A scalable approach for structuring large-scale hierarchical cloud management systems

In recent years, the scale of clouds and networks has increased greatly. It is important to ensure that the management systems used in these environments can scale as well. A centralized system does not scale well, while for distributed approaches, it is difficult to maintain an overview of the global system state. In hierarchical management systems, nodes at a low level in the hierarchy have a detailed view of a small part of the network, while higher-level nodes have a less detailed view of larger parts of the network. This makes hierarchical management systems well suited for large scale systems. The structure of such a hierarchical system should however be impacted by the management system for which it is used, as various properties such as the number of child nodes, tree depth and the distance between nodes can impact the performance of the management system. In this paper, we describe the Scalable Hierarchical Management Framework (SHMF), a scalable approach for constructing a hierarchical management system, suitable for large-scale cloud environments, that automatically optimizes its structure in function of its overlying management system. We evaluate the approach based on the requirements for the cloud application placement problem.