It’s a constant and oft-repeated fallacy that routing software on x86 servers will never forward packets at speed. Here is Vyatta explaining why their software will be able to go past 100 Million Packets Per Second this year on standard COTS hardware.
At Network Field Day 7, we saw a presentation from Brocade on their Vyatta software code and the recent advances in software architecture that can linearly scale the forwarding performance of x86 architectures according to the number of CPUs. The following slide shows that the limitations previously flatlined due to cache misses.
In the Youtube video, Kelly Herrell briefly introduces the performance data and then hands over to the technology guy who explains in quite some details how Vyatta is exploiting the full potential of the Intel architecture.
Click here to Youtube and the video will start directly at the 19:09 mark where the real kicker comes in .