In-storage processing of database scans and joins

Abstract

Flash memory-based SSD is becoming popular because of its outstanding performance compared to conventional magnetic disk drives. Today, SSDs are essentially a block device attached to a legacy host interface. As a result, the system I/O bus remains a bottleneck, and the abundant flash memory bandwidth and the computing capabilities of SSD are largely untapped. In this paper, we propose to accelerate key database operations, scan and join, for large-scale data analysis by moving data-intensive processing from the host CPU to inside flash SSDs ("in-storage processing"), close to the data source itself. To realize the idea of in-storage processing in a cost-effective manner, we deploy special-purpose compute modules using the System-on-Chip technology. While data from flash memory are transferred, a target database operation is applied to the data stream on the fly without any delay. This reduces the amount of data to transfer to the host drastically, and in turn, ensures all components along the data path in an SSD are utilized in a balanced way. Our experimental results show that in-storage processing outperforms conventional processing with a host CPU by over up to 7 x, 5 x and 47 x for scan, join, and their combination, respectively. It also turns out that in-storage processing can be realized at only I% of the total SSD cost, while offering sizable energy savings of up to 45 x compared to host processing.