nexmon – Blame information for rev 1
?pathlinks?
Rev | Author | Line No. | Line |
---|---|---|---|
1 | office | 1 | .TH IPERF 1 "APRIL 2008" NLANR/DAST "User Manuals" |
2 | .SH NAME |
||
3 | iperf \- perform network throughput tests |
||
4 | .SH SYNOPSIS |
||
5 | .B iperf -s [ |
||
6 | .I options |
||
7 | .B ] |
||
8 | |||
9 | .B iperf -c |
||
10 | .I server |
||
11 | .B [ |
||
12 | .I options |
||
13 | .B ] |
||
14 | |||
15 | .B iperf -u -s [ |
||
16 | .I options |
||
17 | .B ] |
||
18 | |||
19 | .B iperf -u -c |
||
20 | .I server |
||
21 | .B [ |
||
22 | .I options |
||
23 | .B ] |
||
24 | .SH DESCRIPTION |
||
25 | iperf is a tool for performing network throughput measurements. It can test |
||
26 | either TCP or UDP throughput. To perform an iperf test the user must |
||
27 | establish both a server (to discard traffic) and a client (to generate |
||
28 | traffic). |
||
29 | .SH "GENERAL OPTIONS" |
||
30 | .TP |
||
31 | .BR -e ", " --enhanced " " |
||
32 | Display enhanced output in reports |
||
33 | .TP |
||
34 | .BR -f ", " --format " " |
||
35 | [kmKM] format to report: Kbits, Mbits, KBytes, MBytes |
||
36 | .TP |
||
37 | .BR -h ", " --help " " |
||
38 | print a help synopsis |
||
39 | .TP |
||
40 | .BR -i ", " --interval " \fIn\fR" |
||
41 | pause \fIn\fR seconds between periodic bandwidth reports |
||
42 | .TP |
||
43 | .BR -l ", " --len " \fIn\fR[KM]" |
||
44 | set length read/write buffer to \fIn\fR (default 8 KB) |
||
45 | .TP |
||
46 | .BR -m ", " --print_mss " " |
||
47 | print TCP maximum segment size (MTU - TCP/IP header) |
||
48 | .TP |
||
49 | .BR -o ", " --output " \fIfilename\fR" |
||
50 | output the report or error message to this specified file |
||
51 | .TP |
||
52 | .BR -p ", " --port " \fIn\fR" |
||
53 | set server port to listen on/connect to to \fIn\fR (default 5001) |
||
54 | .TP |
||
55 | .BR -u ", " --udp " " |
||
56 | use UDP rather than TCP |
||
57 | .TP |
||
58 | .BR -w ", " --window " \fIn\fR[KM]" |
||
59 | TCP window size (socket buffer size) |
||
60 | .TP |
||
61 | .BR -z ", " --realtime " " |
||
62 | Request realtime scheduler, if supported. |
||
63 | .TP |
||
64 | .BR -B ", " --bind " \fIhost\fR" |
||
65 | bind to \fIhost\fR, an interface or multicast address |
||
66 | .TP |
||
67 | .BR -C ", " --compatibility " " |
||
68 | for use with older versions does not sent extra msgs |
||
69 | .TP |
||
70 | .BR -M ", " --mss " \fIn\fR" |
||
71 | set TCP maximum segment size (MTU - 40 bytes) |
||
72 | .TP |
||
73 | .BR -N ", " --nodelay " " |
||
74 | set TCP no delay, disabling Nagle's Algorithm |
||
75 | .TP |
||
76 | .BR -v ", " --version " " |
||
77 | print version information and quit |
||
78 | .TP |
||
79 | .BR -V ", " --IPv6Version " " |
||
80 | Set the domain to IPv6 |
||
81 | .TP |
||
82 | .BR -x ", " --reportexclude " [CDMSV]" |
||
83 | exclude C(connection) D(data) M(multicast) S(settings) V(server) reports |
||
84 | .TP |
||
85 | .BR -y ", " --reportstyle " C|c" |
||
86 | if set to C or c report results as CSV (comma separated values) |
||
87 | .SH "SERVER SPECIFIC OPTIONS" |
||
88 | .TP |
||
89 | .BR -s ", " --server " " |
||
90 | run in server mode |
||
91 | .TP |
||
92 | .BR -U ", " --single_udp " " |
||
93 | run in single threaded UDP mode |
||
94 | .TP |
||
95 | .BR -D ", " --daemon " " |
||
96 | run the server as a daemon. On Windows this will also install the IPerfService. |
||
97 | .TP |
||
98 | .BR -R ", " --remove " " |
||
99 | remove the IPerfService (Windows only). |
||
100 | .SH "CLIENT SPECIFIC OPTIONS" |
||
101 | .TP |
||
102 | .BR -b ", " --bandwidth " \fIn\fR[KMG] | \fIn\fRpps" |
||
103 | set target bandwidth to \fIn\fR bits/sec (default 1 Mbit/sec) or |
||
104 | \fIn\fR packets per sec. This may be used with TCP or UDP. |
||
105 | .TP |
||
106 | .BR -c ", " --client " \fIhost\fR" |
||
107 | run in client mode, connecting to \fIhost\fR |
||
108 | .TP |
||
109 | .BR -d ", " --dualtest " " |
||
110 | Do a bidirectional test simultaneously |
||
111 | .TP |
||
112 | .BR -n ", " --num " \fIn\fR[KM]" |
||
113 | number of bytes to transmit (instead of -t) |
||
114 | .TP |
||
115 | .BR -r ", " --tradeoff " " |
||
116 | Do a bidirectional test individually |
||
117 | .TP |
||
118 | .BR -t ", " --time " \fIn\fR" |
||
119 | time in seconds to transmit for (default 10 secs) |
||
120 | .TP |
||
121 | .BR -B ", " --bind " \fIip\fR | \fIip\fR:\fIport\fR" |
||
122 | bind src addr(s) from which to originate traffic |
||
123 | .TP |
||
124 | .BR -F ", " --fileinput " \fIname\fR" |
||
125 | input the data to be transmitted from a file |
||
126 | .TP |
||
127 | .BR -I ", " --stdin " " |
||
128 | input the data to be transmitted from stdin |
||
129 | .TP |
||
130 | .BR -L ", " --listenport " \fIn\fR" |
||
131 | port to recieve bidirectional tests back on |
||
132 | .TP |
||
133 | .BR -P ", " --parallel " \fIn\fR" |
||
134 | number of parallel client threads to run |
||
135 | .TP |
||
136 | .BR -T ", " --ttl " \fIn\fR" |
||
137 | time-to-live, for multicast (default 1) |
||
138 | .TP |
||
139 | .BR -Z ", " --linux-congestion " \fIalgo\fR" |
||
140 | set TCP congestion control algorithm (Linux only) |
||
141 | .SH ENVIRONMENT |
||
142 | .TP |
||
143 | .BR TCP_WINDOW_SIZE |
||
144 | Controls the size of TCP buffers. |
||
145 | .SH DIAGNOSTICS |
||
146 | This section needs to be filled in. |
||
147 | .SH BUGS |
||
148 | Exit statuses are inconsistent. |
||
149 | The threading implementation is rather heinous. |
||
150 | .SH AUTHORS |
||
151 | Iperf was originally written by Mark Gates and Alex Warshavsky. |
||
152 | Man page and maintence by Jon Dugan <jdugan at x1024 dot net>. |
||
153 | Other contributions from Ajay Tirumala, Jim Ferguson, |
||
154 | Feng Qin, |
||
155 | Kevin Gibbs, |
||
156 | John Estabrook <jestabro at ncsa.uiuc.edu>, |
||
157 | Andrew Gallatin <gallatin at gmail.com>, |
||
158 | Stephen Hemminger <shemminger at linux-foundation.org> |
||
159 | .SH "SEE ALSO" |
||
160 | http://iperf.sourceforge.net/ |