Processing top-k queries in distributed hash tables

  • Authors:
  • Reza Akbarinia;Esther Pacitti;Patrick Valduriez

  • Affiliations:
  • INRIA and LINA, University of Nantes, France and Shahid Bahonar University of Kerman, Iran;INRIA and LINA, University of Nantes, France;INRIA and LINA, University of Nantes, France

  • Venue:
  • Euro-Par'07 Proceedings of the 13th international Euro-Par conference on Parallel Processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Distributed Hash Tables (DHTs) provide a scalable solution for data sharing in large scale distributed systems, e.g. P2P systems. However, they only provide good support for exact-match queries, and it is hard to support complex queries such as top-k queries. In this paper, we propose a family of algorithms which deal with efficient processing of top-k queries in DHTs. We evaluated the performance of our solution through implementation over a 64-node cluster and simulation. Our performance evaluation shows very good performance, in terms of communication cost and response time.