Today's large data centers become cautious about its massive energy consumption. Range of efforts were made to reduce energy consumption from hardware to software level. Meanwhile, advance of technologies and engineering efforts makes flash-based drive an affordable option with higher capacity in the storage. Though this class of storage drive basically use less energy, the energy efficiency of I/O operation varies with different size of I/O requests. We observed that the energy efficiency is degraded with a small size write request in flash drives. This paper describes energy-efficient I/O scheduler for flash drives. Our I/O scheduler merges small size of write requests for better energy efficiency and as a result it reduces the total energy consumption. We evaluated the scheduler simulation with the small-size-dominant trace from TPC-C. The result shows that the total energy consumption are decreased by 17.2%.
展开▼