On the impact of disk scrubbing on energy savings

The increasing use of computers for saving valuable data imposes stringent reliability constraints on storage systems. Reliability improvement via use of redundancy is a common practice. As the disk capacity improves, advanced techniques such as disk scrubbing are being employed to proactively fix latent sector errors. These techniques utilize the disk idle time for reliability improvement. However, the idle time is a key to dynamic energy management that detects such idle periods and turns-off the disks to save energy. In this paper, we are concerned with the distribution of the disk idle periods between reliability and energy management tasks. For this purpose, we define a new metric, energy-reliability product (ERP), to capture the effect of one technique on the other. Our initial investigation using trace-driven simulations of typical enterprise applications shows that the ERP is a suitable metric for identifying efficient idle period utilization. Thus, ERP can facilitate development of systems that provide both reliability and energy managements.