Improving availability of distributed event-based systems via run-time monitoring and analysis
Marija Mikic-Rakic · 2004
A distributed software system's deployment architecture can have a significant impact on the system's availability, which depends on various system parameters, such as network bandwidth, frequencies of software component interactions, and so on. Existing system deployment tools lack support for monitoring, visualizing, and analyzing different factors that influence availability. They also lack support for modifying a running system's deployment to improve its availability. In this paper, we present an approach for runtime assessment of relevant system parameters, their visualization, and estimation and effecting of deployment architectures for large-scale, highly distributed systems.