Redundancy mechanization protocol for a massively parallel router

摘要

A parallel router comprising: 1) a plurality of routing nodes, each of the plurality of routing nodes capable of receiving message packets from and transmitting message packets to external devices, wherein the each of the plurality of routing nodes maintains a routing table suitable for routing message packets from transmitting ones of the plurality of routing nodes to receiving ones of the plurality of routing nodes; and 2) a switch fabric capable of transmitting the messages packets between the transmitting nodes and the receiving nodes, wherein a designated one of the plurality of routing nodes is operable to transmit to at least one non-designated one of the plurality of routing nodes a hello request message operable to cause the non-designated routing node to transmit back a hello acknowledgment message, wherein the designated routing node monitors a time duration between transmission of the hello request message and receipt of the hello acknowledgment message to determine if the non-designated routing node has failed.