Configuration management in the Nexus distributed operating system

The paper describes the approach taken for configuration management in the Nexus distributed operating system. Nexus uses kernel‐level support for monitoring the failure or termination status of distributed components of an application. Periodic user‐level messages are not required for status monitoring. Group and dependency relationships between such components can be defined by the programmer for the purpose of configuration monitoring and management. An object belonging to a distributed application can be monitored by its host kernel for system‐defined exception conditions. When any of these conditions arise, other objects are notified through signals or messages, as specified by the programmer.