NAT preformance and table processing

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi,

I wrote some performance tests of NAT table. The main idea is, that I add
10000 random+senseless rules to the NAT table (snat, postrouting) and then
I add some rule to specific position which will stop traversing of NAT
table. I use UDP packets. 

When I insert my reasonable rule to position 2000 and  run my test, it shows
delay of packets cca 300ms. But when I run it more times, this delay is 2ms.
I don't understand why, because I use UDP(connectionless) - so I think, that
netfilter must process each packet and find appropriate rule. Is this true?
Or does netfilter do some optimalization? Because this behavior is expected
in TCP, but not UDP.

Thanks for replies





[Index of Archives]     [Linux Netfilter Development]     [Linux Kernel Networking Development]     [Netem]     [Berkeley Packet Filter]     [Linux Kernel Development]     [Advanced Routing & Traffice Control]     [Bugtraq]

  Powered by Linux