1IPERF3(1) User Manuals IPERF3(1)
2
6 iperf3 - perform network throughput tests
7
9 iperf3 -s [ options ]
10 iperf3 -c server [ options ]
11
14 iperf3 is a tool for performing network throughput measurements. It
15 can test TCP, UDP, or SCTP throughput. To perform an iperf3 test the
16 user must establish both a server and a client.
17 The iperf3 executable contains both client and server functionality.
19 An iperf3 server can be started using either of the -s or --server com‐
20 mand-line parameters, for example:
21 iperf3 -s
23 iperf3 --server
25 Note that many iperf3 parameters have both short (-s) and long
27 (--server) forms. In this section we will generally use the short form
28 of command-line flags, unless only the long form of a flag is avail‐
29 able.
30 By default, the iperf3 server listens on TCP port 5201 for connections
32 from an iperf3 client. A custom port can be specified by using the -p
33 flag, for example:
34 iperf3 -s -p 5002
36 After the server is started, it will listen for connections from iperf3
38 clients (in other words, the iperf3 program run in client mode). The
39 client mode can be started using the -c command-line option, which also
40 requires a host to which iperf3 should connect. The host can by speci‐
41 fied by hostname, IPv4 literal, or IPv6 literal:
42 iperf3 -c iperf3.example.com
44 iperf3 -c 192.0.2.1
46 iperf3 -c 2001:db8::1
48 If the iperf3 server is running on a non-default TCP port, that port
50 number needs to be specified on the client as well:
51 iperf3 -c iperf3.example.com -p 5002
53 The initial TCP connection is used to exchange test parameters, control
55 the start and end of the test, and to exchange test results. This is
56 sometimes referred to as the "control connection". The actual test
57 data is sent over a separate TCP connection, as a separate flow of UDP
58 packets, or as an independent SCTP connection, depending on what proto‐
59 col was specified by the client.
60 Normally, the test data is sent from the client to the server, and mea‐
62 sures the upload speed of the client. Measuring the download speed
63 from the server can be done by specifying the -R flag on the client.
64 This causes data to be sent from the server to the client.
65 iperf3 -c iperf3.example.com -p 5202 -R
67 Results are displayed on both the client and server. There will be at
69 least one line of output per measurement interval (by default a mea‐
70 surement interval lasts for one second, but this can be changed by the
71 -i option). Each line of output includes (at least) the time since the
72 start of the test, amount of data transferred during the interval, and
73 the average bitrate over that interval. Note that the values for each
74 measurement interval are taken from the point of view of the endpoint
75 process emitting that output (in other words, the output on the client
76 shows the measurement interval data for the client.
77 At the end of the test is a set of statistics that shows (at least as
79 much as possible) a summary of the test as seen by both the sender and
80 the receiver, with lines tagged accordingly. Recall that by default
81 the client is the sender and the server is the receiver, although as
82 indicated above, use of the -R flag will reverse these roles.
83 The client can be made to retrieve the server-side output for a given
85 test by specifying the --get-server-output flag.
86 Either the client or the server can produce its output in a JSON struc‐
88 ture, useful for integration with other programs, by passing it the -J
89 flag. Because the contents of the JSON structure are only completely
90 known after the test has finished, no JSON output will be emitted until
91 the end of the test.
92 iperf3 has a (overly) large set of command-line options that can be
94 used to set the parameters of a test. They are given in the "GENERAL
95 OPTIONS" section of the manual page below, as well as summarized in
96 iperf3's help output, which can be viewed by running iperf3 with the -h
97 flag.
98
100 -p, --port n
101 set server port to listen on/connect to to n (default 5201)
102 -f, --format
104 [kmgtKMGT] format to report: Kbits/Mbits/Gbits/Tbits
105 -i, --interval n
107 pause n seconds between periodic throughput reports; default is
108 1, use 0 to disable
109 -I, --pidfile file
111 write a file with the process ID, most useful when running as a
112 daemon.
113 -F, --file name
115 Use a file as the source (on the sender) or sink (on the re‐
116 ceiver) of data, rather than just generating random data or
117 throwing it away. This feature is used for finding whether or
118 not the storage subsystem is the bottleneck for file transfers.
119 It does not turn iperf3 into a file transfer tool. The length,
120 attributes, and in some cases contents of the received file may
121 not match those of the original file.
122 -A, --affinity n/n,m
124 Set the CPU affinity, if possible (Linux, FreeBSD, and Windows
125 only). On both the client and server you can set the local
126 affinity by using the n form of this argument (where n is a CPU
127 number). In addition, on the client side you can override the
128 server's affinity for just that one test, using the n,m form of
129 argument. Note that when using this feature, a process will
130 only be bound to a single CPU (as opposed to a set containing
131 potentially multiple CPUs).
132 -B, --bind host[%dev]
134 bind to the specific interface associated with address host. If
135 an optional interface is specified, it is treated as a shortcut
136 for --bind-dev dev. Note that a percent sign and interface de‐
137 vice name are required for IPv6 link-local address literals.
138 --bind-dev dev bind to the specified network interface. This
139 option uses SO_BINDTODEVICE, and may require root permissions.
140 (Available on Linux and possibly other systems.)
141 -V, --verbose
143 give more detailed output
144 -J, --json
146 output in JSON format
147 --logfile file
149 send output to a log file.
150 --forceflush
152 force flushing output at every interval. Used to avoid buffer‐
153 ing when sending output to pipe.
154 --timestamps[=format]
156 prepend a timestamp at the start of each output line. By de‐
157 fault, timestamps have the format emitted by ctime(1). Option‐
158 ally, = followed by a format specification can be passed to cus‐
159 tomize the timestamps, see strftime(3). If this optional format
160 is given, the = must immediately follow the --timestamps option
161 with no whitespace intervening.
162 --rcv-timeout #
164 set idle timeout for receiving data during active tests. The re‐
165 ceiver will halt a test if no data is received from the sender
166 for this number of ms (default to 12000 ms, or 2 minutes).
167 -d, --debug
169 emit debugging output. Primarily (perhaps exclusively) of use
170 to developers.
171 -v, --version
173 show version information and quit
174 -h, --help
176 show a help synopsis
177
180 -s, --server
181 run in server mode
182 -D, --daemon
184 run the server in background as a daemon
185 -1, --one-off
187 handle one client connection, then exit. If an idle time is
188 set, the server will exit after that amount of time with no con‐
189 nection.
190 --idle-timeout n
192 restart the server after n seconds in case it gets stuck. In
193 one-off mode, this is the number of seconds the server will wait
194 before exiting.
195 --server-bitrate-limit n[KMGT]
197 set a limit on the server side, which will cause a test to abort
198 if the client specifies a test of more than n bits per second,
199 or if the average data sent or received by the client (including
200 all data streams) is greater than n bits per second. The de‐
201 fault limit is zero, which implies no limit. The interval over
202 which to average the data rate is 5 seconds by default, but can
203 be specified by adding a '/' and a number to the bitrate speci‐
204 fier.
205 --rsa-private-key-path file
207 path to the RSA private key (not password-protected) used to de‐
208 crypt authentication credentials from the client (if built with
209 OpenSSL support).
210 --authorized-users-path file
212 path to the configuration file containing authorized users cre‐
213 dentials to run iperf tests (if built with OpenSSL support).
214 The file is a comma separated list of usernames and password
215 hashes; more information on the structure of the file can be
216 found in the EXAMPLES section.
217 --time-skew-thresholdsecond seconds
219 time skew threshold (in seconds) between the server and client
220 during the authentication process.
221
223 -c, --client host[%dev]
224 run in client mode, connecting to the specified server. By de‐
225 fault, a test consists of sending data from the client to the
226 server, unless the -R flag is specified. If an optional inter‐
227 face is specified, it is treated as a shortcut for --bind-dev
228 dev. Note that a percent sign and interface device name are re‐
229 quired for IPv6 link-local address literals.
230 --sctp use SCTP rather than TCP (FreeBSD and Linux)
232 -u, --udp
234 use UDP rather than TCP
235 --connect-timeout n
237 set timeout for establishing the initial control connection to
238 the server, in milliseconds. The default behavior is the oper‐
239 ating system's timeout for TCP connection establishment. Pro‐
240 viding a shorter value may speed up detection of a down iperf3
241 server.
242 -b, --bitrate n[KMGT]
244 set target bitrate to n bits/sec (default 1 Mbit/sec for UDP,
245 unlimited for TCP/SCTP). If there are multiple streams (-P
246 flag), the throughput limit is applied separately to each
247 stream. You can also add a '/' and a number to the bitrate
248 specifier. This is called "burst mode". It will send the given
249 number of packets without pausing, even if that temporarily ex‐
250 ceeds the specified throughput limit. Setting the target bi‐
251 trate to 0 will disable bitrate limits (particularly useful for
252 UDP tests). This throughput limit is implemented internally in‐
253 side iperf3, and is available on all platforms. Compare with
254 the --fq-rate flag. This option replaces the --bandwidth flag,
255 which is now deprecated but (at least for now) still accepted.
256 --pacing-timer n[KMGT]
258 set pacing timer interval in microseconds (default 1000 mi‐
259 croseconds, or 1 ms). This controls iperf3's internal pacing
260 timer for the -b/--bitrate option. The timer fires at the in‐
261 terval set by this parameter. Smaller values of the pacing
262 timer parameter smooth out the traffic emitted by iperf3, but
263 potentially at the cost of performance due to more frequent
264 timer processing.
265 --fq-rate n[KMGT]
267 Set a rate to be used with fair-queueing based socket-level pac‐
268 ing, in bits per second. This pacing (if specified) will be in
269 addition to any pacing due to iperf3's internal throughput pac‐
270 ing (-b/--bitrate flag), and both can be specified for the same
271 test. Only available on platforms supporting the SO_MAX_PAC‐
272 ING_RATE socket option (currently only Linux). The default is
273 no fair-queueing based pacing.
274 --no-fq-socket-pacing
276 This option is deprecated and will be removed. It is equivalent
277 to specifying --fq-rate=0.
278 -t, --time n
280 time in seconds to transmit for (default 10 secs)
281 -n, --bytes n[KMGT]
283 number of bytes to transmit (instead of -t)
284 -k, --blockcount n[KMGT]
286 number of blocks (packets) to transmit (instead of -t or -n)
287 -l, --length n[KMGT]
289 length of buffer to read or write. For TCP tests, the default
290 value is 128KB. In the case of UDP, iperf3 tries to dynamically
291 determine a reasonable sending size based on the path MTU; if
292 that cannot be determined it uses 1460 bytes as a sending size.
293 For SCTP tests, the default size is 64KB.
294 --cport port
296 bind data streams to a specific client port (for TCP and UDP
297 only, default is to use an ephemeral port)
298 -P, --parallel n
300 number of parallel client streams to run. Note that iperf3 is
301 single threaded, so if you are CPU bound, this will not yield
302 higher throughput.
303 -R, --reverse
305 reverse the direction of a test, so that the server sends data
306 to the client
307 --bidir
309 test in both directions (normal and reverse), with both the
310 client and server sending and receiving data simultaneously
311 -w, --window n[KMGT]
313 set socket buffer size / window size. This value gets sent to
314 the server and used on that side too; on both sides this option
315 sets both the sending and receiving socket buffer sizes. This
316 option can be used to set (indirectly) the maximum TCP window
317 size. Note that on Linux systems, the effective maximum window
318 size is approximately double what is specified by this option
319 (this behavior is not a bug in iperf3 but a "feature" of the
320 Linux kernel, as documented by tcp(7) and socket(7)).
321 -M, --set-mss n
323 set TCP/SCTP maximum segment size (MTU - 40 bytes)
324 -N, --no-delay
326 set TCP/SCTP no delay, disabling Nagle's Algorithm
327 -4, --version4
329 only use IPv4
330 -6, --version6
332 only use IPv6
333 -S, --tos n
335 set the IP type of service. The usual prefixes for octal and hex
336 can be used, i.e. 52, 064 and 0x34 all specify the same value.
337 --dscp dscp
339 set the IP DSCP bits. Both numeric and symbolic values are ac‐
340 cepted. Numeric values can be specified in decimal, octal and
341 hex (see --tos above). To set both the DSCP bits and the ECN
342 bits, use --tos.
343 -L, --flowlabel n
345 set the IPv6 flow label (currently only supported on Linux)
346 -X, --xbind name
348 Bind SCTP associations to a specific subset of links using
349 sctp_bindx(3). The --B flag will be ignored if this flag is
350 specified. Normally SCTP will include the protocol addresses of
351 all active links on the local host when setting up an associa‐
352 tion. Specifying at least one --X name will disable this behav‐
353 iour. This flag must be specified for each link to be included
354 in the association, and is supported for both iperf servers and
355 clients (the latter are supported by passing the first --X argu‐
356 ment to bind(2)). Hostnames are accepted as arguments and are
357 resolved using getaddrinfo(3). If the --4 or --6 flags are
358 specified, names which do not resolve to addresses within the
359 specified protocol family will be ignored.
360 --nstreams n
362 Set number of SCTP streams.
363 -Z, --zerocopy
365 Use a "zero copy" method of sending data, such as sendfile(2),
366 instead of the usual write(2).
367 -O, --omit n
369 Omit the first n seconds of the test, to skip past the TCP slow-
370 start period.
371 -T, --title str
373 Prefix every output line with this string.
374 --extra-data str
376 Specify an extra data string field to be included in JSON out‐
377 put.
378 -C, --congestion algo
380 Set the congestion control algorithm (Linux and FreeBSD only).
381 An older --linux-congestion synonym for this flag is accepted
382 but is deprecated.
383 --get-server-output
385 Get the output from the server. The output format is determined
386 by the server (in particular, if the server was invoked with the
387 --json flag, the output will be in JSON format, otherwise it
388 will be in human-readable format). If the client is run with
389 --json, the server output is included in a JSON object; other‐
390 wise it is appended at the bottom of the human-readable output.
391 --udp-counters-64bit
393 Use 64-bit counters in UDP test packets. The use of this option
394 can help prevent counter overflows during long or high-bitrate
395 UDP tests. Both client and server need to be running at least
396 version 3.1 for this option to work. It may become the default
397 behavior at some point in the future.
398 --repeating-payload
400 Use repeating pattern in payload, instead of random bytes. The
401 same payload is used in iperf2 (ASCII '0..9' repeating). It
402 might help to test and reveal problems in networking gear with
403 hardware compression (including some WiFi access points), where
404 iperf2 and iperf3 perform differently, just based on payload en‐
405 tropy.
406 --dont-fragment
408 Set the IPv4 Don't Fragment (DF) bit on outgoing packets. Only
409 applicable to tests doing UDP over IPv4.
410 --username username
412 username to use for authentication to the iperf server (if built
413 with OpenSSL support). The password will be prompted for inter‐
414 actively when the test is run. Note, the password to use can
415 also be specified via the IPERF3_PASSWORD environment variable.
416 If this variable is present, the password prompt will be
417 skipped.
418 --rsa-public-key-path file
420 path to the RSA public key used to encrypt authentication cre‐
421 dentials (if built with OpenSSL support)
422
425 Authentication - RSA Keypair
426 The authentication feature of iperf3 requires an RSA public keypair.
427 The public key is used to encrypt the authentication token containing
428 the user credentials, while the private key is used to decrypt the au‐
429 thentication token. The private key must be in PEM format and addi‐
430 tionally must not have a password set. The public key must be in PEM
431 format and use SubjectPrefixKeyInfo encoding. An example of a set of
432 UNIX/Linux commands using OpenSSL to generate a correctly-formed key‐
433 pair follows:
434 > openssl genrsa -des3 -out private.pem 2048
436 > openssl rsa -in private.pem -outform PEM -pubout -out public.pem
437 > openssl rsa -in private.pem -out private_not_protected.pem -out‐
438 form PEM
439 After these commands, the public key will be contained in the file pub‐
441 lic.pem and the private key will be contained in the file pri‐
442 vate_not_protected.pem.
443 Authentication - Authorized users configuration file
445 A simple plaintext file must be provided to the iperf3 server in order
446 to specify the authorized user credentials. The file is a simple list
447 of comma-separated pairs of a username and a corresponding password
448 hash. The password hash is a SHA256 hash of the string "{$user}$pass‐
449 word". The file can also contain commented lines (starting with the #
450 character). An example of commands to generate the password hash on a
451 UNIX/Linux system is given below:
452 > S_USER=mario S_PASSWD=rossi
454 > echo -n "{$S_USER}$S_PASSWD" | sha256sum | awk '{ print $1 }'
455 An example of a password file (with an entry corresponding to the above
457 username and password) is given below:
458 > cat credentials.csv
459 # file format: username,sha256
460 mario,bf7a49a846d44b454a5d11e7ac‐
461 faf13d138bbe0b7483aa3e050879700572709b
462
466 A list of the contributors to iperf3 can be found within the documenta‐
467 tion located at https://software.es.net/iperf/dev.html#authors.
468
471 libiperf(3), https://software.es.net/iperf
472ESnet January 2022 IPERF3(1)