Probabilistic Access Allocation of Disk Files for Energy-Efficient Server Systems

Reducing energy consumption is an important issue for data centers. Among the various components of a data center, storage is one of the biggest energy consumers. Previous studies have shown that the average idle period for a server disk in a data center is very small compared to the time taken to spin down and spin up. This significantly limits the effectiveness of disk power management schemes. This article addresses the problem of energy-efficient storage management. More specifically, disk power mode as a measurement on energy consumption, response time as a measurement on system performance, and data popularity as a measurement on system workload are studied. The purpose of reduce energy consumption without significant degrading of system performance is realized by dynamically adjusting the power mode of disks and the location of data. A process policy is also proposed for user access. We proved that based on the constructed underlying infrastructure of server system, this policy leads to an optimal solution to the problem.