Adaptive Disk Spindown via Optimal Rent-to-Buy in Probabilistic Environments

Abstract

In the single rent-to-buy decision problem, without a priori knowledge of the amount of time a resource will be used we need to decide when to buy the resource, given that we can rent the resource for $1 per unit time or buy it once and for all for $c. In this paper we study algorithms that make a sequence of single rent-to-buy decisions, using the assumption that the resource use times are independently drawn from an unknown probability distribution. Our study of this rent-to-buy problem is motivated by important systems applications, specifically, problems arising from deciding when to spindown disks to conserve energy in mobile computers [4], [13], [15], thread blocking decisions during lock acquisition in multiprocessor applications [7], and virtual circuit holding times in IP-over-ATM networks [11], [19].We develop a provably optimal and computationally efficient algorithm for the rent-to-buy problem. Our algorithm uses O( √ t) time and space, and its expected cost for the tth resource use converges to optimal as O( log t/t), for any bounded probability distribution on the resource use times. Alternatively, using O(1) time and space, the algorithm almost converges to optimal.We describe the experimental results for the application of our algorithm to one of the motivating systems problems: the question of when to spindown a disk to save power in a mobile computer. Simulations using disk access traces obtained from an HP workstation environment suggest that our algorithm yields significantly improved power/response time performance over the nonadaptive 2-competitive algorithm which is optimal in the worst-case competitive analysis model.

A survey of design techniques for system-level dynamic power management

“…In the work by Krishnan et al [27], a set of timeout values is maintained and each timeout is associated with an index indicating how successful it would have been. The policy chooses, at each idle time, the timeout that would have performed best among the set of available ones.…”

An Energy-Efficient Framework for Large-Scale Parallel Storage Systems

“…Recently, researchers have realized that energy conservation is also important for large scale parallel disks in the cluster systems. Several techniques proposed to conserve energy in storage systems include dynamic power management schemes [4][5], power-aware cache management strategies [6], poweraware prefetching schemes [7], software-directed power management techniques [8], redundancy techniques [8], and multi-speed settings [10][11] [12]. However, the research on energy-efficient parallel disk systems is still in its infancy.…”

HYBUD: An Energy-Efficient Architecture for Hybrid Parallel Disk Systems

“…One of challenging issues raised in designing hybrid parallel disks with flash drives is to achieve high energy-efficiency in such novel disk systems. Several techniques proposed to conserve energy in disk systems include dynamic power management schemes [4] [14], poweraware cache management strategies [23], software-directed power management techniques [20], redundancy techniques [16], and multi-speed settings [6][8] [13]. However, the research on energy-efficient hybrid parallel disk systems with flash drives is still in its infancy.…”