A distributed state monitoring service for adaptive application management

Anubis is a simple state monitoring service that supports coordinated action among distributed management agents. It uses a temporal consistency model that addresses symmetric and asymmetric network partitions. We have used Anubis to support distributed management of adaptive applications in grid and utility computing environments and our experience has shown that the abstraction and properties provided by the service simplify the task of programming distributed management behavior. We support this claim by examining three common use cases that our developers encountered, namely: resource management, lifecycle coordination, and compositional failure management.