Random Early Detection Web Servers for Dynamic Load Balancing

Abstract

Modern Web-server systems use multiple servers to handle an increased user demand. Such systems need effective methods to spread the load among web servers evenly in order to keep web server utilization high while providing sufficient quality of service for end users. In conventional DNS-based load balancing architecture, a Doman Name Server (DNS) dispatches requests to web servers based on their load status. Because web servers need to inform the DNS server about their load status from time to time, a so-called load buffer range is often employed to reduce the update frequency. Without care, however, using a load buffer range may result in load oscillation among web servers. To address this problem, we propose a Random Early Detection (RED) method with the intuition that the probability for a web server to become overloaded in near future is directly proportional to its current load. Simulation confirms that our method helps reducing the oscillation of the web server load significantly.