Practical solutions for QoS-based resource allocation problems

Abstract

The QoS-based Resource Allocation Model (Q-RAM) proposed in [20] presented an analytical approach for satisfying multiple quality-of-service dimensions in a resource-constrained environment. Using this model, available system resources can be apportioned across multiple applications such that the net utility that accrues to the end-users of those applications is maximized. In this paper, we present several practical solutions to allocation problems that were beyond the limited scope of [20]. First, we show that the Q-RAM problem of finding the optimal resource allocation to satisfy multiple QoS dimensions (at least one of which is dependent on another) is NP-hard. We then present a polynomial solution for this resource allocation problem which yields a solution within a provably fixed and short distance from the optimal allocation. Secondly, [20] dealt mainly with the problem of apportioning a single resource to satisfy multiple QoS dimensions. In this paper, we study the converse problem of apportioning multiple resources to satisfy a single QoS dimension. In practice, this problem becomes complicated, since a single QoS dimension perceived by the user can be satisfied using different combinations of available resources. We show that this problem can be formulated as a mixed integer programming problem that can be solved efficiently to yield an optimal resource allocation. Finally, we also present the run-times of these optimizations to illustrate how these solutions can be applied in practice. We expect that a good understanding of these solutions will yield insights into the general problem of apportioning multiple resources to satisfy simultaneously multiple QoS dimensions of multiple concurrent applications.

Centaur: Host-Side SSD Caching for Storage Performance Control

“…Rajkumar et al proved that optimal cache partitioning is NPhard [32]. Stone et al proposed an approximation algorithm using convex hulls for solving this problem [38].…”

“…Rajkumar et al prove that optimal cache partitioning is NPhard [32]. Stone et al [38] analytically showed that for minimizing overall miss rate and assuming convex MRC curves, optimal partitioning can be achieved by choosing allocation sizes for which derivatives of miss rates are the same across all workloads.…”

Aura: An Architectural Framework for User Mobility in Ubiquitous Computing Environments

“…Aura's architecture addresses the problem of representing the adaptation policy that is appropriate to a user's intent using the notion of utility functions -see for instance [22]. Suppose, for example, that a user is viewing a video over a network connection for which the bandwidth suddenly drops.…”

Application-specific service technologies for commodity operating systems in real-time environments

“…Our work enables COTS systems to be extended with resource management methods to improve and/or guarantee qualities of service [Rajkumar et al 1998] to individual applications without the need for entire QoS architectures [Abdelzaher and Shin 1998;Rosu et al 1998] to be constructed. As stated above, such execution domains do not suffer from scheduling and context-switching overheads as would be the case for services mapped into traditional process address spaces.…”