Improving Data Access in P2p Systems P-grid: Distributed Search and Replication Peer-to-peer Networking

The limitations of client-serverbased systems become evident in an Internet-scale distributed environment. Resources are concentrated on a small number of nodes, which must apply sophisticated load-balancing and fault-tolerance algorithms to provide continuous and reliable access. Additionally, network bandwidth must be increased steadily to handle requests to and from successful Internet servers. Caching and replication were introduced a posteriori to remedy these problems in a client-server setting when the World Wide Web, as the most successful Internet service, developed into a network bandwidth nightmare. Peer-to-peer systems offer an alternative to traditional client-server systems for some application domains. In P2P systems, every node (peer) of the system acts as both client and server (servent) and provides part of the overall information available from the system. The P2P approach circumvents many problems of client-server systems but results in considerably more complex searching, node organization, security, and so on. Napster, which made the P2P idea popular, avoids some of this complexity by employing a centralized database with references to files on peers. Gnutella, another wellknown P2P system, has no central database, but requires a communicationintensive search mechanism. (See the sidebar, “The Gnutella File-Sharing System,” page XX, for a discussion of the Gnutella protocol.) In this article we present Gridella, our Gnutella-compatible P2P system. Gridella is based on the Peer-Grid (P-Grid) approach, which draws on research in distributed and cooperative information systems to provide a decentralized, scalable data access structure.1 Gridella improves the highly chaotic and inefficient Gnutella infrastructure with directed search and advanced concepts, thus enhancing efficiency and providing a model for further analysis and research.