Self Management of Large-Scale Distributed Systems by Combining Peer-to-Peer Networks and Components

This report envisions making large-scale distributed applications self managing by combining component models and structured overlay networks. A key obstacle to deploying large-scale applications running on Internet is the amount of management they require. Often these applications demand specialized personnel for their maintenance. Making applications self managing will help removing this obstacle. Basing the system on a structured overlay network will allow extending the abilities of existing component models to large-scale distributed systems. A structured overlay network is a form of peer-to-peer network that provides strong guarantees on its behavior. The guarantees are provided for efficient communication, efficient load balancing, and self management in case of node joins, leaves, and failures. Component models, on the other hand, support dynamic configuration, the ability of part of the system to reconfigure other parts at run-time. By combining overlay networks with component models we achieve both lowlevel as well as high-level self management. We are working on a practical implementation of this vision. To show its usefulness, we will target multi-tier applications, and in particular we will consider three-tier applications using a self-managing storage service. This research work is carried out under the FP6 Network of Excellence CoreGRID funded by the European Commission (Contract IST-2002004265).