A trustworthy and resilient event broker for monitoring cloud infrastructures

Abstract

We propose a fault- and intrusion-tolerant framework for datacenter and cloud infrastructure monitoring. In contrast to existing approaches, our framework is able to deal with Byzantine faults. It is based on a replicated event broker, lying in the core of the monitoring infrastructure, supporting the dissemination of all monitoring events. We describe the architecture and the behavior of the framework, explaining how we can deal with different requirements on QoS and QoP. We provide evaluation results as proof of concept for the proposed framework. © 2012 IFIP International Federation for Information Processing.