Data management in large scale P2P systems

Abstract

Peer-to-peer (P2P) computing offers new opportunities for building highly distributed data systems. Unlike client-server computing, P2P can operate without central coordination which yields important advantages such as: a very dynamic environment where peers can join and leave the network at any time; direct and fast communication between peers; and scale up to large number of peers. However, most current P2P systems have severe limitations: file-level sharing, read-only access, no content-based search and poor scaling.

In this paper, I discuss the issues of providing high-level data management services (content-based querying, replication, availability, etc.) in a P2P system with heterogeneous data sources such as files, documents and databases. Addressing these issues requires combining complementary technologies such as distributed database management, information retrieval and mobile agent systems. I also propose a scalable, two-level P2P architecture for data management with directory agents and data agents and illustrate its application to data grid computing.