Résumé: This paper presents an experimental set of self-organising mechanisms to support application-level service overlays across the internet. These mechanisms include a base node discovery service and protocol that is resilient to node and network failure, which in turn is a basis for the construction of service-specific overlays. We have also developed a generic service overlay structured according to IP network latencies which uses the GNP virtual coordinate system. We discuss our results and experiences of implementing our platform using an active service infrastructure deployed on PlanetLab. While we have been successful in meeting many of our aims, we have identified some practical shortcomings with regard to latency estimation accuracy, and scalability of some of our mechanisms to internet size. The paper describes lessons learned from experimental development and deployment.

Langue: Anglais