Web object-based policies for managing proxy caches

• Authors: Shikharesh Majumdar;Sivarama Dandamudi;Abdolreza Abhari
• Venue: Web object-based policies for managing proxy caches
• Year: 2003

The continued growth of the World Wide Web necessitates the use of proxy caches to reduce latency, network traffic and Web server loads. These caches utilize a traditional file-based replacement policy such as Least Recently Used (LRU). A file is commonly used as a unit of fetching and replacement. In this research, we propose two new cache management strategies for proxies. Our strategies exploit Web document structure to improve cache performance. The strategies discussed in the thesis, WOLRU and WOLFU, use a Web object that consists of a Web page source file and all of its embedded files, as a unit of fetching and replacement. Since our proposed strategies use a Web object, we first present our study on Web object characterization. This study is based on collected data concerning the size and structure of the Web objects. Then, through a trace-driven simulation based on a number of access logs, we show that WOLRU and WOLFU perform significantly better than their file-based counterparts: LRU and LFU. We also show that WOLRU and WOLFU are simpler in comparison to a number of existing cache management policies available in the literature, and can be implemented on a real system. Insights are presented into system behaviour that includes the effect of cache size on performance and the cost associated with the policies. We also propose a new Web object-based policy to manage the storage system of a proxy cache. We propose two techniques to improve the storage system performance. In the first technique, a Web object is used as a unit for replacement and prefetching between the disk and main memory. The prefetching part improves performance, as most of the files can be provided from the main memory instead of a proxy disk. The second technique stores the Web object members on contiguous disk blocks in order to reduce the disk access time. This in turn reduces the disk response time. We have used trace-driven simulations together with a disk simulator to study the performance improvements that can be obtained with these two techniques. Our results show that a significant performance improvement can be achieved by using these techniques. Most of this performance improvement accrues from the first (i.e., Web object-based prefetching and replacement between disk and main memory). The performance improvement produced by the second (i.e., contiguous allocation of Web object members on disk) is small in comparison.