Latency factor in worldwide IP routed networks

Current Border Gateway Protocol (BGP) serves for worldwide internet backbone connections between different Autonomous Systems (AS) on the routing level. Continuously in real-time changing environment core routers calculate routing decisions based on path-vector database entries. AS path-vector database may contain multiple paths for various Internet Protocol (IP) prefix destinations where smallest entity in the path-vector is AS. In real world AS can be internet service operator, university or any other organization willing to participate in internet network via multi-homed uplinks. Unfortunately, internal part of AS is hidden in path-vector database thus excluding factors like latency, packet loss or throughput from influencing routing decisions. With easier virtual presence possibilities leading European internet operators has direct BGP connections called peering with mostly every other largest operators thus narrowing routing decision objectivity because mostly routing decisions are taken based on AS path length which tends to one. In this paper, a method of measuring latency is proposed and analyzed through lab measurements. The results of this study permit to discuss about requirements and possibilities to extrapolate this technique from small testbed to worldwide routed networks.