Title :
Multi-Site Retrieval of Declustered Data
Author :
Tosun, Ali Saman
Author_Institution :
Dept. of Comput. Sci., Univ. of Texas at San Antonio, San Antonio, TX
Abstract :
Declustering techniques reduce query response times through parallel I/O by distributing data among multiple devices. Recently, replication based approaches were proposed to further reduce the response time. All of the replication based schemes assume that replication is done at a single site. In this paper, we consider replicated data stored at multiple sites. We formulate multi-site retrieval problem as a maximum flow problem and solve it using maximum flow techniques. We propose a low complexity online algorithm for the problem. We investigate the proposed scheme using various replication schemes, query types and query loads. Proposed scheme can easily be extended to nonuniform data and to any number of sites. Experimental results show that replication using orthogonal allocation performs the best under various settings.
Keywords :
computational complexity; query processing; replicated databases; computational complexity; declustering technique; maximum flow problem; multisite retrieval problem; query processing; replicated data; Computer science; Data visualization; Delay; Distributed computing; Geographic Information Systems; Information retrieval; Multidimensional systems; Scalability; Spatial databases; Visual databases; declustering; parallel I/O; retrieval;
Conference_Titel :
Distributed Computing Systems, 2008. ICDCS '08. The 28th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-0-7695-3172-4
Electronic_ISBN :
1063-6927
DOI :
10.1109/ICDCS.2008.72