DISH - Dynamic Information-Based Scalable Hashing on a Cluster of Web Cache Servers

Caching web pages is an important part of web infrastructure. The effects of caching services are even more pronounced for wireless infrastructures due to their limited bandwidth. Medium to large-scale infrastructures deploy a cluster of servers to solve the scalability problem and hot spot problem inherent in caching. In this report, we present Dynamic Information-based Scalable Hashing (DISH) that evenly hashes client requests to a cluster of cache servers. Three types of runtime information are used to determine when and how to cache pages, including cache utilization, CPU usage, and number of connections. Pages cached are stored and retrieved mutually exclusively to/from all the servers. We have implemented our approach and performed various experiments using publicly available traces. Experimental results on a cluster of 16 cache servers demonstrate that the proposed hashing method gives 45% to 114% performance improvement over other widely used methods, while addressing the hot s...

• Type: Conference
• Year: 2007
• Where: HPCC
• Authors: Andrew Sohn, Hukeun Kwak, Kyusik Chung
• Keywords: Cache Servers, Distributed And Parallel Computing, Hot Spot Problem, HPCC 2007, Information-based Scalable Hashing