8 5. Detailed list of parameters
13 1.0 Overview and history
14 ------------------------
15 fio was originally written to save me the hassle of writing special test
16 case programs when I wanted to test a specific workload, either for
17 performance reasons or to find/reproduce a bug. The process of writing
18 such a test app can be tiresome, especially if you have to do it often.
19 Hence I needed a tool that would be able to simulate a given io workload
20 without resorting to writing a tailored test case again and again.
22 A test work load is difficult to define, though. There can be any number
23 of processes or threads involved, and they can each be using their own
24 way of generating io. You could have someone dirtying large amounts of
25 memory in an memory mapped file, or maybe several threads issuing
26 reads using asynchronous io. fio needed to be flexible enough to
27 simulate both of these cases, and many more.
31 The first step in getting fio to simulate a desired io workload, is
32 writing a job file describing that specific setup. A job file may contain
33 any number of threads and/or files - the typical contents of the job file
34 is a global section defining shared parameters, and one or more job
35 sections describing the jobs involved. When run, fio parses this file
36 and sets everything up as described. If we break down a job from top to
37 bottom, it contains the following basic parameters:
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.
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
48 IO size How much data are we going to be reading/writing.
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, syslet, or even
55 IO depth If the io engine is async, how large a queuing
56 depth do we want to maintain?
58 IO type Should we be doing buffered io, or direct/raw io?
60 Num files How many files are we spreading the workload over.
62 Num threads How many threads or processes should we spread
65 The above are the basic parameters defined for a workload, in addition
66 there's a multitude of parameters that modify other aspects of how this
72 See the README file for command line parameters, there are only a few
75 Running fio is normally the easiest part - you just give it the job file
76 (or job files) as parameters:
80 and it will start doing what the job_file tells it to do. You can give
81 more than one job file on the command line, fio will serialize the running
82 of those files. Internally that is the same as using the 'stonewall'
83 parameter described the the parameter section.
85 If the job file contains only one job, you may as well just give the
86 parameters on the command line. The command line parameters are identical
87 to the job parameters, with a few extra that control global parameters
88 (see README). For example, for the job file parameter iodepth=2, the
89 mirror command line option would be --iodepth 2 or --iodepth=2. You can
90 also 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.
92 Command line entries following a --name entry will apply to that job,
93 until there are no more entries or a new --name entry is seen. This is
94 similar to the job file options, where each option applies to the current
95 job until a new [] job entry is seen.
97 fio does not need to run as root, except if the files or devices specified
98 in the job section requires that. Some other options may also be restricted,
99 such as memory locking, io scheduler switching, and decreasing the nice value.
104 As previously described, fio accepts one or more job files describing
105 what it is supposed to do. The job file format is the classic ini file,
106 where the names enclosed in [] brackets define the job name. You are free
107 to use any ascii name you want, except 'global' which has special meaning.
108 A global section sets defaults for the jobs described in that file. A job
109 may override a global section parameter, and a job file may even have
110 several global sections if so desired. A job is only affected by a global
111 section residing above it. If the first character in a line is a ';' or a
112 '#', the entire line is discarded as a comment.
114 So lets look at a really simple job file that define to threads, each
115 randomly reading from a 128MiB file.
117 ; -- start job file --
128 As you can see, the job file sections themselves are empty as all the
129 described parameters are shared. As no filename= option is given, fio
130 makes up a filename for each of the jobs as it sees fit. On the command
131 line, this job would look as follows:
133 $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2
136 Lets look at an example that have a number of processes writing randomly
139 ; -- start job file --
151 Here we have no global section, as we only have one job defined anyway.
152 We want to use async io here, with a depth of 4 for each file. We also
153 increased the buffer size used to 32KiB and define numjobs to 4 to
154 fork 4 identical jobs. The result is 4 processes each randomly writing
155 to their own 64MiB file. Instead of using the above job file, you could
156 have given the parameters on the command line. For this case, you would
159 $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4
161 fio ships with a few example job files, you can also look there for
165 5.0 Detailed list of parameters
166 -------------------------------
168 This section describes in details each parameter associated with a job.
169 Some parameters take an option of a given type, such as an integer or
170 a string. The following types are used:
172 str String. This is a sequence of alpha characters.
173 int Integer. A whole number value, may be negative.
174 siint SI integer. A whole number value, which may contain a postfix
175 describing the base of the number. Accepted postfixes are k/m/g,
176 meaning kilo, mega, and giga. So if you want to specify 4096,
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.
179 If the option accepts an upper and lower range, use a colon ':'
180 or minus '-' to seperate such values. See irange.
181 bool Boolean. Usually parsed as an integer, however only defined for
182 true and false (1 and 0).
183 irange Integer range with postfix. Allows value range to be given, such
184 as 1024-4096. A colon may also be used as the seperator, eg
185 1k:4k. If the option allows two sets of ranges, they can be
186 specified with a ',' or '/' delimiter: 1k-4k/8k-32k. Also see
189 With the above in mind, here follows the complete list of fio job
192 name=str ASCII name of the job. This may be used to override the
193 name printed by fio for this job. Otherwise the job
194 name is used. On the command line this parameter has the
195 special purpose of also signaling the start of a new
198 description=str Text description of the job. Doesn't do anything except
199 dump this text description when this job is run. It's
202 directory=str Prefix filenames with this directory. Used to places files
203 in a different location than "./".
205 filename=str Fio normally makes up a filename based on the job name,
206 thread number, and file number. If you want to share
207 files between threads in a job or several jobs, specify
208 a filename for each of them to override the default. If
209 the ioengine used is 'net', the filename is the host and
210 port to connect to in the format of =host/port. If the
211 ioengine is file based, you can specify a number of files
212 by seperating the names with a ':' colon. So if you wanted
213 a job to open /dev/sda and /dev/sdb as the two working files,
214 you would use filename=/dev/sda:/dev/sdb. '-' is a reserved
215 name, meaning stdin or stdout. Which of the two depends
216 on the read/write direction set.
218 opendir=str Tell fio to recursively add any file it can find in this
219 directory and down the file system tree.
222 rw=str Type of io pattern. Accepted values are:
224 read Sequential reads
225 write Sequential writes
226 randwrite Random writes
227 randread Random reads
228 rw Sequential mixed reads and writes
229 randrw Random mixed reads and writes
231 For the mixed io types, the default is to split them 50/50.
232 For certain types of io the result may still be skewed a bit,
233 since the speed may be different. It is possible to specify
234 a number of IO's to do before getting a new offset - this
235 is only useful for random IO, where fio would normally
236 generate a new random offset for every IO. If you append
237 eg 8 to randread, you would get a new random offset for
238 every 8 IO's. The result would be a seek for only every 8
239 IO's, instead of for every IO. Use rw=randread:8 to specify
242 randrepeat=bool For random IO workloads, seed the generator in a predictable
243 way so that results are repeatable across repetitions.
245 fadvise_hint=bool By default, fio will use fadvise() to advise the kernel
246 on what IO patterns it is likely to issue. Sometimes you
247 want to test specific IO patterns without telling the
248 kernel about it, in which case you can disable this option.
249 If set, fio will use POSIX_FADV_SEQUENTIAL for sequential
250 IO and POSIX_FADV_RANDOM for random IO.
252 size=siint The total size of file io for this job. This may describe
253 the size of the single file the job uses, or it may be
254 divided between the number of files in the job. If the
255 file already exists, the file size will be adjusted to this
256 size if larger than the current file size. If this parameter
257 is not given and the file exists, the file size will be used.
259 filesize=siint Individual file sizes. May be a range, in which case fio
260 will select sizes for files at random within the given range
261 and limited to 'size' in total (if that is given). If not
262 given, each created file is the same size.
265 bs=siint The block size used for the io units. Defaults to 4k. Values
266 can be given for both read and writes. If a single siint is
267 given, it will apply to both. If a second siint is specified
268 after a comma, it will apply to writes only. In other words,
269 the format is either bs=read_and_write or bs=read,write.
270 bs=4k,8k will thus use 4k blocks for reads, and 8k blocks
271 for writes. If you only wish to set the write size, you
272 can do so by passing an empty read size - bs=,8k will set
273 8k for writes and leave the read default value.
275 blocksize_range=irange
276 bsrange=irange Instead of giving a single block size, specify a range
277 and fio will mix the issued io block sizes. The issued
278 io unit will always be a multiple of the minimum value
279 given (also see bs_unaligned). Applies to both reads and
280 writes, however a second range can be given after a comma.
284 bs_unaligned If this option is given, any byte size value within bsrange
285 may be used as a block range. This typically wont work with
286 direct IO, as that normally requires sector alignment.
288 zero_buffers If this option is given, fio will init the IO buffers to
289 all zeroes. The default is to fill them with random data.
291 nrfiles=int Number of files to use for this job. Defaults to 1.
293 openfiles=int Number of files to keep open at the same time. Defaults to
294 the same as nrfiles, can be set smaller to limit the number
297 file_service_type=str Defines how fio decides which file from a job to
298 service next. The following types are defined:
300 random Just choose a file at random.
302 roundrobin Round robin over open files. This
305 The string can have a number appended, indicating how
306 often to switch to a new file. So if option random:4 is
307 given, fio will switch to a new random file after 4 ios
310 ioengine=str Defines how the job issues io to the file. The following
313 sync Basic read(2) or write(2) io. lseek(2) is
314 used to position the io location.
316 libaio Linux native asynchronous io.
318 posixaio glibc posix asynchronous io.
320 mmap File is memory mapped and data copied
321 to/from using memcpy(3).
323 splice splice(2) is used to transfer the data and
324 vmsplice(2) to transfer data from user
327 syslet-rw Use the syslet system calls to make
328 regular read/write async.
330 sg SCSI generic sg v3 io. May either be
331 synchronous using the SG_IO ioctl, or if
332 the target is an sg character device
333 we use read(2) and write(2) for asynchronous
336 null Doesn't transfer any data, just pretends
337 to. This is mainly used to exercise fio
338 itself and for debugging/testing purposes.
340 net Transfer over the network to given host:port.
341 'filename' must be set appropriately to
342 filename=host/port regardless of send
343 or receive, if the latter only the port
346 cpu Doesn't transfer any data, but burns CPU
347 cycles according to the cpuload= and
348 cpucycle= options. Setting cpuload=85
349 will cause that job to do nothing but burn
352 guasi The GUASI IO engine is the Generic Userspace
353 Asyncronous Syscall Interface approach
356 http://www.xmailserver.org/guasi-lib.html
358 for more info on GUASI.
360 external Prefix to specify loading an external
361 IO engine object file. Append the engine
362 filename, eg ioengine=external:/tmp/foo.o
363 to load ioengine foo.o in /tmp.
365 iodepth=int This defines how many io units to keep in flight against
366 the file. The default is 1 for each file defined in this
367 job, can be overridden with a larger value for higher
370 iodepth_batch=int This defines how many pieces of IO to submit at once.
371 It defaults to the same as iodepth, but can be set lower
374 iodepth_low=int The low water mark indicating when to start filling
375 the queue again. Defaults to the same as iodepth, meaning
376 that fio will attempt to keep the queue full at all times.
377 If iodepth is set to eg 16 and iodepth_low is set to 4, then
378 after fio has filled the queue of 16 requests, it will let
379 the depth drain down to 4 before starting to fill it again.
381 direct=bool If value is true, use non-buffered io. This is usually
384 buffered=bool If value is true, use buffered io. This is the opposite
385 of the 'direct' option. Defaults to true.
387 offset=siint Start io at the given offset in the file. The data before
388 the given offset will not be touched. This effectively
389 caps the file size at real_size - offset.
391 fsync=int If writing to a file, issue a sync of the dirty data
392 for every number of blocks given. For example, if you give
393 32 as a parameter, fio will sync the file for every 32
394 writes issued. If fio is using non-buffered io, we may
395 not sync the file. The exception is the sg io engine, which
396 synchronizes the disk cache anyway.
398 overwrite=bool If writing to a file, setup the file first and do overwrites.
400 end_fsync=bool If true, fsync file contents when the job exits.
402 fsync_on_close=bool If true, fio will fsync() a dirty file on close.
403 This differs from end_fsync in that it will happen on every
404 file close, not just at the end of the job.
406 rwmixcycle=int Value in milliseconds describing how often to switch between
407 reads and writes for a mixed workload. The default is
410 rwmixread=int How large a percentage of the mix should be reads.
412 rwmixwrite=int How large a percentage of the mix should be writes. If both
413 rwmixread and rwmixwrite is given and the values do not add
414 up to 100%, the latter of the two will be used to override
417 norandommap Normally fio will cover every block of the file when doing
418 random IO. If this option is given, fio will just get a
419 new random offset without looking at past io history. This
420 means that some blocks may not be read or written, and that
421 some blocks may be read/written more than once. This option
422 is mutually exclusive with verify= for that reason.
424 nice=int Run the job with the given nice value. See man nice(2).
426 prio=int Set the io priority value of this job. Linux limits us to
427 a positive value between 0 and 7, with 0 being the highest.
430 prioclass=int Set the io priority class. See man ionice(1).
432 thinktime=int Stall the job x microseconds after an io has completed before
433 issuing the next. May be used to simulate processing being
434 done by an application. See thinktime_blocks and
438 Only valid if thinktime is set - pretend to spend CPU time
439 doing something with the data received, before falling back
440 to sleeping for the rest of the period specified by
444 Only valid if thinktime is set - control how many blocks
445 to issue, before waiting 'thinktime' usecs. If not set,
446 defaults to 1 which will make fio wait 'thinktime' usecs
449 rate=int Cap the bandwidth used by this job to this number of KiB/sec.
451 ratemin=int Tell fio to do whatever it can to maintain at least this
452 bandwidth. Failing to meet this requirement, will cause
455 rate_iops=int Cap the bandwidth to this number of IOPS. Basically the same
456 as rate, just specified independently of bandwidth. If the
457 job is given a block size range instead of a fixed value,
458 the smallest block size is used as the metric.
460 rate_iops_min=int If fio doesn't meet this rate of IO, it will cause
463 ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number
466 cpumask=int Set the CPU affinity of this job. The parameter given is a
467 bitmask of allowed CPU's the job may run on. See man
468 sched_setaffinity(2). This may not work on all supported
469 operating systems or kernel versions.
471 startdelay=int Start this job the specified number of seconds after fio
472 has started. Only useful if the job file contains several
473 jobs, and you want to delay starting some jobs to a certain
476 runtime=int Tell fio to terminate processing after the specified number
477 of seconds. It can be quite hard to determine for how long
478 a specified job will run, so this parameter is handy to
479 cap the total runtime to a given time.
481 time_based If set, fio will run for the duration of the runtime
482 specified even if the file(s) are completey read or
483 written. It will simply loop over the same workload
484 as many times as the runtime allows.
486 invalidate=bool Invalidate the buffer/page cache parts for this file prior
487 to starting io. Defaults to true.
489 sync=bool Use sync io for buffered writes. For the majority of the
490 io engines, this means using O_SYNC.
493 mem=str Fio can use various types of memory as the io unit buffer.
494 The allowed values are:
496 malloc Use memory from malloc(3) as the buffers.
498 shm Use shared memory as the buffers. Allocated
501 shmhuge Same as shm, but use huge pages as backing.
503 mmap Use mmap to allocate buffers. May either be
504 anonymous memory, or can be file backed if
505 a filename is given after the option. The
506 format is mem=mmap:/path/to/file.
508 mmaphuge Use a memory mapped huge file as the buffer
509 backing. Append filename after mmaphuge, ala
510 mem=mmaphuge:/hugetlbfs/file
512 The area allocated is a function of the maximum allowed
513 bs size for the job, multiplied by the io depth given. Note
514 that for shmhuge and mmaphuge to work, the system must have
515 free huge pages allocated. This can normally be checked
516 and set by reading/writing /proc/sys/vm/nr_hugepages on a
517 Linux system. Fio assumes a huge page is 4MiB in size. So
518 to calculate the number of huge pages you need for a given
519 job file, add up the io depth of all jobs (normally one unless
520 iodepth= is used) and multiply by the maximum bs set. Then
521 divide that number by the huge page size. You can see the
522 size of the huge pages in /proc/meminfo. If no huge pages
523 are allocated by having a non-zero number in nr_hugepages,
524 using mmaphuge or shmhuge will fail. Also see hugepage-size.
526 mmaphuge also needs to have hugetlbfs mounted and the file
527 location should point there. So if it's mounted in /huge,
528 you would use mem=mmaphuge:/huge/somefile.
531 Defines the size of a huge page. Must at least be equal
532 to the system setting, see /proc/meminfo. Defaults to 4MiB.
533 Should probably always be a multiple of megabytes, so using
534 hugepage-size=Xm is the preferred way to set this to avoid
535 setting a non-pow-2 bad value.
537 exitall When one job finishes, terminate the rest. The default is
538 to wait for each job to finish, sometimes that is not the
541 bwavgtime=int Average the calculated bandwidth over the given time. Value
542 is specified in milliseconds.
544 create_serialize=bool If true, serialize the file creating for the jobs.
545 This may be handy to avoid interleaving of data
546 files, which may greatly depend on the filesystem
547 used and even the number of processors in the system.
549 create_fsync=bool fsync the data file after creation. This is the
552 unlink=bool Unlink the job files when done. Not the default, as repeated
553 runs of that job would then waste time recreating the fileset
556 loops=int Run the specified number of iterations of this job. Used
557 to repeat the same workload a given number of times. Defaults
560 verify=str If writing to a file, fio can verify the file contents
561 after each iteration of the job. The allowed values are:
563 md5 Use an md5 sum of the data area and store
564 it in the header of each block.
566 crc32 Use a crc32 sum of the data area and store
567 it in the header of each block.
569 null Only pretend to verify. Useful for testing
570 internals with ioengine=null, not for much
573 This option can be used for repeated burn-in tests of a
574 system to make sure that the written data is also
577 verifysort=bool If set, fio will sort written verify blocks when it deems
578 it faster to read them back in a sorted manner. This is
579 often the case when overwriting an existing file, since
580 the blocks are already laid out in the file system. You
581 can ignore this option unless doing huge amounts of really
582 fast IO where the red-black tree sorting CPU time becomes
585 stonewall Wait for preceeding jobs in the job file to exit, before
586 starting this one. Can be used to insert serialization
587 points in the job file. A stone wall also implies starting
588 a new reporting group.
590 new_group Start a new reporting group. If this option isn't given,
591 jobs in a file will be part of the same reporting group
592 unless seperated by a stone wall (or if it's a group
593 by itself, with the numjobs option).
595 numjobs=int Create the specified number of clones of this job. May be
596 used to setup a larger number of threads/processes doing
597 the same thing. We regard that grouping of jobs as a
600 group_reporting If 'numjobs' is set, it may be interesting to display
601 statistics for the group as a whole instead of for each
602 individual job. This is especially true of 'numjobs' is
603 large, looking at individual thread/process output quickly
604 becomes unwieldy. If 'group_reporting' is specified, fio
605 will show the final report per-group instead of per-job.
607 thread fio defaults to forking jobs, however if this option is
608 given, fio will use pthread_create(3) to create threads
611 zonesize=siint Divide a file into zones of the specified size. See zoneskip.
613 zoneskip=siint Skip the specified number of bytes when zonesize data has
614 been read. The two zone options can be used to only do
615 io on zones of a file.
617 write_iolog=str Write the issued io patterns to the specified file. See
620 read_iolog=str Open an iolog with the specified file name and replay the
621 io patterns it contains. This can be used to store a
622 workload and replay it sometime later. The iolog given
623 may also be a blktrace binary file, which allows fio
624 to replay a workload captured by blktrace. See blktrace
625 for how to capture such logging data. For blktrace replay,
626 the file needs to be turned into a blkparse binary data
627 file first (blktrace <device> -d file_for_fio.bin).
629 write_bw_log If given, write a bandwidth log of the jobs in this job
630 file. Can be used to store data of the bandwidth of the
631 jobs in their lifetime. The included fio_generate_plots
632 script uses gnuplot to turn these text files into nice
635 write_lat_log Same as write_bw_log, except that this option stores io
636 completion latencies instead.
638 lockmem=siint Pin down the specified amount of memory with mlock(2). Can
639 potentially be used instead of removing memory or booting
640 with less memory to simulate a smaller amount of memory.
642 exec_prerun=str Before running this job, issue the command specified
645 exec_postrun=str After the job completes, issue the command specified
648 ioscheduler=str Attempt to switch the device hosting the file to the specified
649 io scheduler before running.
651 cpuload=int If the job is a CPU cycle eater, attempt to use the specified
652 percentage of CPU cycles.
654 cpuchunks=int If the job is a CPU cycle eater, split the load into
655 cycles of the given time. In milliseconds.
657 disk_util=bool Generate disk utilization statistics, if the platform
658 supports it. Defaults to on.
661 6.0 Interpreting the output
662 ---------------------------
664 fio spits out a lot of output. While running, fio will display the
665 status of the jobs created. An example of that would be:
667 Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
669 The characters inside the square brackets denote the current status of
670 each thread. The possible values (in typical life cycle order) are:
674 P Thread setup, but not started.
676 I Thread initialized, waiting.
677 R Running, doing sequential reads.
678 r Running, doing random reads.
679 W Running, doing sequential writes.
680 w Running, doing random writes.
681 M Running, doing mixed sequential reads/writes.
682 m Running, doing mixed random reads/writes.
683 F Running, currently waiting for fsync()
684 V Running, doing verification of written data.
685 E Thread exited, not reaped by main thread yet.
688 The other values are fairly self explanatory - number of threads
689 currently running and doing io, rate of io since last check, and the estimated
690 completion percentage and time for the running group. It's impossible to
691 estimate runtime of the following groups (if any).
693 When fio is done (or interrupted by ctrl-c), it will show the data for
694 each thread, group of threads, and disks in that order. For each data
695 direction, the output looks like:
697 Client1 (g=0): err= 0:
698 write: io= 32MiB, bw= 666KiB/s, runt= 50320msec
699 slat (msec): min= 0, max= 136, avg= 0.03, stdev= 1.92
700 clat (msec): min= 0, max= 631, avg=48.50, stdev=86.82
701 bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, stdev=681.68
702 cpu : usr=1.49%, sys=0.25%, ctx=7969
703 IO depths : 1=0.1%, 2=0.3%, 4=0.5%, 8=99.0%, 16=0.0%, 32=0.0%, >32=0.0%
704 issued r/w: total=0/32768, short=0/0
705 lat (msec): 2=1.6%, 4=0.0%, 10=3.2%, 20=12.8%, 50=38.4%, 100=24.8%,
706 lat (msec): 250=15.2%, 500=0.0%, 750=0.0%, 1000=0.0%, >=2048=0.0%
708 The client number is printed, along with the group id and error of that
709 thread. Below is the io statistics, here for writes. In the order listed,
712 io= Number of megabytes io performed
713 bw= Average bandwidth rate
714 runt= The runtime of that thread
715 slat= Submission latency (avg being the average, stdev being the
716 standard deviation). This is the time it took to submit
717 the io. For sync io, the slat is really the completion
718 latency, since queue/complete is one operation there.
719 clat= Completion latency. Same names as slat, this denotes the
720 time from submission to completion of the io pieces. For
721 sync io, clat will usually be equal (or very close) to 0,
722 as the time from submit to complete is basically just
723 CPU time (io has already been done, see slat explanation).
724 bw= Bandwidth. Same names as the xlat stats, but also includes
725 an approximate percentage of total aggregate bandwidth
726 this thread received in this group. This last value is
727 only really useful if the threads in this group are on the
728 same disk, since they are then competing for disk access.
729 cpu= CPU usage. User and system time, along with the number
730 of context switches this thread went through.
731 IO depths= The distribution of io depths over the job life time. The
732 numbers are divided into powers of 2, so for example the
733 16= entries includes depths up to that value but higher
734 than the previous entry. In other words, it covers the
736 IO issued= The number of read/write requests issued, and how many
738 IO latencies= The distribution of IO completion latencies. This is the
739 time from when IO leaves fio and when it gets completed.
740 The numbers follow the same pattern as the IO depths,
741 meaning that 2=1.6% means that 1.6% of the IO completed
742 within 2 msecs, 20=12.8% means that 12.8% of the IO
743 took more than 10 msecs, but less than (or equal to) 20 msecs.
745 After each client has been listed, the group statistics are printed. They
748 Run status group 0 (all jobs):
749 READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec
750 WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec
752 For each data direction, it prints:
754 io= Number of megabytes io performed.
755 aggrb= Aggregate bandwidth of threads in this group.
756 minb= The minimum average bandwidth a thread saw.
757 maxb= The maximum average bandwidth a thread saw.
758 mint= The smallest runtime of the threads in that group.
759 maxt= The longest runtime of the threads in that group.
761 And finally, the disk statistics are printed. They will look like this:
763 Disk stats (read/write):
764 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
766 Each value is printed for both reads and writes, with reads first. The
769 ios= Number of ios performed by all groups.
770 merge= Number of merges io the io scheduler.
771 ticks= Number of ticks we kept the disk busy.
772 io_queue= Total time spent in the disk queue.
773 util= The disk utilization. A value of 100% means we kept the disk
774 busy constantly, 50% would be a disk idling half of the time.
780 For scripted usage where you typically want to generate tables or graphs
781 of the results, fio can output the results in a semicolon separated format.
782 The format is one long line of values, such as:
784 client1;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%
785 ;0.0%;0.0%;0.0%;0.0%;0.0%
787 Split up, the format is as follows:
789 jobname, groupid, error
791 KiB IO, bandwidth (KiB/sec), runtime (msec)
792 Submission latency: min, max, mean, deviation
793 Completion latency: min, max, mean, deviation
794 Bw: min, max, aggregate percentage of total, mean, deviation
796 KiB IO, bandwidth (KiB/sec), runtime (msec)
797 Submission latency: min, max, mean, deviation
798 Completion latency: min, max, mean, deviation
799 Bw: min, max, aggregate percentage of total, mean, deviation
800 CPU usage: user, system, context switches
801 IO depths: <=1, 2, 4, 8, 16, 32, >=64
802 IO latencies: <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, >=2000