Exploiting the Fine Grain SSD Internal Parallelism for OLTP and Scientific Workloads

Solid State Disks (SSDs) are promising data storage devices in term of performance and energy consumption comparing to Hard Drive Disks (HDDs). They are more and more used, even in On-Line Transaction Processing (OLTP) systems and for scientific data with hard constraints on response time. Consequently, parallel execution and parallel access to data are capital to fulfil this performance requirement. The SSD internal structure provides a potential for parallel access at different levels which can be exploited to match the concurrency naturally present in both OLTP and scientific applications. In this paper, the SSD behaviour is analysed considering two degrees of internal parallelism associated to inter-Dies (degree 1) and interPlanes (degree 2) parallelisms and compared to a sequential scheme (degree 0) as a reference. The study is conducted using representative workloads for both OLTP and scientific applications. The obtained results are significant and show the important performance gain of exploiting the internal SSD parallelism (up to x44 for OLTP). The gain is less important for scientific applications due to their requests size distributions and the interleaving of read/write streams. In conjunction with priority and preemption scheduling strategies, an additional impact is observed, which can be very modest or a factor of x10 according to the context, with a significant impact only if priority is associated to preemption.