EXTENDED LINK AGGREGATION (LAG) FOR USE IN MULTIPLE SWITCHES

摘要

In one embodiment, a method for providing link aggregation (LAG) to heterogeneous switches includes receiving, at a switch controller, LAG requests forwarded by switches and determining that multiple LAG requests corresponding to a server have been received, grouping the multiple LAG requests into LAG groups according to a switch from which they were received and correlating all the LAG groups with the server, instructing each of the switches to setup a LAG group with the server according to the LAG groups determined by the switch controller, and creating alternate flows that correspond to flows through each of the switches to the server through direction from the switch controller. The switches may rely upon OpenFlow to communicate with the switch controller, in some approaches. In addition, other methods for providing LAG to heterogeneous switches are also described, along with systems and computer program products which provide LAG to heterogeneous switches.

主权项

1. A system for providing link aggregation (LAG) to heterogeneous switches, the system comprising:
at least two switches connected to a server, each switch being connected via a plurality of connections, wherein the at least two switches are connected to one another via inter-switch links (ISLs), and wherein the server comprises:
logic adapted for sending a LAG request on each connection to each of the at least two switches in order to create a plurality of LAG groups, one LAG group for each of the at least two switches including all connections therebetween; wherein each of the at least two switches comprises:
logic adapted for receiving the LAG request from the server; andlogic adapted for forwarding the LAG request to a switch controller in electrical communication with the at least two switches, wherein the switch controller comprises:
logic adapted for receiving the forwarded LAG requests from the at least two switches;logic adapted for determining that multiple LAG requests have been received corresponding to the server;logic adapted for grouping the multiple LAG requests into LAG groups according to a switch from which they were received;logic adapted for correlating all the LAG groups with the server;logic adapted for instructing each of the at least two switches to setup a LAG group with the server according to the LAG groups determined by the switch controller; andlogic adapted for creating alternate flows that correspond to flows through each of the at least two switches to the server through direction from the switch controller.