Controlling Distributed Systems Using Parallel Autonomic Managers

The use of virtualization technologies and the introduction of multi-core processors have strongly influenced the way of designing and developing software systems. Thus controlling and effectively managing them is became a fundamental issue, especially in distributed scenarios, as Clouds or Grids, providing QoS-assured services on demand. In this work, the authors propose the adoption of a management layer composed by several, parallel and cooperating sub managers (acting as independent controllers) handling, each one, different aspects (i.e., concerns or topics) of the underlying control system. The separation of concerns, together with the parallelism of managers and with their fractal organization, are fundamental for improving the performance of the whole management system.