Efficient Range and Join Query Processing in Massively Distributed Peer-to-Peer Networks

Abstract

Peer-to-peer (P2P) has become a modern distributed computing architecture that supports massively large-scale data management and query processing. Complex query operators such as range operator and join operator are needed by various distributed applications, including content distribution, locality-aware services, computing resource sharing, and many others.

This dissertation tackles a number of problems related to range and join query processing in P2P systems: fault-tolerant range query processing under structured P2P architecture, distributed range caching under unstructured P2P architecture, and integration of heterogeneous data under unstructured P2P architecture. To support fault-tolerant range query processing so as to provide strong performance guarantees in the presence of network churn, effective replication schemes are developed at either the overlay network level or the query processing level. To facilitate range query processing, a prefetch-based caching approach is proposed to eliminate the performance bottlenecks incurred by those data items that are not well cached in the network. Finally, a purely decentralized partition-based join query operator is devised to realize bandwidth-efficient join query processing under unstructured P2P architecture.

Theoretical analysis and experimental simulations demonstrate the effectiveness of the proposed approaches.