Design theoretic approach to replicated declustering

  • Ali Saman Tosun
  • Published 2005 in
    International Conference on Information…

Abstract

Declustering techniques reduce query response times through parallel I/O by distributing data among multiple devices. Most of the research on declustering is targeted at spatial range queries and investigates schemes with low additive error. Recently, declustering using replication is proposed to reduce the additive overhead. Replication significantly reduces retrieval cost of arbitrary queries. In this paper, we propose a disk allocation and retrieval mechanism for arbitrary queries based on design theory. Using proposed c-copy replicated declustering scheme, (c - 1)k/sup 2/ + ck buckets can be retrieved using at most k disk accesses. Retrieval algorithm is very efficient and is asymptotically optimal with /spl Theta/(|Q|) complexity for a query Q. In addition to the deterministic worst-case bound and efficient retrieval, proposed algorithm handles nonuniform data, high dimensions, supports incremental declustering and has good fault-tolerance property.

DOI: 10.1109/ITCC.2005.124

Extracted Key Phrases

6 Figures and Tables

Cite this paper

@article{Tosun2005DesignTA, title={Design theoretic approach to replicated declustering}, author={Ali Saman Tosun}, journal={International Conference on Information Technology: Coding and Computing (ITCC'05) - Volume II}, year={2005}, volume={1}, pages={226-231 Vol. 1} }