[PATCH] Allow leading , in multi setting parameter
[fio.git] / HOWTO
CommitLineData
71bfa161
JA
1Table 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
52 could be using splice, async io, or even
53 SG (SCSI generic sg).
54
6c219763 55 IO depth If the io engine is async, how large a queuing
71bfa161
JA
56 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
b4692828
JA
85If 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
c2b1e753
JA
89mirror 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.
b4692828 96
71bfa161
JA
97fio 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,
6c219763 99such as memory locking, io scheduler switching, and decreasing the nice value.
71bfa161
JA
100
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
111section residing above it. If the first character in a line is a ';', the
112entire line is discarded as a comment.
113
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
c2b1e753
JA
130makes 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
71bfa161
JA
135
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
b4692828
JA
155to 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
71bfa161
JA
160
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.
173int Integer. A whole number value, may be negative.
174siint SI integer. A whole number value, which may contain a postfix
175 describing the base of the number. Accepted postfixes are k/m/g,
6c219763 176 meaning kilo, mega, and giga. So if you want to specify 4096,
71bfa161
JA
177 you could either write out '4096' or just give 4k. The postfixes
178 signify base 2 values, so 1024 is 1k and 1024k is 1m and so on.
179bool Boolean. Usually parsed as an integer, however only defined for
180 true and false (1 and 0).
181irange Integer range with postfix. Allows value range to be given, such
182 as 1024-4096. Also see siint.
183
184With the above in mind, here follows the complete list of fio job
185parameters.
186
187name=str ASCII name of the job. This may be used to override the
188 name printed by fio for this job. Otherwise the job
c2b1e753 189 name is used. On the command line this parameter has the
6c219763 190 special purpose of also signaling the start of a new
c2b1e753 191 job.
71bfa161
JA
192
193directory=str Prefix filenames with this directory. Used to places files
194 in a different location than "./".
195
196filename=str Fio normally makes up a filename based on the job name,
197 thread number, and file number. If you want to share
198 files between threads in a job or several jobs, specify
199 a filename for each of them to override the default.
200
201rw=str Type of io pattern. Accepted values are:
202
203 read Sequential reads
204 write Sequential writes
205 randwrite Random writes
206 randread Random reads
207 rw Sequential mixed reads and writes
208 randrw Random mixed reads and writes
209
210 For the mixed io types, the default is to split them 50/50.
211 For certain types of io the result may still be skewed a bit,
212 since the speed may be different.
213
214size=siint The total size of file io for this job. This may describe
215 the size of the single file the job uses, or it may be
216 divided between the number of files in the job. If the
217 file already exists, the file size will be adjusted to this
218 size if larger than the current file size. If this parameter
219 is not given and the file exists, the file size will be used.
220
f90eff5a
JA
221bs=siint The block size used for the io units. Defaults to 4k. Values
222 can be given for both read and writes. If a single siint is
223 given, it will apply to both. If a second siint is specified
224 after a comma, it will apply to writes only. In other words,
225 the format is either bs=read_and_write or bs=read,write.
226 bs=4k,8k will thus use 4k blocks for reads, and 8k blocks
787f7e95
JA
227 for writes. If you only wish to set the write size, you
228 can do so by passing an empty read size - bs=,8k will set
229 8k for writes and leave the read default value.
a00735e6 230
71bfa161
JA
231bsrange=irange Instead of giving a single block size, specify a range
232 and fio will mix the issued io block sizes. The issued
233 io unit will always be a multiple of the minimum value
f90eff5a
JA
234 given (also see bs_unaligned). Applies to both reads and
235 writes, however a second range can be given after a comma.
236 See bs=.
a00735e6 237
690adba3
JA
238bs_unaligned If this option is given, any byte size value within bsrange
239 may be used as a block range. This typically wont work with
240 direct IO, as that normally requires sector alignment.
71bfa161
JA
241
242nrfiles=int Number of files to use for this job. Defaults to 1.
243
244ioengine=str Defines how the job issues io to the file. The following
245 types are defined:
246
247 sync Basic read(2) or write(2) io. lseek(2) is
248 used to position the io location.
249
250 libaio Linux native asynchronous io.
251
252 posixaio glibc posix asynchronous io.
253
254 mmap File is memory mapped and data copied
255 to/from using memcpy(3).
256
257 splice splice(2) is used to transfer the data and
258 vmsplice(2) to transfer data from user
259 space to the kernel.
260
261 sg SCSI generic sg v3 io. May either be
6c219763 262 synchronous using the SG_IO ioctl, or if
71bfa161
JA
263 the target is an sg character device
264 we use read(2) and write(2) for asynchronous
265 io.
266
267iodepth=int This defines how many io units to keep in flight against
268 the file. The default is 1 for each file defined in this
269 job, can be overridden with a larger value for higher
270 concurrency.
271
272direct=bool If value is true, use non-buffered io. This is usually
273 O_DIRECT. Defaults to true.
274
275offset=siint Start io at the given offset in the file. The data before
276 the given offset will not be touched. This effectively
277 caps the file size at real_size - offset.
278
279fsync=int If writing to a file, issue a sync of the dirty data
280 for every number of blocks given. For example, if you give
281 32 as a parameter, fio will sync the file for every 32
282 writes issued. If fio is using non-buffered io, we may
283 not sync the file. The exception is the sg io engine, which
6c219763 284 synchronizes the disk cache anyway.
71bfa161
JA
285
286overwrite=bool If writing to a file, setup the file first and do overwrites.
287
288end_fsync=bool If true, fsync file contents when the job exits.
289
6c219763 290rwmixcycle=int Value in milliseconds describing how often to switch between
71bfa161
JA
291 reads and writes for a mixed workload. The default is
292 500 msecs.
293
294rwmixread=int How large a percentage of the mix should be reads.
295
296rwmixwrite=int How large a percentage of the mix should be writes. If both
297 rwmixread and rwmixwrite is given and the values do not add
298 up to 100%, the latter of the two will be used to override
299 the first.
300
bb8895e0
JA
301norandommap Normally fio will cover every block of the file when doing
302 random IO. If this option is given, fio will just get a
303 new random offset without looking at past io history. This
304 means that some blocks may not be read or written, and that
305 some blocks may be read/written more than once. This option
306 is mutually exclusive with verify= for that reason.
307
71bfa161
JA
308nice=int Run the job with the given nice value. See man nice(2).
309
310prio=int Set the io priority value of this job. Linux limits us to
311 a positive value between 0 and 7, with 0 being the highest.
312 See man ionice(1).
313
314prioclass=int Set the io priority class. See man ionice(1).
315
316thinktime=int Stall the job x microseconds after an io has completed before
317 issuing the next. May be used to simulate processing being
318 done by an application.
319
320rate=int Cap the bandwidth used by this job to this number of KiB/sec.
321
322ratemin=int Tell fio to do whatever it can to maintain at least this
323 bandwidth.
324
325ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number
6c219763 326 of milliseconds.
71bfa161
JA
327
328cpumask=int Set the CPU affinity of this job. The parameter given is a
329 bitmask of allowed CPU's the job may run on. See man
330 sched_setaffinity(2).
331
332startdelay=int Start this job the specified number of seconds after fio
333 has started. Only useful if the job file contains several
334 jobs, and you want to delay starting some jobs to a certain
335 time.
336
337timeout=int Tell fio to terminate processing after the specified number
338 of seconds. It can be quite hard to determine for how long
339 a specified job will run, so this parameter is handy to
340 cap the total runtime to a given time.
341
342invalidate=bool Invalidate the buffer/page cache parts for this file prior
343 to starting io. Defaults to true.
344
345sync=bool Use sync io for buffered writes. For the majority of the
346 io engines, this means using O_SYNC.
347
348mem=str Fio can use various types of memory as the io unit buffer.
349 The allowed values are:
350
351 malloc Use memory from malloc(3) as the buffers.
352
353 shm Use shared memory as the buffers. Allocated
354 through shmget(2).
355
356 mmap Use anonymous memory maps as the buffers.
357 Allocated through mmap(2).
358
359 The area allocated is a function of the maximum allowed
360 bs size for the job, multiplied by the io depth given.
361
362exitall When one job finishes, terminate the rest. The default is
363 to wait for each job to finish, sometimes that is not the
364 desired action.
365
366bwavgtime=int Average the calculated bandwidth over the given time. Value
6c219763 367 is specified in milliseconds.
71bfa161
JA
368
369create_serialize=bool If true, serialize the file creating for the jobs.
370 This may be handy to avoid interleaving of data
371 files, which may greatly depend on the filesystem
372 used and even the number of processors in the system.
373
374create_fsync=bool fsync the data file after creation. This is the
375 default.
376
377unlink Unlink the job files when done. fio defaults to doing this,
378 if it created the file itself.
379
380loops=int Run the specified number of iterations of this job. Used
381 to repeat the same workload a given number of times. Defaults
382 to 1.
383
384verify=str If writing to a file, fio can verify the file contents
385 after each iteration of the job. The allowed values are:
386
387 md5 Use an md5 sum of the data area and store
388 it in the header of each block.
389
390 crc32 Use a crc32 sum of the data area and store
391 it in the header of each block.
392
6c219763 393 This option can be used for repeated burn-in tests of a
71bfa161
JA
394 system to make sure that the written data is also
395 correctly read back.
396
397stonewall Wait for preceeding jobs in the job file to exit, before
398 starting this one. Can be used to insert serialization
399 points in the job file.
400
401numjobs=int Create the specified number of clones of this job. May be
402 used to setup a larger number of threads/processes doing
403 the same thing.
404
405thread fio defaults to forking jobs, however if this option is
406 given, fio will use pthread_create(3) to create threads
407 instead.
408
409zonesize=siint Divide a file into zones of the specified size. See zoneskip.
410
411zoneskip=siint Skip the specified number of bytes when zonesize data has
412 been read. The two zone options can be used to only do
413 io on zones of a file.
414
076efc7c
JA
415write_iolog=str Write the issued io patterns to the specified file. See
416 read_iolog.
71bfa161 417
076efc7c 418read_iolog=str Open an iolog with the specified file name and replay the
71bfa161
JA
419 io patterns it contains. This can be used to store a
420 workload and replay it sometime later.
421
422write_bw_log If given, write a bandwidth log of the jobs in this job
423 file. Can be used to store data of the bandwidth of the
e0da9bc2
JA
424 jobs in their lifetime. The included fio_generate_plots
425 script uses gnuplot to turn these text files into nice
426 graphs.
71bfa161
JA
427
428write_lat_log Same as write_bw_log, except that this option stores io
429 completion latencies instead.
430
431lockmem=siint Pin down the specified amount of memory with mlock(2). Can
432 potentially be used instead of removing memory or booting
433 with less memory to simulate a smaller amount of memory.
434
435exec_prerun=str Before running this job, issue the command specified
436 through system(3).
437
438exec_postrun=str After the job completes, issue the command specified
439 though system(3).
440
441ioscheduler=str Attempt to switch the device hosting the file to the specified
442 io scheduler before running.
443
444cpuload=int If the job is a CPU cycle eater, attempt to use the specified
445 percentage of CPU cycles.
446
447cpuchunks=int If the job is a CPU cycle eater, split the load into
6c219763 448 cycles of the given time. In milliseconds.
71bfa161
JA
449
450
4516.0 Interpreting the output
452---------------------------
453
454fio spits out a lot of output. While running, fio will display the
455status of the jobs created. An example of that would be:
456
6043c579 457Threads running: 1: [_r] [24.79% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
71bfa161
JA
458
459The characters inside the square brackets denote the current status of
460each thread. The possible values (in typical life cycle order) are:
461
462Idle Run
463---- ---
464P Thread setup, but not started.
465C Thread created.
466I Thread initialized, waiting.
467 R Running, doing sequential reads.
468 r Running, doing random reads.
469 W Running, doing sequential writes.
470 w Running, doing random writes.
471 M Running, doing mixed sequential reads/writes.
472 m Running, doing mixed random reads/writes.
473 F Running, currently waiting for fsync()
474V Running, doing verification of written data.
475E Thread exited, not reaped by main thread yet.
476_ Thread reaped.
477
478The other values are fairly self explanatory - number of threads
6043c579
JA
479currently running and doing io, rate of io since last check, and the estimated
480completion percentage and time for the running group. It's impossible to
481estimate runtime of the following groups (if any).
71bfa161
JA
482
483When fio is done (or interrupted by ctrl-c), it will show the data for
484each thread, group of threads, and disks in that order. For each data
485direction, the output looks like:
486
487Client1 (g=0): err= 0:
488 write: io= 32MiB, bw= 666KiB/s, runt= 50320msec
489 slat (msec): min= 0, max= 136, avg= 0.03, dev= 1.92
490 clat (msec): min= 0, max= 631, avg=48.50, dev=86.82
491 bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, dev=681.68
492 cpu : usr=1.49%, sys=0.25%, ctx=7969
493
494The client number is printed, along with the group id and error of that
495thread. Below is the io statistics, here for writes. In the order listed,
496they denote:
497
498io= Number of megabytes io performed
499bw= Average bandwidth rate
500runt= The runtime of that thread
501 slat= Submission latency (avg being the average, dev being the
502 standard deviation). This is the time it took to submit
503 the io. For sync io, the slat is really the completion
504 latency, since queue/complete is one operation there.
505 clat= Completion latency. Same names as slat, this denotes the
506 time from submission to completion of the io pieces. For
507 sync io, clat will usually be equal (or very close) to 0,
508 as the time from submit to complete is basically just
509 CPU time (io has already been done, see slat explanation).
510 bw= Bandwidth. Same names as the xlat stats, but also includes
511 an approximate percentage of total aggregate bandwidth
512 this thread received in this group. This last value is
513 only really useful if the threads in this group are on the
514 same disk, since they are then competing for disk access.
515cpu= CPU usage. User and system time, along with the number
516 of context switches this thread went through.
517
518After each client has been listed, the group statistics are printed. They
519will look like this:
520
521Run status group 0 (all jobs):
522 READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec
523 WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec
524
525For each data direction, it prints:
526
527io= Number of megabytes io performed.
528aggrb= Aggregate bandwidth of threads in this group.
529minb= The minimum average bandwidth a thread saw.
530maxb= The maximum average bandwidth a thread saw.
531mint= The smallest runtime of the threads in that group.
532maxt= The longest runtime of the threads in that group.
533
534And finally, the disk statistics are printed. They will look like this:
535
536Disk stats (read/write):
537 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
538
539Each value is printed for both reads and writes, with reads first. The
540numbers denote:
541
542ios= Number of ios performed by all groups.
543merge= Number of merges io the io scheduler.
544ticks= Number of ticks we kept the disk busy.
545io_queue= Total time spent in the disk queue.
546util= The disk utilization. A value of 100% means we kept the disk
547 busy constantly, 50% would be a disk idling half of the time.
548
549
5507.0 Terse output
551----------------
552
553For scripted usage where you typically want to generate tables or graphs
6c219763 554of the results, fio can output the results in a comma separated format.
71bfa161
JA
555The format is one long line of values, such as:
556
557client1,0,0,936,331,2894,0,0,0.000000,0.000000,1,170,22.115385,34.290410,16,714,84.252874%,366.500000,566.417819,3496,1237,2894,0,0,0.000000,0.000000,0,246,6.671625,21.436952,0,2534,55.465300%,1406.600000,2008.044216,0.000000%,0.431928%,1109
558
559Split up, the format is as follows:
560
561 jobname, groupid, error
562 READ status:
563 KiB IO, bandwidth (KiB/sec), runtime (msec)
564 Submission latency: min, max, mean, deviation
565 Completion latency: min, max, mean, deviation
6c219763 566 Bw: min, max, aggregate percentage of total, mean, deviation
71bfa161
JA
567 WRITE status:
568 KiB IO, bandwidth (KiB/sec), runtime (msec)
569 Submission latency: min, max, mean, deviation
570 Completion latency: min, max, mean, deviation
6c219763 571 Bw: min, max, aggregate percentage of total, mean, deviation
71bfa161
JA
572 CPU usage: user, system, context switches
573