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