[netperf-talk] Confusing result of the throughput in wireless network with different UDP packet length.

[Peng Wang]

Hi!

I did a benchmark of throughput in wireless network with different UDP
packet size. The UDP packet size is from 2K bytes to 40k bytes. The MTU is
set to be 2348 bytes.

1)      test measures the throughput over the wireless channel while varying
the packet size from 2000 to 40000 bytes by 1000 byte intervals. In this
test, every test run consists of two steps:

1.       Send packets for 120s.

2.       Record the result and increase the packet size by 1000 bytes.  .

Each test run lasts for120 seconds. The test run begins at size 1000 bytes
and ends at size 40000 bytes. 39 test runs are conducted. If the size is
bigger than MTU, the packets will be fragmented.
The result figure is shown in attachment.

The benchmark platform I use contains two buffalo wireless g router. One
router is the sender, and one is the receiver. The operating system in them
is Linux with 2.4.7 version kernel.

The result of the benchmark confuses me. From the following figure we can
see that the throughput is highest when the UDP packet size is about 20k bytes
which is much bigger than the MTU. I guess it is because of the buffer in
the system, but I am not quite sure. Do you see it before? Could you explain
it?


regards,

Peng
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.netperf.org/pipermail/netperf-talk/attachments/20090220/a5ebe594/attachment-0001.htm 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: throughput with UDP packet size from 2k to 40k bytes.jpg
Type: image/jpeg
Size: 18963 bytes
Desc: not available
Url : http://www.netperf.org/pipermail/netperf-talk/attachments/20090220/a5ebe594/attachment-0001.jpg