Distributed fabric protocol (DFP) switching network architecture

1. A program product, comprising:

a machine-readable storage device; and

program code stored within the machine-readable storage device, wherein the program code, when processed by a machine, causes the machine to perform:

at a master switch of a switching network including an upper tier and a lower tier including a plurality of lower tier entities, the master switch having a plurality of ports each coupled to a respective one of the plurality of lower tier entities, implementing on each of the plurality of ports a plurality of virtual ports each corresponding to a respective one of a plurality of remote physical interfaces (RPIs) at the lower tier entity coupled to that port;

in response to receipt of data traffic from a particular lower tier entity among the plurality of lower tier entities at an ingress port among the plurality of ports of the master switch, queuing the data traffic to the virtual port of the ingress port that corresponds to the RPI on the particular lower tier entity that was the source of the data traffic;

switching the data traffic from the virtual port of the particular port to an egress port among the plurality of ports of the master switch and forwarding the data traffic from the egress port; and

presenting a management interface through which RPIs on the plurality of lower tier entities and the plurality of virtual ports are managed as a unified virtual switch.

2. The program product of claim 1 , wherein:

each of the pluralities of virtual ports comprises a plurality of ingress virtual ports;

the virtual port of the particular port comprises an ingress virtual port;

each of the plurality of ports of the master switch further includes a plurality of egress virtual ports; and

the switching includes switching the data traffic from the ingress virtual port to an egress virtual port among the plurality of egress virtual ports on the particular data port.

3. The program product of claim 1 , wherein:

the data traffic includes an RPI identifier identifying the RPI on the particular lower tier entity;

the queuing includes queuing the data traffic based on the RPI identifier; and

the program code further causes the master switch to update the RPI identifier prior to forwarding the data traffic from the egress port.

4. The program product of claim 1 , wherein:

the switching network includes multiple master switches each connected to each of the plurality of lower tier entities; and

the implementing includes implementing the plurality of virtual ports at each of the multiple master switches.

5. The program product of claim 1 , wherein:

the plurality of lower tier entities includes a follower switch configured in flow through mode; and

the plurality of RPIs comprises data ports.

6. The program product of claim 1 , wherein:

the plurality of lower tier entities includes a host platform; and

the plurality of RPIs on the host platform includes a virtual machine.

7. A master switch of a switching network including an upper tier including the master switch and a lower tier including a plurality of lower tier entities, the master switch comprising:

a plurality of ports each coupled to a respective one of the plurality of lower tier entities, each of the plurality of ports including:

a plurality of virtual ports each corresponding to a respective one of a plurality of remote physical interfaces (RPIs) at the lower tier entity coupled to that port;

a receive interface that, responsive to receipt of data traffic from a particular lower tier entity among the plurality of lower tier entities, queues the data traffic to the virtual port among the plurality of virtual ports that corresponds to the RPI on the particular lower tier entity that was the source of the data traffic;

a switch controller that switches data traffic from the virtual port to an egress port among the plurality of ports from which the data traffic is forwarded; and

a management module that presents a management interface through which RPIs on the plurality of lower tier entities and the plurality of virtual ports are managed as a unified virtual switch.

8. The master switch of claim 7 , wherein:

each of the pluralities of virtual ports comprises a plurality of ingress virtual ports;

the virtual port comprises an ingress virtual port;

each of the plurality of ports further includes a plurality of egress virtual ports; and

the switch controller switches the data traffic from the ingress virtual port to an egress virtual port among the plurality of egress virtual ports on the egress port.

9. The master switch of claim 7 , wherein:

the data traffic includes an RPI identifier identifying the RPI on the particular lower tier entity;

the receive interface queues the data traffic based on the RPI identifier; and

the master switch updates the RPI identifier prior to forwarding the data traffic from the egress port.

10. A switching network including

the master switch of claim 7 ; and

the plurality of lower tier entities.

11. The switching network of claim 10 , wherein:

the switching network includes multiple master switches each connected to each of the plurality of lower tier entities; and

each of the multiple master switches implements the plurality of virtual ports on each of the plurality of ports.

12. The switching network of claim 10 , wherein:

the plurality of lower tier entities includes a follower switch configured in flow through mode; and

the plurality of RPIs comprises data ports.

13. The switching network of claim 12 , wherein:

the master switch implements control for the RPIs at the corresponding virtual ports of the master switch.

14. The switching network of claim 10 , wherein:

the plurality of lower tier entities includes a host platform; and

the plurality of RPIs on the host platform includes a virtual machine.

15. The switching network of claim 10 , wherein the master switch and plurality of lower tier entities share a single data plane and single control plane.

16. The switching network of claim 10 , wherein the plurality of lower tier entities comprises a plurality of follower switches operating in a pass-through mode, such that the plurality of master switch serves as a virtual chassis and the follower switches serve as virtual line cards of the virtual chassis.

17. The switching network of claim 10 , wherein the master switch serves as a virtual switch fabric for the switching network.

18. The switching network of claim 10 , wherein:

the switching network includes multiple master switches including the master switch;

each of the plurality of lower tier entities has a number of port groups corresponding to a number of the multiple master switches;

each of the plurality of lower tier entities forwards data traffic received in each port group to a corresponding one of the multiple master switches.

19. A method of switching in a switching network including an upper tier and a lower tier including a plurality of lower tier entities, the method comprising:

at a master switch in the upper tier having a plurality of ports each coupled to a respective one of the plurality of lower tier entities, implementing on each of the plurality of ports a plurality of virtual ports each corresponding to a respective one of a plurality of remote physical interfaces (RPIs) at the lower tier entity coupled to that port;

in response to receipt of data traffic from a particular lower tier entity among the plurality of lower tier entities at an ingress port among the plurality of ports of the master switch, queuing the data traffic to the virtual port of the ingress port that corresponds to the RPI on the particular lower tier entity that was the source of the data traffic;

switching the data traffic from the virtual port of the particular port to an egress port among the plurality of ports of the master switch and forwarding the data traffic from the egress port; and

the master switch presenting a management interface through which RPIs on the plurality of lower tier entities and the plurality of virtual ports are managed as a unified virtual switch.

20. The method of claim 19 , wherein:

each of the pluralities of virtual ports comprises a plurality of ingress virtual ports;

the virtual port of the particular port comprises an ingress virtual port;

each of the plurality of ports of the master switch further includes a plurality of egress virtual ports; and

the switching includes switching the data traffic from the ingress virtual port to an egress virtual port among the plurality of egress virtual ports on the egress port.

21. The method of claim 19 , wherein:

the data traffic includes an RPI identifier identifying the RPI on the particular lower tier entity;

the queuing includes queuing the data traffic based on the RPI identifier; and

the method further includes the master switch updating the RPI identifier prior to forwarding the data traffic from the egress port.

22. The method of claim 19 , wherein:

the switching network includes multiple master switches each connected to each of the plurality of lower tier entities; and

the implementing includes implementing the plurality of virtual ports at each of the multiple master switches.

23. The method of claim 19 , wherein:

the plurality of lower tier entities includes a follower switch configured in flow through mode; and

the plurality of RPIs comprises data ports.

24. The method of claim 19 , wherein:

the switching network includes multiple master switches each connected to each of the plurality of lower tier entities;

the method further comprises:

implementing multiple RPI groups on each lower tier entity equal in number to a number of the multiple master switches; and

each of the multiple RPI groups transmitting data traffic to one of the multiple master switches.

25. The method of claim 19 , and further comprising dynamically creating at least one virtual port on one of the plurality of ports.

26. The method of claim 19 , and further comprising dynamically migrating at least one virtual port between different ones of the plurality of ports.

27. The method of claim 26 , wherein:

the at least one virtual port is associated with a migrating virtual machine;

the method further comprises buffering data traffic for the virtual machine at ingress until earliest of completion of the migration of the virtual machine and expiration of a predefined flush time.

28. The method of claim 19 , and further comprising:

temporarily disabling at least one virtual port on one of the plurality of ports in response to an interruption of communication with a corresponding lower tier entity; and

enabling the at least one virtual port when communication with the corresponding lower tier entity is restored.

29. The method of claim 28 , and further comprising buffering data traffic for the lower tier entity at ingress until earliest of enabling of the at least one virtual port and expiration of a predefined flush time.