Declustering Large Multidimensional Data Sets for Range Queries over Heterogeneous Disks

Declustering is a technique to distribute data sets over multiple disks so that future retrievals can be well balanced over the disks and be performed in parallel. Although disk heterogeneity often exists in systems like clusters, most work on declustering has focused only on homogeneous environments. In this work, we investigate the declustering problem for a heterogeneous disk environment using virtual servers, and propose novel approaches for deciding the number of virtual servers and the mapping between virtual servers and physical disks. Our experimental results show that by combining our algorithm for choosing the number of virtual servers with a greedy algorithm for mapping virtual servers to disks, users can expect range query retrieval performance within 4% of the optimum achievable in practice on average, in all configurations studied. Compared to the intuitively natural approach to the problem based on randomly assigning virtual servers to physical disks, this represents an improvement of 8–31% in average fetch ratio, as well as a 21–42% reduction in the standard deviation of retrieval performance for small queries.