[c-nsp] Are Nexus and per-interface or FEX MTU settings possible?

[Conkel, Joshua]

We just bought a bundle of 2x 5548Ps and 20x 2248s in order to converge our data and storage networks in our new datacenter. After carefully reading the configuration limitations document and designing around the limitations for our migration, we pulled the trigger and bought the material. The document that I used as prep work for the actual deployment was Data Center Access Design with Cisco Nexus 5000 Series Switches and 2000 Series Fabric Extenders and Virtual PortChannels. I planned on being able to hook the Nexus up to our distribution switches and standalone iSCSI network for the migration process and to provide L3 services (because of the limitations with using the L3 routing modules)
 
Now on to our issue:
The document states that you can configure per-interface MTU size. Our data network distribution switches are 3560s and run the standard MTU size of 1500. Our iSCSI network, on the other hand, use jumbo frames with a MTU of 9000. After trying the steps outlined in the document, I have only been able to set the MTU globally on the Nexus to jumbo or non-jumbo. After contacting TAC, they have initially confirmed that the MTU qos policy can only be applied at the system level, not per interface.
 
So, any ideas other than not converging our networks and buying a standalone 4900 or 3750x series pair for our iSCSI network? Sorry if it's wordy, but this is the content I gave to TAC as well.