Dynamic Cloud management for efficient stream processing

Despite its great promises, current Cloud offering is still typically rather static and does not support very dynamic execution patterns. In fact, while dynamic resource allocation is typically required to ensure efficient and effective usage of the Cloud resources, Cloud providers have to deal with complex services, usually treated as black-boxes; hence, the estimation of the maximum number of resources that could improve service execution is a big challenge. This paper proposes and explores a novel automatic service rescaling approach to solve the deployment scaling problem. The proposed scheme, called Dynamic Cloud Infrastructure (DCI), has been designed and verified as a new architecture for the IBM Cloud infrastructure. DCI provides hints useful to understand if a particular service could take full advantage from additional resources enabling automatic discovery of the deployment configuration that jointly addresses high service scalability and low resource consumption. We detail the lessons learnt from the application of the proposed solution in the IBM Smart Bay project and present experimental results that demonstrate our approach as a viable first step toward run-time service scaling.