Guiding Personal Choices in a Quality Contracts Driven Query Economy

Abstract

The emergence of Web 2.0 has brought upon a plethora of database-driven web applications and services where both Quality of Service (QoS) and Quality of Data (QoD) are of paramount importance to end users. In our previous work, we have proposed Quality Contracts, a comprehensive framework for specifying multiple dimensions of QoS/QoD; we have also developed algorithms to maximize overall system performance under Quality Contracts. In this work, we turn our attention to the user side of the equation, on how to choose and adapt Quality Contracts to better serve users' needs in the presence of other users, who are competing for the same resources, in a virtual "economy" of Quality Contracts at the server. Towards this, we propose the Adaptive Quality Contract (AQC) scheme to maximize the success ratio of user queries. AQC switches between its Overbid (aggressive) mode and Deposit (conservative) mode, to allow users to survive through economic downturns and upturns. Extensive experiments with real traces show that our proposed scheme outperforms other competing schemes, under a variety of environments and a spectrum of workloads. Copyright 2009 VLDB Endowment, ACM.