A modularized routing system includes a control element and forwarding elements, all of which are connected via a private network, for example, an Ethernet. The control element computes a routing table for each of the forwarding elements. Based on information in the routing table, a forwarding element decrements a time-to-live counter in the packet header only if the forwarding element is the first one in the routing system encountered by the packet. Accordingly, the forwarding elements preserve the behavior of a single router while using substantially the same routing protocols as the single router.

Routing packets across multiple forwarding elements

A router comprises a route resolution module to maintain routing information in accordance with a topology of a network, and an indirect next hop manager to maintain indirect next hop data that associates protocol next hops with forwarding next hops. The route resolution module invokes an application programming interface (API) of the indirect next hop manager for associating and disassociating protocol next hops and forwarding next hops. In response to a network event, the route resolution module can modify the indirect next hop data to reduce the time and resources necessary to perform route resolution.

Scalable route resolution

A method and apparatus to search for routing information is described. According to an embodiment, a technique is described to search for routing information that uses a first technique on at least a portion of a first section of an address and a second technique on at least a portion of a second section of an address. In one embodiment, a best-match technique, such as a Longest Prefix Match technique, is used on at least a portion of a topology section of an address, and an exact-match technique is used on a portion of an interface ID of the address.

Technique to improve network routing using best-match and exact-match techniques

Methods and apparatus are disclosed herein for classifying packets using ternary and binary content-addressable memory stages to classify packets. One such system uses a stage of one or more TCAMS followed by a second stage one or more CAMS (or alternatively some other binary associative memories such as hash tables or TRIEs) to classify a packet. One exemplary system includes TCAMs for handling input and output classification and a forwarding CAM to classify packets for Internet Protocol (IP) forwarding decisions on a flow label. This input and output classification may include, but is not limited to routing, access control lists (ACLs), quality of service (QoS), network address translation (NAT), encryption, etc. These IP forwarding decisions may include, but are not limited to IP source and destination addresses, protocol type, flags and layer 4 source and destination ports, a virtual local area network (VLAN) id and/or other fields.

Using ternary and binary content addressable memory stages to classify information such as packets

A content matching engine (CME) uses a content addressable memory (CAM) array that stores a plurality of strings in separate entries. The strings define one or more rules to be matched. The strings of each rule are linked, thereby providing a required order. The strings of each rule can be linked by per-entry counters associated with each string, or by a state machine. The strings in the CAM array are compared with a packet, which is shifted one symbol at a time (because the strings can start on any boundary). When the CAM detects a match, the CAM skips over the string that resulted in the match, thereby preventing erroneous matches. The CAM allows parallel matching to be performed for multiple rules. If the contents of a packet match all of the strings of a rule, in order, then the CME asserts a match/index signal that identifies the matched rule.

Switching circuit implementing variable string matching

A deterministic routing table includes a set of hash circuits and a CAM. The routing table searches for the longest matching destination address stored in any of the hash circuits and the CAM, if any, and outputs an output pointer associated with that destination address within a fixed predetermined time.

Yoichi Hariguchi

Papers

Network routing table