Hello,
I tried to use iperf in order to get some sort of statistics for a udp stream.
[EMAIL PROTECTED]:/# iperf -s -u -B 239.15.101.10 -i 1 -T 32 -l 60k -p 49410
------------------------------------------------------------
Server listening on UDP port 49410
Binding to local address 239.15.101.10
Joining multicast group 239.15.101.10
Receiving 61440 byte datagrams
UDP buffer size: 107 KByte (default)
------------------------------------------------------------
[ 3] local 239.15.101.10 port 49410 connected with 10.11.99.160 port 1481
[ ID] Interval Transfer Bandwidth Jitter Lost/Total Datagrams
[ 3] 0.0- 1.0 sec 29.6 KBytes 242 Kbits/sec 998109480388.430 ms
1195394312/1195394335 (1e+02%)
[ 3] 0.0- 1.0 sec 19 datagrams received out-of-order
[ 3] 1.0- 2.0 sec 185 KBytes 1.52 Mbits/sec 1326472440288.818 ms 0/
0 (nan%)
[ 3] 1.0- 2.0 sec 144 datagrams received out-of-order
[ 3] 2.0- 3.0 sec 193 KBytes 1.58 Mbits/sec 1219396600280.480 ms 0/
0 (nan%)
[ 3] 2.0- 3.0 sec 150 datagrams received out-of-order
[ 3] 3.0- 4.0 sec 184 KBytes 1.51 Mbits/sec 1597225692679.626 ms 0/
0 (nan%)
[ 3] 3.0- 4.0 sec 143 datagrams received out-of-order
[ 3] 4.0- 5.0 sec 186 KBytes 1.53 Mbits/sec 1334942497621.720 ms 0/
0 (nan%)
[ 3] 4.0- 5.0 sec 145 datagrams received out-of-order
[ 3] 5.0- 6.0 sec 184 KBytes 1.51 Mbits/sec 1256119644323.133 ms 0/
0 (nan%)
[ 3] 5.0- 6.0 sec 143 datagrams received out-of-order
[ 3] 6.0- 7.0 sec 179 KBytes 1.46 Mbits/sec 1201240315355.291 ms 0/
0 (nan%)
[ 3] 6.0- 7.0 sec 139 datagrams received out-of-order
[ 3] 7.0- 8.0 sec 177 KBytes 1.45 Mbits/sec 1688932541123.746 ms 0/
0 (nan%)
[ 3] 7.0- 8.0 sec 138 datagrams received out-of-order
[ 3] 8.0- 9.0 sec 170 KBytes 1.39 Mbits/sec 1704649324905.287 ms 0/
0 (nan%)
[ 3] 8.0- 9.0 sec 132 datagrams received out-of-order
[ 3] 9.0-10.0 sec 200 KBytes 1.64 Mbits/sec 1772745478056.681 ms 0/
0 (nan%)
[ 3] 9.0-10.0 sec 156 datagrams received out-of-order
[ 3] 10.0-11.0 sec 173 KBytes 1.42 Mbits/sec 1531515308575.511 ms 0/
0 (nan%)
[ 3] 10.0-11.0 sec 135 datagrams received out-of-order
[ 3] 11.0-12.0 sec 172 KBytes 1.41 Mbits/sec 1265015314995.091 ms 0/
0 (nan%)
[ 3] 11.0-12.0 sec 134 datagrams received out-of-order
[ 3] 12.0-13.0 sec 172 KBytes 1.41 Mbits/sec 1835649298860.555 ms 0/
0 (nan%)
[ 3] 12.0-13.0 sec 134 datagrams received out-of-order
[ 3] 13.0-14.0 sec 167 KBytes 1.37 Mbits/sec 1401992039555.385 ms 0/
0 (nan%)
[ 3] 13.0-14.0 sec 130 datagrams received out-of-order
[ 3] 14.0-15.0 sec 168 KBytes 1.38 Mbits/sec 1275102950555.581 ms 0/
0 (nan%)
[ 3] 14.0-15.0 sec 131 datagrams received out-of-order
[ 3] 15.0-16.0 sec 167 KBytes 1.37 Mbits/sec 1687206638067.240 ms 0/
0 (nan%)
[ 3] 15.0-16.0 sec 130 datagrams received out-of-order
[ 3] 16.0-17.0 sec 162 KBytes 1.33 Mbits/sec 1521373244192.683 ms 0/
0 (nan%)
[ 3] 16.0-17.0 sec 126 datagrams received out-of-order
[ 3] 17.0-18.0 sec 154 KBytes 1.26 Mbits/sec 1447920255147.208 ms 0/
0 (nan%)
[ 3] 17.0-18.0 sec 120 datagrams received out-of-order
[ 3] 18.0-19.0 sec 176 KBytes 1.44 Mbits/sec 1252136486881.482 ms 0/
0 (nan%)
[ 3] 18.0-19.0 sec 137 datagrams received out-of-order
[ 3] 19.0-20.0 sec 157 KBytes 1.28 Mbits/sec 1755323381362.654 ms 0/
0 (nan%)
[ 3] 19.0-20.0 sec 122 datagrams received out-of-order
[ 3] 20.0-21.0 sec 157 KBytes 1.28 Mbits/sec 1463161910162.867 ms 0/
0 (nan%)
[ 3] 20.0-21.0 sec 122 datagrams received out-of-order
[ 3] 21.0-22.0 sec 173 KBytes 1.42 Mbits/sec 1304977333660.666 ms 0/
0 (nan%)
[ 3] 21.0-22.0 sec 135 datagrams received out-of-order
jitter = 1304977333660.666 ms * these are the results that don't
make sense to me
135 datagrams received out-of-order *
I tried this on 2 machines using the package provided by Debian (iperf version
2.0.4 (7 Apr 2008) pthreads), 2.0.4 compiled from source and 2.0.2 from source,
and also tried 2 different sources.
Can anyone tell me why the jitter is reported this way, and also why all the
datagrams are out of order. As I understand it, the clocks on the sender and
receiver don't have to br syncronized for jitter calculation. Is there another
way i can determine these values, or maybe a way check if the sender is the
problem.
-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/
_______________________________________________
Iperf-users mailing list
Iperf-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/iperf-users
