A Scalable and Robust Coordination Architecture for Distributed Management

While opening avenues for unlimited possibilities, distributed systems have introduced management complexity as an unfavorable trait. Therefore, as distributed systems become commonplace, the automation of system management has become a primary challenge in information technology. The state of art in system management assigns each managed resource to an external entity (manager), which monitors, analyzes and controls the resource and a collection of such managers manages a system. In such settings, each manager has to act with partial knowledge about the system, and to maintain the system as a whole in acceptable state, those managers should be controlled and coordinated. This paper presents a scalable and robust coordination architecture for distributed management. The proposed architecture consists of a cloud of managers placed on a P2P network, and a coordinator, which re-elects on failure. Each resource in the system is assigned to a manager, and managers monitor the system and maintain a distributed data model, which reflects system state (a metamodel). Using the meta-model, each manager enforces a set of user-defined management rules to implement resource level management, and the global coordination is achieved using user-defined, global management rules enforced by the coordinator. Main contributions of the paper are, a coordination architecture for distributed management which supports elections based recovery, a meta-model which reflects the system state, and the application of rules on top of the meta-model to achieve manager coordination.