ports/iperf3
ports/iperf3
1
1
Форкнуть 0
Код Релизы Активность

Update on-line manpage to reflect iperf 3.1.5.

Просмотр исходного кода
Этот коммит содержится в:
Bruce A. Mah 2017-01-13 14:23:07 -08:00
родитель 21e756d069
Коммит c5147b68e3
Не найден ключ, соответствующий данной подписи
Идентификатор ключа GPG: 4984910A8CAAEE8A
1 изменённых файлов: 213 добавлений и 202 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

415
docs/invoking.rst
Просмотреть файл

@ -27,216 +27,227 @@ the executable.
:: ::
IPERF3(1) User Manuals IPERF3(1) IPERF3(1) User Manuals IPERF3(1)
NAME NAME
iperf3 - perform network throughput tests iperf3 - perform network throughput tests
SYNOPSIS SYNOPSIS
iperf3 -s [ options ] iperf3 -s [ options ]
iperf3 -c server [ options ] iperf3 -c server [ options ]
DESCRIPTION DESCRIPTION
iperf3 is a tool for performing network throughput measurements. It iperf3 is a tool for performing network throughput measurements. It
can test either TCP or UDP throughput. To perform an iperf3 test the can test either TCP or UDP throughput. To perform an iperf3 test the
user must establish both a server and a client. user must establish both a server and a client.
GENERAL OPTIONS GENERAL OPTIONS
-p, --port n -p, --port n
set server port to listen on/connect to to n (default 5201) set server port to listen on/connect to to n (default 5201)
-f, --format -f, --format
[kmKM] format to report: Kbits, Mbits, KBytes, MBytes [kmKM] format to report: Kbits, Mbits, KBytes, MBytes
-i, --interval n -i, --interval n
pause n seconds between periodic bandwidth reports; default is pause n seconds between periodic bandwidth reports; default is
1, use 0 to disable 1, use 0 to disable
-F, --file name -F, --file name
client-side: read from the file and write to the network, client-side: read from the file and write to the network,
instead of using random data; server-side: read from the network instead of using random data; server-side: read from the network
and write to the file, instead of throwing the data away and write to the file, instead of throwing the data away
-A, --affinity n/n,m -A, --affinity n/n,m
Set the CPU affinity, if possible (Linux and FreeBSD only). On Set the CPU affinity, if possible (Linux and FreeBSD only). On
both the client and server you can set the local affinity by both the client and server you can set the local affinity by
using the n form of this argument (where n is a CPU number). In using the n form of this argument (where n is a CPU number). In
addition, on the client side you can override the server's addition, on the client side you can override the server's
affinity for just that one test, using the n,m form of argument. affinity for just that one test, using the n,m form of argument.
Note that when using this feature, a process will only be bound Note that when using this feature, a process will only be bound
to a single CPU (as opposed to a set containing potentialy mul- to a single CPU (as opposed to a set containing potentialy mul-
tiple CPUs). tiple CPUs).
-B, --bind host -B, --bind host
bind to a specific interface bind to a specific interface
-V, --verbose -V, --verbose
give more detailed output give more detailed output
-J, --json -J, --json
output in JSON format output in JSON format
--logfile file --logfile file
send output to a log file. send output to a log file.
--forceflush --forceflush
force flushing output at every interval. Used to avoid buffer- force flushing output at every interval. Used to avoid buffer-
ing when sending output to pipe. ing when sending output to pipe.
-d, --debug -d, --debug
emit debugging output. Primarily (perhaps exclusively) of use emit debugging output. Primarily (perhaps exclusively) of use
to developers. to developers.
-v, --version -v, --version
show version information and quit show version information and quit
-h, --help -h, --help
show a help synopsis show a help synopsis
SERVER SPECIFIC OPTIONS SERVER SPECIFIC OPTIONS
-s, --server -s, --server
run in server mode run in server mode
-D, --daemon -D, --daemon
run the server in background as a daemon run the server in background as a daemon
-I, --pidfile file -I, --pidfile file
write a file with the process ID, most useful when running as a write a file with the process ID, most useful when running as a
daemon. daemon.
-1, --one-off -1, --one-off
handle one client connection, then exit. handle one client connection, then exit.
CLIENT SPECIFIC OPTIONS CLIENT SPECIFIC OPTIONS
-c, --client host -c, --client host
run in client mode, connecting to the specified server run in client mode, connecting to the specified server
--sctp use SCTP rather than TCP (FreeBSD and Linux) --sctp use SCTP rather than TCP (FreeBSD and Linux)
-u, --udp -u, --udp
use UDP rather than TCP use UDP rather than TCP
-b, --bandwidth n[KM] -b, --bandwidth n[KM]
set target bandwidth to n bits/sec (default 1 Mbit/sec for UDP, set target bandwidth to n bits/sec (default 1 Mbit/sec for UDP,
unlimited for TCP). If there are multiple streams (-P flag), unlimited for TCP). If there are multiple streams (-P flag),
the bandwidth limit is applied separately to each stream. You the bandwidth limit is applied separately to each stream. You
can also add a '/' and a number to the bandwidth specifier. can also add a '/' and a number to the bandwidth specifier.
This is called "burst mode". It will send the given number of This is called "burst mode". It will send the given number of
packets without pausing, even if that temporarily exceeds the packets without pausing, even if that temporarily exceeds the
specified bandwidth limit. Setting the target bandwidth to 0 specified bandwidth limit. Setting the target bandwidth to 0
will disable bandwidth limits (particularly useful for UDP will disable bandwidth limits (particularly useful for UDP
tests). On platforms supporting the SO_MAX_PACING_RATE socket tests). This bandwidth limit is implemented internally inside
option (currently only Linux), fair-queueing socket-level pac- iperf3, and is available on all platforms. Compare with the
ing, implemented in the kernel, will be used. On other plat- --fq-rate flag.
forms, iperf3 will implement its own rate control.
--fq-rate n[KM]
--no-fq-socket-pacing Set a rate to be used with fair-queueing based socket-level pac-
disable the use of fair-queueing based socket-level pacing with ing, in bits per second. This pacing (if specified) will be in
the -b option, and rely on iperf3's internal rate control. addition to any pacing due to iperf3's internal bandwidth pacing
(-b flag), and both can be specified for the same test. Only
-t, --time n available on platforms supporting the SO_MAX_PACING_RATE socket
time in seconds to transmit for (default 10 secs) option (currently only Linux). The default is no fair-queueing
based pacing.
-n, --bytes n[KM]
number of bytes to transmit (instead of -t) --no-fq-socket-pacing
This option is deprecated and will be removed. It is equivalent
-k, --blockcount n[KM] to specifying --fq-rate=0.
number of blocks (packets) to transmit (instead of -t or -n)
-t, --time n
-l, --length n[KM] time in seconds to transmit for (default 10 secs)
length of buffer to read or write (default 128 KB for TCP, 8KB
for UDP) -n, --bytes n[KM]
number of bytes to transmit (instead of -t)
--cport port
bind data streams to a specific client port (for TCP and UDP -k, --blockcount n[KM]
only, default is to use an ephemeral port) number of blocks (packets) to transmit (instead of -t or -n)
-P, --parallel n -l, --length n[KM]
number of parallel client streams to run length of buffer to read or write. For TCP tests, the default
value is 128KB. In the case of UDP, iperf3 tries to dynamically
-R, --reverse determine a reasonable sending size based on the path MTU; if
run in reverse mode (server sends, client receives) that cannot be determined it uses 1460 bytes as a sending size.
For SCTP tests, the default size is 64KB.
-w, --window n[KM]
window size / socket buffer size (this gets sent to the server --cport port
and used on that side too) bind data streams to a specific client port (for TCP and UDP
only, default is to use an ephemeral port)
-M, --set-mss n
set TCP/SCTP maximum segment size (MTU - 40 bytes) -P, --parallel n
number of parallel client streams to run
-N, --no-delay
set TCP/SCTP no delay, disabling Nagle's Algorithm -R, --reverse
run in reverse mode (server sends, client receives)
-4, --version4
only use IPv4 -w, --window n[KM]
window size / socket buffer size (this gets sent to the server
-6, --version6 and used on that side too)
only use IPv6
-M, --set-mss n
-S, --tos n set TCP/SCTP maximum segment size (MTU - 40 bytes)
set the IP 'type of service'
-N, --no-delay
-L, --flowlabel n set TCP/SCTP no delay, disabling Nagle's Algorithm
set the IPv6 flow label (currently only supported on Linux)
-4, --version4
-X, --xbind name only use IPv4
Bind SCTP associations to a specific subset of links using
sctp_bindx(3). The --B flag will be ignored if this flag is -6, --version6
specified. Normally SCTP will include the protocol addresses of only use IPv6
all active links on the local host when setting up an associa-
tion. Specifying at least one --X name will disable this behav- -S, --tos n
iour. This flag must be specified for each link to be included set the IP 'type of service'
in the association, and is supported for both iperf servers and
clients (the latter are supported by passing the first --X argu- -L, --flowlabel n
ment to bind(2)). Hostnames are accepted as arguments and are set the IPv6 flow label (currently only supported on Linux)
resolved using getaddrinfo(3). If the --4 or --6 flags are
specified, names which do not resolve to addresses within the -X, --xbind name
specified protocol family will be ignored. Bind SCTP associations to a specific subset of links using
sctp_bindx(3). The --B flag will be ignored if this flag is
--nstreams n specified. Normally SCTP will include the protocol addresses of
Set number of SCTP streams. all active links on the local host when setting up an associa-
tion. Specifying at least one --X name will disable this behav-
-Z, --zerocopy iour. This flag must be specified for each link to be included
Use a "zero copy" method of sending data, such as sendfile(2), in the association, and is supported for both iperf servers and
instead of the usual write(2). clients (the latter are supported by passing the first --X argu-
ment to bind(2)). Hostnames are accepted as arguments and are
-O, --omit n resolved using getaddrinfo(3). If the --4 or --6 flags are
Omit the first n seconds of the test, to skip past the TCP slow- specified, names which do not resolve to addresses within the
start period. specified protocol family will be ignored.
-T, --title str --nstreams n
Prefix every output line with this string. Set number of SCTP streams.
-C, --congestion algo -Z, --zerocopy
Set the congestion control algorithm (Linux and FreeBSD only). Use a "zero copy" method of sending data, such as sendfile(2),
An older --linux-congestion synonym for this flag is accepted instead of the usual write(2).
but is deprecated.
-O, --omit n
--get-server-output Omit the first n seconds of the test, to skip past the TCP slow-
Get the output from the server. The output format is determined start period.
by the server (in particular, if the server was invoked with the
--json flag, the output will be in JSON format, otherwise it -T, --title str
will be in human-readable format). If the client is run with Prefix every output line with this string.
--json, the server output is included in a JSON object; other-
wise it is appended at the bottom of the human-readable output. -C, --congestion algo
Set the congestion control algorithm (Linux and FreeBSD only).
An older --linux-congestion synonym for this flag is accepted
but is deprecated.
--get-server-output
Get the output from the server. The output format is determined
by the server (in particular, if the server was invoked with the
--json flag, the output will be in JSON format, otherwise it
will be in human-readable format). If the client is run with
--json, the server output is included in a JSON object; other-
wise it is appended at the bottom of the human-readable output.
AUTHORS AUTHORS
A list of the contributors to iperf3 can be found within the documenta- A list of the contributors to iperf3 can be found within the documenta-
tion located at http://software.es.net/iperf/dev.html#authors. tion located at http://software.es.net/iperf/dev.html#authors.
SEE ALSO SEE ALSO
libiperf(3), http://software.es.net/iperf libiperf(3), http://software.es.net/iperf
ESnet May 2016 IPERF3(1) ESnet January 2017 IPERF3(1)
The iperf3 manual page will typically be installed in manual The iperf3 manual page will typically be installed in manual
section 1. section 1.