Low latency shared data path allocation

Abstract

A fast shared path allocation technique is disclosed. Network nodes are pre-configured such that data from multiple data sources or multiple primary data paths may be sent via a shared secondary data path. Merge nodes merge input from a plurality of input ports onto an output port. The merge nodes implement a blocking function such that upon receipt of a signal from one of the input ports, the signals from the other input ports are blocked from reaching the output port. Upon a triggering event indicating a need to allocate the shared path, the data is first sent to the merge node where it is appropriately merged onto the output link and transmitted towards its destination. Only after the data has been sent does the merge node block the remaining input ports from reaching the output port. This blocking may be performed automatically by the merge node or by conventional network signaling.