I’m not the only person pointing out the software routers are reaching unprecedented performance levels. Manav Bhatia starts out with
When i started looking at NFV, i always imagined it being relegated to places in the network that would receive only teeny weeny amount of data traffic since the commodity hardware and software could only handle so much of traffic. I also naively believed that it would be deployed in networks where customers were not uber-sensitive to latency and delay (broadband customers, etc). So if somebody really wanted a loud bang for their buck they had to use specialized hardware to support the network function. You couldnt really use Intel x86-based servers running SW serving customers for whom QoS and QoE were critical and vital.
This opinion is quite common among network engineers but is completely wrong. If you had time to understand what Intel is doing to their processors to be networking friendly you will come to the same conclusion as Manav:
What this shows is that its patently possible for virtual routers to run at speeds comparable to regular hardware based routers and can replace them. This augurs well for NFV since it means that it can be deployed in a lot many places in the carrier network than what most skeptics believed till some time back.
There are many caveats on software based routers. Now that straight line performance has been addressed and acceptably proven at greater than 10gbps, it’s time to consider other functions that might impact performance like Hierarchical QoS or VXLAN/GRE tunneling.
But hey, not many routers actually implement those features in the bigger scheme of things.