Model-based energy-aware data movement optimization in the storage I/O stack

The increasing data demands of applications from various domains and the decreasing relative power cost of CPU computation have gradually exposed data movement cost as the prominent factor of energy consumption in computing systems. The traditional organization of the computer system software into a layered stack, while providing a straightforward modularity, poses a significant challenge for the global optimization of data movement in particular and, thus, the energy efficiency in general. Optimizing the energy efficiency of data movement in large-scale systems is a difficult tasks because it depends on a complex interplay of various factors at different system layers. In this work, we address the challenge of optimizing the data movement of the storage I/O stack in a holistic manner. Our approach consists of a model-based system driver that obtains the current I/O power regime and adapts the CPU frequency level according to this information. On the one hand, for simplifying the understanding of the relation between data movement and energy efficiency, this paper proposes novel energy prediction models for data movement based on series of runtime metrics from several I/O stack layers. We provide an in-depth study of the energy consumption in the data path, including the identification and analysis of power and performance regimes that synthesize the energy consumption patterns in a cross-layer approach. On the other hand, we propose and prototype a kernel driver that exploits data movement awareness for improving the current CPU-centric energy management.