Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 1 | .TH fio 1 "September 2007" "User Manual" |
| 2 | .SH NAME |
| 3 | fio \- flexible I/O tester |
| 4 | .SH SYNOPSIS |
| 5 | .B fio |
| 6 | [\fIoptions\fR] [\fIjobfile\fR]... |
| 7 | .SH DESCRIPTION |
| 8 | .B fio |
| 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. |
| 13 | .SH OPTIONS |
| 14 | .TP |
| 15 | .BI \-\-output \fR=\fPfilename |
| 16 | Write output to \fIfilename\fR. |
| 17 | .TP |
| 18 | .BI \-\-timeout \fR=\fPtimeout |
| 19 | Limit run time to \fItimeout\fR seconds. |
| 20 | .TP |
| 21 | .B \-\-latency\-log |
| 22 | Generate per-job latency logs. |
| 23 | .TP |
| 24 | .B \-\-bandwidth\-log |
| 25 | Generate per-job bandwidth logs. |
| 26 | .TP |
| 27 | .B \-\-minimal |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 28 | Print statistics in a terse, semicolon-delimited format. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 29 | .TP |
| 30 | .BI \-\-showcmd \fR=\fPjobfile |
| 31 | Convert \fIjobfile\fR to a set of command-line options. |
| 32 | .TP |
| 33 | .B \-\-readonly |
| 34 | Enable read-only safety checks. |
| 35 | .TP |
| 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'. |
| 39 | .TP |
| 40 | .BI \-\-cmdhelp \fR=\fPcommand |
| 41 | Print help information for \fIcommand\fR. May be `all' for all commands. |
| 42 | .TP |
| 43 | .B \-\-help |
| 44 | Display usage information and exit. |
| 45 | .TP |
| 46 | .B \-\-version |
| 47 | Display version information and exit. |
| 48 | .SH "JOB FILE FORMAT" |
| 49 | Job files are in `ini' format. They consist of one or more |
| 50 | job definitions, which begin with a job name in square brackets and |
| 51 | extend to the next job name. The job name can be any ASCII string |
| 52 | except `global', which has a special meaning. Following the job name is |
| 53 | a sequence of zero or more parameters, one per line, that define the |
| 54 | behavior of the job. Any line starting with a `;' or `#' character is |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 55 | considered a comment and ignored. |
Aaron Carroll | d9956b6 | 2007-11-16 12:12:45 +0100 | [diff] [blame] | 56 | .P |
| 57 | If \fIjobfile\fR is specified as `-', the job file will be read from |
| 58 | standard input. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 59 | .SS "Global Section" |
| 60 | The global section contains default parameters for jobs specified in the |
| 61 | job file. A job is only affected by global sections residing above it, |
| 62 | and there may be any number of global sections. Specific job definitions |
| 63 | may override any parameter set in global sections. |
| 64 | .SH "JOB PARAMETERS" |
| 65 | .SS Types |
| 66 | Some parameters may take arguments of a specific type. The types used are: |
| 67 | .TP |
| 68 | .I str |
| 69 | String: a sequence of alphanumeric characters. |
| 70 | .TP |
| 71 | .I int |
| 72 | Integer: a whole number, possibly negative. If prefixed with `0x', the value |
| 73 | is assumed to be base 16 (hexadecimal). |
| 74 | .TP |
| 75 | .I siint |
| 76 | SI integer: a whole number, possibly containing a suffix denoting the base unit |
| 77 | of the value. Accepted suffixes are `k', 'M' and 'G', denoting kilo (1024), |
| 78 | mega (1024*1024) and giga (1024*1024*1024) respectively. |
| 79 | .TP |
| 80 | .I bool |
| 81 | Boolean: a true or false value. `0' denotes false, `1' denotes true. |
| 82 | .TP |
| 83 | .I irange |
| 84 | Integer range: a range of integers specified in the format |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 85 | \fIlower\fR:\fIupper\fR or \fIlower\fR\-\fIupper\fR. \fIlower\fR and |
| 86 | \fIupper\fR may contain a suffix as described above. If an option allows two |
| 87 | sets of ranges, they are separated with a `,' or `/' character. For example: |
| 88 | `8\-8k/8M\-4G'. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 89 | .SS "Parameter List" |
| 90 | .TP |
| 91 | .BI name \fR=\fPstr |
Aaron Carroll | d9956b6 | 2007-11-16 12:12:45 +0100 | [diff] [blame] | 92 | May be used to override the job name. On the command line, this parameter |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 93 | has the special purpose of signalling the start of a new job. |
| 94 | .TP |
| 95 | .BI description \fR=\fPstr |
| 96 | Human-readable description of the job. It is printed when the job is run, but |
| 97 | otherwise has no special purpose. |
| 98 | .TP |
| 99 | .BI directory \fR=\fPstr |
| 100 | Prefix filenames with this directory. Used to place files in a location other |
| 101 | than `./'. |
| 102 | .TP |
| 103 | .BI filename \fR=\fPstr |
| 104 | .B fio |
| 105 | normally makes up a file name based on the job name, thread number, and file |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 106 | number. If you want to share files between threads in a job or several jobs, |
| 107 | specify a \fIfilename\fR for each of them to override the default. If the I/O |
| 108 | engine used is `net', \fIfilename\fR is the host and port to connect to in the |
| 109 | format \fIhost\fR/\fIport\fR. If the I/O engine is file-based, you can specify |
| 110 | a number of files by separating the names with a `:' character. `\-' is a |
| 111 | reserved name, meaning stdin or stdout, depending on the read/write direction |
| 112 | set. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 113 | .TP |
| 114 | .BI opendir \fR=\fPstr |
| 115 | Recursively open any files below directory \fIstr\fR. |
| 116 | .TP |
| 117 | .BI readwrite \fR=\fPstr "\fR,\fP rw" \fR=\fPstr |
| 118 | Type of I/O pattern. Accepted values are: |
| 119 | .RS |
| 120 | .RS |
| 121 | .TP |
| 122 | .B read |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 123 | Sequential reads. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 124 | .TP |
| 125 | .B write |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 126 | Sequential writes. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 127 | .TP |
| 128 | .B randread |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 129 | Random reads. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 130 | .TP |
| 131 | .B randwrite |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 132 | Random writes. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 133 | .TP |
| 134 | .B rw |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 135 | Mixed sequential reads and writes. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 136 | .TP |
| 137 | .B randrw |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 138 | Mixed random reads and writes. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 139 | .RE |
| 140 | .P |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 141 | For mixed I/O, the default split is 50/50. For random I/O, the number of I/Os |
| 142 | to perform before getting a new offset can be specified by appending |
| 143 | `:\fIint\fR' to the pattern type. The default is 1. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 144 | .RE |
| 145 | .TP |
| 146 | .BI randrepeat \fR=\fPbool |
| 147 | Seed the random number generator in a predictable way so results are repeatable |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 148 | across runs. Default: true. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 149 | .TP |
| 150 | .BI fadvise_hint \fR=\fPbool |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 151 | Disable use of \fIposix_fadvise\fR\|(2) to advise the kernel what I/O patterns |
| 152 | are likely to be issued. Default: true. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 153 | .TP |
| 154 | .BI size \fR=\fPsiint |
| 155 | Total size of I/O for this job. \fBfio\fR will run until this many bytes have |
| 156 | been transfered, unless limited by other options (\fBruntime\fR, for instance). |
| 157 | Unless \fBnr_files\fR and \fBfilesize\fR options are given, this amount will be |
| 158 | divided between the available files for the job. |
| 159 | .TP |
| 160 | .BI filesize \fR=\fPirange |
| 161 | Individual file sizes. May be a range, in which case \fBfio\fR will select sizes |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 162 | for files at random within the given range, limited to \fBsize\fR in total (if |
| 163 | that is given). If \fBfilesize\fR is not specified, each created file is the |
| 164 | same size. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 165 | .TP |
| 166 | .BI blocksize \fR=\fPsiint "\fR,\fB bs" \fR=\fPsiint |
| 167 | Block size for I/O units. Default: 4k. Values for reads and writes can be |
| 168 | specified seperately in the format \fIread\fR,\fIwrite\fR, either of |
| 169 | which may be empty to leave that value at its default. |
| 170 | .TP |
| 171 | .BI blocksize_range \fR=\fPirange "\fR,\fB bsrange" \fR=\fPirange |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 172 | Specify a range of I/O block sizes. The issued I/O unit will always be a |
| 173 | multiple of the minimum size, unless \fBblocksize_unaligned\fR is set. Applies |
| 174 | to both reads and writes, but can be specified seperately (see \fBblocksize\fR). |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 175 | .TP |
| 176 | .B blocksize_unaligned\fR,\fP bs_unaligned |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 177 | If set, any size in \fBblocksize_range\fR may be used. This typically won't |
| 178 | work with direct I/O, as that normally requires sector alignment. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 179 | .TP |
| 180 | .B zero_buffers |
| 181 | Initialise buffers with all zeros. Default: fill buffers with random data. |
| 182 | .TP |
| 183 | .BI nrfiles \fR=\fPint |
| 184 | Number of files to use for this job. Default: 1. |
| 185 | .TP |
| 186 | .BI openfiles \fR=\fPint |
| 187 | Number of files to keep open at the same time. Default: \fBnrfiles\fR. |
| 188 | .TP |
| 189 | .BI file_service_type \fR=\fPstr |
| 190 | Defines how files to service are selected. The following types are defined: |
| 191 | .RS |
| 192 | .RS |
| 193 | .TP |
| 194 | .B random |
| 195 | Choose a file at random |
| 196 | .TP |
| 197 | .B roundrobin |
| 198 | Round robin over open files (default). |
| 199 | .RE |
| 200 | .P |
| 201 | The number of I/Os to issue before switching a new file can be specified by |
| 202 | appending `:\fIint\fR' to the service type. |
| 203 | .RE |
| 204 | .TP |
| 205 | .BI ioengine \fR=\fPstr |
| 206 | Defines how the job issues I/O. The following types are defined: |
| 207 | .RS |
| 208 | .RS |
| 209 | .TP |
| 210 | .B sync |
| 211 | Basic \fIread\fR\|(2) or \fIwrite\fR\|(2) I/O. \fIfseek\fR\|(2) is used to |
| 212 | position the I/O location. |
| 213 | .TP |
gurudas pai | a31041e | 2007-10-23 15:12:30 +0200 | [diff] [blame] | 214 | .B psync |
| 215 | Basic \fIpread\fR\|(2) or \fIpwrite\fR\|(2) I/O. |
| 216 | .TP |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 217 | .B libaio |
| 218 | Linux native asynchronous I/O. |
| 219 | .TP |
| 220 | .B posixaio |
| 221 | glibc POSIX asynchronous I/O using \fIaio_read\fR\|(3) and \fIaio_write\fR\|(3). |
| 222 | .TP |
| 223 | .B mmap |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 224 | File is memory mapped with \fImmap\fR\|(2) and data copied using |
| 225 | \fImemcpy\fR\|(3). |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 226 | .TP |
| 227 | .B splice |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 228 | \fIsplice\fR\|(2) is used to transfer the data and \fIvmsplice\fR\|(2) to |
| 229 | transfer data from user-space to the kernel. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 230 | .TP |
| 231 | .B syslet-rw |
| 232 | Use the syslet system calls to make regular read/write asynchronous. |
| 233 | .TP |
| 234 | .B sg |
| 235 | SCSI generic sg v3 I/O. May be either synchronous using the SG_IO ioctl, or if |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 236 | the target is an sg character device, we use \fIread\fR\|(2) and |
| 237 | \fIwrite\fR\|(2) for asynchronous I/O. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 238 | .TP |
| 239 | .B null |
| 240 | Doesn't transfer any data, just pretends to. Mainly used to exercise \fBfio\fR |
| 241 | itself and for debugging and testing purposes. |
| 242 | .TP |
| 243 | .B net |
| 244 | Transfer over the network. \fBfilename\fR must be set appropriately to |
| 245 | `\fIhost\fR/\fIport\fR' regardless of data direction. If receiving, only the |
| 246 | \fIport\fR argument is used. |
| 247 | .TP |
| 248 | .B netsplice |
| 249 | Like \fBnet\fR, but uses \fIsplice\fR\|(2) and \fIvmsplice\fR\|(2) to map data |
| 250 | and send/receive. |
| 251 | .TP |
gurudas pai | 53aec0a | 2007-10-05 13:20:18 +0200 | [diff] [blame] | 252 | .B cpuio |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 253 | Doesn't transfer any data, but burns CPU cycles according to \fBcpuload\fR and |
| 254 | \fBcpucycles\fR parameters. |
| 255 | .TP |
| 256 | .B guasi |
| 257 | The GUASI I/O engine is the Generic Userspace Asynchronous Syscall Interface |
| 258 | approach to asycnronous I/O. |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 259 | .br |
| 260 | See <http://www.xmailserver.org/guasi\-lib.html>. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 261 | .TP |
| 262 | .B external |
| 263 | Loads an external I/O engine object file. Append the engine filename as |
| 264 | `:\fIenginepath\fR'. |
| 265 | .RE |
| 266 | .RE |
| 267 | .TP |
| 268 | .BI iodepth \fR=\fPint |
| 269 | Number of I/O units to keep in flight against the file. Default: 1. |
| 270 | .TP |
| 271 | .BI iodepth_batch \fR=\fPint |
| 272 | Number of I/Os to submit at once. Default: \fBiodepth\fR. |
| 273 | .TP |
| 274 | .BI iodepth_low \fR=\fPint |
| 275 | Low watermark indicating when to start filling the queue again. Default: |
| 276 | \fBiodepth\fR. |
| 277 | .TP |
| 278 | .BI direct \fR=\fPbool |
| 279 | If true, use non-buffered I/O (usually O_DIRECT). Default: false. |
| 280 | .TP |
| 281 | .BI buffered \fR=\fPbool |
| 282 | If true, use buffered I/O. This is the opposite of the \fBdirect\fR parameter. |
| 283 | Default: true. |
| 284 | .TP |
| 285 | .BI offset \fR=\fPsiint |
| 286 | Offset in the file to start I/O. Data before the offset will not be touched. |
| 287 | .TP |
| 288 | .BI fsync \fR=\fPint |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 289 | How many I/Os to perform before issuing an \fBfsync\fR\|(2) of dirty data. If |
| 290 | 0, don't sync. Default: 0. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 291 | .TP |
| 292 | .BI overwrite \fR=\fPbool |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 293 | If writing, setup the file first and do overwrites. Default: false. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 294 | .TP |
| 295 | .BI end_fsync \fR=\fPbool |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 296 | Sync file contents when job exits. Default: false. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 297 | .TP |
| 298 | .BI fsync_on_close \fR=\fPbool |
| 299 | If true, sync file contents on close. This differs from \fBend_fsync\fR in that |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 300 | it will happen on every close, not just at the end of the job. Default: false. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 301 | .TP |
| 302 | .BI rwmixcycle \fR=\fPint |
| 303 | How many milliseconds before switching between reads and writes for a mixed |
| 304 | workload. Default: 500ms. |
| 305 | .TP |
| 306 | .BI rwmixread \fR=\fPint |
| 307 | Percentage of a mixed workload that should be reads. Default: 50. |
| 308 | .TP |
| 309 | .BI rwmixwrite \fR=\fPint |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 310 | Percentage of a mixed workload that should be writes. If \fBrwmixread\fR and |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 311 | \fBwrmixwrite\fR are given and do not sum to 100%, the latter of the two |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 312 | overrides the first. Default: 50. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 313 | .TP |
| 314 | .B norandommap |
| 315 | Normally \fBfio\fR will cover every block of the file when doing random I/O. If |
| 316 | this parameter is given, a new offset will be chosen without looking at past |
| 317 | I/O history. This parameter is mutually exclusive with \fBverify\fR. |
| 318 | .TP |
| 319 | .BI nice \fR=\fPint |
| 320 | Run job with given nice value. See \fInice\fR\|(2). |
| 321 | .TP |
| 322 | .BI prio \fR=\fPint |
| 323 | Set I/O priority value of this job between 0 (highest) and 7 (lowest). See |
| 324 | \fIionice\fR\|(1). |
| 325 | .TP |
| 326 | .BI prioclass \fR=\fPint |
| 327 | Set I/O priority class. See \fIionice\fR\|(1). |
| 328 | .TP |
| 329 | .BI thinktime \fR=\fPint |
| 330 | Stall job for given number of microseconds between issuing I/Os. |
| 331 | .TP |
| 332 | .BI thinktime_spin \fR=\fPint |
| 333 | Pretend to spend CPU time for given number of microseconds, sleeping the rest |
| 334 | of the time specified by \fBthinktime\fR. Only valid if \fBthinktime\fR is set. |
| 335 | .TP |
| 336 | .BI thinktime_blocks \fR=\fPint |
| 337 | Number of blocks to issue before waiting \fBthinktime\fR microseconds. |
| 338 | Default: 1. |
| 339 | .TP |
| 340 | .BI rate \fR=\fPint |
| 341 | Cap bandwidth used by this job to this number of KiB/s. |
| 342 | .TP |
| 343 | .BI ratemin \fR=\fPint |
| 344 | Tell \fBfio\fR to do whatever it can to maintain at least the given bandwidth. |
| 345 | Failing to meet this requirement will cause the job to exit. |
| 346 | .TP |
| 347 | .BI rate_iops \fR=\fPint |
| 348 | Cap the bandwidth to this number of IOPS. If \fBblocksize\fR is a range, the |
| 349 | smallest block size is used as the metric. |
| 350 | .TP |
| 351 | .BI rate_iops_min \fR=\fPint |
| 352 | If this rate of I/O is not met, the job will exit. |
| 353 | .TP |
| 354 | .BI ratecycle \fR=\fPint |
| 355 | Average bandwidth for \fBrate\fR and \fBratemin\fR over this number of |
| 356 | milliseconds. Default: 1000ms. |
| 357 | .TP |
| 358 | .BI cpumask \fR=\fPint |
| 359 | Set CPU affinity for this job. \fIint\fR is a bitmask of allowed CPUs the job |
| 360 | may run on. See \fBsched_setaffinity\fR\|(2). |
| 361 | .TP |
| 362 | .BI cpus_allowed \fR=\fPstr |
| 363 | Same as \fBcpumask\fR, but allows a comma-delimited list of CPU numbers. |
| 364 | .TP |
| 365 | .BI startdelay \fR=\fPint |
| 366 | Delay start of job for the specified number of seconds. |
| 367 | .TP |
| 368 | .BI runtime \fR=\fPint |
| 369 | Terminate processing after the specified number of seconds. |
| 370 | .TP |
| 371 | .B time_based |
| 372 | If given, run for the specified \fBruntime\fR duration even if the files are |
| 373 | completely read or written. The same workload will be repeated as many times |
| 374 | as \fBruntime\fR allows. |
| 375 | .TP |
| 376 | .BI invalidate \fR=\fPbool |
| 377 | Invalidate buffer-cache for the file prior to starting I/O. Default: true. |
| 378 | .TP |
| 379 | .BI sync \fR=\fPbool |
| 380 | Use synchronous I/O for buffered writes. For the majority of I/O engines, |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 381 | this means using O_SYNC. Default: false. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 382 | .TP |
| 383 | .BI iomem \fR=\fPstr "\fR,\fP mem" \fR=\fPstr |
| 384 | Allocation method for I/O unit buffer. Allowed values are: |
| 385 | .RS |
| 386 | .RS |
| 387 | .TP |
| 388 | .B malloc |
| 389 | Allocate memory with \fImalloc\fR\|(3). |
| 390 | .TP |
| 391 | .B shm |
| 392 | Use shared memory buffers allocated through \fIshmget\fR\|(2). |
| 393 | .TP |
| 394 | .B shmhuge |
| 395 | Same as \fBshm\fR, but use huge pages as backing. |
| 396 | .TP |
| 397 | .B mmap |
| 398 | Use \fImmap\fR\|(2) for allocation. Uses anonymous memory unless a filename |
| 399 | is given after the option in the format `:\fIfile\fR'. |
| 400 | .TP |
| 401 | .B mmaphuge |
| 402 | Same as \fBmmap\fR, but use huge files as backing. |
| 403 | .RE |
| 404 | .P |
| 405 | The amount of memory allocated is the maximum allowed \fBblocksize\fR for the |
| 406 | job multiplied by \fBiodepth\fR. For \fBshmhuge\fR or \fBmmaphuge\fR to work, |
| 407 | the system must have free huge pages allocated. \fBmmaphuge\fR also needs to |
| 408 | have hugetlbfs mounted, and \fIfile\fR must point there. |
| 409 | .RE |
| 410 | .TP |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 411 | .BI hugepage\-size \fR=\fPsiint |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 412 | Defines the size of a huge page. Must be at least equal to the system setting. |
| 413 | Should be a multiple of 1MiB. Default: 4MiB. |
| 414 | .TP |
| 415 | .B exitall |
| 416 | Terminate all jobs when one finishes. Default: wait for each job to finish. |
| 417 | .TP |
| 418 | .BI bwavgtime \fR=\fPint |
| 419 | Average bandwidth calculations over the given time in milliseconds. Default: |
| 420 | 500ms. |
| 421 | .TP |
| 422 | .BI create_serialize \fR=\fPbool |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 423 | If true, serialize file creation for the jobs. Default: true. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 424 | .TP |
| 425 | .BI create_fsync \fR=\fPbool |
| 426 | \fIfsync\fR\|(2) data file after creation. Default: true. |
| 427 | .TP |
| 428 | .BI unlink \fR=\fPbool |
| 429 | Unlink job files when done. Default: false. |
| 430 | .TP |
| 431 | .BI loops \fR=\fPint |
| 432 | Specifies the number of iterations (runs of the same workload) of this job. |
| 433 | Default: 1. |
| 434 | .TP |
| 435 | .BI do_verify \fR=\fPbool |
| 436 | Run the verify phase after a write phase. Only valid if \fBverify\fR is set. |
| 437 | Default: true. |
| 438 | .TP |
| 439 | .BI verify \fR=\fPstr |
| 440 | Method of verifying file contents after each iteration of the job. Allowed |
| 441 | values are: |
| 442 | .RS |
| 443 | .RS |
| 444 | .TP |
| 445 | .B md5 crc16 crc32 crc64 crc7 sha256 sha512 |
| 446 | Store appropriate checksum in the header of each block. |
| 447 | .TP |
| 448 | .B meta |
| 449 | Write extra information about each I/O (timestamp, block number, etc.). The |
| 450 | block number is verified. |
| 451 | .TP |
| 452 | .B pattern |
| 453 | Fill I/O buffers with a specific pattern that is used to verify. The pattern is |
| 454 | specified by appending `:\fIint\fR' to the parameter. \fIint\fR cannot be larger |
| 455 | than 32-bits. |
| 456 | .TP |
| 457 | .B null |
| 458 | Pretend to verify. Used for testing internals. |
| 459 | .RE |
| 460 | .RE |
| 461 | .TP |
| 462 | .BI verify_sort \fR=\fPbool |
| 463 | If true, written verify blocks are sorted if \fBfio\fR deems it to be faster to |
| 464 | read them back in a sorted manner. Default: true. |
| 465 | .TP |
| 466 | .BI verify_offset \fR=\fPsiint |
| 467 | Swap the verification header with data somewhere else in the block before |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 468 | writing. It is swapped back before verifying. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 469 | .TP |
| 470 | .BI verify_interval \fR=\fPsiint |
| 471 | Write the verification header for this number of bytes, which should divide |
| 472 | \fBblocksize\fR. Default: \fBblocksize\fR. |
| 473 | .TP |
| 474 | .BI verify_fatal \fR=\fPbool |
| 475 | If true, exit the job on the first observed verification failure. Default: |
| 476 | false. |
| 477 | .TP |
| 478 | .B stonewall |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 479 | Wait for preceeding jobs in the job file to exit before starting this one. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 480 | \fBstonewall\fR implies \fBnew_group\fR. |
| 481 | .TP |
| 482 | .B new_group |
| 483 | Start a new reporting group. If not given, all jobs in a file will be part |
| 484 | of the same reporting group, unless separated by a stonewall. |
| 485 | .TP |
| 486 | .BI numjobs \fR=\fPint |
| 487 | Number of clones (processes/threads performing the same workload) of this job. |
| 488 | Default: 1. |
| 489 | .TP |
| 490 | .B group_reporting |
| 491 | If set, display per-group reports instead of per-job when \fBnumjobs\fR is |
| 492 | specified. |
| 493 | .TP |
| 494 | .B thread |
| 495 | Use threads created with \fBpthread_create\fR\|(3) instead of processes created |
| 496 | with \fBfork\fR\|(2). |
| 497 | .TP |
| 498 | .BI zonesize \fR=\fPsiint |
| 499 | Divide file into zones of the specified size in bytes. See \fBzoneskip\fR. |
| 500 | .TP |
| 501 | .BI zoneskip \fR=\fPsiint |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 502 | Skip the specified number of bytes when \fBzonesize\fR bytes of data have been |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 503 | read. |
| 504 | .TP |
| 505 | .BI write_iolog \fR=\fPstr |
| 506 | Write the issued I/O patterns to the specified file. |
| 507 | .TP |
| 508 | .BI read_iolog \fR=\fPstr |
| 509 | Replay the I/O patterns contained in the specified file generated by |
| 510 | \fBwrite_iolog\fR, or may be a \fBblktrace\fR binary file. |
| 511 | .TP |
| 512 | .B write_bw_log |
| 513 | If given, write bandwidth logs of the jobs in this file. |
| 514 | .TP |
| 515 | .B write_lat_log |
| 516 | Same as \fBwrite_bw_log\fR, but writes I/O completion latencies. |
| 517 | .TP |
| 518 | .BI lockmem \fR=\fPsiint |
| 519 | Pin the specified amount of memory with \fBmlock\fR\|(2). Can be used to |
| 520 | simulate a smaller amount of memory. |
| 521 | .TP |
| 522 | .BI exec_prerun \fR=\fPstr |
| 523 | Before running the job, execute the specified command with \fBsystem\fR\|(3). |
| 524 | .TP |
| 525 | .BI exec_postrun \fR=\fPstr |
| 526 | Same as \fBexec_prerun\fR, but the command is executed after the job completes. |
| 527 | .TP |
| 528 | .BI ioscheduler \fR=\fPstr |
| 529 | Attempt to switch the device hosting the file to the specified I/O scheduler. |
| 530 | .TP |
| 531 | .BI cpuload \fR=\fPint |
| 532 | If the job is a CPU cycle-eater, attempt to use the specified percentage of |
| 533 | CPU cycles. |
| 534 | .TP |
| 535 | .BI cpuchunks \fR=\fPint |
| 536 | If the job is a CPU cycle-eater, split the load into cycles of the |
| 537 | given time in milliseconds. |
| 538 | .TP |
| 539 | .BI disk_util \fR=\fPbool |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 540 | Generate disk utilization statistics if the platform supports it. Default: true. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 541 | .SH OUTPUT |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 542 | While running, \fBfio\fR will display the status of the created jobs. For |
| 543 | example: |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 544 | .RS |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 545 | .P |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 546 | Threads: 1: [_r] [24.8% done] [ 13509/ 8334 kb/s] [eta 00h:01m:31s] |
| 547 | .RE |
| 548 | .P |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 549 | The characters in the first set of brackets denote the current status of each |
| 550 | threads. The possible values are: |
| 551 | .P |
| 552 | .PD 0 |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 553 | .RS |
| 554 | .TP |
| 555 | .B P |
| 556 | Setup but not started. |
| 557 | .TP |
| 558 | .B C |
| 559 | Thread created. |
| 560 | .TP |
| 561 | .B I |
| 562 | Initialized, waiting. |
| 563 | .TP |
| 564 | .B R |
| 565 | Running, doing sequential reads. |
| 566 | .TP |
| 567 | .B r |
| 568 | Running, doing random reads. |
| 569 | .TP |
| 570 | .B W |
| 571 | Running, doing sequential writes. |
| 572 | .TP |
| 573 | .B w |
| 574 | Running, doing random writes. |
| 575 | .TP |
| 576 | .B M |
| 577 | Running, doing mixed sequential reads/writes. |
| 578 | .TP |
| 579 | .B m |
| 580 | Running, doing mixed random reads/writes. |
| 581 | .TP |
| 582 | .B F |
| 583 | Running, currently waiting for \fBfsync\fR\|(2). |
| 584 | .TP |
| 585 | .B V |
| 586 | Running, verifying written data. |
| 587 | .TP |
| 588 | .B E |
| 589 | Exited, not reaped by main thread. |
| 590 | .TP |
| 591 | .B \- |
| 592 | Exited, thread reaped. |
| 593 | .RE |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 594 | .PD |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 595 | .P |
| 596 | The second set of brackets shows the estimated completion percentage of |
| 597 | the current group. The third set shows the read and write I/O rate, |
| 598 | respectively. Finally, the estimated run time of the job is displayed. |
| 599 | .P |
| 600 | When \fBfio\fR completes (or is interrupted by Ctrl-C), it will show data |
| 601 | for each thread, each group of threads, and each disk, in that order. |
| 602 | .P |
| 603 | Per-thread statistics first show the threads client number, group-id, and |
| 604 | error code. The remaining figures are as follows: |
| 605 | .RS |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 606 | .TP |
| 607 | .B io |
| 608 | Number of megabytes of I/O performed. |
| 609 | .TP |
| 610 | .B bw |
| 611 | Average data rate (bandwidth). |
| 612 | .TP |
| 613 | .B runt |
| 614 | Threads run time. |
| 615 | .TP |
| 616 | .B slat |
| 617 | Submission latency minimum, maximum, average and standard deviation. This is |
| 618 | the time it took to submit the I/O. |
| 619 | .TP |
| 620 | .B clat |
| 621 | Completion latency minimum, maximum, average and standard deviation. This |
| 622 | is the time between submission and completion. |
| 623 | .TP |
| 624 | .B bw |
| 625 | Bandwidth minimum, maximum, percentage of aggregate bandwidth received, average |
| 626 | and standard deviation. |
| 627 | .TP |
| 628 | .B cpu |
| 629 | CPU usage statistics. Includes user and system time, number of context switches |
| 630 | this thread went through and number of major and minor page faults. |
| 631 | .TP |
| 632 | .B IO depths |
| 633 | Distribution of I/O depths. Each depth includes everything less than (or equal) |
| 634 | to it, but greater than the previous depth. |
| 635 | .TP |
| 636 | .B IO issued |
| 637 | Number of read/write requests issued, and number of short read/write requests. |
| 638 | .TP |
| 639 | .B IO latencies |
| 640 | Distribution of I/O completion latencies. The numbers follow the same pattern |
| 641 | as \fBIO depths\fR. |
| 642 | .RE |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 643 | .P |
| 644 | The group statistics show: |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 645 | .PD 0 |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 646 | .RS |
| 647 | .TP |
| 648 | .B io |
| 649 | Number of megabytes I/O performed. |
| 650 | .TP |
| 651 | .B aggrb |
| 652 | Aggregate bandwidth of threads in the group. |
| 653 | .TP |
| 654 | .B minb |
| 655 | Minimum average bandwidth a thread saw. |
| 656 | .TP |
| 657 | .B maxb |
| 658 | Maximum average bandwidth a thread saw. |
| 659 | .TP |
| 660 | .B mint |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 661 | Shortest runtime of threads in the group. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 662 | .TP |
| 663 | .B maxt |
| 664 | Longest runtime of threads in the group. |
| 665 | .RE |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 666 | .PD |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 667 | .P |
| 668 | Finally, disk statistics are printed with reads first: |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 669 | .PD 0 |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 670 | .RS |
| 671 | .TP |
| 672 | .B ios |
| 673 | Number of I/Os performed by all groups. |
| 674 | .TP |
| 675 | .B merge |
| 676 | Number of merges in the I/O scheduler. |
| 677 | .TP |
| 678 | .B ticks |
| 679 | Number of ticks we kept the disk busy. |
| 680 | .TP |
| 681 | .B io_queue |
| 682 | Total time spent in the disk queue. |
| 683 | .TP |
| 684 | .B util |
| 685 | Disk utilization. |
| 686 | .RE |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 687 | .PD |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 688 | .SH TERSE OUTPUT |
| 689 | If the \fB\-\-minimal\fR option is given, the results will be printed in a |
| 690 | semicolon-delimited format suitable for scripted use. The fields are: |
| 691 | .P |
| 692 | .RS |
| 693 | .B jobname, groupid, error |
| 694 | .P |
| 695 | Read status: |
| 696 | .RS |
| 697 | .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP |
| 698 | .P |
| 699 | Submission latency: |
| 700 | .RS |
| 701 | .B min, max, mean, standard deviation |
| 702 | .RE |
| 703 | Completion latency: |
| 704 | .RS |
| 705 | .B min, max, mean, standard deviation |
| 706 | .RE |
| 707 | Bandwidth: |
| 708 | .RS |
| 709 | .B min, max, aggregate percentage of total, mean, standard deviation |
| 710 | .RE |
| 711 | .RE |
| 712 | .P |
| 713 | Write status: |
| 714 | .RS |
| 715 | .B KiB I/O, bandwidth \fR(KiB/s)\fP, runtime \fR(ms)\fP |
| 716 | .P |
| 717 | Submission latency: |
| 718 | .RS |
| 719 | .B min, max, mean, standard deviation |
| 720 | .RE |
| 721 | Completion latency: |
| 722 | .RS |
| 723 | .B min, max, mean, standard deviation |
| 724 | .RE |
| 725 | Bandwidth: |
| 726 | .RS |
| 727 | .B min, max, aggregate percentage of total, mean, standard deviation |
| 728 | .RE |
| 729 | .RE |
| 730 | .P |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 731 | CPU usage: |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 732 | .RS |
| 733 | .B user, system, context switches |
| 734 | .RE |
| 735 | .P |
| 736 | IO depth distribution: |
| 737 | .RS |
| 738 | .B <=1, 2, 4, 8, 16, 32, >=64 |
| 739 | .RE |
| 740 | .P |
| 741 | IO latency distribution (ms): |
| 742 | .RS |
| 743 | .B <=2, 4, 10, 20, 50, 100, 250, 500, 750, 1000, >=2000 |
| 744 | .RE |
| 745 | .P |
| 746 | .B text description |
| 747 | .RE |
| 748 | .SH AUTHORS |
| 749 | .B fio |
| 750 | was written by Jens Axboe <jens.axboe@oracle.com>. |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 751 | .br |
| 752 | This man page was written by Aaron Carroll <aaronc@cse.unsw.edu.au> based |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 753 | on documentation by Jens Axboe. |
| 754 | .SH "REPORTING BUGS" |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 755 | Report bugs to the \fBfio\fR mailing list <fio-devel@kernel.dk>. |
| 756 | See \fBREADME\fR. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 757 | .SH "SEE ALSO" |
Aaron Carroll | d1429b5 | 2007-09-18 08:10:57 +0200 | [diff] [blame] | 758 | For further documentation see \fBHOWTO\fR and \fBREADME\fR. |
| 759 | .br |
| 760 | Sample jobfiles are available in the \fBexamples\fR directory. |
Aaron Carroll | d60e92d | 2007-09-17 10:32:59 +0200 | [diff] [blame] | 761 | |