Read-Optimized, Cache-Conscious, Page Layouts for Temporal Relational Data

International audienceThe efficient management of temporal data is crucial for many traditional and emerging database applications. A major performance bottleneck for database systems is the memory hierarchy. The performance of the memory hierarchy is directly related to how the content of disk pages maps to the L2 cache lines, i.e. to the organization of data within a page or the page layout. The prevalent page layout in database systems is the N-ary Storage Model (NSM). As demonstrated in this paper, using NSM for temporal data deteriorates memory hierarchy performance for query-intensive workloads. This paper proposes, new cache-conscious, read-optimized, page layouts specifically tailored for temporal data. The proposed page layouts optimize accesses to all levels of the memory hierarchy by avoiding fetching the same data several times (as opposed to NSM). Experiments show that the proposed page layouts are substantially faster than NSM