A Passive System for Server Selection within Mirrored Resource Environments Using AS Path Length Heuristics
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An experiment using a heuristic algorithm that is utilized by clients to select the closest available web server from a group of mirrors indicates this is a promising strategy for passive determination of good, though not always optimal, servers.
Abstract
Abstract: This work presents the results of an experiment using a heuristic algorithm that is utilized by clients to select the closest available web server from a group of mirrors. The heuristic is based on BGP AS path lengths and can be determined without the introduction of any additional measurement traffic into the network. The results indicate this is a promising strategy for passive determination of good, though not always optimal, servers. Many traditional load balancing solutions distribute load based solely on server side criteria such as current processor load, the number of outstanding queued requests, and network saturation. These schemes fail to consider the client’s relationship to the members of the server pool when making the decision of which host to use to process a request. They consider only the
