You could even go beyond sFlow and have ClearFLOW (http://www.extremenetworks.com//libraries/whitepapers/WPCLEAR-Flow_1083.pdf)

Motherboards don’t need to be more complex it could just be another PCIe card, or it could be integrated into the 10GbE chip itself. From talking with a friend at Broadcom their current 10GbE chip used by OEMs is already very sophisticated. The offloading should be transparent.

The way the industry is (trying) to move though it appears is that there will be no local switching anymore period in the hypervisor, if VM #1 wants to talk to VM #2 on the same hypervisor that traffic will go out the network adapter to a switch, the switch then sends the traffic right back. I forget the standard off hand but they are working on it. The issue now is that networking standards prevent a switch from sending traffic in this manor today, otherwise they’d be doing this now.

Not sure that incorporating a switch into the server is the answer. Other than the physical distance, an in-server switch is going to look just like an in-chassis switch. And that shorter distance isn’t really going to buy us anything, not in a properly built enterprise class blade chassis where the backplane is completely passive with only traces on the board connecting the “back” of the servers to the switching fabric I/O.

I’d prefer to keep the switching for VM’s on the same host within the hypervisor itself. This keeps my switching in software, distance is not an issue, and the hop is truly a virtual hop.

Plus, I’m all for making my server motherboards less complex, not more complex. Many companies are taking this approach in MB design, truly trying to minimize the number of on-board components to reduce potential component failures.