No abstract

Currently available discrete event simulation tools exhibit important limitations, either being too specific, or providing only a partial API and possibly not enough scalability. In this paper we introduce our novel general purpose simulator, called DEUS, which aims at becoming one of the reference tools in the field of complex system simulation. Its essential Java API provides basic interfaces and classes for modelling nodes, events and processes characterizing the structure and dynamics of any complex system. High usability, configurability and memory efficiency are among the strengths of DEUS, as exemplified in this paper by means of the simulator of Chord peer-to-peer systems we implemented with minor coding effort.

A peer-to-peer architectural model defines an overlay network topology and a routing strategy. If these aspects are tied together by a deterministic logical model, we say that the architecture is structured. Otherwise, we say it is unstructured.Based on these assumptions, in recent years many complex P2P architectural models have been defined, their performance evaluation being carried out mainly by means of simulative tools. However, there is an emerging need for a general-purpose tool, enabling large-scale overlay network simulations, yet also providing ready-to-use complex building blocks. The widely known PeerSim simulator addresses the first issue quite effectively, although it appears quite limited with respect to several important aspects, i.e. churn modeling.In this paper we propose P2PAM as a PeerSim enhancement providing a rather complete framework for peer-to-peer architectural modeling. P2PAM effectiveness is demonstrated by showing how it has been used to rapidly develop simulations of two interesting systems, namely JXTA and HALO.