Efficient Range Query Processing in Peer-to-Peer Systems

With the increasing popularity of the peer-to-peer (P2P) computing paradigm, many general range query schemes for distributed hash table (DHT)-based P2P systems have been proposed in recent years. Although those schemes can support range query without modifying the underlying DHTs, they cannot guarantee to return the query results with bounded delay. The query delay in these schemes depends on both the scale of the system and the size of the query space or the specific query. In this paper, we propose Armada, an efficient range query processing scheme to support delay-bounded single-attribute and multiple-attribute range queries. We first describe the order-preserving naming algorithms for assigning adjoining ObjectIDs to objects with close attribute values. Then, we present the design of the forwarding tree to efficiently match the search paths of range queries to the underlying DHT topology. Based on the tree, two query processing algorithms are proposed to, respectively, process single-attribute and multiple-attribute range queries within a bounded delay. Analytical and simulation results show that Armada is an effective general range query scheme on constant-degree DHTs, and can return the query results within 2logN hops in a P2P system with N peers, regardless of the queried range or the size of query space.