*>>> LVS UDP has problems (see the HOWTO). AFAIK there isn't a
>test for high throughput single port UDP that we can use to
>check that UDP load balancing is working. ntp was used as a
>test in the early days, but the packet throughput is
>designed to be low. I don't know if your UDP test qualifies
>(it might, but you don't say so). Is your UDP test a single
>port send-reply system? If not should be easy enough to
>write a pair of programs in perl that are a udp ping-echo
>pair.*
My UDP test is a single port send-reply system. I'm using, like I say before
SIPp (http://sipp.sourceforge.net/), which goal is to generate a lot of SIP
calls. But, in my case, it's not very different than your udp ping-echo (2
packets, send and reply ).
I think this test can qualify for a high throughput test (I have only one
network card, and I generate something like 14-15 MB of traffic on my
network, with 3 old computers.).
If your are interested by this kind of test, I can send you the program.
>>>When there are problems with UDP, won't there be a whole lot
>of ports tied up on the UDP server with packets that haven't
>found anywhere to go?
I not very easy with UDP. I know it's not reliable, but I don't know what
kind of action a standard ethernet card or my switch take. But I have just
realized a direct test between my client and my server, and I just have 50%
of network utilization without problem.
--
Grasland Pierrick
ENSSAT - LSI 3
|