A Tabu Based Cache to Improve Latency and Load Balancing on Prefix Trees

Nicolas Hidalgo (1) , Luciana Arantes (1) , Pierre Sens (1) , Xavier Bonnaire (2)

1 Regal - Large-Scale Distributed Systems and Applications
2 Departamento de Informatica [Valparaíso, Chile]

Distributed Hash Tables (DHTs) provide the substrate to build large scale distributed applications over Peer-to-Peer networks. A major limitation of DHTs is that they only support exact-match queries. In order to offer range queries over a DHT it is necessary to build additional indexing structures. Prefix-based indexes, such as Prefix Hash Tree (PHT), are interesting approaches for building distributed indexes on top of DHTs. Nevertheless, the lookup operation of these indexes usually generates a high amount of unnecessary traffic overhead which degrades system performance by increasing response time. In this paper, we propose a novel distributed cache system called Tabu Prefix Table Cache (TPT-C), aiming at improving the performance of the Prefix-trees. We have implemented our solution over PHT, and the results confirm that our searching approach reduces up to a 70% the search latency and traffic overhead.

Domaines: Réseaux et télécommunications [cs.NI]

Nicolas Hidalgo, Luciana Arantes, Pierre Sens, Xavier Bonnaire. A Tabu Based Cache to Improve Latency and Load Balancing on Prefix Trees. ICPADS 2011 - IEEE International Conference on Parallel and Distributed Systems, Dec 2011, Tainan, Taiwan. pp.557-564, ⟨10.1109/ICPADS.2011.18⟩. ⟨inria-00627479⟩