Hierarchical Peer-to-Peer Systems

Abstract

Structured peer-to-peer (P2P) lookup services organize peers into a flat overlay network and offer distributed hash table (DHT) functionality. Data is associated with keys and each peer is responsible for a subset of the keys. In hierarchical DHTs, peers are organized into groups, and each group has its autonomous intra-group overlay network and lookup service. Groups are organized in a top-level overlay network. To find a peer that is responsible for a key, the top-level overlay first determines the group responsible for the key; the responsible group then uses its intra-group overlay to determine the specific peer that is responsible for the key. We provide a general framework for hierarchical DHTs with scalable overlay management. We specifically study a two-tier hierarchy that uses Chord for the top level. Our analysis shows that by using the most reliable peers in the top level, the hierarchical design significantly reduces the expected number of hops. We also present a method to construct hierarchical DHTs that map well to the Internet topology and achieve short intra-group communication delay. The results demonstrate the feasibility of locality-based peer groups, which allow P2P systems to take full advantage of the hierarchical design.

Mastering selfishness and heterogeneity in mobile P2P content distribution networks with multiple source download in cellular networks

“…The idea of selecting proper peers in order to increase the efficiency was also discussed in [13]. This contribution proposes to build hierarchical structures in order to cope with problems locally and not to affect the whole network.…”

Hash-based proximity clustering for efficient load balancing in heterogeneous DHT networks

“…Each supernode operates as a server to its associated regular nodes. The supernode networks proposed in [13,34] take proximity into account by clustering physically close nodes into one group. They take static gateways (or routers) as supernodes.…”

“…The novelty of the approach lies in the construction of the auxiliary network. Existing proximity clustering approaches often designate static gateways or routers of regular nodes as their supernodes [13,34]. In contrast, we cluster the nodes and associate them to supernodes by consistent hashing of their physical proximity information.…”

Enhancing Computational Grids with Peer-to-Peer Technology for Large Scale Service Discovery

“…Within this field, it seems relevant to distinguish two approaches. First, in the supernodes approach [12,31,34], each local domain manages its own DHT and elects supernodes among local nodes considering their bandwidth, proximity with a backbone, or any characteristic allowing to evaluate the performance of a node. to build a top-level DHT.…”