4 fio is a tool that will spawn a number of thread doing a particular
5 type of io action as specified by the user. fio takes a number of
6 global parameters, each inherited by the thread unless otherwise
7 parameters given to them overriding that setting is given.
13 fio resides in a git repo, the canonical place is:
15 git://brick.kernel.dk/data/git/fio.git
17 Snapshots are frequently generated as well and they include the git
18 meta data as well. You can download them here:
20 http://brick.kernel.dk/snaps/
28 -b block size in KiB for each io
29 -t <sec> Runtime in seconds
30 -r For random io, sequence must be repeatable
31 -R <on> If one thread fails to meet rate, quit all
32 -o <on> Use direct IO is 1, buffered if 0
33 -l Generate per-job latency logs
34 -w Generate per-job bandwidth logs
35 -f <file> Read <file> for job descriptions
37 -v Print version information and exit
39 The <jobs> format is as follows:
41 directory=x Use 'x' as the top level directory for storing files
42 rw=x 'x' may be: read, randread, write, randwrite,
43 rw (read-write mix), randrw (read-write random mix)
44 size=x Set file size to x bytes (x string can include k/m/g)
45 ioengine=x 'x' may be: aio/libaio/linuxaio for Linux aio,
46 posixaio for POSIX aio, sync for regular read/write io,
47 mmap for mmap'ed io, splice for using splice/vmsplice,
48 or sgio for direct SG_IO io. The latter only works on
49 Linux on SCSI (or SCSI-like devices, such as
50 usb-storage or sata/libata driven) devices.
51 iodepth=x For async io, allow 'x' ios in flight
52 overwrite=x If 'x', layout a write file first.
53 prio=x Run io at prio X, 0-7 is the kernel allowed range
54 prioclass=x Run io at prio class X
55 bs=x Use 'x' for thread blocksize. May include k/m postfix.
56 bsrange=x-y Mix thread block sizes randomly between x and y. May
57 also include k/m postfix.
58 direct=x 1 for direct IO, 0 for buffered IO
59 thinktime=x "Think" x usec after each io
60 rate=x Throttle rate to x KiB/sec
61 ratemin=x Quit if rate of x KiB/sec can't be met
62 ratecycle=x ratemin averaged over x msecs
63 cpumask=x Only allow job to run on CPUs defined by mask.
64 fsync=x If writing, fsync after every x blocks have been written
65 startdelay=x Start this thread x seconds after startup
66 timeout=x Terminate x seconds after startup
67 offset=x Start io at offset x (x string can include k/m/g)
68 invalidate=x Invalidate page cache for file prior to doing io
69 sync=x Use sync writes if x and writing
70 mem=x If x == malloc, use malloc for buffers. If x == shm,
71 use shm for buffers. If x == mmap, use anon mmap.
72 exitall When one thread quits, terminate the others
73 bwavgtime=x Average bandwidth stats over an x msec window.
74 create_serialize=x If 'x', serialize file creation.
75 create_fsync=x If 'x', run fsync() after file creation.
76 loops=x Run the job 'x' number of times.
77 verify=x If 'x' == md5, use md5 for verifies. If 'x' == crc32,
78 use crc32 for verifies. md5 is 'safer', but crc32 is
79 a lot faster. Only makes sense for writing to a file.
80 stonewall Wait for preceeding jobs to end before running.
81 numjobs=x Create 'x' similar entries for this job
82 thread Use pthreads instead of forked jobs
84 zoneskip=y Zone options must be paired. If given, the job
85 will skip y bytes for every x read/written. This
86 can be used to gauge hard drive speed over the entire
87 platter, without reading everything. Both x/y can
89 iolog=x Open and read io pattern from file 'x'. The file must
90 contain one io action per line in the following format:
92 where with rw=0/1 for read/write, and the offset
93 and length entries being in bytes.
96 Examples using a job file
97 -------------------------
99 A sample job file doing the same as above would look like this:
109 And fio would be invoked as:
111 $ fio -o1 -s -f file_with_above
113 The second example would look like this:
128 And fio would be invoked as:
130 $ fio -o0 -s -b4096 -f file_with_above
132 'global' is a reserved keyword. When used as the filename, it sets the
133 default options for the threads following that section. It is possible
134 to have more than one global section in the file, as it only affects
137 Also see the examples/ dir for sample job files.
140 Interpreting the output
141 -----------------------
143 fio spits out a lot of output. While running, fio will display the
144 status of the jobs created. An example of that would be:
146 Threads now running: 2 : [ww] [5.73% done]
148 The characters inside the square brackets denote the current status of
149 each thread. The possible values (in typical life cycle order) are:
153 P Thread setup, but not started.
154 C Thread created and running, but not doing anything yet
155 R Running, doing sequential reads.
156 r Running, doing random reads.
157 W Running, doing sequential writes.
158 w Running, doing random writes.
159 V Running, doing verification of written data.
160 E Thread exited, not reaped by main thread yet.
163 The other values are fairly self explanatory - number of thread currently
164 running and doing io, and the estimated completion percentage.
166 When fio is done (or interrupted by ctrl-c), it will show the data for
167 each thread, group of threads, and disks in that order. For each data
168 direction, the output looks like:
170 Client1 (g=0): err= 0:
171 write: io= 32MiB, bw= 666KiB/s, runt= 50320msec
172 slat (msec): min= 0, max= 136, avg= 0.03, dev= 1.92
173 clat (msec): min= 0, max= 631, avg=48.50, dev=86.82
174 bw (KiB/s) : min= 0, max= 1196, per=51.00%, avg=664.02, dev=681.68
175 cpu : usr=1.49%, sys=0.25%, ctx=7969
177 The client number is printed, along with the group id and error of that
178 thread. Below is the io statistics, here for writes. In the order listed,
181 io= Number of megabytes io performed
182 bw= Average bandwidth rate
183 runt= The runtime of that thread
184 slat= Submission latency (avg being the average, dev being the
185 standard deviation). This is the time it took to submit
186 the io. For sync io, the slat is really the completion
187 latency, since queue/complete is one operation there.
188 clat= Completion latency. Same names as slat, this denotes the
189 time from submission to completion of the io pieces. For
190 sync io, clat will usually be equal (or very close) to 0,
191 as the time from submit to complete is basically just
192 CPU time (io has already been done, see slat explanation).
193 bw= Bandwidth. Same names as the xlat stats, but also includes
194 an approximate percentage of total aggregate bandwidth
195 this thread received in this group. This last value is
196 only really useful if the threads in this group are on the
197 same disk, since they are then competing for disk access.
198 cpu= CPU usage. User and system time, along with the number
199 of context switches this thread went through.
201 After each client has been listed, the group statistics are printed. They
204 Run status group 0 (all jobs):
205 READ: io=64MiB, aggrb=22178, minb=11355, maxb=11814, mint=2840msec, maxt=2955msec
206 WRITE: io=64MiB, aggrb=1302, minb=666, maxb=669, mint=50093msec, maxt=50320msec
208 For each data direction, it prints:
210 io= Number of megabytes io performed.
211 aggrb= Aggregate bandwidth of threads in this group.
212 minb= The minimum average bandwidth a thread saw.
213 maxb= The maximum average bandwidth a thread saw.
214 mint= The minimum runtime of a thread.
215 maxt= The maximum runtime of a thread.
217 And finally, the disk statistics are printed. They will look like this:
219 Disk stats (read/write):
220 sda: ios=16398/16511, merge=30/162, ticks=6853/819634, in_queue=826487, util=100.00%
222 Each value is printed for both reads and writes, with reads first. The
225 ios= Number of ios performed by all groups.
226 merge= Number of merges io the io scheduler.
227 ticks= Number of ticks we kept the disk busy.
228 io_queue= Total time spent in the disk queue.
229 util= The disk utilization. A value of 100% means we kept the disk
230 busy constantly, 50% would be a disk idling half of the time.