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. \fBbssplit\fR also supports giving separate
191 splits to reads and writes. The format is identical to what the
192 \fBbs\fR option accepts, the read and write parts are separated with a
195 .B blocksize_unaligned\fR,\fP bs_unaligned
196 If set, any size in \fBblocksize_range\fR may be used. This typically won't
197 work with direct I/O, as that normally requires sector alignment.
199 .BI blockalign \fR=\fPint[,int] "\fR,\fB ba" \fR=\fPint[,int]
200 At what boundary to align random IO offsets. Defaults to the same as 'blocksize'
201 the minimum blocksize given. Minimum alignment is typically 512b
202 for using direct IO, though it usually depends on the hardware block size.
203 This option is mutually exclusive with using a random map for files, so it
204 will turn off that option.
207 Initialise buffers with all zeros. Default: fill buffers with random data.
210 If this option is given, fio will refill the IO buffers on every submit. The
211 default is to only fill it at init time and reuse that data. Only makes sense
212 if zero_buffers isn't specified, naturally. If data verification is enabled,
213 refill_buffers is also automatically enabled.
215 .BI nrfiles \fR=\fPint
216 Number of files to use for this job. Default: 1.
218 .BI openfiles \fR=\fPint
219 Number of files to keep open at the same time. Default: \fBnrfiles\fR.
221 .BI file_service_type \fR=\fPstr
222 Defines how files to service are selected. The following types are defined:
227 Choose a file at random
230 Round robin over open files (default).
232 Do each file in the set sequentially.
235 The number of I/Os to issue before switching a new file can be specified by
236 appending `:\fIint\fR' to the service type.
239 .BI ioengine \fR=\fPstr
240 Defines how the job issues I/O. The following types are defined:
245 Basic \fIread\fR\|(2) or \fIwrite\fR\|(2) I/O. \fIfseek\fR\|(2) is used to
246 position the I/O location.
249 Basic \fIpread\fR\|(2) or \fIpwrite\fR\|(2) I/O.
252 Basic \fIreadv\fR\|(2) or \fIwritev\fR\|(2) I/O. Will emulate queuing by
253 coalescing adjacents IOs into a single submission.
256 Linux native asynchronous I/O.
259 glibc POSIX asynchronous I/O using \fIaio_read\fR\|(3) and \fIaio_write\fR\|(3).
262 File is memory mapped with \fImmap\fR\|(2) and data copied using
266 \fIsplice\fR\|(2) is used to transfer the data and \fIvmsplice\fR\|(2) to
267 transfer data from user-space to the kernel.
270 Use the syslet system calls to make regular read/write asynchronous.
273 SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if
274 the target is an sg character device, we use \fIread\fR\|(2) and
275 \fIwrite\fR\|(2) for asynchronous I/O.
278 Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR
279 itself and for debugging and testing purposes.
282 Transfer over the network. \fBfilename\fR must be set appropriately to
283 `\fIhost\fR/\fIport\fR' regardless of data direction. If receiving, only the
284 \fIport\fR argument is used.
287 Like \fBnet\fR, but uses \fIsplice\fR\|(2) and \fIvmsplice\fR\|(2) to map data
291 Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and
292 \fBcpucycles\fR parameters.
295 The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface
296 approach to asycnronous I/O.
298 See <http://www.xmailserver.org/guasi\-lib.html>.
301 Loads an external I/O engine object file. Append the engine filename as
306 .BI iodepth \fR=\fPint
307 Number of I/O units to keep in flight against the file. Default: 1.
309 .BI iodepth_batch \fR=\fPint
310 Number of I/Os to submit at once. Default: \fBiodepth\fR.
312 .BI iodepth_low \fR=\fPint
313 Low watermark indicating when to start filling the queue again. Default:
316 .BI direct \fR=\fPbool
317 If true, use non-buffered I/O (usually O_DIRECT). Default: false.
319 .BI buffered \fR=\fPbool
320 If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter.
323 .BI offset \fR=\fPint
324 Offset in the file to start I/O. Data before the offset will not be touched.
327 How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If
328 0, don't sync. Default: 0.
330 .BI overwrite \fR=\fPbool
331 If writing, setup the file first and do overwrites. Default: false.
333 .BI end_fsync \fR=\fPbool
334 Sync file contents when job exits. Default: false.
336 .BI fsync_on_close \fR=\fPbool
337 If true, sync file contents on close. This differs from \fBend_fsync\fR in that
338 it will happen on every close, not just at the end of the job. Default: false.
340 .BI rwmixcycle \fR=\fPint
341 How many milliseconds before switching between reads and writes for a mixed
342 workload. Default: 500ms.
344 .BI rwmixread \fR=\fPint
345 Percentage of a mixed workload that should be reads. Default: 50.
347 .BI rwmixwrite \fR=\fPint
348 Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and
349 \fBrwmixwrite\fR are given and do not sum to 100%, the latter of the two
350 overrides the first. This may interfere with a given rate setting, if fio is
351 asked to limit reads or writes to a certain rate. If that is the case, then
352 the distribution may be skewed. Default: 50.
355 Normally \fBfio\fR will cover every block of the file when doing random I/O. If
356 this parameter is given, a new offset will be chosen without looking at past
357 I/O history. This parameter is mutually exclusive with \fBverify\fR.
360 Run job with given nice value. See \fInice\fR\|(2).
363 Set I/O priority value of this job between 0 (highest) and 7 (lowest). See
366 .BI prioclass \fR=\fPint
367 Set I/O priority class. See \fIionice\fR\|(1).
369 .BI thinktime \fR=\fPint
370 Stall job for given number of microseconds between issuing I/Os.
372 .BI thinktime_spin \fR=\fPint
373 Pretend to spend CPU time for given number of microseconds, sleeping the rest
374 of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set.
376 .BI thinktime_blocks \fR=\fPint
377 Number of blocks to issue before waiting \fBthinktime\fR microseconds.
381 Cap bandwidth used by this job. The number is in bytes/sec, the normal postfix
382 rules apply. You can use \fBrate\fR=500k to limit reads and writes to 500k each,
383 or you can specify read and writes separately. Using \fBrate\fR=1m,500k would
384 limit reads to 1MB/sec and writes to 500KB/sec. Capping only reads or writes
385 can be done with \fBrate\fR=,500k or \fBrate\fR=500k,. The former will only
386 limit writes (to 500KB/sec), the latter will only limit reads.
388 .BI ratemin \fR=\fPint
389 Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth.
390 Failing to meet this requirement will cause the job to exit. The same format
391 as \fBrate\fR is used for read vs write separation.
393 .BI rate_iops \fR=\fPint
394 Cap the bandwidth to this number of IOPS. Basically the same as rate, just
395 specified independently of bandwidth. The same format as \fBrate\fR is used for
396 read vs write seperation. If \fBblocksize\fR is a range, the smallest block
397 size is used as the metric.
399 .BI rate_iops_min \fR=\fPint
400 If this rate of I/O is not met, the job will exit. The same format as \fBrate\fR
401 is used for read vs write seperation.
403 .BI ratecycle \fR=\fPint
404 Average bandwidth for \fBrate\fR and \fBratemin\fR over this number of
405 milliseconds. Default: 1000ms.
407 .BI cpumask \fR=\fPint
408 Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job
409 may run on. See \fBsched_setaffinity\fR\|(2).
411 .BI cpus_allowed \fR=\fPstr
412 Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers.
414 .BI startdelay \fR=\fPint
415 Delay start of job for the specified number of seconds.
417 .BI runtime \fR=\fPint
418 Terminate processing after the specified number of seconds.
421 If given, run for the specified \fBruntime\fR duration even if the files are
422 completely read or written. The same workload will be repeated as many times
423 as \fBruntime\fR allows.
425 .BI ramp_time \fR=\fPint
426 If set, fio will run the specified workload for this amount of time before
427 logging any performance numbers. Useful for letting performance settle before
428 logging results, thus minimizing the runtime required for stable results. Note
429 that the \fBramp_time\fR is considered lead in time for a job, thus it will
430 increase the total runtime if a special timeout or runtime is specified.
432 .BI invalidate \fR=\fPbool
433 Invalidate buffer-cache for the file prior to starting I/O. Default: true.
436 Use synchronous I/O for buffered writes. For the majority of I/O engines,
437 this means using O_SYNC. Default: false.
439 .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr
440 Allocation method for I/O unit buffer. Allowed values are:
445 Allocate memory with \fImalloc\fR\|(3).
448 Use shared memory buffers allocated through \fIshmget\fR\|(2).
451 Same as \fBshm\fR, but use huge pages as backing.
454 Use \fImmap\fR\|(2) for allocation. Uses anonymous memory unless a filename
455 is given after the option in the format `:\fIfile\fR'.
458 Same as \fBmmap\fR, but use huge files as backing.
461 The amount of memory allocated is the maximum allowed \fBblocksize\fR for the
462 job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work,
463 the system must have free huge pages allocated. \fBmmaphuge\fR also needs to
464 have hugetlbfs mounted, and \fIfile\fR must point there.
467 .BI hugepage\-size \fR=\fPint
468 Defines the size of a huge page. Must be at least equal to the system setting.
469 Should be a multiple of 1MiB. Default: 4MiB.
472 Terminate all jobs when one finishes. Default: wait for each job to finish.
474 .BI bwavgtime \fR=\fPint
475 Average bandwidth calculations over the given time in milliseconds. Default:
478 .BI create_serialize \fR=\fPbool
479 If true, serialize file creation for the jobs. Default: true.
481 .BI create_fsync \fR=\fPbool
482 \fIfsync\fR\|(2) data file after creation. Default: true.
484 .BI create_on_open \fR=\fPbool
485 If true, the files are not created until they are opened for IO by the job.
487 .BI pre_read \fR=\fPbool
488 If this is given, files will be pre-read into memory before starting the given
489 IO operation. This will also clear the \fR \fBinvalidate\fR flag, since it is
490 pointless to pre-read and then drop the cache.
492 .BI unlink \fR=\fPbool
493 Unlink job files when done. Default: false.
496 Specifies the number of iterations (runs of the same workload) of this job.
499 .BI do_verify \fR=\fPbool
500 Run the verify phase after a write phase. Only valid if \fBverify\fR is set.
503 .BI verify \fR=\fPstr
504 Method of verifying file contents after each iteration of the job. Allowed
509 .B md5 crc16 crc32 crc64 crc7 sha256 sha512
510 Store appropriate checksum in the header of each block.
513 Write extra information about each I/O (timestamp, block number, etc.). The
514 block number is verified.
517 Fill I/O buffers with a specific pattern that is used to verify. The pattern is
518 specified by appending `:\fIint\fR' to the parameter. \fIint\fR cannot be larger
522 Pretend to verify. Used for testing internals.
526 .BI verify_sort \fR=\fPbool
527 If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to
528 read them back in a sorted manner. Default: true.
530 .BI verify_offset \fR=\fPint
531 Swap the verification header with data somewhere else in the block before
532 writing. It is swapped back before verifying.
534 .BI verify_interval \fR=\fPint
535 Write the verification header for this number of bytes, which should divide
536 \fBblocksize\fR. Default: \fBblocksize\fR.
538 .BI verify_fatal \fR=\fPbool
539 If true, exit the job on the first observed verification failure. Default:
543 Wait for preceeding jobs in the job file to exit before starting this one.
544 \fBstonewall\fR implies \fBnew_group\fR.
547 Start a new reporting group. If not given, all jobs in a file will be part
548 of the same reporting group, unless separated by a stonewall.
550 .BI numjobs \fR=\fPint
551 Number of clones (processes/threads performing the same workload) of this job.
555 If set, display per-group reports instead of per-job when \fBnumjobs\fR is
559 Use threads created with \fBpthread_create\fR\|(3) instead of processes created
560 with \fBfork\fR\|(2).
562 .BI zonesize \fR=\fPint
563 Divide file into zones of the specified size in bytes. See \fBzoneskip\fR.
565 .BI zoneskip \fR=\fPint
566 Skip the specified number of bytes when \fBzonesize\fR bytes of data have been
569 .BI write_iolog \fR=\fPstr
570 Write the issued I/O patterns to the specified file.
572 .BI read_iolog \fR=\fPstr
573 Replay the I/O patterns contained in the specified file generated by
574 \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file.
576 .B write_bw_log \fR=\fPstr
577 If given, write a bandwidth log of the jobs in this job file. Can be used to
578 store data of the bandwidth of the jobs in their lifetime. The included
579 fio_generate_plots script uses gnuplot to turn these text files into nice
580 graphs. See \fBwrite_log_log\fR for behaviour of given filename. For this
581 option, the postfix is _bw.log.
584 Same as \fBwrite_bw_log\fR, but writes I/O completion latencies. If no
585 filename is given with this option, the default filename of "jobname_type.log"
586 is used. Even if the filename is given, fio will still append the type of log.
588 .B disable_clat \fR=\fPbool
589 Disable measurements of completion latency numbers. Useful only for cutting
590 back the number of calls to gettimeofday, as that does impact performance at
591 really high IOPS rates. Note that to really get rid of a large amount of these
592 calls, this option must be used with disable_slat and disable_bw as well.
594 .B disable_slat \fR=\fPbool
595 Disable measurements of submission latency numbers. See \fBdisable_clat\fR.
597 .B disable_bw_measurement \fR=\fPbool
598 Disable measurements of throughput/bandwidth numbers. See \fBdisable_clat\fR.
600 .BI lockmem \fR=\fPint
601 Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to
602 simulate a smaller amount of memory.
604 .BI exec_prerun \fR=\fPstr
605 Before running the job, execute the specified command with \fBsystem\fR\|(3).
607 .BI exec_postrun \fR=\fPstr
608 Same as \fBexec_prerun\fR, but the command is executed after the job completes.
610 .BI ioscheduler \fR=\fPstr
611 Attempt to switch the device hosting the file to the specified I/O scheduler.
613 .BI cpuload \fR=\fPint
614 If the job is a CPU cycle-eater, attempt to use the specified percentage of
617 .BI cpuchunks \fR=\fPint
618 If the job is a CPU cycle-eater, split the load into cycles of the
619 given time in milliseconds.
621 .BI disk_util \fR=\fPbool
622 Generate disk utilization statistics if the platform supports it. Default: true.
624 .BI gtod_reduce \fR=\fPbool
625 Enable all of the gettimeofday() reducing options (disable_clat, disable_slat,
626 disable_bw) plus reduce precision of the timeout somewhat to really shrink the
627 gettimeofday() call count. With this option enabled, we only do about 0.4% of
628 the gtod() calls we would have done if all time keeping was enabled.
630 .BI gtod_cpu \fR=\fPint
631 Sometimes it's cheaper to dedicate a single thread of execution to just getting
632 the current time. Fio (and databases, for instance) are very intensive on
633 gettimeofday() calls. With this option, you can set one CPU aside for doing
634 nothing but logging current time to a shared memory location. Then the other
635 threads/processes that run IO workloads need only copy that segment, instead of
636 entering the kernel with a gettimeofday() call. The CPU set aside for doing
637 these time calls will be excluded from other uses. Fio will manually clear it
638 from the CPU mask of other jobs.
640 While running, \fBfio\fR will display the status of the created jobs. For
644 Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s]
647 The characters in the first set of brackets denote the current status of each
648 threads. The possible values are:
654 Setup but not started.
660 Initialized, waiting.
663 Running, doing sequential reads.
666 Running, doing random reads.
669 Running, doing sequential writes.
672 Running, doing random writes.
675 Running, doing mixed sequential reads/writes.
678 Running, doing mixed random reads/writes.
681 Running, currently waiting for \fBfsync\fR\|(2).
684 Running, verifying written data.
687 Exited, not reaped by main thread.
690 Exited, thread reaped.
694 The second set of brackets shows the estimated completion percentage of
695 the current group. The third set shows the read and write I/O rate,
696 respectively. Finally, the estimated run time of the job is displayed.
698 When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data
699 for each thread, each group of threads, and each disk, in that order.
701 Per-thread statistics first show the threads client number, group-id, and
702 error code. The remaining figures are as follows:
706 Number of megabytes of I/O performed.
709 Average data rate (bandwidth).
715 Submission latency minimum, maximum, average and standard deviation. This is
716 the time it took to submit the I/O.
719 Completion latency minimum, maximum, average and standard deviation. This
720 is the time between submission and completion.
723 Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average
724 and standard deviation.
727 CPU usage statistics. Includes user and system time, number of context switches
728 this thread went through and number of major and minor page faults.
731 Distribution of I/O depths. Each depth includes everything less than (or equal)
732 to it, but greater than the previous depth.
735 Number of read/write requests issued, and number of short read/write requests.
738 Distribution of I/O completion latencies. The numbers follow the same pattern
742 The group statistics show:
747 Number of megabytes I/O performed.
750 Aggregate bandwidth of threads in the group.
753 Minimum average bandwidth a thread saw.
756 Maximum average bandwidth a thread saw.
759 Shortest runtime of threads in the group.
762 Longest runtime of threads in the group.
766 Finally, disk statistics are printed with reads first:
771 Number of I/Os performed by all groups.
774 Number of merges in the I/O scheduler.
777 Number of ticks we kept the disk busy.
780 Total time spent in the disk queue.
787 If the \fB\-\-minimal\fR option is given, the results will be printed in a
788 semicolon-delimited format suitable for scripted use. The fields are:
791 .B jobname, groupid, error
795 .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP
799 .B min, max, mean, standard deviation
803 .B min, max, mean, standard deviation
807 .B min, max, aggregate percentage of total, mean, standard deviation
813 .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP
817 .B min, max, mean, standard deviation
821 .B min, max, mean, standard deviation
825 .B min, max, aggregate percentage of total, mean, standard deviation
831 .B user, system, context switches, major page faults, minor page faults
834 IO depth distribution:
836 .B <=1, 2, 4, 8, 16, 32, >=64
839 IO latency distribution (ms):
841 .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, >=2000
848 was written by Jens Axboe <jens.axboe@oracle.com>.
850 This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based
851 on documentation by Jens Axboe.
853 Report bugs to the \fBfio\fR mailing list <fio@vger.kernel.org>.
856 For further documentation see \fBHOWTO\fR and \fBREADME\fR.
858 Sample jobfiles are available in the \fBexamples\fR directory.
projects / fio.git / blob