ONE: A Predictable and Scalable DW Model

Authors

Abstract

The star schema model has been widely used as the facto DW storage organization on relational database management systems (RDBMS). The physical division in normalized fact tables (with metrics) and denormalized dimension tables allows a trade-off between performance and storage space while, at the same time offering a simple business understanding of the overall model as a set of metrics (facts) and attributes for business analysis (dimensions). However, the underlying premises of such trade-off between performance and storage have changed. Nowadays, storage capacity increased significantly at affordable prices (below 50$/terabyte) with improved transfer rates, and faster random access times particularly with modern SSD disks. In this paper we evaluate if the underlying premises of the star schema model storage organization still upholds. We propose an alternative storage organization (called ONE) that physically stores the whole star schema into a single relation, providing a predictable and scalable alternative to the star schema model. We use the TPC-H benchmark to evaluate ONE and the star schema model, assessing both the required storage size and query execution time.

Keywords

dw

Subject

DW

Conference

DaWaK, August 2011