A column-oriented storage query optimization for flash-based database

The existing database systems are designed based on the physical characteristics of the magnetic disks, and they have failed to obviously improve the performance of solid-state disks (SSD). Therefore, a new connection algorithm, namely CSub-Join, is proposed in this paper. It is a query optimization algorithm for flash databases based on a column storage model. The algorithm first reads columns from two joining tables as CSub tables, and then executes joint operations on CSub tables to generate a join index table and a fetch sequence table. Finally, according to the two generated tables, the query results are taken back from the two joining tables by columns. Using the small size of column oriented storage and the high-speed random read of SSD, the algorithm overcomes the speed mismatch between database systems and flash memories. The results of experiments show that CSub-Join algorithm clearly outperforms CSub-Join algorithm under various selectivities and memory sizes.