Adaptive Resource Management Schemes for Web Services

Abstract

Web cluster systems provide cost-effective solutions when scalable and reliable web services are required. However, as the number of servers in web cluster systems increase, web cluster systems incur long and unpredictable delays to manage servers. This study presents the efficient management schemes for web cluster systems. First of all, we propose an efficient request distribution scheme in web cluster systems. Distributor-based systems forward user requests to a balanced set of waiting servers in complete transparency to the users. The policy employed in forwarding requests from the frontend distributor to the backend servers plays an important role in the overall system performance. In this study, we present a proactive request distribution (ProRD) to provide an intelligent distribution at the distributor. Second, we propose the heuristic memory management schemes through a web prefetching scheme. For this study, we design a Double Prediction-by-Partial-Match Scheme (DPS) that can be adapted to the modern web frameworks. In addition, we present an Adaptive Rate Controller (ARC) to determine the prefetch rate depending on the memory status dynamically. For evaluating the prefetch gain in a server node, we implement an Apache module. Lastly, we design an adaptive web streaming system in wireless networks. The rapid growth of new wireless and mobile devices accessing the internet has contributed to a whole new level of heterogeneity in web streaming systems. Particularly, in-home networks have also increased in heterogeneity by using various devices such as laptops, cell phone and PDAs. In our study, a set-top box(STB) is the access pointer between the internet and a home network. We design an ActiveSTB which has a capability of buffering and quality adaptation based on the estimation for the available bandwidth in the wireless LAN.