Optimized Range Queries for Large Scale Networks

Abstract

[EN] Distributed Hash Tables (DHTs) provide the substrate to build scalable and efficient Peer-to-Peer (P2P) networks: distributed systems with the potential to handle massive amounts of data on a very large scale. However, traditional DHTs provide very poor support for range queries. In this article we present a search mechanism that efficiently supports range queries over a ring-like DHT structure using a prefix tree index. Load balancing is improved by delegating the routing of queries to the nodes that store data, and by updating neighbor information through an optimistic approach. Our solution reduces latency and message traffic in environments where queries are more frequent than data insertion operations. We evaluate the performance of the system through simulations and show that our solution in not affected by data skewness.