BitTorrent Swarm Analysis through Automation and Enhanced Logging

Peer-to-Peer protocols currently form the most heavily used protocol class in the Internet, with BitTorrent, the most popular protocol for content distribution, as its flagship. A high number of studies and investigations have been undertaken to measure, analyse and improve the inner workings of the BitTorrent protocol. Approaches such as tracker message analysis, network probing and packet sniffing have been deployed to understand and enhance BitTorrent's internal behaviour. In this paper we present a novel approach that aims to collect, process and analyse large amounts of local peer information in BitTorrent swarms. We classify the information as periodic status information able to be monitored in real time and as verbose logging information to be used for subsequent analysis. We have designed and implemented a retrieval, storage and presentation infrastructure that enables easy analysis of BitTorrent protocol internals. Our approach can be employed both as a comparison tool, as well as a measurement system of how network characteristics and protocol implementation influence the overall BitTorrent swarm performance. We base our approach on a framework that allows easy swarm creation and control for different BitTorrent clients. With the help of a virtualized infrastructure and a client-server software layer we are able to create, command and manage large sized BitTorrent swarms. The framework allows a user to run, schedule, start, stop clients within a swarm and collect information regarding their behavior.