SET vs NIC Teaming for Hyper-V Switch

I have built 3 clusters using 3 Dell R805's and a Dell MD3000i SAN connected to one switch and had similar issues to what people are saying here. The fix was to disable "IPv4 Large Send Offload". Since doing this all clusters and 40 VM's have not missed a beat. (4 months now).

"Large Send Offload (LSO) is a feature provided by Broadcom network adapters that prevents an upper level protocol such as TCP from breaking a large data packet into a series of smaller packets with headers appended to them. The protocol stack need only generate a single header for a data packet as large as 64 KB, and the adapter hardware breaks the data buffer into appropriately-sized Ethernet frames with the correctly sequenced header (based on the single header originally provided)."

Below is a link to the full article. http://www.sadikhov.com/forum/index.php?showtopic=132434

Usually on a Hyper-V server extra NICs are used for:

• Live migration (often gets its own LAN, since it will have extremely heavy traffic when migrating)
• Cluster communications (again, own LAN so nothing else interferres or causes high latency)
• Storage network, if using iSCSI
• Management network, if you have a seperate management network
• The host system
• Dedicated to specific VMs

Since you don't intend to run a cluster, I would setup

• One port dedicated to the host OS, so anything that breaks in the VMs shouldn't interfere with you accessing the host
• Two ports in a team for the VMs, either load balancing or active/standby, depending on card and switch support. Active/standby doesn't help increase capacity, but saves you if a port on the NIC or switch dies, or a cable breaks. It may also let you have redundant switches
• One port left unused. If one of your VMs turns out to need more network performance, you have the option of dedicating this port to that VM later on.