Commit | Line | Data |
---|---|---|
71bfa161 JA |
1 | Table of contents |
2 | ----------------- | |
3 | ||
4 | 1. Overview | |
5 | 2. How fio works | |
6 | 3. Running fio | |
7 | 4. Job file format | |
8 | 5. Detailed list of parameters | |
9 | 6. Normal output | |
10 | 7. Terse output | |
11 | ||
12 | ||
13 | 1.0 Overview and history | |
14 | ------------------------ | |
15 | fio was originally written to save me the hassle of writing special test | |
16 | case programs when I wanted to test a specific workload, either for | |
17 | performance reasons or to find/reproduce a bug. The process of writing | |
18 | such a test app can be tiresome, especially if you have to do it often. | |
19 | Hence I needed a tool that would be able to simulate a given io workload | |
20 | without resorting to writing a tailored test case again and again. | |
21 | ||
22 | A test work load is difficult to define, though. There can be any number | |
23 | of processes or threads involved, and they can each be using their own | |
24 | way of generating io. You could have someone dirtying large amounts of | |
25 | memory in an memory mapped file, or maybe several threads issuing | |
26 | reads using asynchronous io. fio needed to be flexible enough to | |
27 | simulate both of these cases, and many more. | |
28 | ||
29 | 2.0 How fio works | |
30 | ----------------- | |
31 | The first step in getting fio to simulate a desired io workload, is | |
32 | writing a job file describing that specific setup. A job file may contain | |
33 | any number of threads and/or files - the typical contents of the job file | |
34 | is a global section defining shared parameters, and one or more job | |
35 | sections describing the jobs involved. When run, fio parses this file | |
36 | and sets everything up as described. If we break down a job from top to | |
37 | bottom, it contains the following basic parameters: | |
38 | ||
39 | IO type Defines the io pattern issued to the file(s). | |
40 | We may only be reading sequentially from this | |
41 | file(s), or we may be writing randomly. Or even | |
42 | mixing reads and writes, sequentially or randomly. | |
43 | ||
44 | Block size In how large chunks are we issuing io? This may be | |
45 | a single value, or it may describe a range of | |
46 | block sizes. | |
47 | ||
48 | IO size How much data are we going to be reading/writing. | |
49 | ||
50 | IO engine How do we issue io? We could be memory mapping the | |
51 | file, we could be using regular read/write, we | |
52 | could be using splice, async io, or even | |
53 | SG (SCSI generic sg). | |
54 | ||
55 | IO depth If the io engine is async, how large a queueing | |
56 | depth do we want to maintain? | |
57 | ||
58 | IO type Should we be doing buffered io, or direct/raw io? | |
59 | ||
60 | Num files How many files are we spreading the workload over. | |
61 | ||
62 | Num threads How many threads or processes should we spread | |
63 | this workload over. | |
64 | ||
65 | The above are the basic parameters defined for a workload, in addition | |
66 | there's a multitude of parameters that modify other aspects of how this | |
67 | job behaves. | |
68 | ||
69 | ||
70 | 3.0 Running fio | |
71 | --------------- | |
72 | See the README file for command line parameters, there are only a few | |
73 | of them. | |
74 | ||
75 | Running fio is normally the easiest part - you just give it the job file | |
76 | (or job files) as parameters: | |
77 | ||
78 | $ fio job_file | |
79 | ||
80 | and it will start doing what the job_file tells it to do. You can give | |
81 | more than one job file on the command line, fio will serialize the running | |
82 | of those files. Internally that is the same as using the 'stonewall' | |
83 | parameter described the the parameter section. | |
84 | ||
85 | fio does not need to run as root, except if the files or devices specified | |
86 | in the job section requires that. Some other options may also be restricted, | |
87 | such as memory locking, io scheduler switching, and descreasing the nice value. | |
88 | ||
89 | ||
90 | 4.0 Job file format | |
91 | ------------------- | |
92 | As previously described, fio accepts one or more job files describing | |
93 | what it is supposed to do. The job file format is the classic ini file, | |
94 | where the names enclosed in [] brackets define the job name. You are free | |
95 | to use any ascii name you want, except 'global' which has special meaning. | |
96 | A global section sets defaults for the jobs described in that file. A job | |
97 | may override a global section parameter, and a job file may even have | |
98 | several global sections if so desired. A job is only affected by a global | |
99 | section residing above it. If the first character in a line is a ';', the | |
100 | entire line is discarded as a comment. | |
101 | ||
102 | So lets look at a really simple job file that define to threads, each | |
103 | randomly reading from a 128MiB file. | |
104 | ||
105 | ; -- start job file -- | |
106 | [global] | |
107 | rw=randread | |
108 | size=128m | |
109 | ||
110 | [job1] | |
111 | ||
112 | [job2] | |
113 | ||
114 | ; -- end job file -- | |
115 | ||
116 | As you can see, the job file sections themselves are empty as all the | |
117 | described parameters are shared. As no filename= option is given, fio | |
118 | makes up a filename for each of the jobs as it sees fit. | |
119 | ||
120 | Lets look at an example that have a number of processes writing randomly | |
121 | to files. | |
122 | ||
123 | ; -- start job file -- | |
124 | [random-writers] | |
125 | ioengine=libaio | |
126 | iodepth=4 | |
127 | rw=randwrite | |
128 | bs=32k | |
129 | direct=0 | |
130 | size=64m | |
131 | numjobs=4 | |
132 | ||
133 | ; -- end job file -- | |
134 | ||
135 | Here we have no global section, as we only have one job defined anyway. | |
136 | We want to use async io here, with a depth of 4 for each file. We also | |
137 | increased the buffer size used to 32KiB and define numjobs to 4 to | |
138 | fork 4 identical jobs. The result is 4 processes each randomly writing | |
139 | to their own 64MiB file. | |
140 | ||
141 | fio ships with a few example job files, you can also look there for | |
142 | inspiration. | |
143 | ||
144 | ||
145 | 5.0 Detailed list of parameters | |
146 | ------------------------------- | |
147 | ||
148 | This section describes in details each parameter associated with a job. | |
149 | Some parameters take an option of a given type, such as an integer or | |
150 | a string. The following types are used: | |
151 | ||
152 | str String. This is a sequence of alpha characters. | |
153 | int Integer. A whole number value, may be negative. | |
154 | siint SI integer. A whole number value, which may contain a postfix | |
155 | describing the base of the number. Accepted postfixes are k/m/g, | |
156 | meaning kilo, mega, and giga. So if you want to specifiy 4096, | |
157 | you could either write out '4096' or just give 4k. The postfixes | |
158 | signify base 2 values, so 1024 is 1k and 1024k is 1m and so on. | |
159 | bool Boolean. Usually parsed as an integer, however only defined for | |
160 | true and false (1 and 0). | |
161 | irange Integer range with postfix. Allows value range to be given, such | |
162 | as 1024-4096. Also see siint. | |
163 | ||
164 | With the above in mind, here follows the complete list of fio job | |
165 | parameters. | |
166 | ||
167 | name=str ASCII name of the job. This may be used to override the | |
168 | name printed by fio for this job. Otherwise the job | |
169 | name is used. | |
170 | ||
171 | directory=str Prefix filenames with this directory. Used to places files | |
172 | in a different location than "./". | |
173 | ||
174 | filename=str Fio normally makes up a filename based on the job name, | |
175 | thread number, and file number. If you want to share | |
176 | files between threads in a job or several jobs, specify | |
177 | a filename for each of them to override the default. | |
178 | ||
179 | rw=str Type of io pattern. Accepted values are: | |
180 | ||
181 | read Sequential reads | |
182 | write Sequential writes | |
183 | randwrite Random writes | |
184 | randread Random reads | |
185 | rw Sequential mixed reads and writes | |
186 | randrw Random mixed reads and writes | |
187 | ||
188 | For the mixed io types, the default is to split them 50/50. | |
189 | For certain types of io the result may still be skewed a bit, | |
190 | since the speed may be different. | |
191 | ||
192 | size=siint The total size of file io for this job. This may describe | |
193 | the size of the single file the job uses, or it may be | |
194 | divided between the number of files in the job. If the | |
195 | file already exists, the file size will be adjusted to this | |
196 | size if larger than the current file size. If this parameter | |
197 | is not given and the file exists, the file size will be used. | |
198 | ||
199 | bs=siint The block size used for the io units. Defaults to 4k. | |
200 | ||
201 | bsrange=irange Instead of giving a single block size, specify a range | |
202 | and fio will mix the issued io block sizes. The issued | |
203 | io unit will always be a multiple of the minimum value | |
204 | given. | |
205 | ||
206 | nrfiles=int Number of files to use for this job. Defaults to 1. | |
207 | ||
208 | ioengine=str Defines how the job issues io to the file. The following | |
209 | types are defined: | |
210 | ||
211 | sync Basic read(2) or write(2) io. lseek(2) is | |
212 | used to position the io location. | |
213 | ||
214 | libaio Linux native asynchronous io. | |
215 | ||
216 | posixaio glibc posix asynchronous io. | |
217 | ||
218 | mmap File is memory mapped and data copied | |
219 | to/from using memcpy(3). | |
220 | ||
221 | splice splice(2) is used to transfer the data and | |
222 | vmsplice(2) to transfer data from user | |
223 | space to the kernel. | |
224 | ||
225 | sg SCSI generic sg v3 io. May either be | |
226 | syncrhonous using the SG_IO ioctl, or if | |
227 | the target is an sg character device | |
228 | we use read(2) and write(2) for asynchronous | |
229 | io. | |
230 | ||
231 | iodepth=int This defines how many io units to keep in flight against | |
232 | the file. The default is 1 for each file defined in this | |
233 | job, can be overridden with a larger value for higher | |
234 | concurrency. | |
235 | ||
236 | direct=bool If value is true, use non-buffered io. This is usually | |
237 | O_DIRECT. Defaults to true. | |
238 | ||
239 | offset=siint Start io at the given offset in the file. The data before | |
240 | the given offset will not be touched. This effectively | |
241 | caps the file size at real_size - offset. | |
242 | ||
243 | fsync=int If writing to a file, issue a sync of the dirty data | |
244 | for every number of blocks given. For example, if you give | |
245 | 32 as a parameter, fio will sync the file for every 32 | |
246 | writes issued. If fio is using non-buffered io, we may | |
247 | not sync the file. The exception is the sg io engine, which | |
248 | syncronizes the disk cache anyway. | |
249 | ||
250 | overwrite=bool If writing to a file, setup the file first and do overwrites. | |
251 | ||
252 | end_fsync=bool If true, fsync file contents when the job exits. | |
253 | ||
254 | rwmixcycle=int Value in miliseconds describing how often to switch between | |
255 | reads and writes for a mixed workload. The default is | |
256 | 500 msecs. | |
257 | ||
258 | rwmixread=int How large a percentage of the mix should be reads. | |
259 | ||
260 | rwmixwrite=int How large a percentage of the mix should be writes. If both | |
261 | rwmixread and rwmixwrite is given and the values do not add | |
262 | up to 100%, the latter of the two will be used to override | |
263 | the first. | |
264 | ||
265 | nice=int Run the job with the given nice value. See man nice(2). | |
266 | ||
267 | prio=int Set the io priority value of this job. Linux limits us to | |
268 | a positive value between 0 and 7, with 0 being the highest. | |
269 | See man ionice(1). | |
270 | ||
271 | prioclass=int Set the io priority class. See man ionice(1). | |
272 | ||
273 | thinktime=int Stall the job x microseconds after an io has completed before | |
274 | issuing the next. May be used to simulate processing being | |
275 | done by an application. | |
276 | ||
277 | rate=int Cap the bandwidth used by this job to this number of KiB/sec. | |
278 | ||
279 | ratemin=int Tell fio to do whatever it can to maintain at least this | |
280 | bandwidth. | |
281 | ||
282 | ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number | |
283 | of miliseconds. | |
284 | ||
285 | cpumask=int Set the CPU affinity of this job. The parameter given is a | |
286 | bitmask of allowed CPU's the job may run on. See man | |
287 | sched_setaffinity(2). | |
288 | ||
289 | startdelay=int Start this job the specified number of seconds after fio | |
290 | has started. Only useful if the job file contains several | |
291 | jobs, and you want to delay starting some jobs to a certain | |
292 | time. | |
293 | ||
294 | timeout=int Tell fio to terminate processing after the specified number | |
295 | of seconds. It can be quite hard to determine for how long | |
296 | a specified job will run, so this parameter is handy to | |
297 | cap the total runtime to a given time. | |
298 | ||
299 | invalidate=bool Invalidate the buffer/page cache parts for this file prior | |
300 | to starting io. Defaults to true. | |
301 | ||
302 | sync=bool Use sync io for buffered writes. For the majority of the | |
303 | io engines, this means using O_SYNC. | |
304 | ||
305 | mem=str Fio can use various types of memory as the io unit buffer. | |
306 | The allowed values are: | |
307 | ||
308 | malloc Use memory from malloc(3) as the buffers. | |
309 | ||
310 | shm Use shared memory as the buffers. Allocated | |
311 | through shmget(2). | |
312 | ||
313 | mmap Use anonymous memory maps as the buffers. | |
314 | Allocated through mmap(2). | |
315 | ||
316 | The area allocated is a function of the maximum allowed | |
317 | bs size for the job, multiplied by the io depth given. | |
318 | ||
319 | exitall When one job finishes, terminate the rest. The default is | |
320 | to wait for each job to finish, sometimes that is not the | |
321 | desired action. | |
322 | ||
323 | bwavgtime=int Average the calculated bandwidth over the given time. Value | |
324 | is specified in miliseconds. | |
325 | ||
326 | create_serialize=bool If true, serialize the file creating for the jobs. | |
327 | This may be handy to avoid interleaving of data | |
328 | files, which may greatly depend on the filesystem | |
329 | used and even the number of processors in the system. | |
330 | ||
331 | create_fsync=bool fsync the data file after creation. This is the | |
332 | default. | |
333 | ||
334 | unlink Unlink the job files when done. fio defaults to doing this, | |
335 | if it created the file itself. | |
336 | ||
337 | loops=int Run the specified number of iterations of this job. Used | |
338 | to repeat the same workload a given number of times. Defaults | |
339 | to 1. | |
340 | ||
341 | verify=str If writing to a file, fio can verify the file contents | |
342 | after each iteration of the job. The allowed values are: | |
343 | ||
344 | md5 Use an md5 sum of the data area and store | |
345 | it in the header of each block. | |
346 | ||
347 | crc32 Use a crc32 sum of the data area and store | |
348 | it in the header of each block. | |
349 | ||
350 | This option can be used for repeated burnin tests of a | |
351 | system to make sure that the written data is also | |
352 | correctly read back. | |
353 | ||
354 | stonewall Wait for preceeding jobs in the job file to exit, before | |
355 | starting this one. Can be used to insert serialization | |
356 | points in the job file. | |
357 | ||
358 | numjobs=int Create the specified number of clones of this job. May be | |
359 | used to setup a larger number of threads/processes doing | |
360 | the same thing. | |
361 | ||
362 | thread fio defaults to forking jobs, however if this option is | |
363 | given, fio will use pthread_create(3) to create threads | |
364 | instead. | |
365 | ||
366 | zonesize=siint Divide a file into zones of the specified size. See zoneskip. | |
367 | ||
368 | zoneskip=siint Skip the specified number of bytes when zonesize data has | |
369 | been read. The two zone options can be used to only do | |
370 | io on zones of a file. | |
371 | ||
372 | write_iolog=str Write the issued io patterns to the specified file. See iolog. | |
373 | ||
374 | iolog=str Open an iolog with the specified file name and replay the | |
375 | io patterns it contains. This can be used to store a | |
376 | workload and replay it sometime later. | |
377 | ||
378 | write_bw_log If given, write a bandwidth log of the jobs in this job | |
379 | file. Can be used to store data of the bandwidth of the | |
380 | jobs in their lifetime. | |
381 | ||
382 | write_lat_log Same as write_bw_log, except that this option stores io | |
383 | completion latencies instead. | |
384 | ||
385 | lockmem=siint Pin down the specified amount of memory with mlock(2). Can | |
386 | potentially be used instead of removing memory or booting | |
387 | with less memory to simulate a smaller amount of memory. | |
388 | ||
389 | exec_prerun=str Before running this job, issue the command specified | |
390 | through system(3). | |
391 | ||
392 | exec_postrun=str After the job completes, issue the command specified | |
393 | though system(3). | |
394 | ||
395 | ioscheduler=str Attempt to switch the device hosting the file to the specified | |
396 | io scheduler before running. | |
397 | ||
398 | cpuload=int If the job is a CPU cycle eater, attempt to use the specified | |
399 | percentage of CPU cycles. | |
400 | ||
401 | cpuchunks=int If the job is a CPU cycle eater, split the load into | |
402 | cycles of the given time. In miliseconds. | |
403 | ||
404 | ||
405 | 6.0 Interpreting the output | |
406 | --------------------------- | |
407 | ||
408 | fio spits out a lot of output. While running, fio will display the | |
409 | status of the jobs created. An example of that would be: | |
410 | ||
411 | Threads running: 1: [_r] [24.79% done] [eta 00h:01m:31s] | |
412 | ||
413 | The characters inside the square brackets denote the current status of | |
414 | each thread. The possible values (in typical life cycle order) are: | |
415 | ||
416 | Idle Run | |
417 | ---- --- | |
418 | P Thread setup, but not started. | |
419 | C Thread created. | |
420 | I Thread initialized, waiting. | |
421 | R Running, doing sequential reads. | |
422 | r Running, doing random reads. | |
423 | W Running, doing sequential writes. | |
424 | w Running, doing random writes. | |
425 | M Running, doing mixed sequential reads/writes. | |
426 | m Running, doing mixed random reads/writes. | |
427 | F Running, currently waiting for fsync() | |
428 | V Running, doing verification of written data. | |
429 | E Thread exited, not reaped by main thread yet. | |
430 | _ Thread reaped. | |
431 | ||
432 | The other values are fairly self explanatory - number of threads | |
433 | currently running and doing io, and the estimated completion percentage | |
434 | and time for the running group. It's impossible to estimate runtime | |
435 | of the following groups (if any). | |
436 | ||
437 | When fio is done (or interrupted by ctrl-c), it will show the data for | |
438 | each thread, group of threads, and disks in that order. For each data | |
439 | direction, the output looks like: | |
440 | ||
441 | Client1 (g=0): err= 0: | |
442 | write: io= 32MiB, bw= 666KiB/s, runt= 50320msec | |
443 | slat (msec): min= 0, max= 136, avg= 0.03, dev= 1.92 | |
444 | clat (msec): min= 0, max= 631, avg=48.50, dev=86.82 | |
445 | bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, dev=681.68 | |
446 | cpu : usr=1.49%, sys=0.25%, ctx=7969 | |
447 | ||
448 | The client number is printed, along with the group id and error of that | |
449 | thread. Below is the io statistics, here for writes. In the order listed, | |
450 | they denote: | |
451 | ||
452 | io= Number of megabytes io performed | |
453 | bw= Average bandwidth rate | |
454 | runt= The runtime of that thread | |
455 | slat= Submission latency (avg being the average, dev being the | |
456 | standard deviation). This is the time it took to submit | |
457 | the io. For sync io, the slat is really the completion | |
458 | latency, since queue/complete is one operation there. | |
459 | clat= Completion latency. Same names as slat, this denotes the | |
460 | time from submission to completion of the io pieces. For | |
461 | sync io, clat will usually be equal (or very close) to 0, | |
462 | as the time from submit to complete is basically just | |
463 | CPU time (io has already been done, see slat explanation). | |
464 | bw= Bandwidth. Same names as the xlat stats, but also includes | |
465 | an approximate percentage of total aggregate bandwidth | |
466 | this thread received in this group. This last value is | |
467 | only really useful if the threads in this group are on the | |
468 | same disk, since they are then competing for disk access. | |
469 | cpu= CPU usage. User and system time, along with the number | |
470 | of context switches this thread went through. | |
471 | ||
472 | After each client has been listed, the group statistics are printed. They | |
473 | will look like this: | |
474 | ||
475 | Run status group 0 (all jobs): | |
476 | READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec | |
477 | WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec | |
478 | ||
479 | For each data direction, it prints: | |
480 | ||
481 | io= Number of megabytes io performed. | |
482 | aggrb= Aggregate bandwidth of threads in this group. | |
483 | minb= The minimum average bandwidth a thread saw. | |
484 | maxb= The maximum average bandwidth a thread saw. | |
485 | mint= The smallest runtime of the threads in that group. | |
486 | maxt= The longest runtime of the threads in that group. | |
487 | ||
488 | And finally, the disk statistics are printed. They will look like this: | |
489 | ||
490 | Disk stats (read/write): | |
491 | sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00% | |
492 | ||
493 | Each value is printed for both reads and writes, with reads first. The | |
494 | numbers denote: | |
495 | ||
496 | ios= Number of ios performed by all groups. | |
497 | merge= Number of merges io the io scheduler. | |
498 | ticks= Number of ticks we kept the disk busy. | |
499 | io_queue= Total time spent in the disk queue. | |
500 | util= The disk utilization. A value of 100% means we kept the disk | |
501 | busy constantly, 50% would be a disk idling half of the time. | |
502 | ||
503 | ||
504 | 7.0 Terse output | |
505 | ---------------- | |
506 | ||
507 | For scripted usage where you typically want to generate tables or graphs | |
508 | of the results, fio can output the results in a comma seperated format. | |
509 | The format is one long line of values, such as: | |
510 | ||
511 | client1,0,0,936,331,2894,0,0,0.000000,0.000000,1,170,22.115385,34.290410,16,714,84.252874%,366.500000,566.417819,3496,1237,2894,0,0,0.000000,0.000000,0,246,6.671625,21.436952,0,2534,55.465300%,1406.600000,2008.044216,0.000000%,0.431928%,1109 | |
512 | ||
513 | Split up, the format is as follows: | |
514 | ||
515 | jobname, groupid, error | |
516 | READ status: | |
517 | KiB IO, bandwidth (KiB/sec), runtime (msec) | |
518 | Submission latency: min, max, mean, deviation | |
519 | Completion latency: min, max, mean, deviation | |
520 | Bw: min, max, aggreate percentage of total, mean, deviation | |
521 | WRITE status: | |
522 | KiB IO, bandwidth (KiB/sec), runtime (msec) | |
523 | Submission latency: min, max, mean, deviation | |
524 | Completion latency: min, max, mean, deviation | |
525 | Bw: min, max, aggreate percentage of total, mean, deviation | |
526 | CPU usage: user, system, context switches | |
527 |