A Network Aware Resource Discovery Service

Abstract

Internet in recent years has become a huge set of channels for content distribution highlighting limits and inefficiencies of the current protocol suite originally designed for host-to-host communication. In this paper we exploit recent advances in Information Centric Networks in the attempt to reshape the actual Internet infrastructure from a host-centric to a name-centric paradigm where the focus is on named data instead of machine name hosting those data. In particular, we propose a Content Name System Service that provides a new network aware Content Discovery Service. The CNS behavior and architecture uses the BGP inter-domain routing information. In particular, the service registers and discovers resource names in each Autonomous System: contents are discovered by searching through the augmented AS graph representation classifying ASes into customer, provider, and peering, as the BGP protocol does. Performance of CNS can be characterized by the fraction of Autonomous Systems that successfully locate a requested content and by the average number of CNS Servers explored during the search phase. A C-based simulator of CNS is developed and is run over real ASes topologies provided by the Center for Applied Internet Data Analysis to provide estimates of both performance indexes. Preliminary performance and sensitivity results show the CNS approach is promising and can be efficiently implemented by incrementally deploying CNS Servers.