Router pooling in a network flowswitch

#The present invention relates to network systems and, more particularly, to router fault tolerance and host-to-router traffic load balancing.

#The growth of networking and the popularity of the Internet have created a need to improve the performance and reliability of network architectures. For example, FIG. 1 shows a block diagram of a local network 100 according to a conventional network architecture. Network 100 is connected to a network backbone 102 that connects several external networks. Backbone 102 may be, for example, the Internet or an Intranet. In this example, network 100 includes a router 104 connected to backbone 102 through a interface 105. Network 100 also includes a first server 106 connected to router 104 through a interface 107 and a second server 108 connected to router 104 through a interface 109. In this example, network 100 uses the TCP/IP communication protocols, which are well known in the art of networking.

#Clients connected to backbone 102 may send packets to a specific server in network 100 (e.g., server 106) through router 104. Conversely, server 106 may send packets to the client through router 104 and onto backbone 102. However, network 100 is not fault tolerant in that router 104 represents a possible single point failure for network 100. More specifically, when router 104 fails, servers 106 and 108 can no longer communicate with clients connected to backbone 102. In particular, servers are typically not configured to detect failure of "first hop" routers (i.e., the first router encountered by an outbound packet from a server). Thus, the servers will continue to send packets to the failed router, never knowing that the outbound packets do not leave network 100 (sometimes referred to as a "black hole" for outbound traffic).

#FIG. 1 is a block diagram of a conventional network architecture.

#FIG. 2 is a block diagram of a conventional network architecture using a shared media to provide router fault tolerance.

#FIG. 3 is a block diagram of a network with a switch circuit for providing router fault tolerance, in accordance with one embodiment of the present invention.

#FIG. 3 is a block diagram of a network 300 for providing router fault tolerance, in accordance with one embodiment of the present invention. Network 300 is similar in topography to network 200 (FIG. 2) except that network 300 includes a flowswitch 302 instead of shared media 204 (FIG. 2) of network 200.

#In particular, network 300 includes two routers 202 and 104 respectively connected to network backbone 102 through interfaces 203 and 105. Routers 202 and 104 are also connected to flowswitch 302 through interfaces 206 and 208, respectively. Routers 202 and 104 can be of any suitable type of router available from any vendor. In this embodiment, routers 202 and 104 are configured to support the TCP/IP communication protocol. Also, Routers 202 and 104 are configured in the manner standard for the particular router models to provide symmetrical network routing for all routes from the servers to clients (i.e., the routers both have all of the routes for all known clients). In this embodiment, this symmetry is implemented and maintained by providing a link between routers 202 and 104.

#Network 300 also includes two servers 106 and 108 respectively connected to flowswitch 302 through interfaces 210 and 302. In this embodiment, servers 106 and 108 are configured to have default routers (i.e., dynamic routing in the servers is disabled) in the standard manner for the particular server models. Similarly, the servers can be of any suitable type, vendor or model that supports TCP/IP and is interoperable with routers 202 and 104.