Column-aware Transaction Management Scheme for Column-Oriented Databases

ABSTRACT The column-oriented database storage is a very advanced model f or large-volume data analysis systems because of its superior I/O performance. Traditional data storages exploit row-oriented storage where the attributes of a record are placed contiguously in hard disk for fast write operations. However, for search-mostly datawarehouse systems, column-oriented storage has become a mo re proper model because of its superior read performance. Recently , solid state drive using MLC flash memory is largely recognized as the preferred storage media for high-speed data analysis system s. The features of non-volatility, low power consumption, and f ast access time for read operations are sufficient grounds to suppo rt flash memory as major storage components of modern database servers. However, we need to improve traditional transaction management scheme due to the relatively slow characteristics of column compression and flash operation as compared to RAM memory. In this research, we propose a new scheme called Column-aware Multi-Version Locking (CaMVL) scheme for efficient transaction processing. CaMVL improves transaction performance by using compression lock and multi version reads f or efficiently handling slow flash write/erase operation in lock management process. We also propose a simulation model to show the performance of CaMVL. Based on the results of the performance evaluation, we conclude that CaMVL scheme outperfor ms the traditional scheme.