The user experience for networked applications is becoming a key benchmark for customers and network providers. Perceived user experience is largely determined by the frequency, duration and severity of network events that impact a service. While today's networks implement sophisticated infrastructure that issues alarms for most failures, there remains a class of silent outages (e.g., caused by configuration errors) that are not detected. Further, existing alarms provide little information to help operators understand the impact of network events on services. Attempts to address this limitation by deploying infrastructure to monitor end-to-end performance for customers have been hampered by the cost of deployment and by the volume of data generated by these solutions.;This dissertation proposes addressing these issues by pushing monitoring to applications on end systems and using their collective view to detect network events and their impact on services -- an approach called Crowdsourcing Event Monitoring (CEM). This work presents a general framework for CEM systems and demonstrates its effectiveness using a large dataset gathered from BitTorrent users, together with confirmed network events from two ISPs. We discuss how we designed and deployed an extension to BitTorrent that implements CEM. This is the first system that performs real-time service-level network event detection through passive monitoring and correlation of perceived performance in end-users' applications. It has already been installed more than 44,000 times as of May, 2010.
展开▼
