1 .TH fio 1 "October 2013" "User Manual"
3 fio \- flexible I/O tester
6 [\fIoptions\fR] [\fIjobfile\fR]...
9 is a tool that will spawn a number of threads or processes doing a
10 particular type of I/O action as specified by the user.
11 The typical use of fio is to write a job file matching the I/O load
12 one wants to simulate.
15 .BI \-\-debug \fR=\fPtype
16 Enable verbose tracing of various fio actions. May be `all' for all types
17 or individual types separated by a comma (eg \-\-debug=io,file). `help' will
18 list all available tracing options.
20 .BI \-\-output \fR=\fPfilename
21 Write output to \fIfilename\fR.
23 .BI \-\-runtime \fR=\fPruntime
24 Limit run time to \fIruntime\fR seconds.
27 Generate per-job latency logs.
30 Generate per-job bandwidth logs.
33 Print statistics in a terse, semicolon-delimited format.
36 Print statistics in selected mode AND terse, semicolon-delimited format.
39 Display version information and exit.
41 .BI \-\-terse\-version \fR=\fPversion
42 Set terse version output format (Current version 3, or older version 2).
45 Display usage information and exit.
48 Perform test and validation of internal CPU clock
50 .BI \-\-crctest[\fR=\fPtest]
51 Test the speed of the builtin checksumming functions. If no argument is given,
52 all of them are tested. Or a comma separated list can be passed, in which
53 case the given ones are tested.
55 .BI \-\-cmdhelp \fR=\fPcommand
56 Print help information for \fIcommand\fR. May be `all' for all commands.
58 .BI \-\-enghelp \fR=\fPioengine[,command]
59 List all commands defined by \fIioengine\fR, or print help for \fIcommand\fR defined by \fIioengine\fR.
61 .BI \-\-showcmd \fR=\fPjobfile
62 Convert \fIjobfile\fR to a set of command-line options.
64 .BI \-\-eta \fR=\fPwhen
65 Specifies when real-time ETA estimate should be printed. \fIwhen\fR may
66 be one of `always', `never' or `auto'.
68 .BI \-\-eta\-newline \fR=\fPtime
69 Force an ETA newline for every `time` period passed.
71 .BI \-\-status\-interval \fR=\fPtime
72 Report full output status every `time` period passed.
75 Turn on safety read-only checks, preventing any attempted write.
77 .BI \-\-section \fR=\fPsec
78 Only run section \fIsec\fR from job file. This option can be used multiple times to add more sections to run.
80 .BI \-\-alloc\-size \fR=\fPkb
81 Set the internal smalloc pool size to \fIkb\fP kilobytes.
83 .BI \-\-warnings\-fatal
84 All fio parser warnings are fatal, causing fio to exit with an error.
86 .BI \-\-max\-jobs \fR=\fPnr
87 Set the maximum allowed number of jobs (threads/processes) to support.
89 .BI \-\-server \fR=\fPargs
90 Start a backend server, with \fIargs\fP specifying what to listen to. See client/server section.
92 .BI \-\-daemonize \fR=\fPpidfile
93 Background a fio server, writing the pid to the given pid file.
95 .BI \-\-client \fR=\fPhost
96 Instead of running the jobs locally, send and run them on the given host.
98 .BI \-\-idle\-prof \fR=\fPoption
99 Report cpu idleness on a system or percpu basis (\fIoption\fP=system,percpu) or run unit work calibration only (\fIoption\fP=calibrate).
100 .SH "JOB FILE FORMAT"
101 Job files are in `ini' format. They consist of one or more
102 job definitions, which begin with a job name in square brackets and
103 extend to the next job name. The job name can be any ASCII string
104 except `global', which has a special meaning. Following the job name is
105 a sequence of zero or more parameters, one per line, that define the
106 behavior of the job. Any line starting with a `;' or `#' character is
107 considered a comment and ignored.
109 If \fIjobfile\fR is specified as `-', the job file will be read from
112 The global section contains default parameters for jobs specified in the
113 job file. A job is only affected by global sections residing above it,
114 and there may be any number of global sections. Specific job definitions
115 may override any parameter set in global sections.
118 Some parameters may take arguments of a specific type. The types used are:
121 String: a sequence of alphanumeric characters.
124 SI integer: a whole number, possibly containing a suffix denoting the base unit
125 of the value. Accepted suffixes are `k', 'M', 'G', 'T', and 'P', denoting
126 kilo (1024), mega (1024^2), giga (1024^3), tera (1024^4), and peta (1024^5)
127 respectively. If prefixed with '0x', the value is assumed to be base 16
128 (hexadecimal). A suffix may include a trailing 'b', for instance 'kb' is
129 identical to 'k'. You can specify a base 10 value by using 'KiB', 'MiB','GiB',
130 etc. This is useful for disk drives where values are often given in base 10
131 values. Specifying '30GiB' will get you 30*1000^3 bytes.
132 When specifying times the default suffix meaning changes, still denoting the
133 base unit of the value, but accepted suffixes are 'D' (days), 'H' (hours), 'M'
134 (minutes), 'S' Seconds, 'ms' (or msec) milli seconds, 'us' (or 'usec') micro
135 seconds. Time values without a unit specify seconds.
136 The suffixes are not case sensitive.
139 Boolean: a true or false value. `0' denotes false, `1' denotes true.
142 Integer range: a range of integers specified in the format
143 \fIlower\fR:\fIupper\fR or \fIlower\fR\-\fIupper\fR. \fIlower\fR and
144 \fIupper\fR may contain a suffix as described above. If an option allows two
145 sets of ranges, they are separated with a `,' or `/' character. For example:
149 List of floating numbers: A list of floating numbers, separated by
154 May be used to override the job name. On the command line, this parameter
155 has the special purpose of signalling the start of a new job.
157 .BI description \fR=\fPstr
158 Human-readable description of the job. It is printed when the job is run, but
159 otherwise has no special purpose.
161 .BI directory \fR=\fPstr
162 Prefix filenames with this directory. Used to place files in a location other
164 You can specify a number of directories by separating the names with a ':'
165 character. These directories will be assigned equally distributed to job clones
166 creates with \fInumjobs\fR as long as they are using generated filenames.
167 If specific \fIfilename(s)\fR are set fio will use the first listed directory,
168 and thereby matching the \fIfilename\fR semantic which generates a file each
169 clone if not specified, but let all clones use the same if set. See
170 \fIfilename\fR for considerations regarding escaping certain characters on
173 .BI filename \fR=\fPstr
175 normally makes up a file name based on the job name, thread number, and file
176 number. If you want to share files between threads in a job or several jobs,
177 specify a \fIfilename\fR for each of them to override the default.
178 If the I/O engine is file-based, you can specify
179 a number of files by separating the names with a `:' character. `\-' is a
180 reserved name, meaning stdin or stdout, depending on the read/write direction
181 set. On Windows, disk devices are accessed as \\.\PhysicalDrive0 for the first
182 device, \\.\PhysicalDrive1 for the second etc. Note: Windows and FreeBSD
183 prevent write access to areas of the disk containing in-use data
184 (e.g. filesystems). If the wanted filename does need to include a colon, then
185 escape that with a '\\' character. For instance, if the filename is
186 "/dev/dsk/foo@3,0:c", then you would use filename="/dev/dsk/foo@3,0\\:c".
188 .BI filename_format \fR=\fPstr
189 If sharing multiple files between jobs, it is usually necessary to have
190 fio generate the exact names that you want. By default, fio will name a file
191 based on the default file format specification of
192 \fBjobname.jobnumber.filenumber\fP. With this option, that can be
193 customized. Fio will recognize and replace the following keywords in this
199 The name of the worker thread or process.
202 The incremental number of the worker thread or process.
205 The incremental number of the file for that worker thread or process.
208 To have dependent jobs share a set of files, this option can be set to
209 have fio generate filenames that are shared between the two. For instance,
210 if \fBtestfiles.$filenum\fR is specified, file number 4 for any job will
211 be named \fBtestfiles.4\fR. The default of \fB$jobname.$jobnum.$filenum\fR
212 will be used if no other format specifier is given.
216 .BI lockfile \fR=\fPstr
217 Fio defaults to not locking any files before it does IO to them. If a file or
218 file descriptor is shared, fio can serialize IO to that file to make the end
219 result consistent. This is usual for emulating real workloads that share files.
225 No locking. This is the default.
228 Only one thread or process may do IO at a time, excluding all others.
231 Read-write locking on the file. Many readers may access the file at the same
232 time, but writes get exclusive access.
236 .BI opendir \fR=\fPstr
237 Recursively open any files below directory \fIstr\fR.
239 .BI readwrite \fR=\fPstr "\fR,\fP rw" \fR=\fPstr
240 Type of I/O pattern. Accepted values are:
251 Sequential trim (Linux block devices only).
260 Random trim (Linux block devices only).
263 Mixed sequential reads and writes.
266 Mixed random reads and writes.
269 For mixed I/O, the default split is 50/50. For certain types of io the result
270 may still be skewed a bit, since the speed may be different. It is possible to
271 specify a number of IO's to do before getting a new offset, this is done by
272 appending a `:\fI<nr>\fR to the end of the string given. For a random read, it
273 would look like \fBrw=randread:8\fR for passing in an offset modifier with a
274 value of 8. If the postfix is used with a sequential IO pattern, then the value
275 specified will be added to the generated offset for each IO. For instance,
276 using \fBrw=write:4k\fR will skip 4k for every write. It turns sequential IO
277 into sequential IO with holes. See the \fBrw_sequencer\fR option.
280 .BI rw_sequencer \fR=\fPstr
281 If an offset modifier is given by appending a number to the \fBrw=<str>\fR line,
282 then this option controls how that number modifies the IO offset being
283 generated. Accepted values are:
288 Generate sequential offset
291 Generate the same offset
294 \fBsequential\fR is only useful for random IO, where fio would normally
295 generate a new random offset for every IO. If you append eg 8 to randread, you
296 would get a new random offset for every 8 IO's. The result would be a seek for
297 only every 8 IO's, instead of for every IO. Use \fBrw=randread:8\fR to specify
298 that. As sequential IO is already sequential, setting \fBsequential\fR for that
299 would not result in any differences. \fBidentical\fR behaves in a similar
300 fashion, except it sends the same offset 8 number of times before generating a
305 .BI kb_base \fR=\fPint
306 The base unit for a kilobyte. The defacto base is 2^10, 1024. Storage
307 manufacturers like to use 10^3 or 1000 as a base ten unit instead, for obvious
308 reasons. Allowed values are 1024 or 1000, with 1024 being the default.
310 .BI unified_rw_reporting \fR=\fPbool
311 Fio normally reports statistics on a per data direction basis, meaning that
312 read, write, and trim are accounted and reported separately. If this option is
313 set fio sums the results and reports them as "mixed" instead.
315 .BI randrepeat \fR=\fPbool
316 Seed the random number generator used for random I/O patterns in a predictable
317 way so the pattern is repeatable across runs. Default: true.
319 .BI allrandrepeat \fR=\fPbool
320 Seed all random number generators in a predictable way so results are
321 repeatable across runs. Default: false.
323 .BI randseed \fR=\fPint
324 Seed the random number generators based on this seed value, to be able to
325 control what sequence of output is being generated. If not set, the random
326 sequence depends on the \fBrandrepeat\fR setting.
328 .BI use_os_rand \fR=\fPbool
329 Fio can either use the random generator supplied by the OS to generate random
330 offsets, or it can use its own internal generator (based on Tausworthe).
331 Default is to use the internal generator, which is often of better quality and
332 faster. Default: false.
334 .BI fallocate \fR=\fPstr
335 Whether pre-allocation is performed when laying down files. Accepted values
341 Do not pre-allocate space.
344 Pre-allocate via \fBposix_fallocate\fR\|(3).
347 Pre-allocate via \fBfallocate\fR\|(2) with FALLOC_FL_KEEP_SIZE set.
350 Backward-compatible alias for 'none'.
353 Backward-compatible alias for 'posix'.
356 May not be available on all supported platforms. 'keep' is only
357 available on Linux. If using ZFS on Solaris this must be set to 'none'
358 because ZFS doesn't support it. Default: 'posix'.
361 .BI fadvise_hint \fR=\fPbool
362 Use \fBposix_fadvise\fR\|(2) to advise the kernel what I/O patterns
363 are likely to be issued. Default: true.
366 Total size of I/O for this job. \fBfio\fR will run until this many bytes have
367 been transferred, unless limited by other options (\fBruntime\fR, for instance).
368 Unless \fBnrfiles\fR and \fBfilesize\fR options are given, this amount will be
369 divided between the available files for the job. If not set, fio will use the
370 full size of the given files or devices. If the files do not exist, size
371 must be given. It is also possible to give size as a percentage between 1 and
372 100. If size=20% is given, fio will use 20% of the full size of the given
375 .BI io_limit \fR=\fPint
376 Normally fio operates within the region set by \fBsize\fR, which means that
377 the \fBsize\fR option sets both the region and size of IO to be performed.
378 Sometimes that is not what you want. With this option, it is possible to
379 define just the amount of IO that fio should do. For instance, if \fBsize\fR
380 is set to 20G and \fBio_limit\fR is set to 5G, fio will perform IO within
381 the first 20G but exit when 5G have been done.
383 .BI fill_device \fR=\fPbool "\fR,\fB fill_fs" \fR=\fPbool
384 Sets size to something really large and waits for ENOSPC (no space left on
385 device) as the terminating condition. Only makes sense with sequential write.
386 For a read workload, the mount point will be filled first then IO started on
387 the result. This option doesn't make sense if operating on a raw device node,
388 since the size of that is already known by the file system. Additionally,
389 writing beyond end-of-device will not return ENOSPC there.
391 .BI filesize \fR=\fPirange
392 Individual file sizes. May be a range, in which case \fBfio\fR will select sizes
393 for files at random within the given range, limited to \fBsize\fR in total (if
394 that is given). If \fBfilesize\fR is not specified, each created file is the
397 .BI file_append \fR=\fPbool
398 Perform IO after the end of the file. Normally fio will operate within the
399 size of a file. If this option is set, then fio will append to the file
400 instead. This has identical behavior to setting \fRoffset\fP to the size
401 of a file. This option is ignored on non-regular files.
403 .BI blocksize \fR=\fPint[,int] "\fR,\fB bs" \fR=\fPint[,int]
404 Block size for I/O units. Default: 4k. Values for reads, writes, and trims
405 can be specified separately in the format \fIread\fR,\fIwrite\fR,\fItrim\fR
406 either of which may be empty to leave that value at its default. If a trailing
407 comma isn't given, the remainder will inherit the last value set.
409 .BI blocksize_range \fR=\fPirange[,irange] "\fR,\fB bsrange" \fR=\fPirange[,irange]
410 Specify a range of I/O block sizes. The issued I/O unit will always be a
411 multiple of the minimum size, unless \fBblocksize_unaligned\fR is set. Applies
412 to both reads and writes if only one range is given, but can be specified
413 separately with a comma separating the values. Example: bsrange=1k-4k,2k-8k.
414 Also (see \fBblocksize\fR).
416 .BI bssplit \fR=\fPstr
417 This option allows even finer grained control of the block sizes issued,
418 not just even splits between them. With this option, you can weight various
419 block sizes for exact control of the issued IO for a job that has mixed
420 block sizes. The format of the option is bssplit=blocksize/percentage,
421 optionally adding as many definitions as needed separated by a colon.
422 Example: bssplit=4k/10:64k/50:32k/40 would issue 50% 64k blocks, 10% 4k
423 blocks and 40% 32k blocks. \fBbssplit\fR also supports giving separate
424 splits to reads and writes. The format is identical to what the
425 \fBbs\fR option accepts, the read and write parts are separated with a
428 .B blocksize_unaligned\fR,\fP bs_unaligned
429 If set, any size in \fBblocksize_range\fR may be used. This typically won't
430 work with direct I/O, as that normally requires sector alignment.
432 .BI blockalign \fR=\fPint[,int] "\fR,\fB ba" \fR=\fPint[,int]
433 At what boundary to align random IO offsets. Defaults to the same as 'blocksize'
434 the minimum blocksize given. Minimum alignment is typically 512b
435 for using direct IO, though it usually depends on the hardware block size.
436 This option is mutually exclusive with using a random map for files, so it
437 will turn off that option.
439 .BI bs_is_seq_rand \fR=\fPbool
440 If this option is set, fio will use the normal read,write blocksize settings as
441 sequential,random instead. Any random read or write will use the WRITE
442 blocksize settings, and any sequential read or write will use the READ
446 Initialize buffers with all zeros. Default: fill buffers with random data.
447 The resulting IO buffers will not be completely zeroed, unless
448 \fPscramble_buffers\fR is also turned off.
451 If this option is given, fio will refill the IO buffers on every submit. The
452 default is to only fill it at init time and reuse that data. Only makes sense
453 if zero_buffers isn't specified, naturally. If data verification is enabled,
454 refill_buffers is also automatically enabled.
456 .BI scramble_buffers \fR=\fPbool
457 If \fBrefill_buffers\fR is too costly and the target is using data
458 deduplication, then setting this option will slightly modify the IO buffer
459 contents to defeat normal de-dupe attempts. This is not enough to defeat
460 more clever block compression attempts, but it will stop naive dedupe
461 of blocks. Default: true.
463 .BI buffer_compress_percentage \fR=\fPint
464 If this is set, then fio will attempt to provide IO buffer content (on WRITEs)
465 that compress to the specified level. Fio does this by providing a mix of
466 random data and zeroes. Note that this is per block size unit, for file/disk
467 wide compression level that matches this setting, you'll also want to set
468 \fBrefill_buffers\fR.
470 .BI buffer_compress_chunk \fR=\fPint
471 See \fBbuffer_compress_percentage\fR. This setting allows fio to manage how
472 big the ranges of random data and zeroed data is. Without this set, fio will
473 provide \fBbuffer_compress_percentage\fR of blocksize random data, followed by
474 the remaining zeroed. With this set to some chunk size smaller than the block
475 size, fio can alternate random and zeroed data throughout the IO buffer.
477 .BI buffer_pattern \fR=\fPstr
478 If set, fio will fill the IO buffers with this pattern. If not set, the contents
479 of IO buffers is defined by the other options related to buffer contents. The
480 setting can be any pattern of bytes, and can be prefixed with 0x for hex
481 values. It may also be a string, where the string must then be wrapped with
484 .BI nrfiles \fR=\fPint
485 Number of files to use for this job. Default: 1.
487 .BI openfiles \fR=\fPint
488 Number of files to keep open at the same time. Default: \fBnrfiles\fR.
490 .BI file_service_type \fR=\fPstr
491 Defines how files to service are selected. The following types are defined:
496 Choose a file at random.
499 Round robin over opened files (default).
502 Do each file in the set sequentially.
505 The number of I/Os to issue before switching to a new file can be specified by
506 appending `:\fIint\fR' to the service type.
509 .BI ioengine \fR=\fPstr
510 Defines how the job issues I/O. The following types are defined:
515 Basic \fBread\fR\|(2) or \fBwrite\fR\|(2) I/O. \fBfseek\fR\|(2) is used to
516 position the I/O location.
519 Basic \fBpread\fR\|(2) or \fBpwrite\fR\|(2) I/O.
522 Basic \fBreadv\fR\|(2) or \fBwritev\fR\|(2) I/O. Will emulate queuing by
523 coalescing adjacent IOs into a single submission.
526 Basic \fBpreadv\fR\|(2) or \fBpwritev\fR\|(2) I/O.
529 Linux native asynchronous I/O. This ioengine defines engine specific options.
532 POSIX asynchronous I/O using \fBaio_read\fR\|(3) and \fBaio_write\fR\|(3).
535 Solaris native asynchronous I/O.
538 Windows native asynchronous I/O.
541 File is memory mapped with \fBmmap\fR\|(2) and data copied using
545 \fBsplice\fR\|(2) is used to transfer the data and \fBvmsplice\fR\|(2) to
546 transfer data from user-space to the kernel.
549 Use the syslet system calls to make regular read/write asynchronous.
552 SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if
553 the target is an sg character device, we use \fBread\fR\|(2) and
554 \fBwrite\fR\|(2) for asynchronous I/O.
557 Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR
558 itself and for debugging and testing purposes.
561 Transfer over the network. The protocol to be used can be defined with the
562 \fBprotocol\fR parameter. Depending on the protocol, \fBfilename\fR,
563 \fBhostname\fR, \fBport\fR, or \fBlisten\fR must be specified.
564 This ioengine defines engine specific options.
567 Like \fBnet\fR, but uses \fBsplice\fR\|(2) and \fBvmsplice\fR\|(2) to map data
568 and send/receive. This ioengine defines engine specific options.
571 Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and
572 \fBcpucycles\fR parameters.
575 The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface
576 approach to asynchronous I/O.
578 See <http://www.xmailserver.org/guasi\-lib.html>.
581 The RDMA I/O engine supports both RDMA memory semantics (RDMA_WRITE/RDMA_READ)
582 and channel semantics (Send/Recv) for the InfiniBand, RoCE and iWARP protocols.
585 Loads an external I/O engine object file. Append the engine filename as
589 IO engine that does regular linux native fallocate call to simulate data
590 transfer as fio ioengine
592 DDIR_READ does fallocate(,mode = FALLOC_FL_KEEP_SIZE,)
594 DIR_WRITE does fallocate(,mode = 0)
596 DDIR_TRIM does fallocate(,mode = FALLOC_FL_KEEP_SIZE|FALLOC_FL_PUNCH_HOLE)
599 IO engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate defragment activity
600 request to DDIR_WRITE event
603 IO engine supporting direct access to Ceph Rados Block Devices (RBD) via librbd
604 without the need to use the kernel rbd driver. This ioengine defines engine specific
608 Using Glusterfs libgfapi sync interface to direct access to Glusterfs volumes without
609 having to go through FUSE. This ioengine defines engine specific
613 Using Glusterfs libgfapi async interface to direct access to Glusterfs volumes without
614 having to go through FUSE. This ioengine defines engine specific
618 Read and write through Hadoop (HDFS). The \fBfilename\fR option is used to
619 specify host,port of the hdfs name-node to connect. This engine interprets
620 offsets a little differently. In HDFS, files once created cannot be modified.
621 So random writes are not possible. To imitate this, libhdfs engine expects
622 bunch of small files to be created over HDFS, and engine will randomly pick a
623 file out of those files based on the offset generated by fio backend. (see the
624 example job file to create such files, use rw=write option). Please note, you
625 might want to set necessary environment variables to work with hdfs/libhdfs
631 .BI iodepth \fR=\fPint
632 Number of I/O units to keep in flight against the file. Note that increasing
633 iodepth beyond 1 will not affect synchronous ioengines (except for small
634 degress when verify_async is in use). Even async engines may impose OS
635 restrictions causing the desired depth not to be achieved. This may happen on
636 Linux when using libaio and not setting \fBdirect\fR=1, since buffered IO is
637 not async on that OS. Keep an eye on the IO depth distribution in the
638 fio output to verify that the achieved depth is as expected. Default: 1.
640 .BI iodepth_batch \fR=\fPint
641 Number of I/Os to submit at once. Default: \fBiodepth\fR.
643 .BI iodepth_batch_complete \fR=\fPint
644 This defines how many pieces of IO to retrieve at once. It defaults to 1 which
645 means that we'll ask for a minimum of 1 IO in the retrieval process from the
646 kernel. The IO retrieval will go on until we hit the limit set by
647 \fBiodepth_low\fR. If this variable is set to 0, then fio will always check for
648 completed events before queuing more IO. This helps reduce IO latency, at the
649 cost of more retrieval system calls.
651 .BI iodepth_low \fR=\fPint
652 Low watermark indicating when to start filling the queue again. Default:
655 .BI direct \fR=\fPbool
656 If true, use non-buffered I/O (usually O_DIRECT). Default: false.
658 .BI atomic \fR=\fPbool
659 If value is true, attempt to use atomic direct IO. Atomic writes are guaranteed
660 to be stable once acknowledged by the operating system. Only Linux supports
663 .BI buffered \fR=\fPbool
664 If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter.
667 .BI offset \fR=\fPint
668 Offset in the file to start I/O. Data before the offset will not be touched.
670 .BI offset_increment \fR=\fPint
671 If this is provided, then the real offset becomes the
672 offset + offset_increment * thread_number, where the thread number is a
673 counter that starts at 0 and is incremented for each sub-job (i.e. when
674 numjobs option is specified). This option is useful if there are several jobs
675 which are intended to operate on a file in parallel disjoint segments, with
676 even spacing between the starting points.
678 .BI number_ios \fR=\fPint
679 Fio will normally perform IOs until it has exhausted the size of the region
680 set by \fBsize\fR, or if it exhaust the allocated time (or hits an error
681 condition). With this setting, the range/size can be set independently of
682 the number of IOs to perform. When fio reaches this number, it will exit
683 normally and report status.
686 How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If
687 0, don't sync. Default: 0.
689 .BI fdatasync \fR=\fPint
690 Like \fBfsync\fR, but uses \fBfdatasync\fR\|(2) instead to only sync the
691 data parts of the file. Default: 0.
693 .BI write_barrier \fR=\fPint
694 Make every Nth write a barrier write.
696 .BI sync_file_range \fR=\fPstr:int
697 Use \fBsync_file_range\fR\|(2) for every \fRval\fP number of write operations. Fio will
698 track range of writes that have happened since the last \fBsync_file_range\fR\|(2) call.
699 \fRstr\fP can currently be one or more of:
703 SYNC_FILE_RANGE_WAIT_BEFORE
706 SYNC_FILE_RANGE_WRITE
709 SYNC_FILE_RANGE_WRITE
713 So if you do sync_file_range=wait_before,write:8, fio would use
714 \fBSYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE\fP for every 8 writes.
715 Also see the \fBsync_file_range\fR\|(2) man page. This option is Linux specific.
717 .BI overwrite \fR=\fPbool
718 If writing, setup the file first and do overwrites. Default: false.
720 .BI end_fsync \fR=\fPbool
721 Sync file contents when a write stage has completed. Default: false.
723 .BI fsync_on_close \fR=\fPbool
724 If true, sync file contents on close. This differs from \fBend_fsync\fR in that
725 it will happen on every close, not just at the end of the job. Default: false.
727 .BI rwmixread \fR=\fPint
728 Percentage of a mixed workload that should be reads. Default: 50.
730 .BI rwmixwrite \fR=\fPint
731 Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and
732 \fBrwmixwrite\fR are given and do not sum to 100%, the latter of the two
733 overrides the first. This may interfere with a given rate setting, if fio is
734 asked to limit reads or writes to a certain rate. If that is the case, then
735 the distribution may be skewed. Default: 50.
737 .BI random_distribution \fR=\fPstr:float
738 By default, fio will use a completely uniform random distribution when asked
739 to perform random IO. Sometimes it is useful to skew the distribution in
740 specific ways, ensuring that some parts of the data is more hot than others.
741 Fio includes the following distribution models:
745 Uniform random distribution
755 When using a zipf or pareto distribution, an input value is also needed to
756 define the access pattern. For zipf, this is the zipf theta. For pareto,
757 it's the pareto power. Fio includes a test program, genzipf, that can be
758 used visualize what the given input values will yield in terms of hit rates.
759 If you wanted to use zipf with a theta of 1.2, you would use
760 random_distribution=zipf:1.2 as the option. If a non-uniform model is used,
761 fio will disable use of the random map.
763 .BI percentage_random \fR=\fPint
764 For a random workload, set how big a percentage should be random. This defaults
765 to 100%, in which case the workload is fully random. It can be set from
766 anywhere from 0 to 100. Setting it to 0 would make the workload fully
767 sequential. It is possible to set different values for reads, writes, and
768 trim. To do so, simply use a comma separated list. See \fBblocksize\fR.
771 Normally \fBfio\fR will cover every block of the file when doing random I/O. If
772 this parameter is given, a new offset will be chosen without looking at past
773 I/O history. This parameter is mutually exclusive with \fBverify\fR.
775 .BI softrandommap \fR=\fPbool
776 See \fBnorandommap\fR. If fio runs with the random block map enabled and it
777 fails to allocate the map, if this option is set it will continue without a
778 random block map. As coverage will not be as complete as with random maps, this
779 option is disabled by default.
781 .BI random_generator \fR=\fPstr
782 Fio supports the following engines for generating IO offsets for random IO:
786 Strong 2^88 cycle random number generator
789 Linear feedback shift register generator
793 Tausworthe is a strong random number generator, but it requires tracking on the
794 side if we want to ensure that blocks are only read or written once. LFSR
795 guarantees that we never generate the same offset twice, and it's also less
796 computationally expensive. It's not a true random generator, however, though
797 for IO purposes it's typically good enough. LFSR only works with single block
798 sizes, not with workloads that use multiple block sizes. If used with such a
799 workload, fio may read or write some blocks multiple times.
802 Run job with given nice value. See \fBnice\fR\|(2).
805 Set I/O priority value of this job between 0 (highest) and 7 (lowest). See
808 .BI prioclass \fR=\fPint
809 Set I/O priority class. See \fBionice\fR\|(1).
811 .BI thinktime \fR=\fPint
812 Stall job for given number of microseconds between issuing I/Os.
814 .BI thinktime_spin \fR=\fPint
815 Pretend to spend CPU time for given number of microseconds, sleeping the rest
816 of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set.
818 .BI thinktime_blocks \fR=\fPint
819 Only valid if thinktime is set - control how many blocks to issue, before
820 waiting \fBthinktime\fR microseconds. If not set, defaults to 1 which will
821 make fio wait \fBthinktime\fR microseconds after every block. This
822 effectively makes any queue depth setting redundant, since no more than 1 IO
823 will be queued before we have to complete it and do our thinktime. In other
824 words, this setting effectively caps the queue depth if the latter is larger.
828 Cap bandwidth used by this job. The number is in bytes/sec, the normal postfix
829 rules apply. You can use \fBrate\fR=500k to limit reads and writes to 500k each,
830 or you can specify read and writes separately. Using \fBrate\fR=1m,500k would
831 limit reads to 1MB/sec and writes to 500KB/sec. Capping only reads or writes
832 can be done with \fBrate\fR=,500k or \fBrate\fR=500k,. The former will only
833 limit writes (to 500KB/sec), the latter will only limit reads.
835 .BI ratemin \fR=\fPint
836 Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth.
837 Failing to meet this requirement will cause the job to exit. The same format
838 as \fBrate\fR is used for read vs write separation.
840 .BI rate_iops \fR=\fPint
841 Cap the bandwidth to this number of IOPS. Basically the same as rate, just
842 specified independently of bandwidth. The same format as \fBrate\fR is used for
843 read vs write separation. If \fBblocksize\fR is a range, the smallest block
844 size is used as the metric.
846 .BI rate_iops_min \fR=\fPint
847 If this rate of I/O is not met, the job will exit. The same format as \fBrate\fR
848 is used for read vs write separation.
850 .BI ratecycle \fR=\fPint
851 Average bandwidth for \fBrate\fR and \fBratemin\fR over this number of
852 milliseconds. Default: 1000ms.
854 .BI latency_target \fR=\fPint
855 If set, fio will attempt to find the max performance point that the given
856 workload will run at while maintaining a latency below this target. The
857 values is given in microseconds. See \fBlatency_window\fR and
858 \fBlatency_percentile\fR.
860 .BI latency_window \fR=\fPint
861 Used with \fBlatency_target\fR to specify the sample window that the job
862 is run at varying queue depths to test the performance. The value is given
865 .BI latency_percentile \fR=\fPfloat
866 The percentage of IOs that must fall within the criteria specified by
867 \fBlatency_target\fR and \fBlatency_window\fR. If not set, this defaults
868 to 100.0, meaning that all IOs must be equal or below to the value set
869 by \fBlatency_target\fR.
871 .BI max_latency \fR=\fPint
872 If set, fio will exit the job if it exceeds this maximum latency. It will exit
875 .BI cpumask \fR=\fPint
876 Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job
877 may run on. See \fBsched_setaffinity\fR\|(2).
879 .BI cpus_allowed \fR=\fPstr
880 Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers.
882 .BI cpus_allowed_policy \fR=\fPstr
883 Set the policy of how fio distributes the CPUs specified by \fBcpus_allowed\fR
884 or \fBcpumask\fR. Two policies are supported:
889 All jobs will share the CPU set specified.
892 Each job will get a unique CPU from the CPU set.
895 \fBshared\fR is the default behaviour, if the option isn't specified. If
896 \fBsplit\fR is specified, then fio will assign one cpu per job. If not enough
897 CPUs are given for the jobs listed, then fio will roundrobin the CPUs in
902 .BI numa_cpu_nodes \fR=\fPstr
903 Set this job running on specified NUMA nodes' CPUs. The arguments allow
904 comma delimited list of cpu numbers, A-B ranges, or 'all'.
906 .BI numa_mem_policy \fR=\fPstr
907 Set this job's memory policy and corresponding NUMA nodes. Format of
911 .B <mode>[:<nodelist>]
914 is one of the following memory policy:
916 .B default, prefer, bind, interleave, local
919 For \fBdefault\fR and \fBlocal\fR memory policy, no \fBnodelist\fR is
920 needed to be specified. For \fBprefer\fR, only one node is
921 allowed. For \fBbind\fR and \fBinterleave\fR, \fBnodelist\fR allows
922 comma delimited list of numbers, A-B ranges, or 'all'.
924 .BI startdelay \fR=\fPirange
925 Delay start of job for the specified number of seconds. Supports all time
926 suffixes to allow specification of hours, minutes, seconds and
927 milliseconds - seconds are the default if a unit is ommited.
928 Can be given as a range which causes each thread to choose randomly out of the
931 .BI runtime \fR=\fPint
932 Terminate processing after the specified number of seconds.
935 If given, run for the specified \fBruntime\fR duration even if the files are
936 completely read or written. The same workload will be repeated as many times
937 as \fBruntime\fR allows.
939 .BI ramp_time \fR=\fPint
940 If set, fio will run the specified workload for this amount of time before
941 logging any performance numbers. Useful for letting performance settle before
942 logging results, thus minimizing the runtime required for stable results. Note
943 that the \fBramp_time\fR is considered lead in time for a job, thus it will
944 increase the total runtime if a special timeout or runtime is specified.
946 .BI invalidate \fR=\fPbool
947 Invalidate buffer-cache for the file prior to starting I/O. Default: true.
950 Use synchronous I/O for buffered writes. For the majority of I/O engines,
951 this means using O_SYNC. Default: false.
953 .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr
954 Allocation method for I/O unit buffer. Allowed values are:
959 Allocate memory with \fBmalloc\fR\|(3).
962 Use shared memory buffers allocated through \fBshmget\fR\|(2).
965 Same as \fBshm\fR, but use huge pages as backing.
968 Use \fBmmap\fR\|(2) for allocation. Uses anonymous memory unless a filename
969 is given after the option in the format `:\fIfile\fR'.
972 Same as \fBmmap\fR, but use huge files as backing.
975 The amount of memory allocated is the maximum allowed \fBblocksize\fR for the
976 job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work,
977 the system must have free huge pages allocated. \fBmmaphuge\fR also needs to
978 have hugetlbfs mounted, and \fIfile\fR must point there. At least on Linux,
979 huge pages must be manually allocated. See \fB/proc/sys/vm/nr_hugehages\fR
980 and the documentation for that. Normally you just need to echo an appropriate
981 number, eg echoing 8 will ensure that the OS has 8 huge pages ready for
985 .BI iomem_align \fR=\fPint "\fR,\fP mem_align" \fR=\fPint
986 This indicates the memory alignment of the IO memory buffers. Note that the
987 given alignment is applied to the first IO unit buffer, if using \fBiodepth\fR
988 the alignment of the following buffers are given by the \fBbs\fR used. In
989 other words, if using a \fBbs\fR that is a multiple of the page sized in the
990 system, all buffers will be aligned to this value. If using a \fBbs\fR that
991 is not page aligned, the alignment of subsequent IO memory buffers is the
992 sum of the \fBiomem_align\fR and \fBbs\fR used.
994 .BI hugepage\-size \fR=\fPint
995 Defines the size of a huge page. Must be at least equal to the system setting.
996 Should be a multiple of 1MB. Default: 4MB.
999 Terminate all jobs when one finishes. Default: wait for each job to finish.
1001 .BI bwavgtime \fR=\fPint
1002 Average bandwidth calculations over the given time in milliseconds. Default:
1005 .BI iopsavgtime \fR=\fPint
1006 Average IOPS calculations over the given time in milliseconds. Default:
1009 .BI create_serialize \fR=\fPbool
1010 If true, serialize file creation for the jobs. Default: true.
1012 .BI create_fsync \fR=\fPbool
1013 \fBfsync\fR\|(2) data file after creation. Default: true.
1015 .BI create_on_open \fR=\fPbool
1016 If true, the files are not created until they are opened for IO by the job.
1018 .BI create_only \fR=\fPbool
1019 If true, fio will only run the setup phase of the job. If files need to be
1020 laid out or updated on disk, only that will be done. The actual job contents
1023 .BI pre_read \fR=\fPbool
1024 If this is given, files will be pre-read into memory before starting the given
1025 IO operation. This will also clear the \fR \fBinvalidate\fR flag, since it is
1026 pointless to pre-read and then drop the cache. This will only work for IO
1027 engines that are seekable, since they allow you to read the same data
1028 multiple times. Thus it will not work on eg network or splice IO.
1030 .BI unlink \fR=\fPbool
1031 Unlink job files when done. Default: false.
1033 .BI loops \fR=\fPint
1034 Specifies the number of iterations (runs of the same workload) of this job.
1037 .BI verify_only \fR=\fPbool
1038 Do not perform the specified workload, only verify data still matches previous
1039 invocation of this workload. This option allows one to check data multiple
1040 times at a later date without overwriting it. This option makes sense only for
1041 workloads that write data, and does not support workloads with the
1042 \fBtime_based\fR option set.
1044 .BI do_verify \fR=\fPbool
1045 Run the verify phase after a write phase. Only valid if \fBverify\fR is set.
1048 .BI verify \fR=\fPstr
1049 Method of verifying file contents after each iteration of the job. Allowed
1054 .B md5 crc16 crc32 crc32c crc32c-intel crc64 crc7 sha256 sha512 sha1 xxhash
1055 Store appropriate checksum in the header of each block. crc32c-intel is
1056 hardware accelerated SSE4.2 driven, falls back to regular crc32c if
1057 not supported by the system.
1060 Write extra information about each I/O (timestamp, block number, etc.). The
1061 block number is verified. See \fBverify_pattern\fR as well.
1064 Pretend to verify. Used for testing internals.
1067 This option can be used for repeated burn-in tests of a system to make sure
1068 that the written data is also correctly read back. If the data direction given
1069 is a read or random read, fio will assume that it should verify a previously
1070 written file. If the data direction includes any form of write, the verify will
1071 be of the newly written data.
1074 .BI verifysort \fR=\fPbool
1075 If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to
1076 read them back in a sorted manner. Default: true.
1078 .BI verifysort_nr \fR=\fPint
1079 Pre-load and sort verify blocks for a read workload.
1081 .BI verify_offset \fR=\fPint
1082 Swap the verification header with data somewhere else in the block before
1083 writing. It is swapped back before verifying.
1085 .BI verify_interval \fR=\fPint
1086 Write the verification header for this number of bytes, which should divide
1087 \fBblocksize\fR. Default: \fBblocksize\fR.
1089 .BI verify_pattern \fR=\fPstr
1090 If set, fio will fill the io buffers with this pattern. Fio defaults to filling
1091 with totally random bytes, but sometimes it's interesting to fill with a known
1092 pattern for io verification purposes. Depending on the width of the pattern,
1093 fio will fill 1/2/3/4 bytes of the buffer at the time(it can be either a
1094 decimal or a hex number). The verify_pattern if larger than a 32-bit quantity
1095 has to be a hex number that starts with either "0x" or "0X". Use with
1098 .BI verify_fatal \fR=\fPbool
1099 If true, exit the job on the first observed verification failure. Default:
1102 .BI verify_dump \fR=\fPbool
1103 If set, dump the contents of both the original data block and the data block we
1104 read off disk to files. This allows later analysis to inspect just what kind of
1105 data corruption occurred. Off by default.
1107 .BI verify_async \fR=\fPint
1108 Fio will normally verify IO inline from the submitting thread. This option
1109 takes an integer describing how many async offload threads to create for IO
1110 verification instead, causing fio to offload the duty of verifying IO contents
1111 to one or more separate threads. If using this offload option, even sync IO
1112 engines can benefit from using an \fBiodepth\fR setting higher than 1, as it
1113 allows them to have IO in flight while verifies are running.
1115 .BI verify_async_cpus \fR=\fPstr
1116 Tell fio to set the given CPU affinity on the async IO verification threads.
1117 See \fBcpus_allowed\fP for the format used.
1119 .BI verify_backlog \fR=\fPint
1120 Fio will normally verify the written contents of a job that utilizes verify
1121 once that job has completed. In other words, everything is written then
1122 everything is read back and verified. You may want to verify continually
1123 instead for a variety of reasons. Fio stores the meta data associated with an
1124 IO block in memory, so for large verify workloads, quite a bit of memory would
1125 be used up holding this meta data. If this option is enabled, fio will write
1126 only N blocks before verifying these blocks.
1128 .BI verify_backlog_batch \fR=\fPint
1129 Control how many blocks fio will verify if verify_backlog is set. If not set,
1130 will default to the value of \fBverify_backlog\fR (meaning the entire queue is
1131 read back and verified). If \fBverify_backlog_batch\fR is less than
1132 \fBverify_backlog\fR then not all blocks will be verified, if
1133 \fBverify_backlog_batch\fR is larger than \fBverify_backlog\fR, some blocks
1134 will be verified more than once.
1136 .BI trim_percentage \fR=\fPint
1137 Number of verify blocks to discard/trim.
1139 .BI trim_verify_zero \fR=\fPbool
1140 Verify that trim/discarded blocks are returned as zeroes.
1142 .BI trim_backlog \fR=\fPint
1143 Trim after this number of blocks are written.
1145 .BI trim_backlog_batch \fR=\fPint
1146 Trim this number of IO blocks.
1148 .BI experimental_verify \fR=\fPbool
1149 Enable experimental verification.
1151 .B stonewall "\fR,\fP wait_for_previous"
1152 Wait for preceding jobs in the job file to exit before starting this one.
1153 \fBstonewall\fR implies \fBnew_group\fR.
1156 Start a new reporting group. If not given, all jobs in a file will be part
1157 of the same reporting group, unless separated by a stonewall.
1159 .BI numjobs \fR=\fPint
1160 Number of clones (processes/threads performing the same workload) of this job.
1164 If set, display per-group reports instead of per-job when \fBnumjobs\fR is
1168 Use threads created with \fBpthread_create\fR\|(3) instead of processes created
1169 with \fBfork\fR\|(2).
1171 .BI zonesize \fR=\fPint
1172 Divide file into zones of the specified size in bytes. See \fBzoneskip\fR.
1174 .BI zonerange \fR=\fPint
1175 Give size of an IO zone. See \fBzoneskip\fR.
1177 .BI zoneskip \fR=\fPint
1178 Skip the specified number of bytes when \fBzonesize\fR bytes of data have been
1181 .BI write_iolog \fR=\fPstr
1182 Write the issued I/O patterns to the specified file. Specify a separate file
1183 for each job, otherwise the iologs will be interspersed and the file may be
1186 .BI read_iolog \fR=\fPstr
1187 Replay the I/O patterns contained in the specified file generated by
1188 \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file.
1190 .BI replay_no_stall \fR=\fPint
1191 While replaying I/O patterns using \fBread_iolog\fR the default behavior
1192 attempts to respect timing information between I/Os. Enabling
1193 \fBreplay_no_stall\fR causes I/Os to be replayed as fast as possible while
1194 still respecting ordering.
1196 .BI replay_redirect \fR=\fPstr
1197 While replaying I/O patterns using \fBread_iolog\fR the default behavior
1198 is to replay the IOPS onto the major/minor device that each IOP was recorded
1199 from. Setting \fBreplay_redirect\fR causes all IOPS to be replayed onto the
1200 single specified device regardless of the device it was recorded from.
1202 .BI write_bw_log \fR=\fPstr
1203 If given, write a bandwidth log of the jobs in this job file. Can be used to
1204 store data of the bandwidth of the jobs in their lifetime. The included
1205 fio_generate_plots script uses gnuplot to turn these text files into nice
1206 graphs. See \fBwrite_lat_log\fR for behaviour of given filename. For this
1207 option, the postfix is _bw.x.log, where x is the index of the job (1..N,
1208 where N is the number of jobs)
1210 .BI write_lat_log \fR=\fPstr
1211 Same as \fBwrite_bw_log\fR, but writes I/O completion latencies. If no
1212 filename is given with this option, the default filename of
1213 "jobname_type.x.log" is used, where x is the index of the job (1..N, where
1214 N is the number of jobs). Even if the filename is given, fio will still
1215 append the type of log.
1217 .BI write_iops_log \fR=\fPstr
1218 Same as \fBwrite_bw_log\fR, but writes IOPS. If no filename is given with this
1219 option, the default filename of "jobname_type.x.log" is used, where x is the
1220 index of the job (1..N, where N is the number of jobs). Even if the filename
1221 is given, fio will still append the type of log.
1223 .BI log_avg_msec \fR=\fPint
1224 By default, fio will log an entry in the iops, latency, or bw log for every
1225 IO that completes. When writing to the disk log, that can quickly grow to a
1226 very large size. Setting this option makes fio average the each log entry
1227 over the specified period of time, reducing the resolution of the log.
1230 .BI log_offset \fR=\fPbool
1231 If this is set, the iolog options will include the byte offset for the IO
1232 entry as well as the other data values.
1234 .BI log_compression \fR=\fPint
1235 If this is set, fio will compress the IO logs as it goes, to keep the memory
1236 footprint lower. When a log reaches the specified size, that chunk is removed
1237 and compressed in the background. Given that IO logs are fairly highly
1238 compressible, this yields a nice memory savings for longer runs. The downside
1239 is that the compression will consume some background CPU cycles, so it may
1240 impact the run. This, however, is also true if the logging ends up consuming
1241 most of the system memory. So pick your poison. The IO logs are saved
1242 normally at the end of a run, by decompressing the chunks and storing them
1243 in the specified log file. This feature depends on the availability of zlib.
1245 .BI log_store_compressed \fR=\fPbool
1246 If set, and \fBlog\fR_compression is also set, fio will store the log files in
1247 a compressed format. They can be decompressed with fio, using the
1248 \fB\-\-inflate-log\fR command line parameter. The files will be stored with a
1251 .BI disable_lat \fR=\fPbool
1252 Disable measurements of total latency numbers. Useful only for cutting
1253 back the number of calls to \fBgettimeofday\fR\|(2), as that does impact performance at
1254 really high IOPS rates. Note that to really get rid of a large amount of these
1255 calls, this option must be used with disable_slat and disable_bw as well.
1257 .BI disable_clat \fR=\fPbool
1258 Disable measurements of completion latency numbers. See \fBdisable_lat\fR.
1260 .BI disable_slat \fR=\fPbool
1261 Disable measurements of submission latency numbers. See \fBdisable_lat\fR.
1263 .BI disable_bw_measurement \fR=\fPbool
1264 Disable measurements of throughput/bandwidth numbers. See \fBdisable_lat\fR.
1266 .BI lockmem \fR=\fPint
1267 Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to
1268 simulate a smaller amount of memory. The amount specified is per worker.
1270 .BI exec_prerun \fR=\fPstr
1271 Before running the job, execute the specified command with \fBsystem\fR\|(3).
1273 Output is redirected in a file called \fBjobname.prerun.txt\fR
1276 .BI exec_postrun \fR=\fPstr
1277 Same as \fBexec_prerun\fR, but the command is executed after the job completes.
1279 Output is redirected in a file called \fBjobname.postrun.txt\fR
1282 .BI ioscheduler \fR=\fPstr
1283 Attempt to switch the device hosting the file to the specified I/O scheduler.
1285 .BI disk_util \fR=\fPbool
1286 Generate disk utilization statistics if the platform supports it. Default: true.
1288 .BI clocksource \fR=\fPstr
1289 Use the given clocksource as the base of timing. The supported options are:
1293 \fBgettimeofday\fR\|(2)
1296 \fBclock_gettime\fR\|(2)
1299 Internal CPU clock source
1303 \fBcpu\fR is the preferred clocksource if it is reliable, as it is very fast
1304 (and fio is heavy on time calls). Fio will automatically use this clocksource
1305 if it's supported and considered reliable on the system it is running on,
1306 unless another clocksource is specifically set. For x86/x86-64 CPUs, this
1307 means supporting TSC Invariant.
1309 .BI gtod_reduce \fR=\fPbool
1310 Enable all of the \fBgettimeofday\fR\|(2) reducing options (disable_clat, disable_slat,
1311 disable_bw) plus reduce precision of the timeout somewhat to really shrink the
1312 \fBgettimeofday\fR\|(2) call count. With this option enabled, we only do about 0.4% of
1313 the gtod() calls we would have done if all time keeping was enabled.
1315 .BI gtod_cpu \fR=\fPint
1316 Sometimes it's cheaper to dedicate a single thread of execution to just getting
1317 the current time. Fio (and databases, for instance) are very intensive on
1318 \fBgettimeofday\fR\|(2) calls. With this option, you can set one CPU aside for doing
1319 nothing but logging current time to a shared memory location. Then the other
1320 threads/processes that run IO workloads need only copy that segment, instead of
1321 entering the kernel with a \fBgettimeofday\fR\|(2) call. The CPU set aside for doing
1322 these time calls will be excluded from other uses. Fio will manually clear it
1323 from the CPU mask of other jobs.
1325 .BI ignore_error \fR=\fPstr
1326 Sometimes you want to ignore some errors during test in that case you can specify
1327 error list for each error type.
1329 ignore_error=READ_ERR_LIST,WRITE_ERR_LIST,VERIFY_ERR_LIST
1331 errors for given error type is separated with ':'.
1332 Error may be symbol ('ENOSPC', 'ENOMEM') or an integer.
1334 Example: ignore_error=EAGAIN,ENOSPC:122 .
1336 This option will ignore EAGAIN from READ, and ENOSPC and 122(EDQUOT) from WRITE.
1338 .BI error_dump \fR=\fPbool
1339 If set dump every error even if it is non fatal, true by default. If disabled
1340 only fatal error will be dumped
1342 .BI profile \fR=\fPstr
1343 Select a specific builtin performance test.
1345 .BI cgroup \fR=\fPstr
1346 Add job to this control group. If it doesn't exist, it will be created.
1347 The system must have a mounted cgroup blkio mount point for this to work. If
1348 your system doesn't have it mounted, you can do so with:
1350 # mount \-t cgroup \-o blkio none /cgroup
1352 .BI cgroup_weight \fR=\fPint
1353 Set the weight of the cgroup to this value. See the documentation that comes
1354 with the kernel, allowed values are in the range of 100..1000.
1356 .BI cgroup_nodelete \fR=\fPbool
1357 Normally fio will delete the cgroups it has created after the job completion.
1358 To override this behavior and to leave cgroups around after the job completion,
1359 set cgroup_nodelete=1. This can be useful if one wants to inspect various
1360 cgroup files after job completion. Default: false
1363 Instead of running as the invoking user, set the user ID to this value before
1364 the thread/process does any work.
1367 Set group ID, see \fBuid\fR.
1369 .BI unit_base \fR=\fPint
1370 Base unit for reporting. Allowed values are:
1374 Use auto-detection (default).
1384 .BI flow_id \fR=\fPint
1385 The ID of the flow. If not specified, it defaults to being a global flow. See
1389 Weight in token-based flow control. If this value is used, then there is a
1390 \fBflow counter\fR which is used to regulate the proportion of activity between
1391 two or more jobs. fio attempts to keep this flow counter near zero. The
1392 \fBflow\fR parameter stands for how much should be added or subtracted to the
1393 flow counter on each iteration of the main I/O loop. That is, if one job has
1394 \fBflow=8\fR and another job has \fBflow=-1\fR, then there will be a roughly
1395 1:8 ratio in how much one runs vs the other.
1397 .BI flow_watermark \fR=\fPint
1398 The maximum value that the absolute value of the flow counter is allowed to
1399 reach before the job must wait for a lower value of the counter.
1401 .BI flow_sleep \fR=\fPint
1402 The period of time, in microseconds, to wait after the flow watermark has been
1403 exceeded before retrying operations
1405 .BI clat_percentiles \fR=\fPbool
1406 Enable the reporting of percentiles of completion latencies.
1408 .BI percentile_list \fR=\fPfloat_list
1409 Overwrite the default list of percentiles for completion
1410 latencies. Each number is a floating number in the range (0,100], and
1411 the maximum length of the list is 20. Use ':' to separate the
1412 numbers. For example, \-\-percentile_list=99.5:99.9 will cause fio to
1413 report the values of completion latency below which 99.5% and 99.9% of
1414 the observed latencies fell, respectively.
1415 .SS "Ioengine Parameters List"
1416 Some parameters are only valid when a specific ioengine is in use. These are
1417 used identically to normal parameters, with the caveat that when used on the
1418 command line, they must come after the ioengine.
1420 .BI (cpu)cpuload \fR=\fPint
1421 Attempt to use the specified percentage of CPU cycles.
1423 .BI (cpu)cpuchunks \fR=\fPint
1424 Split the load into cycles of the given time. In microseconds.
1426 .BI (cpu)exit_on_io_done \fR=\fPbool
1427 Detect when IO threads are done, then exit.
1429 .BI (libaio)userspace_reap
1430 Normally, with the libaio engine in use, fio will use
1431 the io_getevents system call to reap newly returned events.
1432 With this flag turned on, the AIO ring will be read directly
1433 from user-space to reap events. The reaping mode is only
1434 enabled when polling for a minimum of 0 events (eg when
1435 iodepth_batch_complete=0).
1437 .BI (net,netsplice)hostname \fR=\fPstr
1438 The host name or IP address to use for TCP or UDP based IO.
1439 If the job is a TCP listener or UDP reader, the hostname is not
1440 used and must be omitted unless it is a valid UDP multicast address.
1442 .BI (net,netsplice)port \fR=\fPint
1443 The TCP or UDP port to bind to or connect to.
1445 .BI (net,netsplice)interface \fR=\fPstr
1446 The IP address of the network interface used to send or receive UDP multicast
1449 .BI (net,netsplice)ttl \fR=\fPint
1450 Time-to-live value for outgoing UDP multicast packets. Default: 1
1452 .BI (net,netsplice)nodelay \fR=\fPbool
1453 Set TCP_NODELAY on TCP connections.
1455 .BI (net,netsplice)protocol \fR=\fPstr "\fR,\fP proto" \fR=\fPstr
1456 The network protocol to use. Accepted values are:
1461 Transmission control protocol
1464 Transmission control protocol V6
1467 User datagram protocol
1470 User datagram protocol V6
1476 When the protocol is TCP or UDP, the port must also be given,
1477 as well as the hostname if the job is a TCP listener or UDP
1478 reader. For unix sockets, the normal filename option should be
1479 used and the port is invalid.
1482 .BI (net,netsplice)listen
1483 For TCP network connections, tell fio to listen for incoming
1484 connections rather than initiating an outgoing connection. The
1485 hostname must be omitted if this option is used.
1487 .BI (net, pingpong) \fR=\fPbool
1488 Normally a network writer will just continue writing data, and a network reader
1489 will just consume packets. If pingpong=1 is set, a writer will send its normal
1490 payload to the reader, then wait for the reader to send the same payload back.
1491 This allows fio to measure network latencies. The submission and completion
1492 latencies then measure local time spent sending or receiving, and the
1493 completion latency measures how long it took for the other end to receive and
1494 send back. For UDP multicast traffic pingpong=1 should only be set for a single
1495 reader when multiple readers are listening to the same address.
1497 .BI (e4defrag,donorname) \fR=\fPstr
1498 File will be used as a block donor (swap extents between files)
1500 .BI (e4defrag,inplace) \fR=\fPint
1501 Configure donor file block allocation strategy
1504 Preallocate donor's file on init
1507 allocate space immediately inside defragment event, and free right after event
1510 .BI (rbd)rbdname \fR=\fPstr
1511 Specifies the name of the RBD.
1513 .BI (rbd)pool \fR=\fPstr
1514 Specifies the name of the Ceph pool containing the RBD.
1516 .BI (rbd)clientname \fR=\fPstr
1517 Specifies the username (without the 'client.' prefix) used to access the Ceph cluster.
1519 While running, \fBfio\fR will display the status of the created jobs. For
1523 Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
1526 The characters in the first set of brackets denote the current status of each
1527 threads. The possible values are:
1533 Setup but not started.
1539 Initialized, waiting.
1542 Running, doing sequential reads.
1545 Running, doing random reads.
1548 Running, doing sequential writes.
1551 Running, doing random writes.
1554 Running, doing mixed sequential reads/writes.
1557 Running, doing mixed random reads/writes.
1560 Running, currently waiting for \fBfsync\fR\|(2).
1563 Running, verifying written data.
1566 Exited, not reaped by main thread.
1569 Exited, thread reaped.
1573 The second set of brackets shows the estimated completion percentage of
1574 the current group. The third set shows the read and write I/O rate,
1575 respectively. Finally, the estimated run time of the job is displayed.
1577 When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data
1578 for each thread, each group of threads, and each disk, in that order.
1580 Per-thread statistics first show the threads client number, group-id, and
1581 error code. The remaining figures are as follows:
1585 Number of megabytes of I/O performed.
1588 Average data rate (bandwidth).
1594 Submission latency minimum, maximum, average and standard deviation. This is
1595 the time it took to submit the I/O.
1598 Completion latency minimum, maximum, average and standard deviation. This
1599 is the time between submission and completion.
1602 Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average
1603 and standard deviation.
1606 CPU usage statistics. Includes user and system time, number of context switches
1607 this thread went through and number of major and minor page faults.
1610 Distribution of I/O depths. Each depth includes everything less than (or equal)
1611 to it, but greater than the previous depth.
1614 Number of read/write requests issued, and number of short read/write requests.
1617 Distribution of I/O completion latencies. The numbers follow the same pattern
1621 The group statistics show:
1626 Number of megabytes I/O performed.
1629 Aggregate bandwidth of threads in the group.
1632 Minimum average bandwidth a thread saw.
1635 Maximum average bandwidth a thread saw.
1638 Shortest runtime of threads in the group.
1641 Longest runtime of threads in the group.
1645 Finally, disk statistics are printed with reads first:
1650 Number of I/Os performed by all groups.
1653 Number of merges in the I/O scheduler.
1656 Number of ticks we kept the disk busy.
1659 Total time spent in the disk queue.
1666 It is also possible to get fio to dump the current output while it is
1667 running, without terminating the job. To do that, send fio the \fBUSR1\fR
1670 If the \fB\-\-minimal\fR / \fB\-\-append-terse\fR options are given, the
1671 results will be printed/appended in a semicolon-delimited format suitable for
1673 A job description (if provided) follows on a new line. Note that the first
1674 number in the line is the version number. If the output has to be changed
1675 for some reason, this number will be incremented by 1 to signify that
1676 change. The fields are:
1679 .B terse version, fio version, jobname, groupid, error
1683 .B Total I/O \fR(KB)\fP, bandwidth \fR(KB/s)\fP, IOPS, runtime \fR(ms)\fP
1687 .B min, max, mean, standard deviation
1691 .B min, max, mean, standard deviation
1693 Completion latency percentiles (20 fields):
1695 .B Xth percentile=usec
1699 .B min, max, mean, standard deviation
1703 .B min, max, aggregate percentage of total, mean, standard deviation
1709 .B Total I/O \fR(KB)\fP, bandwidth \fR(KB/s)\fP, IOPS, runtime \fR(ms)\fP
1713 .B min, max, mean, standard deviation
1717 .B min, max, mean, standard deviation
1719 Completion latency percentiles (20 fields):
1721 .B Xth percentile=usec
1725 .B min, max, mean, standard deviation
1729 .B min, max, aggregate percentage of total, mean, standard deviation
1735 .B user, system, context switches, major page faults, minor page faults
1738 IO depth distribution:
1740 .B <=1, 2, 4, 8, 16, 32, >=64
1743 IO latency distribution:
1747 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000
1751 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000
1755 Disk utilization (1 for each disk used):
1757 .B name, read ios, write ios, read merges, write merges, read ticks, write ticks, read in-queue time, write in-queue time, disk utilization percentage
1760 Error Info (dependent on continue_on_error, default off):
1762 .B total # errors, first error code
1765 .B text description (if provided in config - appears on newline)
1768 Normally you would run fio as a stand-alone application on the machine
1769 where the IO workload should be generated. However, it is also possible to
1770 run the frontend and backend of fio separately. This makes it possible to
1771 have a fio server running on the machine(s) where the IO workload should
1772 be running, while controlling it from another machine.
1774 To start the server, you would do:
1776 \fBfio \-\-server=args\fR
1778 on that machine, where args defines what fio listens to. The arguments
1779 are of the form 'type:hostname or IP:port'. 'type' is either 'ip' (or ip4)
1780 for TCP/IP v4, 'ip6' for TCP/IP v6, or 'sock' for a local unix domain
1781 socket. 'hostname' is either a hostname or IP address, and 'port' is the port to
1782 listen to (only valid for TCP/IP, not a local socket). Some examples:
1786 Start a fio server, listening on all interfaces on the default port (8765).
1788 2) fio \-\-server=ip:hostname,4444
1790 Start a fio server, listening on IP belonging to hostname and on port 4444.
1792 3) fio \-\-server=ip6:::1,4444
1794 Start a fio server, listening on IPv6 localhost ::1 and on port 4444.
1796 4) fio \-\-server=,4444
1798 Start a fio server, listening on all interfaces on port 4444.
1800 5) fio \-\-server=1.2.3.4
1802 Start a fio server, listening on IP 1.2.3.4 on the default port.
1804 6) fio \-\-server=sock:/tmp/fio.sock
1806 Start a fio server, listening on the local socket /tmp/fio.sock.
1808 When a server is running, you can connect to it from a client. The client
1811 fio \-\-local-args \-\-client=server \-\-remote-args <job file(s)>
1813 where \-\-local-args are arguments that are local to the client where it is
1814 running, 'server' is the connect string, and \-\-remote-args and <job file(s)>
1815 are sent to the server. The 'server' string follows the same format as it
1816 does on the server side, to allow IP/hostname/socket and port strings.
1817 You can connect to multiple clients as well, to do that you could run:
1819 fio \-\-client=server2 \-\-client=server2 <job file(s)>
1823 was written by Jens Axboe <jens.axboe@oracle.com>,
1824 now Jens Axboe <jaxboe@fusionio.com>.
1826 This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based
1827 on documentation by Jens Axboe.
1828 .SH "REPORTING BUGS"
1829 Report bugs to the \fBfio\fR mailing list <fio@vger.kernel.org>.
1832 For further documentation see \fBHOWTO\fR and \fBREADME\fR.
1834 Sample jobfiles are available in the \fBexamples\fR directory.
projects / fio.git / blob