired. A job is only affected by a global
Jens Axboe65db0852007-02-20 10:22:01 +0100111section residing above it. If the first character in a line is a ';' or a
112'#', the entire line is discarded as a comment.
Jens Axboe71bfa162006-10-25 11:08:19 +0200113
114So lets look at a really simple job file that define to threads, each
115randomly reading from a 128MiB file.
116
117; -- start job file --
118[global]
119rw=randread
120size=128m
121
122[job1]
123
124[job2]
125
126; -- end job file --
127
128As you can see, the job file sections themselves are empty as all the
129described parameters are shared. As no filename= option is given, fio
Jens Axboec2b1e752006-10-30 09:03:13 +0100130makes up a filename for each of the jobs as it sees fit. On the command
131line, this job would look as follows:
132
133$ fio --name=global --rw=randread --size=128m --name=job1 --name=job2
134
Jens Axboe71bfa162006-10-25 11:08:19 +0200135
136Lets look at an example that have a number of processes writing randomly
137to files.
138
139; -- start job file --
140[random-writers]
141ioengine=libaio
142iodepth=4
143rw=randwrite
144bs=32k
145direct=0
146size=64m
147numjobs=4
148
149; -- end job file --
150
151Here we have no global section, as we only have one job defined anyway.
152We want to use async io here, with a depth of 4 for each file. We also
153increased the buffer size used to 32KiB and define numjobs to 4 to
154fork 4 identical jobs. The result is 4 processes each randomly writing
Jens Axboeb4692822006-10-27 13:43:22 +0200155to their own 64MiB file. Instead of using the above job file, you could
156have given the parameters on the command line. For this case, you would
157specify:
158
159$ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4
Jens Axboe71bfa162006-10-25 11:08:19 +0200160
161fio ships with a few example job files, you can also look there for
162inspiration.
163
164
1655.0 Detailed list of parameters
166-------------------------------
167
168This section describes in details each parameter associated with a job.
169Some parameters take an option of a given type, such as an integer or
170a string. The following types are used:
171
172str String. This is a sequence of alpha characters.
Jens Axboe6d16ecb2007-07-30 09:08:01 +0200173int Integer. A whole number value, can be negative. If prefixed with
174 0x, the integer is assumed to be of base 16 (hexidecimal).
Jens Axboe71bfa162006-10-25 11:08:19 +0200175siint SI integer. A whole number value, which may contain a postfix
176 describing the base of the number. Accepted postfixes are k/m/g,
Jens Axboe6c219762006-11-03 15:51:45 +0100177 meaning kilo, mega, and giga. So if you want to specify 4096,
Jens Axboe71bfa162006-10-25 11:08:19 +0200178 you could either write out '4096' or just give 4k. The postfixes
179 signify base 2 values, so 1024 is 1k and 1024k is 1m and so on.
Jens Axboe43159d12007-03-15 09:15:51 +0100180 If the option accepts an upper and lower range, use a colon ':'
181 or minus '-' to seperate such values. See irange.
Jens Axboe71bfa162006-10-25 11:08:19 +0200182bool Boolean. Usually parsed as an integer, however only defined for
183 true and false (1 and 0).
184irange Integer range with postfix. Allows value range to be given, such
Jens Axboe0c9baf92007-01-11 15:59:26 +0100185 as 1024-4096. A colon may also be used as the seperator, eg
186 1k:4k. If the option allows two sets of ranges, they can be
187 specified with a ',' or '/' delimiter: 1k-4k/8k-32k. Also see
188 siint.
Jens Axboe71bfa162006-10-25 11:08:19 +0200189
190With the above in mind, here follows the complete list of fio job
191parameters.
192
193name=str ASCII name of the job. This may be used to override the
194 name printed by fio for this job. Otherwise the job
Jens Axboec2b1e752006-10-30 09:03:13 +0100195 name is used. On the command line this parameter has the
Jens Axboe6c219762006-11-03 15:51:45 +0100196 special purpose of also signaling the start of a new
Jens Axboec2b1e752006-10-30 09:03:13 +0100197 job.
Jens Axboe71bfa162006-10-25 11:08:19 +0200198
Jens Axboe61697c32007-02-05 15:04:46 +0100199description=str Text description of the job. Doesn't do anything except
200 dump this text description when this job is run. It's
201 not parsed.
202
Jens Axboe71bfa162006-10-25 11:08:19 +0200203directory=str Prefix filenames with this directory. Used to places files
204 in a different location than "./".
205
206filename=str Fio normally makes up a filename based on the job name,
207 thread number, and file number. If you want to share
208 files between threads in a job or several jobs, specify
Jens Axboeed92ac02007-02-06 14:43:52 +0100209 a filename for each of them to override the default. If
210 the ioengine used is 'net', the filename is the host and
Jens Axboe9f9214f2007-03-13 14:02:16 +0100211 port to connect to in the format of =host/port. If the
Jens Axboeaf52b342007-03-13 10:07:47 +0100212 ioengine is file based, you can specify a number of files
213 by seperating the names with a ':' colon. So if you wanted
214 a job to open /dev/sda and /dev/sdb as the two working files,
Jens Axboe66159822007-04-16 21:54:24 +0200215 you would use filename=/dev/sda:/dev/sdb. '-' is a reserved
216 name, meaning stdin or stdout. Which of the two depends
217 on the read/write direction set.
Jens Axboe71bfa162006-10-25 11:08:19 +0200218
Jens Axboebbf6b542007-03-13 15:28:55 +0100219opendir=str Tell fio to recursively add any file it can find in this
220 directory and down the file system tree.
221
Jens Axboed3aad8f2007-03-15 14:12:05 +0100222readwrite=str
Jens Axboe71bfa162006-10-25 11:08:19 +0200223rw=str Type of io pattern. Accepted values are:
224
225 read Sequential reads
226 write Sequential writes
227 randwrite Random writes
228 randread Random reads
229 rw Sequential mixed reads and writes
230 randrw Random mixed reads and writes
231
232 For the mixed io types, the default is to split them 50/50.
233 For certain types of io the result may still be skewed a bit,
Jens Axboe211097b2007-03-22 18:56:45 +0100234 since the speed may be different. It is possible to specify
235 a number of IO's to do before getting a new offset - this
236 is only useful for random IO, where fio would normally
237 generate a new random offset for every IO. If you append
238 eg 8 to randread, you would get a new random offset for
239 every 8 IO's. The result would be a seek for only every 8
240 IO's, instead of for every IO. Use rw=randread:8 to specify
241 that.
Jens Axboe71bfa162006-10-25 11:08:19 +0200242
Jens Axboeee738492007-01-10 11:23:16 +0100243randrepeat=bool For random IO workloads, seed the generator in a predictable
244 way so that results are repeatable across repetitions.
245
Jens Axboed2f3ac32007-03-22 19:24:09 +0100246fadvise_hint=bool By default, fio will use fadvise() to advise the kernel
247 on what IO patterns it is likely to issue. Sometimes you
248 want to test specific IO patterns without telling the
249 kernel about it, in which case you can disable this option.
250 If set, fio will use POSIX_FADV_SEQUENTIAL for sequential
251 IO and POSIX_FADV_RANDOM for random IO.
252
Jens Axboe7616caf2007-05-25 09:26:05 +0200253size=siint The total size of file io for this job. Fio will run until
254 this many bytes has been transferred, unless runtime is
255 limited by other options (such as 'runtime', for instance).
256 Unless specific nr_files and filesize options are given,
257 fio will divide this size between the available files
258 specified by the job.
Jens Axboe71bfa162006-10-25 11:08:19 +0200259
Jens Axboe9c60ce62007-03-15 09:14:47 +0100260filesize=siint Individual file sizes. May be a range, in which case fio
261 will select sizes for files at random within the given range
262 and limited to 'size' in total (if that is given). If not
263 given, each created file is the same size.
264
Jens Axboed3aad8f2007-03-15 14:12:05 +0100265blocksize=siint
Jens Axboef90eff52006-11-06 11:08:21 +0100266bs=siint The block size used for the io units. Defaults to 4k. Values
267 can be given for both read and writes. If a single siint is
268 given, it will apply to both. If a second siint is specified
269 after a comma, it will apply to writes only. In other words,
270 the format is either bs=read_and_write or bs=read,write.
271 bs=4k,8k will thus use 4k blocks for reads, and 8k blocks
Jens Axboe787f7e92006-11-06 13:26:29 +0100272 for writes. If you only wish to set the write size, you
273 can do so by passing an empty read size - bs=,8k will set
274 8k for writes and leave the read default value.
Jens Axboea00735e2006-11-03 08:58:08 +0100275
Jens Axboed3aad8f2007-03-15 14:12:05 +0100276blocksize_range=irange
Jens Axboe71bfa162006-10-25 11:08:19 +0200277bsrange=irange Instead of giving a single block size, specify a range
278 and fio will mix the issued io block sizes. The issued
279 io unit will always be a multiple of the minimum value
Jens Axboef90eff52006-11-06 11:08:21 +0100280 given (also see bs_unaligned). Applies to both reads and
281 writes, however a second range can be given after a comma.
282 See bs=.
Jens Axboea00735e2006-11-03 08:58:08 +0100283
Jens Axboed3aad8f2007-03-15 14:12:05 +0100284blocksize_unaligned
Jens Axboe690adba2006-10-30 15:25:09 +0100285bs_unaligned If this option is given, any byte size value within bsrange
286 may be used as a block range. This typically wont work with
287 direct IO, as that normally requires sector alignment.
Jens Axboe71bfa162006-10-25 11:08:19 +0200288
Jens Axboee9459e52007-04-17 15:46:32 +0200289zero_buffers If this option is given, fio will init the IO buffers to
290 all zeroes. The default is to fill them with random data.
291
Jens Axboe71bfa162006-10-25 11:08:19 +0200292nrfiles=int Number of files to use for this job. Defaults to 1.
293
Jens Axboe390b1532007-03-09 13:03:00 +0100294openfiles=int Number of files to keep open at the same time. Defaults to
295 the same as nrfiles, can be set smaller to limit the number
296 simultaneous opens.
297
Jens Axboe5af1c6f2007-03-01 10:06:10 +0100298file_service_type=str Defines how fio decides which file from a job to
299 service next. The following types are defined:
300
301 random Just choose a file at random.
302
303 roundrobin Round robin over open files. This
304 is the default.
305
Jens Axboe1907dbc2007-03-12 11:44:28 +0100306 The string can have a number appended, indicating how
307 often to switch to a new file. So if option random:4 is
308 given, fio will switch to a new random file after 4 ios
309 have been issued.
310
Jens Axboe71bfa162006-10-25 11:08:19 +0200311ioengine=str Defines how the job issues io to the file. The following
312 types are defined:
313
314 sync Basic read(2) or write(2) io. lseek(2) is
315 used to position the io location.
316
317 libaio Linux native asynchronous io.
318
319 posixaio glibc posix asynchronous io.
320
321 mmap File is memory mapped and data copied
322 to/from using memcpy(3).
323
324 splice splice(2) is used to transfer the data and
325 vmsplice(2) to transfer data from user
326 space to the kernel.
327
Jens Axboed0ff85d2007-02-14 01:19:41 +0100328 syslet-rw Use the syslet system calls to make
329 regular read/write async.
330
Jens Axboe71bfa162006-10-25 11:08:19 +0200331 sg SCSI generic sg v3 io. May either be
Jens Axboe6c219762006-11-03 15:51:45 +0100332 synchronous using the SG_IO ioctl, or if
Jens Axboe71bfa162006-10-25 11:08:19 +0200333 the target is an sg character device
334 we use read(2) and write(2) for asynchronous
335 io.
336
Jens Axboea94ea282006-11-24 12:37:34 +0100337 null Doesn't transfer any data, just pretends
338 to. This is mainly used to exercise fio
339 itself and for debugging/testing purposes.
340
Jens Axboeed92ac02007-02-06 14:43:52 +0100341 net Transfer over the network to given host:port.
342 'filename' must be set appropriately to
Jens Axboe9f9214f2007-03-13 14:02:16 +0100343 filename=host/port regardless of send
Jens Axboeed92ac02007-02-06 14:43:52 +0100344 or receive, if the latter only the port
345 argument is used.
346
Jens Axboe9cce02e2007-06-22 15:42:21 +0200347 netsplice Like net, but uses splice/vmsplice to
348 map data and send/receive.
349
Jens Axboeba0fbe12007-03-09 14:34:23 +0100350 cpu Doesn't transfer any data, but burns CPU
351 cycles according to the cpuload= and
352 cpucycle= options. Setting cpuload=85
353 will cause that job to do nothing but burn
354 85% of the CPU.
355
Jens Axboee9a18062007-03-21 08:51:56 +0100356 guasi The GUASI IO engine is the Generic Userspace
357 Asyncronous Syscall Interface approach
358 to async IO. See
359
360 http://www.xmailserver.org/guasi-lib.html
361
362 for more info on GUASI.
363
Jens Axboe8a7bd872007-02-28 11:12:25 +0100364 external Prefix to specify loading an external
365 IO engine object file. Append the engine
366 filename, eg ioengine=external:/tmp/foo.o
367 to load ioengine foo.o in /tmp.
368
Jens Axboe71bfa162006-10-25 11:08:19 +0200369iodepth=int This defines how many io units to keep in flight against
370 the file. The default is 1 for each file defined in this
371 job, can be overridden with a larger value for higher
372 concurrency.
373
Jens Axboecb5ab512007-02-26 12:57:09 +0100374iodepth_batch=int This defines how many pieces of IO to submit at once.
375 It defaults to the same as iodepth, but can be set lower
376 if one so desires.
377
Jens Axboee916b392007-02-20 14:37:26 +0100378iodepth_low=int The low water mark indicating when to start filling
379 the queue again. Defaults to the same as iodepth, meaning
380 that fio will attempt to keep the queue full at all times.
381 If iodepth is set to eg 16 and iodepth_low is set to 4, then
382 after fio has filled the queue of 16 requests, it will let
383 the depth drain down to 4 before starting to fill it again.
384
Jens Axboe71bfa162006-10-25 11:08:19 +0200385direct=bool If value is true, use non-buffered io. This is usually
Jens Axboe76a43db2007-01-11 13:24:44 +0100386 O_DIRECT.
387
388buffered=bool If value is true, use buffered io. This is the opposite
389 of the 'direct' option. Defaults to true.
Jens Axboe71bfa162006-10-25 11:08:19 +0200390
391offset=siint Start io at the given offset in the file. The data before
392 the given offset will not be touched. This effectively
393 caps the file size at real_size - offset.
394
395fsync=int If writing to a file, issue a sync of the dirty data
396 for every number of blocks given. For example, if you give
397 32 as a parameter, fio will sync the file for every 32
398 writes issued. If fio is using non-buffered io, we may
399 not sync the file. The exception is the sg io engine, which
Jens Axboe6c219762006-11-03 15:51:45 +0100400 synchronizes the disk cache anyway.
Jens Axboe71bfa162006-10-25 11:08:19 +0200401
402overwrite=bool If writing to a file, setup the file first and do overwrites.
403
404end_fsync=bool If true, fsync file contents when the job exits.
405
Jens Axboeebb14152007-03-13 14:42:15 +0100406fsync_on_close=bool If true, fio will fsync() a dirty file on close.
407 This differs from end_fsync in that it will happen on every
408 file close, not just at the end of the job.
409
Jens Axboe6c219762006-11-03 15:51:45 +0100410rwmixcycle=int Value in milliseconds describing how often to switch between
Jens Axboe71bfa162006-10-25 11:08:19 +0200411 reads and writes for a mixed workload. The default is
412 500 msecs.
413
414rwmixread=int How large a percentage of the mix should be reads.
415
416rwmixwrite=int How large a percentage of the mix should be writes. If both
417 rwmixread and rwmixwrite is given and the values do not add
418 up to 100%, the latter of the two will be used to override
419 the first.
420
Jens Axboebb8895e2006-10-30 15:14:48 +0100421norandommap Normally fio will cover every block of the file when doing
422 random IO. If this option is given, fio will just get a
423 new random offset without looking at past io history. This
424 means that some blocks may not be read or written, and that
425 some blocks may be read/written more than once. This option
Jens Axboe7616caf2007-05-25 09:26:05 +0200426 is mutually exclusive with verify= for that reason, since
427 fio doesn't track potential block rewrites which may alter
428 the calculated checksum for that block.
Jens Axboebb8895e2006-10-30 15:14:48 +0100429
Jens Axboe71bfa162006-10-25 11:08:19 +0200430nice=int Run the job with the given nice value. See man nice(2).
431
432prio=int Set the io priority value of this job. Linux limits us to
433 a positive value between 0 and 7, with 0 being the highest.
434 See man ionice(1).
435
436prioclass=int Set the io priority class. See man ionice(1).
437
438thinktime=int Stall the job x microseconds after an io has completed before
439 issuing the next. May be used to simulate processing being
Jens Axboe48097d52007-02-17 06:30:44 +0100440 done by an application. See thinktime_blocks and
441 thinktime_spin.
442
443thinktime_spin=int
444 Only valid if thinktime is set - pretend to spend CPU time
445 doing something with the data received, before falling back
446 to sleeping for the rest of the period specified by
447 thinktime.
Jens Axboe9c1f7432007-01-03 20:43:19 +0100448
449thinktime_blocks
450 Only valid if thinktime is set - control how many blocks
451 to issue, before waiting 'thinktime' usecs. If not set,
452 defaults to 1 which will make fio wait 'thinktime' usecs
453 after every block.
Jens Axboe71bfa162006-10-25 11:08:19 +0200454
455rate=int Cap the bandwidth used by this job to this number of KiB/sec.
456
457ratemin=int Tell fio to do whatever it can to maintain at least this
Jens Axboe4e991c22007-03-15 11:41:11 +0100458 bandwidth. Failing to meet this requirement, will cause
459 the job to exit.
460
461rate_iops=int Cap the bandwidth to this number of IOPS. Basically the same
462 as rate, just specified independently of bandwidth. If the
463 job is given a block size range instead of a fixed value,
464 the smallest block size is used as the metric.
465
466rate_iops_min=int If fio doesn't meet this rate of IO, it will cause
467 the job to exit.
Jens Axboe71bfa162006-10-25 11:08:19 +0200468
469ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number
Jens Axboe6c219762006-11-03 15:51:45 +0100470 of milliseconds.
Jens Axboe71bfa162006-10-25 11:08:19 +0200471
472cpumask=int Set the CPU affinity of this job. The parameter given is a
Jens Axboea08bc172007-06-13 21:00:46 +0200473 bitmask of allowed CPU's the job may run on. So if you want
474 the allowed CPUs to be 1 and 5, you would pass the decimal
475 value of (1 << 1 | 1 << 5), or 34. See man
Jens Axboe7dbb6eb2007-05-22 09:13:31 +0200476 sched_setaffinity(2). This may not work on all supported
477 operating systems or kernel versions.
Jens Axboe71bfa162006-10-25 11:08:19 +0200478
Jens Axboed2e268b2007-06-15 10:33:49 +0200479cpus_allowed=str Controls the same options as cpumask, but it allows a text
480 setting of the permitted CPUs instead. So to use CPUs 1 and
481 5, you would specify cpus_allowed=1,5.
482
Jens Axboe71bfa162006-10-25 11:08:19 +0200483startdelay=int Start this job the specified number of seconds after fio
484 has started. Only useful if the job file contains several
485 jobs, and you want to delay starting some jobs to a certain
486 time.
487
Jens Axboe03b74b32007-01-11 11:04:31 +0100488runtime=int Tell fio to terminate processing after the specified number
Jens Axboe71bfa162006-10-25 11:08:19 +0200489 of seconds. It can be quite hard to determine for how long
490 a specified job will run, so this parameter is handy to
491 cap the total runtime to a given time.
492
Jens Axboecf4464c2007-04-17 20:14:42 +0200493time_based If set, fio will run for the duration of the runtime
494 specified even if the file(s) are completey read or
495 written. It will simply loop over the same workload
496 as many times as the runtime allows.
497
Jens Axboe71bfa162006-10-25 11:08:19 +0200498invalidate=bool Invalidate the buffer/page cache parts for this file prior
499 to starting io. Defaults to true.
500
501sync=bool Use sync io for buffered writes. For the majority of the
502 io engines, this means using O_SYNC.
503
Jens Axboed3aad8f2007-03-15 14:12:05 +0100504iomem=str
Jens Axboe71bfa162006-10-25 11:08:19 +0200505mem=str Fio can use various types of memory as the io unit buffer.
506 The allowed values are:
507
508 malloc Use memory from malloc(3) as the buffers.
509
510 shm Use shared memory as the buffers. Allocated
511 through shmget(2).
512
Jens Axboe74b025b2006-12-19 15:18:14 +0100513 shmhuge Same as shm, but use huge pages as backing.
514
Jens Axboe313cb202006-12-21 09:50:00 +0100515 mmap Use mmap to allocate buffers. May either be
516 anonymous memory, or can be file backed if
517 a filename is given after the option. The
518 format is mem=mmap:/path/to/file.
Jens Axboe71bfa162006-10-25 11:08:19 +0200519
Jens Axboed0bdaf42006-12-20 14:40:44 +0100520 mmaphuge Use a memory mapped huge file as the buffer
521 backing. Append filename after mmaphuge, ala
522 mem=mmaphuge:/hugetlbfs/file
523
Jens Axboe71bfa162006-10-25 11:08:19 +0200524 The area allocated is a function of the maximum allowed
Jens Axboe5394ae52006-12-20 20:15:41 +0100525 bs size for the job, multiplied by the io depth given. Note
526 that for shmhuge and mmaphuge to work, the system must have
527 free huge pages allocated. This can normally be checked
528 and set by reading/writing /proc/sys/vm/nr_hugepages on a
529 Linux system. Fio assumes a huge page is 4MiB in size. So
530 to calculate the number of huge pages you need for a given
531 job file, add up the io depth of all jobs (normally one unless
532 iodepth= is used) and multiply by the maximum bs set. Then
533 divide that number by the huge page size. You can see the
534 size of the huge pages in /proc/meminfo. If no huge pages
535 are allocated by having a non-zero number in nr_hugepages,
Jens Axboe56bb17f2006-12-20 20:27:36 +0100536 using mmaphuge or shmhuge will fail. Also see hugepage-size.
Jens Axboe5394ae52006-12-20 20:15:41 +0100537
538 mmaphuge also needs to have hugetlbfs mounted and the file
539 location should point there. So if it's mounted in /huge,
540 you would use mem=mmaphuge:/huge/somefile.
Jens Axboe71bfa162006-10-25 11:08:19 +0200541
Jens Axboe56bb17f2006-12-20 20:27:36 +0100542hugepage-size=siint
543 Defines the size of a huge page. Must at least be equal
544 to the system setting, see /proc/meminfo. Defaults to 4MiB.
Jens Axboec51074e2006-12-20 20:28:33 +0100545 Should probably always be a multiple of megabytes, so using
546 hugepage-size=Xm is the preferred way to set this to avoid
547 setting a non-pow-2 bad value.
Jens Axboe56bb17f2006-12-20 20:27:36 +0100548
Jens Axboe71bfa162006-10-25 11:08:19 +0200549exitall When one job finishes, terminate the rest. The default is
550 to wait for each job to finish, sometimes that is not the
551 desired action.
552
553bwavgtime=int Average the calculated bandwidth over the given time. Value
Jens Axboe6c219762006-11-03 15:51:45 +0100554 is specified in milliseconds.
Jens Axboe71bfa162006-10-25 11:08:19 +0200555
556create_serialize=bool If true, serialize the file creating for the jobs.
557 This may be handy to avoid interleaving of data
558 files, which may greatly depend on the filesystem
559 used and even the number of processors in the system.
560
561create_fsync=bool fsync the data file after creation. This is the
562 default.
563
Jens Axboee545a6c2007-01-14 00:00:29 +0100564unlink=bool Unlink the job files when done. Not the default, as repeated
565 runs of that job would then waste time recreating the fileset
566 again and again.
Jens Axboe71bfa162006-10-25 11:08:19 +0200567
568loops=int Run the specified number of iterations of this job. Used
569 to repeat the same workload a given number of times. Defaults
570 to 1.
571
Shawn Lewise84c73a2007-08-02 22:19:32 +0200572do_verify=int Run the verify phase after a write phase. Only makes sense if
573 verify is set. Defaults to 1.
574
Jens Axboe71bfa162006-10-25 11:08:19 +0200575verify=str If writing to a file, fio can verify the file contents
576 after each iteration of the job. The allowed values are:
577
578 md5 Use an md5 sum of the data area and store
579 it in the header of each block.
580
Jens Axboe17dc34d2007-07-27 15:36:02 +0200581 crc64 Use an experimental crc64 sum of the data
582 area and store it in the header of each
583 block.
584
Jens Axboe71bfa162006-10-25 11:08:19 +0200585 crc32 Use a crc32 sum of the data area and store
586 it in the header of each block.
587
Jens Axboe969f7ed2007-07-27 09:07:17 +0200588 crc16 Use a crc16 sum of the data area and store
589 it in the header of each block.
590
Jens Axboe17dc34d2007-07-27 15:36:02 +0200591 crc7 Use a crc7 sum of the data area and store
592 it in the header of each block.
593
Jens Axboecd14cc12007-07-30 10:59:33 +0200594 sha512 Use sha512 as the checksum function.
595
596 sha256 Use sha256 as the checksum function.
597
Shawn Lewis7437ee82007-08-02 21:05:58 +0200598 meta Write extra information about each io
599 (timestamp, block number etc.). The block
600 number is verified.
601
Jens Axboe36690c92007-03-26 10:23:34 +0200602 null Only pretend to verify. Useful for testing
603 internals with ioengine=null, not for much
604 else.
605
Jens Axboe6c219762006-11-03 15:51:45 +0100606 This option can be used for repeated burn-in tests of a
Jens Axboe71bfa162006-10-25 11:08:19 +0200607 system to make sure that the written data is also
608 correctly read back.
609
Jens Axboe160b9662007-03-27 10:59:49 +0200610verifysort=bool If set, fio will sort written verify blocks when it deems
611 it faster to read them back in a sorted manner. This is
612 often the case when overwriting an existing file, since
613 the blocks are already laid out in the file system. You
614 can ignore this option unless doing huge amounts of really
615 fast IO where the red-black tree sorting CPU time becomes
616 significant.
Shawn Lewis3f9f4e22007-07-28 21:10:37 +0200617
Jens Axboea59e1702007-07-30 08:53:27 +0200618verify_offset=siint Swap the verification header with data somewhere else
Shawn Lewis546a9142007-07-28 21:11:37 +0200619 in the block before writing. Its swapped back before
620 verifying.
621
Jens Axboea59e1702007-07-30 08:53:27 +0200622verify_interval=siint Write the verification header at a finer granularity
Shawn Lewis3f9f4e22007-07-28 21:10:37 +0200623 than the blocksize. It will be written for chunks the
624 size of header_interval. blocksize should divide this
625 evenly.
Jens Axboe90059d62007-07-30 09:33:12 +0200626
627verify_pattern=int If set, fio will fill the io buffers with this
628 pattern. Fio defaults to filling with totally random
629 bytes, but sometimes it's interesting to fill with a known
630 pattern for io verification purposes. Depending on the
631 width of the pattern, fio will fill 1/2/3/4 bytes of the
632 buffer at the time. The verify_pattern cannot be larger than
633 a 32-bit quantity.
Jens Axboe160b9662007-03-27 10:59:49 +0200634
Jens Axboe71bfa162006-10-25 11:08:19 +0200635stonewall Wait for preceeding jobs in the job file to exit, before
636 starting this one. Can be used to insert serialization
Jens Axboeb3d62a72007-03-20 14:23:26 +0100637 points in the job file. A stone wall also implies starting
638 a new reporting group.
639
640new_group Start a new reporting group. If this option isn't given,
641 jobs in a file will be part of the same reporting group
642 unless seperated by a stone wall (or if it's a group
643 by itself, with the numjobs option).
Jens Axboe71bfa162006-10-25 11:08:19 +0200644
645numjobs=int Create the specified number of clones of this job. May be
646 used to setup a larger number of threads/processes doing
Jens Axboefa28c852007-03-06 15:40:49 +0100647 the same thing. We regard that grouping of jobs as a
648 specific group.
649
650group_reporting If 'numjobs' is set, it may be interesting to display
651 statistics for the group as a whole instead of for each
652 individual job. This is especially true of 'numjobs' is
653 large, looking at individual thread/process output quickly
654 becomes unwieldy. If 'group_reporting' is specified, fio
655 will show the final report per-group instead of per-job.
Jens Axboe71bfa162006-10-25 11:08:19 +0200656
657thread fio defaults to forking jobs, however if this option is
658 given, fio will use pthread_create(3) to create threads
659 instead.
660
661zonesize=siint Divide a file into zones of the specified size. See zoneskip.
662
663zoneskip=siint Skip the specified number of bytes when zonesize data has
664 been read. The two zone options can be used to only do
665 io on zones of a file.
666
Jens Axboe076efc72006-10-27 11:24:25 +0200667write_iolog=str Write the issued io patterns to the specified file. See
668 read_iolog.
Jens Axboe71bfa162006-10-25 11:08:19 +0200669
Jens Axboe076efc72006-10-27 11:24:25 +0200670read_iolog=str Open an iolog with the specified file name and replay the
Jens Axboe71bfa162006-10-25 11:08:19 +0200671 io patterns it contains. This can be used to store a
Jens Axboe6df8ada2007-05-15 13:23:19 +0200672 workload and replay it sometime later. The iolog given
673 may also be a blktrace binary file, which allows fio
674 to replay a workload captured by blktrace. See blktrace
675 for how to capture such logging data. For blktrace replay,
676 the file needs to be turned into a blkparse binary data
677 file first (blktrace <device> -d file_for_fio.bin).
Jens Axboe71bfa162006-10-25 11:08:19 +0200678
679write_bw_log If given, write a bandwidth log of the jobs in this job
680 file. Can be used to store data of the bandwidth of the
Jens Axboee0da9bc2006-10-25 13:08:57 +0200681 jobs in their lifetime. The included fio_generate_plots
682 script uses gnuplot to turn these text files into nice
683 graphs.
Jens Axboe71bfa162006-10-25 11:08:19 +0200684
685write_lat_log Same as write_bw_log, except that this option stores io
686 completion latencies instead.
687
688lockmem=siint Pin down the specified amount of memory with mlock(2). Can
689 potentially be used instead of removing memory or booting
690 with less memory to simulate a smaller amount of memory.
691
692exec_prerun=str Before running this job, issue the command specified
693 through system(3).
694
695exec_postrun=str After the job completes, issue the command specified
696 though system(3).
697
698ioscheduler=str Attempt to switch the device hosting the file to the specified
699 io scheduler before running.
700
701cpuload=int If the job is a CPU cycle eater, attempt to use the specified
702 percentage of CPU cycles.
703
704cpuchunks=int If the job is a CPU cycle eater, split the load into
Jens Axboe6c219762006-11-03 15:51:45 +0100705 cycles of the given time. In milliseconds.
Jens Axboe71bfa162006-10-25 11:08:19 +0200706
Jens Axboe0a839f32007-04-26 09:02:34 +0200707disk_util=bool Generate disk utilization statistics, if the platform
708 supports it. Defaults to on.
709
Jens Axboe71bfa162006-10-25 11:08:19 +0200710
7116.0 Interpreting the output
712---------------------------
713
714fio spits out a lot of output. While running, fio will display the
715status of the jobs created. An example of that would be:
716
Jens Axboe73c8b082007-01-11 19:25:52 +0100717Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
Jens Axboe71bfa162006-10-25 11:08:19 +0200718
719The characters inside the square brackets denote the current status of
720each thread. The possible values (in typical life cycle order) are:
721
722Idle Run
723---- ---
724P Thread setup, but not started.
725C Thread created.
726I Thread initialized, waiting.
727 R Running, doing sequential reads.
728 r Running, doing random reads.
729 W Running, doing sequential writes.
730 w Running, doing random writes.
731 M Running, doing mixed sequential reads/writes.
732 m Running, doing mixed random reads/writes.
733 F Running, currently waiting for fsync()
734V Running, doing verification of written data.
735E Thread exited, not reaped by main thread yet.
736_ Thread reaped.
737
738The other values are fairly self explanatory - number of threads
Jens Axboec9f60302007-07-20 12:43:05 +0200739currently running and doing io, rate of io since last check (read speed
740listed first, then write speed), and the estimated completion percentage
741and time for the running group. It's impossible to estimate runtime of
742the following groups (if any).
Jens Axboe71bfa162006-10-25 11:08:19 +0200743
744When fio is done (or interrupted by ctrl-c), it will show the data for
745each thread, group of threads, and disks in that order. For each data
746direction, the output looks like:
747
748Client1 (g=0): err= 0:
749 write: io= 32MiB, bw= 666KiB/s, runt= 50320msec
Jens Axboe6104ddb2007-01-11 14:24:29 +0100750 slat (msec): min= 0, max= 136, avg= 0.03, stdev= 1.92
751 clat (msec): min= 0, max= 631, avg=48.50, stdev=86.82
752 bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, stdev=681.68
Jens Axboe71bfa162006-10-25 11:08:19 +0200753 cpu : usr=1.49%, sys=0.25%, ctx=7969
Jens Axboe71619dc2007-01-13 23:56:33 +0100754 IO depths : 1=0.1%, 2=0.3%, 4=0.5%, 8=99.0%, 16=0.0%, 32=0.0%, >32=0.0%
Jens Axboe30061b92007-04-17 13:31:34 +0200755 issued r/w: total=0/32768, short=0/0
Jens Axboe8abdce62007-02-21 10:22:55 +0100756 lat (msec): 2=1.6%, 4=0.0%, 10=3.2%, 20=12.8%, 50=38.4%, 100=24.8%,
757 lat (msec): 250=15.2%, 500=0.0%, 750=0.0%, 1000=0.0%, >=2048=0.0%
Jens Axboe71bfa162006-10-25 11:08:19 +0200758
759The client number is printed, along with the group id and error of that
760thread. Below is the io statistics, here for writes. In the order listed,
761they denote:
762
763io= Number of megabytes io performed
764bw= Average bandwidth rate
765runt= The runtime of that thread
Jens Axboe72fbda22007-03-20 10:02:06 +0100766 slat= Submission latency (avg being the average, stdev being the
Jens Axboe71bfa162006-10-25 11:08:19 +0200767 standard deviation). This is the time it took to submit
768 the io. For sync io, the slat is really the completion
Jens Axboe8a35c712007-06-19 09:53:31 +0200769 latency, since queue/complete is one operation there. This
770 value can be in miliseconds or microseconds, fio will choose
771 the most appropriate base and print that. In the example
772 above, miliseconds is the best scale.
Jens Axboe71bfa162006-10-25 11:08:19 +0200773 clat= Completion latency. Same names as slat, this denotes the
774 time from submission to completion of the io pieces. For
775 sync io, clat will usually be equal (or very close) to 0,
776 as the time from submit to complete is basically just
777 CPU time (io has already been done, see slat explanation).
778 bw= Bandwidth. Same names as the xlat stats, but also includes
779 an approximate percentage of total aggregate bandwidth
780 this thread received in this group. This last value is
781 only really useful if the threads in this group are on the
782 same disk, since they are then competing for disk access.
783cpu= CPU usage. User and system time, along with the number
784 of context switches this thread went through.
Jens Axboe71619dc2007-01-13 23:56:33 +0100785IO depths= The distribution of io depths over the job life time. The
786 numbers are divided into powers of 2, so for example the
787 16= entries includes depths up to that value but higher
788 than the previous entry. In other words, it covers the
789 range from 16 to 31.
Jens Axboe30061b92007-04-17 13:31:34 +0200790IO issued= The number of read/write requests issued, and how many
791 of them were short.
Jens Axboeec118302007-02-17 04:38:20 +0100792IO latencies= The distribution of IO completion latencies. This is the
793 time from when IO leaves fio and when it gets completed.
794 The numbers follow the same pattern as the IO depths,
795 meaning that 2=1.6% means that 1.6% of the IO completed
Jens Axboe8abdce62007-02-21 10:22:55 +0100796 within 2 msecs, 20=12.8% means that 12.8% of the IO
797 took more than 10 msecs, but less than (or equal to) 20 msecs.
Jens Axboe71bfa162006-10-25 11:08:19 +0200798
799After each client has been listed, the group statistics are printed. They
800will look like this:
801
802Run status group 0 (all jobs):
803 READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec
804 WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec
805
806For each data direction, it prints:
807
808io= Number of megabytes io performed.
809aggrb= Aggregate bandwidth of threads in this group.
810minb= The minimum average bandwidth a thread saw.
811maxb= The maximum average bandwidth a thread saw.
812mint= The smallest runtime of the threads in that group.
813maxt= The longest runtime of the threads in that group.
814
815And finally, the disk statistics are printed. They will look like this:
816
817Disk stats (read/write):
818 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
819
820Each value is printed for both reads and writes, with reads first. The
821numbers denote:
822
823ios= Number of ios performed by all groups.
824merge= Number of merges io the io scheduler.
825ticks= Number of ticks we kept the disk busy.
826io_queue= Total time spent in the disk queue.
827util= The disk utilization. A value of 100% means we kept the disk
828 busy constantly, 50% would be a disk idling half of the time.
829
830
8317.0 Terse output
832----------------
833
834For scripted usage where you typically want to generate tables or graphs
Jens Axboe6af019c2007-03-06 19:50:58 +0100835of the results, fio can output the results in a semicolon separated format.
Jens Axboe71bfa162006-10-25 11:08:19 +0200836The format is one long line of values, such as:
837
Jens Axboe6af019c2007-03-06 19:50:58 +0100838client1;0;0;1906777;1090804;1790;0;0;0.000000;0.000000;0;0;0.000000;0.000000;929380;1152890;25.510151%;1078276.333333;128948.113404;0;0;0;0;0;0.000000;0.000000;0;0;0.000000;0.000000;0;0;0.000000%;0.000000;0.000000;100.000000%;0.000000%;324;100.0%;0.0%;0.0%;0.0%;0.0%;0.0%;0.0%;100.0%;0.0%;0.0%;0.0%;0.0%;0.0%
839;0.0%;0.0%;0.0%;0.0%;0.0%
Jens Axboe71bfa162006-10-25 11:08:19 +0200840
841Split up, the format is as follows:
842
843 jobname, groupid, error
844 READ status:
845 KiB IO, bandwidth (KiB/sec), runtime (msec)
846 Submission latency: min, max, mean, deviation
847 Completion latency: min, max, mean, deviation
Jens Axboe6c219762006-11-03 15:51:45 +0100848 Bw: min, max, aggregate percentage of total, mean, deviation
Jens Axboe71bfa162006-10-25 11:08:19 +0200849 WRITE status:
850 KiB IO, bandwidth (KiB/sec), runtime (msec)
851 Submission latency: min, max, mean, deviation
852 Completion latency: min, max, mean, deviation
Jens Axboe6c219762006-11-03 15:51:45 +0100853 Bw: min, max, aggregate percentage of total, mean, deviation
Jens Axboe71bfa162006-10-25 11:08:19 +0200854 CPU usage: user, system, context switches
Jens Axboe22708902007-03-06 17:05:32 +0100855 IO depths: <=1, 2, 4, 8, 16, 32, >=64
856 IO latencies: <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, >=2000
857 Text description
Jens Axboe71bfa162006-10-25 11:08:19 +0200858