1 .TH fio 1 "September 2007" "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 \-\-timeout \fR=\fPtimeout
24 Limit run time to \fItimeout\fR seconds.
27 Generate per-job latency logs.
30 Generate per-job bandwidth logs.
33 Print statistics in a terse, semicolon-delimited format.
36 Display version information and exit.
38 .BI \-\-terse\-version \fR=\fPversion
39 Set terse version output format (Current version 3, or older version 2).
42 Display usage information and exit.
44 .BI \-\-cmdhelp \fR=\fPcommand
45 Print help information for \fIcommand\fR. May be `all' for all commands.
47 .BI \-\-enghelp \fR=\fPioengine[,command]
48 List all commands defined by \fIioengine\fR, or print help for \fIcommand\fR defined by \fIioengine\fR.
50 .BI \-\-showcmd \fR=\fPjobfile
51 Convert \fIjobfile\fR to a set of command-line options.
54 Enable read-only safety checks.
56 .BI \-\-eta \fR=\fPwhen
57 Specifies when real-time ETA estimate should be printed. \fIwhen\fR may
58 be one of `always', `never' or `auto'.
61 Turn on safety read-only checks, preventing any attempted write.
63 .BI \-\-section \fR=\fPsec
64 Only run section \fIsec\fR from job file. Multiple of these options can be given, adding more sections to run.
66 .BI \-\-alloc\-size \fR=\fPkb
67 Set the internal smalloc pool size to \fIkb\fP kilobytes.
69 .BI \-\-warnings\-fatal
70 All fio parser warnings are fatal, causing fio to exit with an error.
72 .BI \-\-max\-jobs \fR=\fPnr
73 Set the maximum allowed number of jobs (threads/processes) to suport.
75 .BI \-\-server \fR=\fPargs
76 Start a backend server, with \fIargs\fP specifying what to listen to. See client/server section.
78 .BI \-\-daemonize \fR=\fPpidfile
79 Background a fio server, writing the pid to the given pid file.
81 .BI \-\-client \fR=\fPhost
82 Instead of running the jobs locally, send and run them on the given host.
84 Job files are in `ini' format. They consist of one or more
85 job definitions, which begin with a job name in square brackets and
86 extend to the next job name. The job name can be any ASCII string
87 except `global', which has a special meaning. Following the job name is
88 a sequence of zero or more parameters, one per line, that define the
89 behavior of the job. Any line starting with a `;' or `#' character is
90 considered a comment and ignored.
92 If \fIjobfile\fR is specified as `-', the job file will be read from
95 The global section contains default parameters for jobs specified in the
96 job file. A job is only affected by global sections residing above it,
97 and there may be any number of global sections. Specific job definitions
98 may override any parameter set in global sections.
101 Some parameters may take arguments of a specific type. The types used are:
104 String: a sequence of alphanumeric characters.
107 SI integer: a whole number, possibly containing a suffix denoting the base unit
108 of the value. Accepted suffixes are `k', 'M', 'G', 'T', and 'P', denoting
109 kilo (1024), mega (1024^2), giga (1024^3), tera (1024^4), and peta (1024^5)
110 respectively. The suffix is not case sensitive. If prefixed with '0x', the
111 value is assumed to be base 16 (hexadecimal). A suffix may include a trailing 'b',
112 for instance 'kb' is identical to 'k'. You can specify a base 10 value
113 by using 'KiB', 'MiB', 'GiB', etc. This is useful for disk drives where
114 values are often given in base 10 values. Specifying '30GiB' will get you
118 Boolean: a true or false value. `0' denotes false, `1' denotes true.
121 Integer range: a range of integers specified in the format
122 \fIlower\fR:\fIupper\fR or \fIlower\fR\-\fIupper\fR. \fIlower\fR and
123 \fIupper\fR may contain a suffix as described above. If an option allows two
124 sets of ranges, they are separated with a `,' or `/' character. For example:
128 List of floating numbers: A list of floating numbers, separated by
133 May be used to override the job name. On the command line, this parameter
134 has the special purpose of signalling the start of a new job.
136 .BI description \fR=\fPstr
137 Human-readable description of the job. It is printed when the job is run, but
138 otherwise has no special purpose.
140 .BI directory \fR=\fPstr
141 Prefix filenames with this directory. Used to place files in a location other
144 .BI filename \fR=\fPstr
146 normally makes up a file name based on the job name, thread number, and file
147 number. If you want to share files between threads in a job or several jobs,
148 specify a \fIfilename\fR for each of them to override the default.
149 If the I/O engine is file-based, you can specify
150 a number of files by separating the names with a `:' character. `\-' is a
151 reserved name, meaning stdin or stdout, depending on the read/write direction
154 .BI lockfile \fR=\fPstr
155 Fio defaults to not locking any files before it does IO to them. If a file or
156 file descriptor is shared, fio can serialize IO to that file to make the end
157 result consistent. This is usual for emulating real workloads that share files.
163 No locking. This is the default.
166 Only one thread or process may do IO at the time, excluding all others.
169 Read-write locking on the file. Many readers may access the file at the same
170 time, but writes get exclusive access.
173 The option may be post-fixed with a lock batch number. If set, then each
174 thread/process may do that amount of IOs to the file before giving up the lock.
175 Since lock acquisition is expensive, batching the lock/unlocks will speed up IO.
178 .BI opendir \fR=\fPstr
179 Recursively open any files below directory \fIstr\fR.
181 .BI readwrite \fR=\fPstr "\fR,\fP rw" \fR=\fPstr
182 Type of I/O pattern. Accepted values are:
199 Mixed sequential reads and writes.
202 Mixed random reads and writes.
205 For mixed I/O, the default split is 50/50. For certain types of io the result
206 may still be skewed a bit, since the speed may be different. It is possible to
207 specify a number of IO's to do before getting a new offset, this is one by
208 appending a `:\fI<nr>\fR to the end of the string given. For a random read, it
209 would look like \fBrw=randread:8\fR for passing in an offset modifier with a
210 value of 8. If the postfix is used with a sequential IO pattern, then the value
211 specified will be added to the generated offset for each IO. For instance,
212 using \fBrw=write:4k\fR will skip 4k for every write. It turns sequential IO
213 into sequential IO with holes. See the \fBrw_sequencer\fR option.
216 .BI rw_sequencer \fR=\fPstr
217 If an offset modifier is given by appending a number to the \fBrw=<str>\fR line,
218 then this option controls how that number modifies the IO offset being
219 generated. Accepted values are:
224 Generate sequential offset
227 Generate the same offset
230 \fBsequential\fR is only useful for random IO, where fio would normally
231 generate a new random offset for every IO. If you append eg 8 to randread, you
232 would get a new random offset for every 8 IO's. The result would be a seek for
233 only every 8 IO's, instead of for every IO. Use \fBrw=randread:8\fR to specify
234 that. As sequential IO is already sequential, setting \fBsequential\fR for that
235 would not result in any differences. \fBidentical\fR behaves in a similar
236 fashion, except it sends the same offset 8 number of times before generating a
241 .BI kb_base \fR=\fPint
242 The base unit for a kilobyte. The defacto base is 2^10, 1024. Storage
243 manufacturers like to use 10^3 or 1000 as a base ten unit instead, for obvious
244 reasons. Allow values are 1024 or 1000, with 1024 being the default.
246 .BI randrepeat \fR=\fPbool
247 Seed the random number generator in a predictable way so results are repeatable
248 across runs. Default: true.
250 .BI use_os_rand \fR=\fPbool
251 Fio can either use the random generator supplied by the OS to generator random
252 offsets, or it can use it's own internal generator (based on Tausworthe).
253 Default is to use the internal generator, which is often of better quality and
254 faster. Default: false.
256 .BI fallocate \fR=\fPstr
257 Whether pre-allocation is performed when laying down files. Accepted values
263 Do not pre-allocate space.
266 Pre-allocate via posix_fallocate().
269 Pre-allocate via fallocate() with FALLOC_FL_KEEP_SIZE set.
272 Backward-compatible alias for 'none'.
275 Backward-compatible alias for 'posix'.
278 May not be available on all supported platforms. 'keep' is only
279 available on Linux. If using ZFS on Solaris this must be set to 'none'
280 because ZFS doesn't support it. Default: 'posix'.
283 .BI fadvise_hint \fR=\fPbool
284 Use of \fIposix_fadvise\fR\|(2) to advise the kernel what I/O patterns
285 are likely to be issued. Default: true.
288 Total size of I/O for this job. \fBfio\fR will run until this many bytes have
289 been transfered, unless limited by other options (\fBruntime\fR, for instance).
290 Unless \fBnrfiles\fR and \fBfilesize\fR options are given, this amount will be
291 divided between the available files for the job. If not set, fio will use the
292 full size of the given files or devices. If the the files do not exist, size
293 must be given. It is also possible to give size as a percentage between 1 and
294 100. If size=20% is given, fio will use 20% of the full size of the given files
297 .BI fill_device \fR=\fPbool "\fR,\fB fill_fs" \fR=\fPbool
298 Sets size to something really large and waits for ENOSPC (no space left on
299 device) as the terminating condition. Only makes sense with sequential write.
300 For a read workload, the mount point will be filled first then IO started on
301 the result. This option doesn't make sense if operating on a raw device node,
302 since the size of that is already known by the file system. Additionally,
303 writing beyond end-of-device will not return ENOSPC there.
305 .BI filesize \fR=\fPirange
306 Individual file sizes. May be a range, in which case \fBfio\fR will select sizes
307 for files at random within the given range, limited to \fBsize\fR in total (if
308 that is given). If \fBfilesize\fR is not specified, each created file is the
311 .BI blocksize \fR=\fPint[,int] "\fR,\fB bs" \fR=\fPint[,int]
312 Block size for I/O units. Default: 4k. Values for reads and writes can be
313 specified separately in the format \fIread\fR,\fIwrite\fR, either of
314 which may be empty to leave that value at its default.
316 .BI blocksize_range \fR=\fPirange[,irange] "\fR,\fB bsrange" \fR=\fPirange[,irange]
317 Specify a range of I/O block sizes. The issued I/O unit will always be a
318 multiple of the minimum size, unless \fBblocksize_unaligned\fR is set. Applies
319 to both reads and writes if only one range is given, but can be specified
320 separately with a comma seperating the values. Example: bsrange=1k-4k,2k-8k.
321 Also (see \fBblocksize\fR).
323 .BI bssplit \fR=\fPstr
324 This option allows even finer grained control of the block sizes issued,
325 not just even splits between them. With this option, you can weight various
326 block sizes for exact control of the issued IO for a job that has mixed
327 block sizes. The format of the option is bssplit=blocksize/percentage,
328 optionally adding as many definitions as needed separated by a colon.
329 Example: bssplit=4k/10:64k/50:32k/40 would issue 50% 64k blocks, 10% 4k
330 blocks and 40% 32k blocks. \fBbssplit\fR also supports giving separate
331 splits to reads and writes. The format is identical to what the
332 \fBbs\fR option accepts, the read and write parts are separated with a
335 .B blocksize_unaligned\fR,\fP bs_unaligned
336 If set, any size in \fBblocksize_range\fR may be used. This typically won't
337 work with direct I/O, as that normally requires sector alignment.
339 .BI blockalign \fR=\fPint[,int] "\fR,\fB ba" \fR=\fPint[,int]
340 At what boundary to align random IO offsets. Defaults to the same as 'blocksize'
341 the minimum blocksize given. Minimum alignment is typically 512b
342 for using direct IO, though it usually depends on the hardware block size.
343 This option is mutually exclusive with using a random map for files, so it
344 will turn off that option.
347 Initialise buffers with all zeros. Default: fill buffers with random data.
350 If this option is given, fio will refill the IO buffers on every submit. The
351 default is to only fill it at init time and reuse that data. Only makes sense
352 if zero_buffers isn't specified, naturally. If data verification is enabled,
353 refill_buffers is also automatically enabled.
355 .BI scramble_buffers \fR=\fPbool
356 If \fBrefill_buffers\fR is too costly and the target is using data
357 deduplication, then setting this option will slightly modify the IO buffer
358 contents to defeat normal de-dupe attempts. This is not enough to defeat
359 more clever block compression attempts, but it will stop naive dedupe
360 of blocks. Default: true.
362 .BI nrfiles \fR=\fPint
363 Number of files to use for this job. Default: 1.
365 .BI openfiles \fR=\fPint
366 Number of files to keep open at the same time. Default: \fBnrfiles\fR.
368 .BI file_service_type \fR=\fPstr
369 Defines how files to service are selected. The following types are defined:
374 Choose a file at random
377 Round robin over open files (default).
379 Do each file in the set sequentially.
382 The number of I/Os to issue before switching a new file can be specified by
383 appending `:\fIint\fR' to the service type.
386 .BI ioengine \fR=\fPstr
387 Defines how the job issues I/O. The following types are defined:
392 Basic \fIread\fR\|(2) or \fIwrite\fR\|(2) I/O. \fIfseek\fR\|(2) is used to
393 position the I/O location.
396 Basic \fIpread\fR\|(2) or \fIpwrite\fR\|(2) I/O.
399 Basic \fIreadv\fR\|(2) or \fIwritev\fR\|(2) I/O. Will emulate queuing by
400 coalescing adjacents IOs into a single submission.
403 Linux native asynchronous I/O. This ioengine defines engine specific options.
406 POSIX asynchronous I/O using \fIaio_read\fR\|(3) and \fIaio_write\fR\|(3).
409 Solaris native asynchronous I/O.
412 Windows native asynchronous I/O.
415 File is memory mapped with \fImmap\fR\|(2) and data copied using
419 \fIsplice\fR\|(2) is used to transfer the data and \fIvmsplice\fR\|(2) to
420 transfer data from user-space to the kernel.
423 Use the syslet system calls to make regular read/write asynchronous.
426 SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if
427 the target is an sg character device, we use \fIread\fR\|(2) and
428 \fIwrite\fR\|(2) for asynchronous I/O.
431 Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR
432 itself and for debugging and testing purposes.
435 Transfer over the network. The protocol to be used can be defined with the
436 \fBprotocol\fR parameter. Depending on the protocol, \fBfilename\fR,
437 \fBhostname\fR, \fBport\fR, or \fBlisten\fR must be specified.
438 This ioengine defines engine specific options.
441 Like \fBnet\fR, but uses \fIsplice\fR\|(2) and \fIvmsplice\fR\|(2) to map data
442 and send/receive. This ioengine defines engine specific options.
445 Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and
446 \fBcpucycles\fR parameters.
449 The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface
450 approach to asycnronous I/O.
452 See <http://www.xmailserver.org/guasi\-lib.html>.
455 The RDMA I/O engine supports both RDMA memory semantics (RDMA_WRITE/RDMA_READ)
456 and channel semantics (Send/Recv) for the InfiniBand, RoCE and iWARP protocols.
459 Loads an external I/O engine object file. Append the engine filename as
464 .BI iodepth \fR=\fPint
465 Number of I/O units to keep in flight against the file. Note that increasing
466 iodepth beyond 1 will not affect synchronous ioengines (except for small
467 degress when verify_async is in use). Even async engines my impose OS
468 restrictions causing the desired depth not to be achieved. This may happen on
469 Linux when using libaio and not setting \fBdirect\fR=1, since buffered IO is
470 not async on that OS. Keep an eye on the IO depth distribution in the
471 fio output to verify that the achieved depth is as expected. Default: 1.
473 .BI iodepth_batch \fR=\fPint
474 Number of I/Os to submit at once. Default: \fBiodepth\fR.
476 .BI iodepth_batch_complete \fR=\fPint
477 This defines how many pieces of IO to retrieve at once. It defaults to 1 which
478 means that we'll ask for a minimum of 1 IO in the retrieval process from the
479 kernel. The IO retrieval will go on until we hit the limit set by
480 \fBiodepth_low\fR. If this variable is set to 0, then fio will always check for
481 completed events before queuing more IO. This helps reduce IO latency, at the
482 cost of more retrieval system calls.
484 .BI iodepth_low \fR=\fPint
485 Low watermark indicating when to start filling the queue again. Default:
488 .BI direct \fR=\fPbool
489 If true, use non-buffered I/O (usually O_DIRECT). Default: false.
491 .BI buffered \fR=\fPbool
492 If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter.
495 .BI offset \fR=\fPint
496 Offset in the file to start I/O. Data before the offset will not be touched.
498 .BI offset_increment \fR=\fPint
499 If this is provided, then the real offset becomes the
500 offset + offset_increment * thread_number, where the thread number is a counter
501 that starts at 0 and is incremented for each job. This option is useful if
502 there are several jobs which are intended to operate on a file in parallel in
503 disjoint segments, with even spacing between the starting points.
506 How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If
507 0, don't sync. Default: 0.
509 .BI fdatasync \fR=\fPint
510 Like \fBfsync\fR, but uses \fBfdatasync\fR\|(2) instead to only sync the
511 data parts of the file. Default: 0.
513 .BI sync_file_range \fR=\fPstr:int
514 Use sync_file_range() for every \fRval\fP number of write operations. Fio will
515 track range of writes that have happened since the last sync_file_range() call.
516 \fRstr\fP can currently be one or more of:
520 SYNC_FILE_RANGE_WAIT_BEFORE
523 SYNC_FILE_RANGE_WRITE
526 SYNC_FILE_RANGE_WRITE
530 So if you do sync_file_range=wait_before,write:8, fio would use
531 \fBSYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE\fP for every 8 writes.
532 Also see the sync_file_range(2) man page. This option is Linux specific.
534 .BI overwrite \fR=\fPbool
535 If writing, setup the file first and do overwrites. Default: false.
537 .BI end_fsync \fR=\fPbool
538 Sync file contents when job exits. Default: false.
540 .BI fsync_on_close \fR=\fPbool
541 If true, sync file contents on close. This differs from \fBend_fsync\fR in that
542 it will happen on every close, not just at the end of the job. Default: false.
544 .BI rwmixcycle \fR=\fPint
545 How many milliseconds before switching between reads and writes for a mixed
546 workload. Default: 500ms.
548 .BI rwmixread \fR=\fPint
549 Percentage of a mixed workload that should be reads. Default: 50.
551 .BI rwmixwrite \fR=\fPint
552 Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and
553 \fBrwmixwrite\fR are given and do not sum to 100%, the latter of the two
554 overrides the first. This may interfere with a given rate setting, if fio is
555 asked to limit reads or writes to a certain rate. If that is the case, then
556 the distribution may be skewed. Default: 50.
559 Normally \fBfio\fR will cover every block of the file when doing random I/O. If
560 this parameter is given, a new offset will be chosen without looking at past
561 I/O history. This parameter is mutually exclusive with \fBverify\fR.
563 .BI softrandommap \fR=\fPbool
564 See \fBnorandommap\fR. If fio runs with the random block map enabled and it
565 fails to allocate the map, if this option is set it will continue without a
566 random block map. As coverage will not be as complete as with random maps, this
567 option is disabled by default.
570 Run job with given nice value. See \fInice\fR\|(2).
573 Set I/O priority value of this job between 0 (highest) and 7 (lowest). See
576 .BI prioclass \fR=\fPint
577 Set I/O priority class. See \fIionice\fR\|(1).
579 .BI thinktime \fR=\fPint
580 Stall job for given number of microseconds between issuing I/Os.
582 .BI thinktime_spin \fR=\fPint
583 Pretend to spend CPU time for given number of microseconds, sleeping the rest
584 of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set.
586 .BI thinktime_blocks \fR=\fPint
587 Number of blocks to issue before waiting \fBthinktime\fR microseconds.
591 Cap bandwidth used by this job. The number is in bytes/sec, the normal postfix
592 rules apply. You can use \fBrate\fR=500k to limit reads and writes to 500k each,
593 or you can specify read and writes separately. Using \fBrate\fR=1m,500k would
594 limit reads to 1MB/sec and writes to 500KB/sec. Capping only reads or writes
595 can be done with \fBrate\fR=,500k or \fBrate\fR=500k,. The former will only
596 limit writes (to 500KB/sec), the latter will only limit reads.
598 .BI ratemin \fR=\fPint
599 Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth.
600 Failing to meet this requirement will cause the job to exit. The same format
601 as \fBrate\fR is used for read vs write separation.
603 .BI rate_iops \fR=\fPint
604 Cap the bandwidth to this number of IOPS. Basically the same as rate, just
605 specified independently of bandwidth. The same format as \fBrate\fR is used for
606 read vs write seperation. If \fBblocksize\fR is a range, the smallest block
607 size is used as the metric.
609 .BI rate_iops_min \fR=\fPint
610 If this rate of I/O is not met, the job will exit. The same format as \fBrate\fR
611 is used for read vs write seperation.
613 .BI ratecycle \fR=\fPint
614 Average bandwidth for \fBrate\fR and \fBratemin\fR over this number of
615 milliseconds. Default: 1000ms.
617 .BI cpumask \fR=\fPint
618 Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job
619 may run on. See \fBsched_setaffinity\fR\|(2).
621 .BI cpus_allowed \fR=\fPstr
622 Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers.
624 .BI startdelay \fR=\fPint
625 Delay start of job for the specified number of seconds.
627 .BI runtime \fR=\fPint
628 Terminate processing after the specified number of seconds.
631 If given, run for the specified \fBruntime\fR duration even if the files are
632 completely read or written. The same workload will be repeated as many times
633 as \fBruntime\fR allows.
635 .BI ramp_time \fR=\fPint
636 If set, fio will run the specified workload for this amount of time before
637 logging any performance numbers. Useful for letting performance settle before
638 logging results, thus minimizing the runtime required for stable results. Note
639 that the \fBramp_time\fR is considered lead in time for a job, thus it will
640 increase the total runtime if a special timeout or runtime is specified.
642 .BI invalidate \fR=\fPbool
643 Invalidate buffer-cache for the file prior to starting I/O. Default: true.
646 Use synchronous I/O for buffered writes. For the majority of I/O engines,
647 this means using O_SYNC. Default: false.
649 .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr
650 Allocation method for I/O unit buffer. Allowed values are:
655 Allocate memory with \fImalloc\fR\|(3).
658 Use shared memory buffers allocated through \fIshmget\fR\|(2).
661 Same as \fBshm\fR, but use huge pages as backing.
664 Use \fImmap\fR\|(2) for allocation. Uses anonymous memory unless a filename
665 is given after the option in the format `:\fIfile\fR'.
668 Same as \fBmmap\fR, but use huge files as backing.
671 The amount of memory allocated is the maximum allowed \fBblocksize\fR for the
672 job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work,
673 the system must have free huge pages allocated. \fBmmaphuge\fR also needs to
674 have hugetlbfs mounted, and \fIfile\fR must point there. At least on Linux,
675 huge pages must be manually allocated. See \fB/proc/sys/vm/nr_hugehages\fR
676 and the documentation for that. Normally you just need to echo an appropriate
677 number, eg echoing 8 will ensure that the OS has 8 huge pages ready for
681 .BI iomem_align \fR=\fPint "\fR,\fP mem_align" \fR=\fPint
682 This indiciates the memory alignment of the IO memory buffers. Note that the
683 given alignment is applied to the first IO unit buffer, if using \fBiodepth\fR
684 the alignment of the following buffers are given by the \fBbs\fR used. In
685 other words, if using a \fBbs\fR that is a multiple of the page sized in the
686 system, all buffers will be aligned to this value. If using a \fBbs\fR that
687 is not page aligned, the alignment of subsequent IO memory buffers is the
688 sum of the \fBiomem_align\fR and \fBbs\fR used.
690 .BI hugepage\-size \fR=\fPint
691 Defines the size of a huge page. Must be at least equal to the system setting.
692 Should be a multiple of 1MB. Default: 4MB.
695 Terminate all jobs when one finishes. Default: wait for each job to finish.
697 .BI bwavgtime \fR=\fPint
698 Average bandwidth calculations over the given time in milliseconds. Default:
701 .BI iopsavgtime \fR=\fPint
702 Average IOPS calculations over the given time in milliseconds. Default:
705 .BI create_serialize \fR=\fPbool
706 If true, serialize file creation for the jobs. Default: true.
708 .BI create_fsync \fR=\fPbool
709 \fIfsync\fR\|(2) data file after creation. Default: true.
711 .BI create_on_open \fR=\fPbool
712 If true, the files are not created until they are opened for IO by the job.
714 .BI pre_read \fR=\fPbool
715 If this is given, files will be pre-read into memory before starting the given
716 IO operation. This will also clear the \fR \fBinvalidate\fR flag, since it is
717 pointless to pre-read and then drop the cache. This will only work for IO
718 engines that are seekable, since they allow you to read the same data
719 multiple times. Thus it will not work on eg network or splice IO.
721 .BI unlink \fR=\fPbool
722 Unlink job files when done. Default: false.
725 Specifies the number of iterations (runs of the same workload) of this job.
728 .BI do_verify \fR=\fPbool
729 Run the verify phase after a write phase. Only valid if \fBverify\fR is set.
732 .BI verify \fR=\fPstr
733 Method of verifying file contents after each iteration of the job. Allowed
738 .B md5 crc16 crc32 crc32c crc32c-intel crc64 crc7 sha256 sha512 sha1
739 Store appropriate checksum in the header of each block. crc32c-intel is
740 hardware accelerated SSE4.2 driven, falls back to regular crc32c if
741 not supported by the system.
744 Write extra information about each I/O (timestamp, block number, etc.). The
745 block number is verified. See \fBverify_pattern\fR as well.
748 Pretend to verify. Used for testing internals.
751 This option can be used for repeated burn-in tests of a system to make sure
752 that the written data is also correctly read back. If the data direction given
753 is a read or random read, fio will assume that it should verify a previously
754 written file. If the data direction includes any form of write, the verify will
755 be of the newly written data.
758 .BI verify_sort \fR=\fPbool
759 If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to
760 read them back in a sorted manner. Default: true.
762 .BI verify_offset \fR=\fPint
763 Swap the verification header with data somewhere else in the block before
764 writing. It is swapped back before verifying.
766 .BI verify_interval \fR=\fPint
767 Write the verification header for this number of bytes, which should divide
768 \fBblocksize\fR. Default: \fBblocksize\fR.
770 .BI verify_pattern \fR=\fPstr
771 If set, fio will fill the io buffers with this pattern. Fio defaults to filling
772 with totally random bytes, but sometimes it's interesting to fill with a known
773 pattern for io verification purposes. Depending on the width of the pattern,
774 fio will fill 1/2/3/4 bytes of the buffer at the time(it can be either a
775 decimal or a hex number). The verify_pattern if larger than a 32-bit quantity
776 has to be a hex number that starts with either "0x" or "0X". Use with
779 .BI verify_fatal \fR=\fPbool
780 If true, exit the job on the first observed verification failure. Default:
783 .BI verify_dump \fR=\fPbool
784 If set, dump the contents of both the original data block and the data block we
785 read off disk to files. This allows later analysis to inspect just what kind of
786 data corruption occurred. Off by default.
788 .BI verify_async \fR=\fPint
789 Fio will normally verify IO inline from the submitting thread. This option
790 takes an integer describing how many async offload threads to create for IO
791 verification instead, causing fio to offload the duty of verifying IO contents
792 to one or more separate threads. If using this offload option, even sync IO
793 engines can benefit from using an \fBiodepth\fR setting higher than 1, as it
794 allows them to have IO in flight while verifies are running.
796 .BI verify_async_cpus \fR=\fPstr
797 Tell fio to set the given CPU affinity on the async IO verification threads.
798 See \fBcpus_allowed\fP for the format used.
800 .BI verify_backlog \fR=\fPint
801 Fio will normally verify the written contents of a job that utilizes verify
802 once that job has completed. In other words, everything is written then
803 everything is read back and verified. You may want to verify continually
804 instead for a variety of reasons. Fio stores the meta data associated with an
805 IO block in memory, so for large verify workloads, quite a bit of memory would
806 be used up holding this meta data. If this option is enabled, fio will write
807 only N blocks before verifying these blocks.
809 .BI verify_backlog_batch \fR=\fPint
810 Control how many blocks fio will verify if verify_backlog is set. If not set,
811 will default to the value of \fBverify_backlog\fR (meaning the entire queue is
812 read back and verified). If \fBverify_backlog_batch\fR is less than
813 \fBverify_backlog\fR then not all blocks will be verified, if
814 \fBverify_backlog_batch\fR is larger than \fBverify_backlog\fR, some blocks
815 will be verified more than once.
817 .B stonewall "\fR,\fP wait_for_previous"
818 Wait for preceding jobs in the job file to exit before starting this one.
819 \fBstonewall\fR implies \fBnew_group\fR.
822 Start a new reporting group. If not given, all jobs in a file will be part
823 of the same reporting group, unless separated by a stonewall.
825 .BI numjobs \fR=\fPint
826 Number of clones (processes/threads performing the same workload) of this job.
830 If set, display per-group reports instead of per-job when \fBnumjobs\fR is
834 Use threads created with \fBpthread_create\fR\|(3) instead of processes created
835 with \fBfork\fR\|(2).
837 .BI zonesize \fR=\fPint
838 Divide file into zones of the specified size in bytes. See \fBzoneskip\fR.
840 .BI zoneskip \fR=\fPint
841 Skip the specified number of bytes when \fBzonesize\fR bytes of data have been
844 .BI write_iolog \fR=\fPstr
845 Write the issued I/O patterns to the specified file. Specify a separate file
846 for each job, otherwise the iologs will be interspersed and the file may be
849 .BI read_iolog \fR=\fPstr
850 Replay the I/O patterns contained in the specified file generated by
851 \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file.
853 .BI replay_no_stall \fR=\fPint
854 While replaying I/O patterns using \fBread_iolog\fR the default behavior
855 attempts to respect timing information between I/Os. Enabling
856 \fBreplay_no_stall\fR causes I/Os to be replayed as fast as possible while
857 still respecting ordering.
859 .BI replay_redirect \fR=\fPstr
860 While replaying I/O patterns using \fBread_iolog\fR the default behavior
861 is to replay the IOPS onto the major/minor device that each IOP was recorded
862 from. Setting \fBreplay_redirect\fR causes all IOPS to be replayed onto the
863 single specified device regardless of the device it was recorded from.
865 .BI write_bw_log \fR=\fPstr
866 If given, write a bandwidth log of the jobs in this job file. Can be used to
867 store data of the bandwidth of the jobs in their lifetime. The included
868 fio_generate_plots script uses gnuplot to turn these text files into nice
869 graphs. See \fBwrite_log_log\fR for behaviour of given filename. For this
870 option, the postfix is _bw.log.
872 .BI write_lat_log \fR=\fPstr
873 Same as \fBwrite_bw_log\fR, but writes I/O completion latencies. If no
874 filename is given with this option, the default filename of "jobname_type.log"
875 is used. Even if the filename is given, fio will still append the type of log.
877 .BI write_iops_log \fR=\fPstr
878 Same as \fBwrite_bw_log\fR, but writes IOPS. If no filename is given with this
879 option, the default filename of "jobname_type.log" is used. Even if the
880 filename is given, fio will still append the type of log.
882 .BI log_avg_msec \fR=\fPint
883 By default, fio will log an entry in the iops, latency, or bw log for every
884 IO that completes. When writing to the disk log, that can quickly grow to a
885 very large size. Setting this option makes fio average the each log entry
886 over the specified period of time, reducing the resolution of the log.
889 .BI disable_lat \fR=\fPbool
890 Disable measurements of total latency numbers. Useful only for cutting
891 back the number of calls to gettimeofday, as that does impact performance at
892 really high IOPS rates. Note that to really get rid of a large amount of these
893 calls, this option must be used with disable_slat and disable_bw as well.
895 .BI disable_clat \fR=\fPbool
896 Disable measurements of completion latency numbers. See \fBdisable_lat\fR.
898 .BI disable_slat \fR=\fPbool
899 Disable measurements of submission latency numbers. See \fBdisable_lat\fR.
901 .BI disable_bw_measurement \fR=\fPbool
902 Disable measurements of throughput/bandwidth numbers. See \fBdisable_lat\fR.
904 .BI lockmem \fR=\fPint
905 Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to
906 simulate a smaller amount of memory.
908 .BI exec_prerun \fR=\fPstr
909 Before running the job, execute the specified command with \fBsystem\fR\|(3).
911 .BI exec_postrun \fR=\fPstr
912 Same as \fBexec_prerun\fR, but the command is executed after the job completes.
914 .BI ioscheduler \fR=\fPstr
915 Attempt to switch the device hosting the file to the specified I/O scheduler.
917 .BI cpuload \fR=\fPint
918 If the job is a CPU cycle-eater, attempt to use the specified percentage of
921 .BI cpuchunks \fR=\fPint
922 If the job is a CPU cycle-eater, split the load into cycles of the
923 given time in milliseconds.
925 .BI disk_util \fR=\fPbool
926 Generate disk utilization statistics if the platform supports it. Default: true.
928 .BI gtod_reduce \fR=\fPbool
929 Enable all of the gettimeofday() reducing options (disable_clat, disable_slat,
930 disable_bw) plus reduce precision of the timeout somewhat to really shrink the
931 gettimeofday() call count. With this option enabled, we only do about 0.4% of
932 the gtod() calls we would have done if all time keeping was enabled.
934 .BI gtod_cpu \fR=\fPint
935 Sometimes it's cheaper to dedicate a single thread of execution to just getting
936 the current time. Fio (and databases, for instance) are very intensive on
937 gettimeofday() calls. With this option, you can set one CPU aside for doing
938 nothing but logging current time to a shared memory location. Then the other
939 threads/processes that run IO workloads need only copy that segment, instead of
940 entering the kernel with a gettimeofday() call. The CPU set aside for doing
941 these time calls will be excluded from other uses. Fio will manually clear it
942 from the CPU mask of other jobs.
944 .BI cgroup \fR=\fPstr
945 Add job to this control group. If it doesn't exist, it will be created.
946 The system must have a mounted cgroup blkio mount point for this to work. If
947 your system doesn't have it mounted, you can do so with:
949 # mount \-t cgroup \-o blkio none /cgroup
951 .BI cgroup_weight \fR=\fPint
952 Set the weight of the cgroup to this value. See the documentation that comes
953 with the kernel, allowed values are in the range of 100..1000.
955 .BI cgroup_nodelete \fR=\fPbool
956 Normally fio will delete the cgroups it has created after the job completion.
957 To override this behavior and to leave cgroups around after the job completion,
958 set cgroup_nodelete=1. This can be useful if one wants to inspect various
959 cgroup files after job completion. Default: false
962 Instead of running as the invoking user, set the user ID to this value before
963 the thread/process does any work.
966 Set group ID, see \fBuid\fR.
968 .BI flow_id \fR=\fPint
969 The ID of the flow. If not specified, it defaults to being a global flow. See
973 Weight in token-based flow control. If this value is used, then there is a
974 \fBflow counter\fR which is used to regulate the proportion of activity between
975 two or more jobs. fio attempts to keep this flow counter near zero. The
976 \fBflow\fR parameter stands for how much should be added or subtracted to the
977 flow counter on each iteration of the main I/O loop. That is, if one job has
978 \fBflow=8\fR and another job has \fBflow=-1\fR, then there will be a roughly
979 1:8 ratio in how much one runs vs the other.
981 .BI flow_watermark \fR=\fPint
982 The maximum value that the absolute value of the flow counter is allowed to
983 reach before the job must wait for a lower value of the counter.
985 .BI flow_sleep \fR=\fPint
986 The period of time, in microseconds, to wait after the flow watermark has been
987 exceeded before retrying operations
989 .BI clat_percentiles \fR=\fPbool
990 Enable the reporting of percentiles of completion latencies.
992 .BI percentile_list \fR=\fPfloat_list
993 Overwrite the default list of percentiles for completion
994 latencies. Each number is a floating number in the range (0,100], and
995 the maximum length of the list is 20. Use ':' to separate the
996 numbers. For example, \-\-percentile_list=99.5:99.9 will cause fio to
997 report the values of completion latency below which 99.5% and 99.9% of
998 the observed latencies fell, respectively.
999 .SS "Ioengine Parameters List"
1000 Some parameters are only valid when a specific ioengine is in use. These are
1001 used identically to normal parameters, with the caveat that when used on the
1002 command line, the must come after the ioengine that defines them is selected.
1004 .BI (libaio)userspace_reap
1005 Normally, with the libaio engine in use, fio will use
1006 the io_getevents system call to reap newly returned events.
1007 With this flag turned on, the AIO ring will be read directly
1008 from user-space to reap events. The reaping mode is only
1009 enabled when polling for a minimum of 0 events (eg when
1010 iodepth_batch_complete=0).
1012 .BI (net,netsplice)hostname \fR=\fPstr
1013 The host name or IP address to use for TCP or UDP based IO.
1014 If the job is a TCP listener or UDP reader, the hostname is not
1015 used and must be omitted.
1017 .BI (net,netsplice)port \fR=\fPint
1018 The TCP or UDP port to bind to or connect to.
1020 .BI (net,netsplice)protocol \fR=\fPstr "\fR,\fP proto" \fR=\fPstr
1021 The network protocol to use. Accepted values are:
1026 Transmission control protocol
1029 Unreliable datagram protocol
1035 When the protocol is TCP or UDP, the port must also be given,
1036 as well as the hostname if the job is a TCP listener or UDP
1037 reader. For unix sockets, the normal filename option should be
1038 used and the port is invalid.
1041 .BI (net,netsplice)listen
1042 For TCP network connections, tell fio to listen for incoming
1043 connections rather than initiating an outgoing connection. The
1044 hostname must be omitted if this option is used.
1046 While running, \fBfio\fR will display the status of the created jobs. For
1050 Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
1053 The characters in the first set of brackets denote the current status of each
1054 threads. The possible values are:
1060 Setup but not started.
1066 Initialized, waiting.
1069 Running, doing sequential reads.
1072 Running, doing random reads.
1075 Running, doing sequential writes.
1078 Running, doing random writes.
1081 Running, doing mixed sequential reads/writes.
1084 Running, doing mixed random reads/writes.
1087 Running, currently waiting for \fBfsync\fR\|(2).
1090 Running, verifying written data.
1093 Exited, not reaped by main thread.
1096 Exited, thread reaped.
1100 The second set of brackets shows the estimated completion percentage of
1101 the current group. The third set shows the read and write I/O rate,
1102 respectively. Finally, the estimated run time of the job is displayed.
1104 When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data
1105 for each thread, each group of threads, and each disk, in that order.
1107 Per-thread statistics first show the threads client number, group-id, and
1108 error code. The remaining figures are as follows:
1112 Number of megabytes of I/O performed.
1115 Average data rate (bandwidth).
1121 Submission latency minimum, maximum, average and standard deviation. This is
1122 the time it took to submit the I/O.
1125 Completion latency minimum, maximum, average and standard deviation. This
1126 is the time between submission and completion.
1129 Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average
1130 and standard deviation.
1133 CPU usage statistics. Includes user and system time, number of context switches
1134 this thread went through and number of major and minor page faults.
1137 Distribution of I/O depths. Each depth includes everything less than (or equal)
1138 to it, but greater than the previous depth.
1141 Number of read/write requests issued, and number of short read/write requests.
1144 Distribution of I/O completion latencies. The numbers follow the same pattern
1148 The group statistics show:
1153 Number of megabytes I/O performed.
1156 Aggregate bandwidth of threads in the group.
1159 Minimum average bandwidth a thread saw.
1162 Maximum average bandwidth a thread saw.
1165 Shortest runtime of threads in the group.
1168 Longest runtime of threads in the group.
1172 Finally, disk statistics are printed with reads first:
1177 Number of I/Os performed by all groups.
1180 Number of merges in the I/O scheduler.
1183 Number of ticks we kept the disk busy.
1186 Total time spent in the disk queue.
1193 If the \fB\-\-minimal\fR option is given, the results will be printed in a
1194 semicolon-delimited format suitable for scripted use - a job description
1195 (if provided) follows on a new line. Note that the first
1196 number in the line is the version number. If the output has to be changed
1197 for some reason, this number will be incremented by 1 to signify that
1198 change. The fields are:
1201 .B terse version, fio version, jobname, groupid, error
1205 .B Total I/O \fR(KB)\fP, bandwidth \fR(KB/s)\fP, IOPS, runtime \fR(ms)\fP
1209 .B min, max, mean, standard deviation
1213 .B min, max, mean, standard deviation
1215 Completion latency percentiles (20 fields):
1217 .B Xth percentile=usec
1221 .B min, max, mean, standard deviation
1225 .B min, max, aggregate percentage of total, mean, standard deviation
1231 .B Total I/O \fR(KB)\fP, bandwidth \fR(KB/s)\fP, IOPS, runtime \fR(ms)\fP
1235 .B min, max, mean, standard deviation
1239 .B min, max, mean, standard deviation
1241 Completion latency percentiles (20 fields):
1243 .B Xth percentile=usec
1247 .B min, max, mean, standard deviation
1251 .B min, max, aggregate percentage of total, mean, standard deviation
1257 .B user, system, context switches, major page faults, minor page faults
1260 IO depth distribution:
1262 .B <=1, 2, 4, 8, 16, 32, >=64
1265 IO latency distribution:
1269 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000
1273 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, 2000, >=2000
1277 Disk utilization (1 for each disk used):
1279 .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
1282 Error Info (dependent on continue_on_error, default off):
1284 .B total # errors, first error code
1287 .B text description (if provided in config - appears on newline)
1290 Normally you would run fio as a stand-alone application on the machine
1291 where the IO workload should be generated. However, it is also possible to
1292 run the frontend and backend of fio separately. This makes it possible to
1293 have a fio server running on the machine(s) where the IO workload should
1294 be running, while controlling it from another machine.
1296 To start the server, you would do:
1298 \fBfio \-\-server=args\fR
1300 on that machine, where args defines what fio listens to. The arguments
1301 are of the form 'type:hostname or IP:port'. 'type' is either 'ip' (or ip4)
1302 for TCP/IP v4, 'ip6' for TCP/IP v6, or 'sock' for a local unix domain socket.
1303 'hostname' is either a hostname or IP address, and 'port' is the port to
1304 listen to (only valid for TCP/IP, not a local socket). Some examples:
1308 Start a fio server, listening on all interfaces on the default port (8765).
1310 2) fio --server=ip:hostname,4444
1312 Start a fio server, listening on IP belonging to hostname and on port 4444.
1314 3) fio --server=ip6:::1,4444
1316 Start a fio server, listening on IPv6 localhost ::1 and on port 4444.
1318 4) fio --server=,4444
1320 Start a fio server, listening on all interfaces on port 4444.
1322 5) fio --server=1.2.3.4
1324 Start a fio server, listening on IP 1.2.3.4 on the default port.
1326 6) fio --server=sock:/tmp/fio.sock
1328 Start a fio server, listening on the local socket /tmp/fio.sock.
1330 When a server is running, you can connect to it from a client. The client
1333 fio --local-args --client=server --remote-args <job file(s)>
1335 where --local-args are arguments that are local to the client where it is
1336 running, 'server' is the connect string, and --remote-args and <job file(s)>
1337 are sent to the server. The 'server' string follows the same format as it
1338 does on the server side, to allow IP/hostname/socket and port strings.
1339 You can connect to multiple clients as well, to do that you could run:
1341 fio --client=server2 --client=server2 <job file(s)>
1345 was written by Jens Axboe <jens.axboe@oracle.com>,
1346 now Jens Axboe <jaxboe@fusionio.com>.
1348 This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based
1349 on documentation by Jens Axboe.
1350 .SH "REPORTING BUGS"
1351 Report bugs to the \fBfio\fR mailing list <fio@vger.kernel.org>.
1354 For further documentation see \fBHOWTO\fR and \fBREADME\fR.
1356 Sample jobfiles are available in the \fBexamples\fR directory.
projects / fio.git / blob