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 \-\-output \fR=\fPfilename
16 Write output to \fIfilename\fR.
18 .BI \-\-timeout \fR=\fPtimeout
19 Limit run time to \fItimeout\fR seconds.
22 Generate per-job latency logs.
25 Generate per-job bandwidth logs.
28 Print statistics in a terse, semicolon-delimited format.
30 .BI \-\-showcmd \fR=\fPjobfile
31 Convert \fIjobfile\fR to a set of command-line options.
34 Enable read-only safety checks.
36 .BI \-\-eta \fR=\fPwhen
37 Specifies when real-time ETA estimate should be printed. \fIwhen\fR may
38 be one of `always', `never' or `auto'.
40 .BI \-\-section \fR=\fPsec
41 Only run section \fIsec\fR from job file.
43 .BI \-\-cmdhelp \fR=\fPcommand
44 Print help information for \fIcommand\fR. May be `all' for all commands.
46 .BI \-\-debug \fR=\fPtype
47 Enable verbose tracing of various fio actions. May be `all' for all types
48 or individual types seperated by a comma (eg --debug=io,file). `help' will
49 list all available tracing options.
52 Display usage information and exit.
55 Display version information and exit.
57 Job files are in `ini' format. They consist of one or more
58 job definitions, which begin with a job name in square brackets and
59 extend to the next job name. The job name can be any ASCII string
60 except `global', which has a special meaning. Following the job name is
61 a sequence of zero or more parameters, one per line, that define the
62 behavior of the job. Any line starting with a `;' or `#' character is
63 considered a comment and ignored.
65 If \fIjobfile\fR is specified as `-', the job file will be read from
68 The global section contains default parameters for jobs specified in the
69 job file. A job is only affected by global sections residing above it,
70 and there may be any number of global sections. Specific job definitions
71 may override any parameter set in global sections.
74 Some parameters may take arguments of a specific type. The types used are:
77 String: a sequence of alphanumeric characters.
80 SI integer: a whole number, possibly containing a suffix denoting the base unit
81 of the value. Accepted suffixes are `k', 'M' and 'G', denoting kilo (1024),
82 mega (1024*1024) and giga (1024*1024*1024) respectively. If prefixed with '0x',
83 the value is assumed to be base 16 (hexadecimal).
86 Boolean: a true or false value. `0' denotes false, `1' denotes true.
89 Integer range: a range of integers specified in the format
90 \fIlower\fR:\fIupper\fR or \fIlower\fR\-\fIupper\fR. \fIlower\fR and
91 \fIupper\fR may contain a suffix as described above. If an option allows two
92 sets of ranges, they are separated with a `,' or `/' character. For example:
97 May be used to override the job name. On the command line, this parameter
98 has the special purpose of signalling the start of a new job.
100 .BI description \fR=\fPstr
101 Human-readable description of the job. It is printed when the job is run, but
102 otherwise has no special purpose.
104 .BI directory \fR=\fPstr
105 Prefix filenames with this directory. Used to place files in a location other
108 .BI filename \fR=\fPstr
110 normally makes up a file name based on the job name, thread number, and file
111 number. If you want to share files between threads in a job or several jobs,
112 specify a \fIfilename\fR for each of them to override the default. If the I/O
113 engine used is `net', \fIfilename\fR is the host and port to connect to in the
114 format \fIhost\fR/\fIport\fR. If the I/O engine is file-based, you can specify
115 a number of files by separating the names with a `:' character. `\-' is a
116 reserved name, meaning stdin or stdout, depending on the read/write direction
119 .BI opendir \fR=\fPstr
120 Recursively open any files below directory \fIstr\fR.
122 .BI readwrite \fR=\fPstr "\fR,\fP rw" \fR=\fPstr
123 Type of I/O pattern. Accepted values are:
140 Mixed sequential reads and writes.
143 Mixed random reads and writes.
146 For mixed I/O, the default split is 50/50. For random I/O, the number of I/Os
147 to perform before getting a new offset can be specified by appending
148 `:\fIint\fR' to the pattern type. The default is 1.
151 .BI randrepeat \fR=\fPbool
152 Seed the random number generator in a predictable way so results are repeatable
153 across runs. Default: true.
155 .BI fadvise_hint \fR=\fPbool
156 Disable use of \fIposix_fadvise\fR\|(2) to advise the kernel what I/O patterns
157 are likely to be issued. Default: true.
160 Total size of I/O for this job. \fBfio\fR will run until this many bytes have
161 been transfered, unless limited by other options (\fBruntime\fR, for instance).
162 Unless \fBnr_files\fR and \fBfilesize\fR options are given, this amount will be
163 divided between the available files for the job.
165 .BI filesize \fR=\fPirange
166 Individual file sizes. May be a range, in which case \fBfio\fR will select sizes
167 for files at random within the given range, limited to \fBsize\fR in total (if
168 that is given). If \fBfilesize\fR is not specified, each created file is the
171 .BI blocksize \fR=\fPint[,int] "\fR,\fB bs" \fR=\fPint[,int]
172 Block size for I/O units. Default: 4k. Values for reads and writes can be
173 specified seperately in the format \fIread\fR,\fIwrite\fR, either of
174 which may be empty to leave that value at its default.
176 .BI blocksize_range \fR=\fPirange[,irange] "\fR,\fB bsrange" \fR=\fPirange[,irange]
177 Specify a range of I/O block sizes. The issued I/O unit will always be a
178 multiple of the minimum size, unless \fBblocksize_unaligned\fR is set. Applies
179 to both reads and writes if only one range is given, but can be specified
180 seperately with a comma seperating the values. Example: bsrange=1k-4k,2k-8k.
181 Also (see \fBblocksize\fR).
183 .BI bssplit \fR=\fPstr
184 This option allows even finer grained control of the block sizes issued,
185 not just even splits between them. With this option, you can weight various
186 block sizes for exact control of the issued IO for a job that has mixed
187 block sizes. The format of the option is bssplit=blocksize/percentage,
188 optionally adding as many definitions as needed seperated by a colon.
189 Example: bssplit=4k/10:64k/50:32k/40 would issue 50% 64k blocks, 10% 4k
190 blocks and 40% 32k blocks.
192 .B blocksize_unaligned\fR,\fP bs_unaligned
193 If set, any size in \fBblocksize_range\fR may be used. This typically won't
194 work with direct I/O, as that normally requires sector alignment.
197 Initialise buffers with all zeros. Default: fill buffers with random data.
199 .BI nrfiles \fR=\fPint
200 Number of files to use for this job. Default: 1.
202 .BI openfiles \fR=\fPint
203 Number of files to keep open at the same time. Default: \fBnrfiles\fR.
205 .BI file_service_type \fR=\fPstr
206 Defines how files to service are selected. The following types are defined:
211 Choose a file at random
214 Round robin over open files (default).
217 The number of I/Os to issue before switching a new file can be specified by
218 appending `:\fIint\fR' to the service type.
221 .BI ioengine \fR=\fPstr
222 Defines how the job issues I/O. The following types are defined:
227 Basic \fIread\fR\|(2) or \fIwrite\fR\|(2) I/O. \fIfseek\fR\|(2) is used to
228 position the I/O location.
231 Basic \fIpread\fR\|(2) or \fIpwrite\fR\|(2) I/O.
234 Basic \fIreadv\fR\|(2) or \fIwritev\fR\|(2) I/O. Will emulate queuing by
235 coalescing adjacents IOs into a single submission.
238 Linux native asynchronous I/O.
241 glibc POSIX asynchronous I/O using \fIaio_read\fR\|(3) and \fIaio_write\fR\|(3).
244 File is memory mapped with \fImmap\fR\|(2) and data copied using
248 \fIsplice\fR\|(2) is used to transfer the data and \fIvmsplice\fR\|(2) to
249 transfer data from user-space to the kernel.
252 Use the syslet system calls to make regular read/write asynchronous.
255 SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if
256 the target is an sg character device, we use \fIread\fR\|(2) and
257 \fIwrite\fR\|(2) for asynchronous I/O.
260 Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR
261 itself and for debugging and testing purposes.
264 Transfer over the network. \fBfilename\fR must be set appropriately to
265 `\fIhost\fR/\fIport\fR' regardless of data direction. If receiving, only the
266 \fIport\fR argument is used.
269 Like \fBnet\fR, but uses \fIsplice\fR\|(2) and \fIvmsplice\fR\|(2) to map data
273 Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and
274 \fBcpucycles\fR parameters.
277 The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface
278 approach to asycnronous I/O.
280 See <http://www.xmailserver.org/guasi\-lib.html>.
283 Loads an external I/O engine object file. Append the engine filename as
288 .BI iodepth \fR=\fPint
289 Number of I/O units to keep in flight against the file. Default: 1.
291 .BI iodepth_batch \fR=\fPint
292 Number of I/Os to submit at once. Default: \fBiodepth\fR.
294 .BI iodepth_low \fR=\fPint
295 Low watermark indicating when to start filling the queue again. Default:
298 .BI direct \fR=\fPbool
299 If true, use non-buffered I/O (usually O_DIRECT). Default: false.
301 .BI buffered \fR=\fPbool
302 If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter.
305 .BI offset \fR=\fPint
306 Offset in the file to start I/O. Data before the offset will not be touched.
309 How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If
310 0, don't sync. Default: 0.
312 .BI overwrite \fR=\fPbool
313 If writing, setup the file first and do overwrites. Default: false.
315 .BI end_fsync \fR=\fPbool
316 Sync file contents when job exits. Default: false.
318 .BI fsync_on_close \fR=\fPbool
319 If true, sync file contents on close. This differs from \fBend_fsync\fR in that
320 it will happen on every close, not just at the end of the job. Default: false.
322 .BI rwmixcycle \fR=\fPint
323 How many milliseconds before switching between reads and writes for a mixed
324 workload. Default: 500ms.
326 .BI rwmixread \fR=\fPint
327 Percentage of a mixed workload that should be reads. Default: 50.
329 .BI rwmixwrite \fR=\fPint
330 Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and
331 \fBwrmixwrite\fR are given and do not sum to 100%, the latter of the two
332 overrides the first. Default: 50.
335 Normally \fBfio\fR will cover every block of the file when doing random I/O. If
336 this parameter is given, a new offset will be chosen without looking at past
337 I/O history. This parameter is mutually exclusive with \fBverify\fR.
340 Run job with given nice value. See \fInice\fR\|(2).
343 Set I/O priority value of this job between 0 (highest) and 7 (lowest). See
346 .BI prioclass \fR=\fPint
347 Set I/O priority class. See \fIionice\fR\|(1).
349 .BI thinktime \fR=\fPint
350 Stall job for given number of microseconds between issuing I/Os.
352 .BI thinktime_spin \fR=\fPint
353 Pretend to spend CPU time for given number of microseconds, sleeping the rest
354 of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set.
356 .BI thinktime_blocks \fR=\fPint
357 Number of blocks to issue before waiting \fBthinktime\fR microseconds.
361 Cap bandwidth used by this job to this number of KiB/s.
363 .BI ratemin \fR=\fPint
364 Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth.
365 Failing to meet this requirement will cause the job to exit.
367 .BI rate_iops \fR=\fPint
368 Cap the bandwidth to this number of IOPS. If \fBblocksize\fR is a range, the
369 smallest block size is used as the metric.
371 .BI rate_iops_min \fR=\fPint
372 If this rate of I/O is not met, the job will exit.
374 .BI ratecycle \fR=\fPint
375 Average bandwidth for \fBrate\fR and \fBratemin\fR over this number of
376 milliseconds. Default: 1000ms.
378 .BI cpumask \fR=\fPint
379 Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job
380 may run on. See \fBsched_setaffinity\fR\|(2).
382 .BI cpus_allowed \fR=\fPstr
383 Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers.
385 .BI startdelay \fR=\fPint
386 Delay start of job for the specified number of seconds.
388 .BI runtime \fR=\fPint
389 Terminate processing after the specified number of seconds.
392 If given, run for the specified \fBruntime\fR duration even if the files are
393 completely read or written. The same workload will be repeated as many times
394 as \fBruntime\fR allows.
396 .BI invalidate \fR=\fPbool
397 Invalidate buffer-cache for the file prior to starting I/O. Default: true.
400 Use synchronous I/O for buffered writes. For the majority of I/O engines,
401 this means using O_SYNC. Default: false.
403 .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr
404 Allocation method for I/O unit buffer. Allowed values are:
409 Allocate memory with \fImalloc\fR\|(3).
412 Use shared memory buffers allocated through \fIshmget\fR\|(2).
415 Same as \fBshm\fR, but use huge pages as backing.
418 Use \fImmap\fR\|(2) for allocation. Uses anonymous memory unless a filename
419 is given after the option in the format `:\fIfile\fR'.
422 Same as \fBmmap\fR, but use huge files as backing.
425 The amount of memory allocated is the maximum allowed \fBblocksize\fR for the
426 job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work,
427 the system must have free huge pages allocated. \fBmmaphuge\fR also needs to
428 have hugetlbfs mounted, and \fIfile\fR must point there.
431 .BI hugepage\-size \fR=\fPint
432 Defines the size of a huge page. Must be at least equal to the system setting.
433 Should be a multiple of 1MiB. Default: 4MiB.
436 Terminate all jobs when one finishes. Default: wait for each job to finish.
438 .BI bwavgtime \fR=\fPint
439 Average bandwidth calculations over the given time in milliseconds. Default:
442 .BI create_serialize \fR=\fPbool
443 If true, serialize file creation for the jobs. Default: true.
445 .BI create_fsync \fR=\fPbool
446 \fIfsync\fR\|(2) data file after creation. Default: true.
448 .BI unlink \fR=\fPbool
449 Unlink job files when done. Default: false.
452 Specifies the number of iterations (runs of the same workload) of this job.
455 .BI do_verify \fR=\fPbool
456 Run the verify phase after a write phase. Only valid if \fBverify\fR is set.
459 .BI verify \fR=\fPstr
460 Method of verifying file contents after each iteration of the job. Allowed
465 .B md5 crc16 crc32 crc64 crc7 sha256 sha512
466 Store appropriate checksum in the header of each block.
469 Write extra information about each I/O (timestamp, block number, etc.). The
470 block number is verified.
473 Fill I/O buffers with a specific pattern that is used to verify. The pattern is
474 specified by appending `:\fIint\fR' to the parameter. \fIint\fR cannot be larger
478 Pretend to verify. Used for testing internals.
482 .BI verify_sort \fR=\fPbool
483 If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to
484 read them back in a sorted manner. Default: true.
486 .BI verify_offset \fR=\fPint
487 Swap the verification header with data somewhere else in the block before
488 writing. It is swapped back before verifying.
490 .BI verify_interval \fR=\fPint
491 Write the verification header for this number of bytes, which should divide
492 \fBblocksize\fR. Default: \fBblocksize\fR.
494 .BI verify_fatal \fR=\fPbool
495 If true, exit the job on the first observed verification failure. Default:
499 Wait for preceeding jobs in the job file to exit before starting this one.
500 \fBstonewall\fR implies \fBnew_group\fR.
503 Start a new reporting group. If not given, all jobs in a file will be part
504 of the same reporting group, unless separated by a stonewall.
506 .BI numjobs \fR=\fPint
507 Number of clones (processes/threads performing the same workload) of this job.
511 If set, display per-group reports instead of per-job when \fBnumjobs\fR is
515 Use threads created with \fBpthread_create\fR\|(3) instead of processes created
516 with \fBfork\fR\|(2).
518 .BI zonesize \fR=\fPint
519 Divide file into zones of the specified size in bytes. See \fBzoneskip\fR.
521 .BI zoneskip \fR=\fPint
522 Skip the specified number of bytes when \fBzonesize\fR bytes of data have been
525 .BI write_iolog \fR=\fPstr
526 Write the issued I/O patterns to the specified file.
528 .BI read_iolog \fR=\fPstr
529 Replay the I/O patterns contained in the specified file generated by
530 \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file.
533 If given, write bandwidth logs of the jobs in this file.
536 Same as \fBwrite_bw_log\fR, but writes I/O completion latencies.
538 .BI lockmem \fR=\fPint
539 Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to
540 simulate a smaller amount of memory.
542 .BI exec_prerun \fR=\fPstr
543 Before running the job, execute the specified command with \fBsystem\fR\|(3).
545 .BI exec_postrun \fR=\fPstr
546 Same as \fBexec_prerun\fR, but the command is executed after the job completes.
548 .BI ioscheduler \fR=\fPstr
549 Attempt to switch the device hosting the file to the specified I/O scheduler.
551 .BI cpuload \fR=\fPint
552 If the job is a CPU cycle-eater, attempt to use the specified percentage of
555 .BI cpuchunks \fR=\fPint
556 If the job is a CPU cycle-eater, split the load into cycles of the
557 given time in milliseconds.
559 .BI disk_util \fR=\fPbool
560 Generate disk utilization statistics if the platform supports it. Default: true.
562 While running, \fBfio\fR will display the status of the created jobs. For
566 Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
569 The characters in the first set of brackets denote the current status of each
570 threads. The possible values are:
576 Setup but not started.
582 Initialized, waiting.
585 Running, doing sequential reads.
588 Running, doing random reads.
591 Running, doing sequential writes.
594 Running, doing random writes.
597 Running, doing mixed sequential reads/writes.
600 Running, doing mixed random reads/writes.
603 Running, currently waiting for \fBfsync\fR\|(2).
606 Running, verifying written data.
609 Exited, not reaped by main thread.
612 Exited, thread reaped.
616 The second set of brackets shows the estimated completion percentage of
617 the current group. The third set shows the read and write I/O rate,
618 respectively. Finally, the estimated run time of the job is displayed.
620 When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data
621 for each thread, each group of threads, and each disk, in that order.
623 Per-thread statistics first show the threads client number, group-id, and
624 error code. The remaining figures are as follows:
628 Number of megabytes of I/O performed.
631 Average data rate (bandwidth).
637 Submission latency minimum, maximum, average and standard deviation. This is
638 the time it took to submit the I/O.
641 Completion latency minimum, maximum, average and standard deviation. This
642 is the time between submission and completion.
645 Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average
646 and standard deviation.
649 CPU usage statistics. Includes user and system time, number of context switches
650 this thread went through and number of major and minor page faults.
653 Distribution of I/O depths. Each depth includes everything less than (or equal)
654 to it, but greater than the previous depth.
657 Number of read/write requests issued, and number of short read/write requests.
660 Distribution of I/O completion latencies. The numbers follow the same pattern
664 The group statistics show:
669 Number of megabytes I/O performed.
672 Aggregate bandwidth of threads in the group.
675 Minimum average bandwidth a thread saw.
678 Maximum average bandwidth a thread saw.
681 Shortest runtime of threads in the group.
684 Longest runtime of threads in the group.
688 Finally, disk statistics are printed with reads first:
693 Number of I/Os performed by all groups.
696 Number of merges in the I/O scheduler.
699 Number of ticks we kept the disk busy.
702 Total time spent in the disk queue.
709 If the \fB\-\-minimal\fR option is given, the results will be printed in a
710 semicolon-delimited format suitable for scripted use. The fields are:
713 .B jobname, groupid, error
717 .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP
721 .B min, max, mean, standard deviation
725 .B min, max, mean, standard deviation
729 .B min, max, aggregate percentage of total, mean, standard deviation
735 .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP
739 .B min, max, mean, standard deviation
743 .B min, max, mean, standard deviation
747 .B min, max, aggregate percentage of total, mean, standard deviation
753 .B user, system, context switches, major page faults, minor page faults
756 IO depth distribution:
758 .B <=1, 2, 4, 8, 16, 32, >=64
761 IO latency distribution (ms):
763 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, >=2000
770 was written by Jens Axboe <jens.axboe@oracle.com>.
772 This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based
773 on documentation by Jens Axboe.
775 Report bugs to the \fBfio\fR mailing list <fio-devel@kernel.dk>.
778 For further documentation see \fBHOWTO\fR and \fBREADME\fR.
780 Sample jobfiles are available in the \fBexamples\fR directory.
projects / fio.git / blob