Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 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 | |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 55 | IO depth If the io engine is async, how large a queuing |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 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 | |
Jens Axboe | b469282 | 2006-10-27 13:43:22 +0200 | [diff] [blame] | 85 | If the job file contains only one job, you may as well just give the |
| 86 | parameters on the command line. The command line parameters are identical |
| 87 | to the job parameters, with a few extra that control global parameters |
| 88 | (see README). For example, for the job file parameter iodepth=2, the |
Jens Axboe | c2b1e75 | 2006-10-30 09:03:13 +0100 | [diff] [blame] | 89 | mirror command line option would be --iodepth 2 or --iodepth=2. You can |
| 90 | also use the command line for giving more than one job entry. For each |
| 91 | --name option that fio sees, it will start a new job with that name. |
| 92 | Command line entries following a --name entry will apply to that job, |
| 93 | until there are no more entries or a new --name entry is seen. This is |
| 94 | similar to the job file options, where each option applies to the current |
| 95 | job until a new [] job entry is seen. |
Jens Axboe | b469282 | 2006-10-27 13:43:22 +0200 | [diff] [blame] | 96 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 97 | fio does not need to run as root, except if the files or devices specified |
| 98 | in the job section requires that. Some other options may also be restricted, |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 99 | such as memory locking, io scheduler switching, and decreasing the nice value. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 100 | |
| 101 | |
| 102 | 4.0 Job file format |
| 103 | ------------------- |
| 104 | As previously described, fio accepts one or more job files describing |
| 105 | what it is supposed to do. The job file format is the classic ini file, |
| 106 | where the names enclosed in [] brackets define the job name. You are free |
| 107 | to use any ascii name you want, except 'global' which has special meaning. |
| 108 | A global section sets defaults for the jobs described in that file. A job |
| 109 | may override a global section parameter, and a job file may even have |
| 110 | several global sections if so desired. A job is only affected by a global |
| 111 | section residing above it. If the first character in a line is a ';', the |
| 112 | entire line is discarded as a comment. |
| 113 | |
| 114 | So lets look at a really simple job file that define to threads, each |
| 115 | randomly reading from a 128MiB file. |
| 116 | |
| 117 | ; -- start job file -- |
| 118 | [global] |
| 119 | rw=randread |
| 120 | size=128m |
| 121 | |
| 122 | [job1] |
| 123 | |
| 124 | [job2] |
| 125 | |
| 126 | ; -- end job file -- |
| 127 | |
| 128 | As you can see, the job file sections themselves are empty as all the |
| 129 | described parameters are shared. As no filename= option is given, fio |
Jens Axboe | c2b1e75 | 2006-10-30 09:03:13 +0100 | [diff] [blame] | 130 | makes up a filename for each of the jobs as it sees fit. On the command |
| 131 | line, this job would look as follows: |
| 132 | |
| 133 | $ fio --name=global --rw=randread --size=128m --name=job1 --name=job2 |
| 134 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 135 | |
| 136 | Lets look at an example that have a number of processes writing randomly |
| 137 | to files. |
| 138 | |
| 139 | ; -- start job file -- |
| 140 | [random-writers] |
| 141 | ioengine=libaio |
| 142 | iodepth=4 |
| 143 | rw=randwrite |
| 144 | bs=32k |
| 145 | direct=0 |
| 146 | size=64m |
| 147 | numjobs=4 |
| 148 | |
| 149 | ; -- end job file -- |
| 150 | |
| 151 | Here we have no global section, as we only have one job defined anyway. |
| 152 | We want to use async io here, with a depth of 4 for each file. We also |
| 153 | increased the buffer size used to 32KiB and define numjobs to 4 to |
| 154 | fork 4 identical jobs. The result is 4 processes each randomly writing |
Jens Axboe | b469282 | 2006-10-27 13:43:22 +0200 | [diff] [blame] | 155 | to their own 64MiB file. Instead of using the above job file, you could |
| 156 | have given the parameters on the command line. For this case, you would |
| 157 | specify: |
| 158 | |
| 159 | $ fio --name=random-writers --ioengine=libaio --iodepth=4 --rw=randwrite --bs=32k --direct=0 --size=64m --numjobs=4 |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 160 | |
| 161 | fio ships with a few example job files, you can also look there for |
| 162 | inspiration. |
| 163 | |
| 164 | |
| 165 | 5.0 Detailed list of parameters |
| 166 | ------------------------------- |
| 167 | |
| 168 | This section describes in details each parameter associated with a job. |
| 169 | Some parameters take an option of a given type, such as an integer or |
| 170 | a string. The following types are used: |
| 171 | |
| 172 | str String. This is a sequence of alpha characters. |
| 173 | int Integer. A whole number value, may be negative. |
| 174 | siint SI integer. A whole number value, which may contain a postfix |
| 175 | describing the base of the number. Accepted postfixes are k/m/g, |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 176 | meaning kilo, mega, and giga. So if you want to specify 4096, |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 177 | you could either write out '4096' or just give 4k. The postfixes |
| 178 | signify base 2 values, so 1024 is 1k and 1024k is 1m and so on. |
| 179 | bool Boolean. Usually parsed as an integer, however only defined for |
| 180 | true and false (1 and 0). |
| 181 | irange Integer range with postfix. Allows value range to be given, such |
Jens Axboe | 0c9baf9 | 2007-01-11 15:59:26 +0100 | [diff] [blame] | 182 | as 1024-4096. A colon may also be used as the seperator, eg |
| 183 | 1k:4k. If the option allows two sets of ranges, they can be |
| 184 | specified with a ',' or '/' delimiter: 1k-4k/8k-32k. Also see |
| 185 | siint. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 186 | |
| 187 | With the above in mind, here follows the complete list of fio job |
| 188 | parameters. |
| 189 | |
| 190 | name=str ASCII name of the job. This may be used to override the |
| 191 | name printed by fio for this job. Otherwise the job |
Jens Axboe | c2b1e75 | 2006-10-30 09:03:13 +0100 | [diff] [blame] | 192 | name is used. On the command line this parameter has the |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 193 | special purpose of also signaling the start of a new |
Jens Axboe | c2b1e75 | 2006-10-30 09:03:13 +0100 | [diff] [blame] | 194 | job. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 195 | |
Jens Axboe | 61697c3 | 2007-02-05 15:04:46 +0100 | [diff] [blame] | 196 | description=str Text description of the job. Doesn't do anything except |
| 197 | dump this text description when this job is run. It's |
| 198 | not parsed. |
| 199 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 200 | directory=str Prefix filenames with this directory. Used to places files |
| 201 | in a different location than "./". |
| 202 | |
| 203 | filename=str Fio normally makes up a filename based on the job name, |
| 204 | thread number, and file number. If you want to share |
| 205 | files between threads in a job or several jobs, specify |
Jens Axboe | ed92ac0 | 2007-02-06 14:43:52 +0100 | [diff] [blame^] | 206 | a filename for each of them to override the default. If |
| 207 | the ioengine used is 'net', the filename is the host and |
| 208 | port to connect to in the format of =host:port. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 209 | |
| 210 | rw=str Type of io pattern. Accepted values are: |
| 211 | |
| 212 | read Sequential reads |
| 213 | write Sequential writes |
| 214 | randwrite Random writes |
| 215 | randread Random reads |
| 216 | rw Sequential mixed reads and writes |
| 217 | randrw Random mixed reads and writes |
| 218 | |
| 219 | For the mixed io types, the default is to split them 50/50. |
| 220 | For certain types of io the result may still be skewed a bit, |
| 221 | since the speed may be different. |
| 222 | |
Jens Axboe | ee73849 | 2007-01-10 11:23:16 +0100 | [diff] [blame] | 223 | randrepeat=bool For random IO workloads, seed the generator in a predictable |
| 224 | way so that results are repeatable across repetitions. |
| 225 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 226 | size=siint The total size of file io for this job. This may describe |
| 227 | the size of the single file the job uses, or it may be |
| 228 | divided between the number of files in the job. If the |
| 229 | file already exists, the file size will be adjusted to this |
| 230 | size if larger than the current file size. If this parameter |
| 231 | is not given and the file exists, the file size will be used. |
| 232 | |
Jens Axboe | f90eff5 | 2006-11-06 11:08:21 +0100 | [diff] [blame] | 233 | bs=siint The block size used for the io units. Defaults to 4k. Values |
| 234 | can be given for both read and writes. If a single siint is |
| 235 | given, it will apply to both. If a second siint is specified |
| 236 | after a comma, it will apply to writes only. In other words, |
| 237 | the format is either bs=read_and_write or bs=read,write. |
| 238 | bs=4k,8k will thus use 4k blocks for reads, and 8k blocks |
Jens Axboe | 787f7e9 | 2006-11-06 13:26:29 +0100 | [diff] [blame] | 239 | for writes. If you only wish to set the write size, you |
| 240 | can do so by passing an empty read size - bs=,8k will set |
| 241 | 8k for writes and leave the read default value. |
Jens Axboe | a00735e | 2006-11-03 08:58:08 +0100 | [diff] [blame] | 242 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 243 | bsrange=irange Instead of giving a single block size, specify a range |
| 244 | and fio will mix the issued io block sizes. The issued |
| 245 | io unit will always be a multiple of the minimum value |
Jens Axboe | f90eff5 | 2006-11-06 11:08:21 +0100 | [diff] [blame] | 246 | given (also see bs_unaligned). Applies to both reads and |
| 247 | writes, however a second range can be given after a comma. |
| 248 | See bs=. |
Jens Axboe | a00735e | 2006-11-03 08:58:08 +0100 | [diff] [blame] | 249 | |
Jens Axboe | 690adba | 2006-10-30 15:25:09 +0100 | [diff] [blame] | 250 | bs_unaligned If this option is given, any byte size value within bsrange |
| 251 | may be used as a block range. This typically wont work with |
| 252 | direct IO, as that normally requires sector alignment. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 253 | |
| 254 | nrfiles=int Number of files to use for this job. Defaults to 1. |
| 255 | |
| 256 | ioengine=str Defines how the job issues io to the file. The following |
| 257 | types are defined: |
| 258 | |
| 259 | sync Basic read(2) or write(2) io. lseek(2) is |
| 260 | used to position the io location. |
| 261 | |
| 262 | libaio Linux native asynchronous io. |
| 263 | |
| 264 | posixaio glibc posix asynchronous io. |
| 265 | |
| 266 | mmap File is memory mapped and data copied |
| 267 | to/from using memcpy(3). |
| 268 | |
| 269 | splice splice(2) is used to transfer the data and |
| 270 | vmsplice(2) to transfer data from user |
| 271 | space to the kernel. |
| 272 | |
| 273 | sg SCSI generic sg v3 io. May either be |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 274 | synchronous using the SG_IO ioctl, or if |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 275 | the target is an sg character device |
| 276 | we use read(2) and write(2) for asynchronous |
| 277 | io. |
| 278 | |
Jens Axboe | a94ea28 | 2006-11-24 12:37:34 +0100 | [diff] [blame] | 279 | null Doesn't transfer any data, just pretends |
| 280 | to. This is mainly used to exercise fio |
| 281 | itself and for debugging/testing purposes. |
| 282 | |
Jens Axboe | ed92ac0 | 2007-02-06 14:43:52 +0100 | [diff] [blame^] | 283 | net Transfer over the network to given host:port. |
| 284 | 'filename' must be set appropriately to |
| 285 | filename=host:port regardless of send |
| 286 | or receive, if the latter only the port |
| 287 | argument is used. |
| 288 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 289 | iodepth=int This defines how many io units to keep in flight against |
| 290 | the file. The default is 1 for each file defined in this |
| 291 | job, can be overridden with a larger value for higher |
| 292 | concurrency. |
| 293 | |
| 294 | direct=bool If value is true, use non-buffered io. This is usually |
Jens Axboe | 76a43db | 2007-01-11 13:24:44 +0100 | [diff] [blame] | 295 | O_DIRECT. |
| 296 | |
| 297 | buffered=bool If value is true, use buffered io. This is the opposite |
| 298 | of the 'direct' option. Defaults to true. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 299 | |
| 300 | offset=siint Start io at the given offset in the file. The data before |
| 301 | the given offset will not be touched. This effectively |
| 302 | caps the file size at real_size - offset. |
| 303 | |
| 304 | fsync=int If writing to a file, issue a sync of the dirty data |
| 305 | for every number of blocks given. For example, if you give |
| 306 | 32 as a parameter, fio will sync the file for every 32 |
| 307 | writes issued. If fio is using non-buffered io, we may |
| 308 | not sync the file. The exception is the sg io engine, which |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 309 | synchronizes the disk cache anyway. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 310 | |
| 311 | overwrite=bool If writing to a file, setup the file first and do overwrites. |
| 312 | |
| 313 | end_fsync=bool If true, fsync file contents when the job exits. |
| 314 | |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 315 | rwmixcycle=int Value in milliseconds describing how often to switch between |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 316 | reads and writes for a mixed workload. The default is |
| 317 | 500 msecs. |
| 318 | |
| 319 | rwmixread=int How large a percentage of the mix should be reads. |
| 320 | |
| 321 | rwmixwrite=int How large a percentage of the mix should be writes. If both |
| 322 | rwmixread and rwmixwrite is given and the values do not add |
| 323 | up to 100%, the latter of the two will be used to override |
| 324 | the first. |
| 325 | |
Jens Axboe | bb8895e | 2006-10-30 15:14:48 +0100 | [diff] [blame] | 326 | norandommap Normally fio will cover every block of the file when doing |
| 327 | random IO. If this option is given, fio will just get a |
| 328 | new random offset without looking at past io history. This |
| 329 | means that some blocks may not be read or written, and that |
| 330 | some blocks may be read/written more than once. This option |
| 331 | is mutually exclusive with verify= for that reason. |
| 332 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 333 | nice=int Run the job with the given nice value. See man nice(2). |
| 334 | |
| 335 | prio=int Set the io priority value of this job. Linux limits us to |
| 336 | a positive value between 0 and 7, with 0 being the highest. |
| 337 | See man ionice(1). |
| 338 | |
| 339 | prioclass=int Set the io priority class. See man ionice(1). |
| 340 | |
| 341 | thinktime=int Stall the job x microseconds after an io has completed before |
| 342 | issuing the next. May be used to simulate processing being |
Jens Axboe | 9c1f743 | 2007-01-03 20:43:19 +0100 | [diff] [blame] | 343 | done by an application. See thinktime_blocks. |
| 344 | |
| 345 | thinktime_blocks |
| 346 | Only valid if thinktime is set - control how many blocks |
| 347 | to issue, before waiting 'thinktime' usecs. If not set, |
| 348 | defaults to 1 which will make fio wait 'thinktime' usecs |
| 349 | after every block. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 350 | |
| 351 | rate=int Cap the bandwidth used by this job to this number of KiB/sec. |
| 352 | |
| 353 | ratemin=int Tell fio to do whatever it can to maintain at least this |
| 354 | bandwidth. |
| 355 | |
| 356 | ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 357 | of milliseconds. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 358 | |
| 359 | cpumask=int Set the CPU affinity of this job. The parameter given is a |
| 360 | bitmask of allowed CPU's the job may run on. See man |
| 361 | sched_setaffinity(2). |
| 362 | |
| 363 | startdelay=int Start this job the specified number of seconds after fio |
| 364 | has started. Only useful if the job file contains several |
| 365 | jobs, and you want to delay starting some jobs to a certain |
| 366 | time. |
| 367 | |
Jens Axboe | 03b74b3 | 2007-01-11 11:04:31 +0100 | [diff] [blame] | 368 | runtime=int Tell fio to terminate processing after the specified number |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 369 | of seconds. It can be quite hard to determine for how long |
| 370 | a specified job will run, so this parameter is handy to |
| 371 | cap the total runtime to a given time. |
| 372 | |
| 373 | invalidate=bool Invalidate the buffer/page cache parts for this file prior |
| 374 | to starting io. Defaults to true. |
| 375 | |
| 376 | sync=bool Use sync io for buffered writes. For the majority of the |
| 377 | io engines, this means using O_SYNC. |
| 378 | |
| 379 | mem=str Fio can use various types of memory as the io unit buffer. |
| 380 | The allowed values are: |
| 381 | |
| 382 | malloc Use memory from malloc(3) as the buffers. |
| 383 | |
| 384 | shm Use shared memory as the buffers. Allocated |
| 385 | through shmget(2). |
| 386 | |
Jens Axboe | 74b025b | 2006-12-19 15:18:14 +0100 | [diff] [blame] | 387 | shmhuge Same as shm, but use huge pages as backing. |
| 388 | |
Jens Axboe | 313cb20 | 2006-12-21 09:50:00 +0100 | [diff] [blame] | 389 | mmap Use mmap to allocate buffers. May either be |
| 390 | anonymous memory, or can be file backed if |
| 391 | a filename is given after the option. The |
| 392 | format is mem=mmap:/path/to/file. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 393 | |
Jens Axboe | d0bdaf4 | 2006-12-20 14:40:44 +0100 | [diff] [blame] | 394 | mmaphuge Use a memory mapped huge file as the buffer |
| 395 | backing. Append filename after mmaphuge, ala |
| 396 | mem=mmaphuge:/hugetlbfs/file |
| 397 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 398 | The area allocated is a function of the maximum allowed |
Jens Axboe | 5394ae5 | 2006-12-20 20:15:41 +0100 | [diff] [blame] | 399 | bs size for the job, multiplied by the io depth given. Note |
| 400 | that for shmhuge and mmaphuge to work, the system must have |
| 401 | free huge pages allocated. This can normally be checked |
| 402 | and set by reading/writing /proc/sys/vm/nr_hugepages on a |
| 403 | Linux system. Fio assumes a huge page is 4MiB in size. So |
| 404 | to calculate the number of huge pages you need for a given |
| 405 | job file, add up the io depth of all jobs (normally one unless |
| 406 | iodepth= is used) and multiply by the maximum bs set. Then |
| 407 | divide that number by the huge page size. You can see the |
| 408 | size of the huge pages in /proc/meminfo. If no huge pages |
| 409 | are allocated by having a non-zero number in nr_hugepages, |
Jens Axboe | 56bb17f | 2006-12-20 20:27:36 +0100 | [diff] [blame] | 410 | using mmaphuge or shmhuge will fail. Also see hugepage-size. |
Jens Axboe | 5394ae5 | 2006-12-20 20:15:41 +0100 | [diff] [blame] | 411 | |
| 412 | mmaphuge also needs to have hugetlbfs mounted and the file |
| 413 | location should point there. So if it's mounted in /huge, |
| 414 | you would use mem=mmaphuge:/huge/somefile. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 415 | |
Jens Axboe | 56bb17f | 2006-12-20 20:27:36 +0100 | [diff] [blame] | 416 | hugepage-size=siint |
| 417 | Defines the size of a huge page. Must at least be equal |
| 418 | to the system setting, see /proc/meminfo. Defaults to 4MiB. |
Jens Axboe | c51074e | 2006-12-20 20:28:33 +0100 | [diff] [blame] | 419 | Should probably always be a multiple of megabytes, so using |
| 420 | hugepage-size=Xm is the preferred way to set this to avoid |
| 421 | setting a non-pow-2 bad value. |
Jens Axboe | 56bb17f | 2006-12-20 20:27:36 +0100 | [diff] [blame] | 422 | |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 423 | exitall When one job finishes, terminate the rest. The default is |
| 424 | to wait for each job to finish, sometimes that is not the |
| 425 | desired action. |
| 426 | |
| 427 | bwavgtime=int Average the calculated bandwidth over the given time. Value |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 428 | is specified in milliseconds. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 429 | |
| 430 | create_serialize=bool If true, serialize the file creating for the jobs. |
| 431 | This may be handy to avoid interleaving of data |
| 432 | files, which may greatly depend on the filesystem |
| 433 | used and even the number of processors in the system. |
| 434 | |
| 435 | create_fsync=bool fsync the data file after creation. This is the |
| 436 | default. |
| 437 | |
Jens Axboe | e545a6c | 2007-01-14 00:00:29 +0100 | [diff] [blame] | 438 | unlink=bool Unlink the job files when done. Not the default, as repeated |
| 439 | runs of that job would then waste time recreating the fileset |
| 440 | again and again. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 441 | |
| 442 | loops=int Run the specified number of iterations of this job. Used |
| 443 | to repeat the same workload a given number of times. Defaults |
| 444 | to 1. |
| 445 | |
| 446 | verify=str If writing to a file, fio can verify the file contents |
| 447 | after each iteration of the job. The allowed values are: |
| 448 | |
| 449 | md5 Use an md5 sum of the data area and store |
| 450 | it in the header of each block. |
| 451 | |
| 452 | crc32 Use a crc32 sum of the data area and store |
| 453 | it in the header of each block. |
| 454 | |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 455 | This option can be used for repeated burn-in tests of a |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 456 | system to make sure that the written data is also |
| 457 | correctly read back. |
| 458 | |
| 459 | stonewall Wait for preceeding jobs in the job file to exit, before |
| 460 | starting this one. Can be used to insert serialization |
| 461 | points in the job file. |
| 462 | |
| 463 | numjobs=int Create the specified number of clones of this job. May be |
| 464 | used to setup a larger number of threads/processes doing |
| 465 | the same thing. |
| 466 | |
| 467 | thread fio defaults to forking jobs, however if this option is |
| 468 | given, fio will use pthread_create(3) to create threads |
| 469 | instead. |
| 470 | |
| 471 | zonesize=siint Divide a file into zones of the specified size. See zoneskip. |
| 472 | |
| 473 | zoneskip=siint Skip the specified number of bytes when zonesize data has |
| 474 | been read. The two zone options can be used to only do |
| 475 | io on zones of a file. |
| 476 | |
Jens Axboe | 076efc7 | 2006-10-27 11:24:25 +0200 | [diff] [blame] | 477 | write_iolog=str Write the issued io patterns to the specified file. See |
| 478 | read_iolog. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 479 | |
Jens Axboe | 076efc7 | 2006-10-27 11:24:25 +0200 | [diff] [blame] | 480 | read_iolog=str Open an iolog with the specified file name and replay the |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 481 | io patterns it contains. This can be used to store a |
| 482 | workload and replay it sometime later. |
| 483 | |
| 484 | write_bw_log If given, write a bandwidth log of the jobs in this job |
| 485 | file. Can be used to store data of the bandwidth of the |
Jens Axboe | e0da9bc | 2006-10-25 13:08:57 +0200 | [diff] [blame] | 486 | jobs in their lifetime. The included fio_generate_plots |
| 487 | script uses gnuplot to turn these text files into nice |
| 488 | graphs. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 489 | |
| 490 | write_lat_log Same as write_bw_log, except that this option stores io |
| 491 | completion latencies instead. |
| 492 | |
| 493 | lockmem=siint Pin down the specified amount of memory with mlock(2). Can |
| 494 | potentially be used instead of removing memory or booting |
| 495 | with less memory to simulate a smaller amount of memory. |
| 496 | |
| 497 | exec_prerun=str Before running this job, issue the command specified |
| 498 | through system(3). |
| 499 | |
| 500 | exec_postrun=str After the job completes, issue the command specified |
| 501 | though system(3). |
| 502 | |
| 503 | ioscheduler=str Attempt to switch the device hosting the file to the specified |
| 504 | io scheduler before running. |
| 505 | |
| 506 | cpuload=int If the job is a CPU cycle eater, attempt to use the specified |
| 507 | percentage of CPU cycles. |
| 508 | |
| 509 | cpuchunks=int If the job is a CPU cycle eater, split the load into |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 510 | cycles of the given time. In milliseconds. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 511 | |
| 512 | |
| 513 | 6.0 Interpreting the output |
| 514 | --------------------------- |
| 515 | |
| 516 | fio spits out a lot of output. While running, fio will display the |
| 517 | status of the jobs created. An example of that would be: |
| 518 | |
Jens Axboe | 73c8b08 | 2007-01-11 19:25:52 +0100 | [diff] [blame] | 519 | Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s] |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 520 | |
| 521 | The characters inside the square brackets denote the current status of |
| 522 | each thread. The possible values (in typical life cycle order) are: |
| 523 | |
| 524 | Idle Run |
| 525 | ---- --- |
| 526 | P Thread setup, but not started. |
| 527 | C Thread created. |
| 528 | I Thread initialized, waiting. |
| 529 | R Running, doing sequential reads. |
| 530 | r Running, doing random reads. |
| 531 | W Running, doing sequential writes. |
| 532 | w Running, doing random writes. |
| 533 | M Running, doing mixed sequential reads/writes. |
| 534 | m Running, doing mixed random reads/writes. |
| 535 | F Running, currently waiting for fsync() |
| 536 | V Running, doing verification of written data. |
| 537 | E Thread exited, not reaped by main thread yet. |
| 538 | _ Thread reaped. |
| 539 | |
| 540 | The other values are fairly self explanatory - number of threads |
Jens Axboe | 6043c57 | 2006-11-03 11:37:47 +0100 | [diff] [blame] | 541 | currently running and doing io, rate of io since last check, and the estimated |
| 542 | completion percentage and time for the running group. It's impossible to |
| 543 | estimate runtime of the following groups (if any). |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 544 | |
| 545 | When fio is done (or interrupted by ctrl-c), it will show the data for |
| 546 | each thread, group of threads, and disks in that order. For each data |
| 547 | direction, the output looks like: |
| 548 | |
| 549 | Client1 (g=0): err= 0: |
| 550 | write: io= 32MiB, bw= 666KiB/s, runt= 50320msec |
Jens Axboe | 6104ddb | 2007-01-11 14:24:29 +0100 | [diff] [blame] | 551 | slat (msec): min= 0, max= 136, avg= 0.03, stdev= 1.92 |
| 552 | clat (msec): min= 0, max= 631, avg=48.50, stdev=86.82 |
| 553 | bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, stdev=681.68 |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 554 | cpu : usr=1.49%, sys=0.25%, ctx=7969 |
Jens Axboe | 71619dc | 2007-01-13 23:56:33 +0100 | [diff] [blame] | 555 | IO depths : 1=0.1%, 2=0.3%, 4=0.5%, 8=99.0%, 16=0.0%, 32=0.0%, >32=0.0% |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 556 | |
| 557 | The client number is printed, along with the group id and error of that |
| 558 | thread. Below is the io statistics, here for writes. In the order listed, |
| 559 | they denote: |
| 560 | |
| 561 | io= Number of megabytes io performed |
| 562 | bw= Average bandwidth rate |
| 563 | runt= The runtime of that thread |
| 564 | slat= Submission latency (avg being the average, dev being the |
| 565 | standard deviation). This is the time it took to submit |
| 566 | the io. For sync io, the slat is really the completion |
| 567 | latency, since queue/complete is one operation there. |
| 568 | clat= Completion latency. Same names as slat, this denotes the |
| 569 | time from submission to completion of the io pieces. For |
| 570 | sync io, clat will usually be equal (or very close) to 0, |
| 571 | as the time from submit to complete is basically just |
| 572 | CPU time (io has already been done, see slat explanation). |
| 573 | bw= Bandwidth. Same names as the xlat stats, but also includes |
| 574 | an approximate percentage of total aggregate bandwidth |
| 575 | this thread received in this group. This last value is |
| 576 | only really useful if the threads in this group are on the |
| 577 | same disk, since they are then competing for disk access. |
| 578 | cpu= CPU usage. User and system time, along with the number |
| 579 | of context switches this thread went through. |
Jens Axboe | 71619dc | 2007-01-13 23:56:33 +0100 | [diff] [blame] | 580 | IO depths= The distribution of io depths over the job life time. The |
| 581 | numbers are divided into powers of 2, so for example the |
| 582 | 16= entries includes depths up to that value but higher |
| 583 | than the previous entry. In other words, it covers the |
| 584 | range from 16 to 31. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 585 | |
| 586 | After each client has been listed, the group statistics are printed. They |
| 587 | will look like this: |
| 588 | |
| 589 | Run status group 0 (all jobs): |
| 590 | READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec |
| 591 | WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec |
| 592 | |
| 593 | For each data direction, it prints: |
| 594 | |
| 595 | io= Number of megabytes io performed. |
| 596 | aggrb= Aggregate bandwidth of threads in this group. |
| 597 | minb= The minimum average bandwidth a thread saw. |
| 598 | maxb= The maximum average bandwidth a thread saw. |
| 599 | mint= The smallest runtime of the threads in that group. |
| 600 | maxt= The longest runtime of the threads in that group. |
| 601 | |
| 602 | And finally, the disk statistics are printed. They will look like this: |
| 603 | |
| 604 | Disk stats (read/write): |
| 605 | sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00% |
| 606 | |
| 607 | Each value is printed for both reads and writes, with reads first. The |
| 608 | numbers denote: |
| 609 | |
| 610 | ios= Number of ios performed by all groups. |
| 611 | merge= Number of merges io the io scheduler. |
| 612 | ticks= Number of ticks we kept the disk busy. |
| 613 | io_queue= Total time spent in the disk queue. |
| 614 | util= The disk utilization. A value of 100% means we kept the disk |
| 615 | busy constantly, 50% would be a disk idling half of the time. |
| 616 | |
| 617 | |
| 618 | 7.0 Terse output |
| 619 | ---------------- |
| 620 | |
| 621 | For scripted usage where you typically want to generate tables or graphs |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 622 | of the results, fio can output the results in a comma separated format. |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 623 | The format is one long line of values, such as: |
| 624 | |
| 625 | 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 |
| 626 | |
| 627 | Split up, the format is as follows: |
| 628 | |
| 629 | jobname, groupid, error |
| 630 | READ status: |
| 631 | KiB IO, bandwidth (KiB/sec), runtime (msec) |
| 632 | Submission latency: min, max, mean, deviation |
| 633 | Completion latency: min, max, mean, deviation |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 634 | Bw: min, max, aggregate percentage of total, mean, deviation |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 635 | WRITE status: |
| 636 | KiB IO, bandwidth (KiB/sec), runtime (msec) |
| 637 | Submission latency: min, max, mean, deviation |
| 638 | Completion latency: min, max, mean, deviation |
Jens Axboe | 6c21976 | 2006-11-03 15:51:45 +0100 | [diff] [blame] | 639 | Bw: min, max, aggregate percentage of total, mean, deviation |
Jens Axboe | 71bfa16 | 2006-10-25 11:08:19 +0200 | [diff] [blame] | 640 | CPU usage: user, system, context switches |
| 641 | |