A comparison of load balancing techniques for scalable Web servers

Scalable Web servers can be built using a network of workstations where ser ver capacity can be extended by adding new workstations as the workload inc reases. The topic of our article is a comparison of different methods to do load-balancing of HTTP traffic for scalable Web servers. We present a clas sification framework the different load-balancing methods and compare their performance. In addition, we evaluate in detail one class of methods using a prototype implementation with instruction-level analysis of processing o verhead. The comparison is based on a trace driven simulation of traces fro m a large ISP (Internet Service Provider) in Norway. The simulation model i s used to analyze different load-balancing schemes based on redirection of request in the network and redirection in the mapping between a canonical n ame (CNAME) and IP address. The latter is vulnerable to spatial and tempora l locality, although for the set of traces used, the impact of locality is limited. The best performance is obtained with redirection in the network.