Column-store database systems open new vistas for improved maintenance through self-organization. Individual columns are the focal point, which simplify balancing conflicting requirements. This work presents two workload-driven selforganizing techniques in a column-store, i.e. adaptive segmentation and adaptive replication. Adaptive segmentation splits a column into non-overlapping segments based on the actual query load. Likewise, adaptive replication creates segment replicas. The strategies can support different application requirements by trading off the reorganization overhead for storage cost. Both techniques can significantly improve system performance as demonstrated in an evaluation of different scenarios.
Milena Ivanova, Martin L. Kersten, Niels Nes