Project JXTA is an open-source effort to specify the standard protocols for peer-to-peer communication and collaboration. This paper proposes a JXTA performance model and presents results obtained by benchmarking the JXTA 1.0 reference implementation in Java.

This study focuses on the performance evaluation of typical peer operations and consequences for the peer network, the user and the developer. The important tradeoff between peer startup latency and the maintenance of the local cache is shown and discussed. The throughput limits of pipes, the core JXTA communication concept, are also measured in a LAN environment for smooth and bursty traffic. The results indicate that the limiting factor for reliable throughput is the number of messages rather than size in bytes, as well as that small JXTA messages carry an excessive overhead of control data. Important performance issues and trade-offs are identified and explored, as a basis for the formulation of guidelines for system designers and simulation-based research of JXTA networks.