The oversubscription of intra-Data Center links and the high volatility of Virtual Machine deployments require a flexible and agile control of the Data Center network infrastructure, possibly coordinated with computing and storage resources control. In this scenario, the Software-Defined Networking paradigm opens up new opportunities to design orchestrated resources control strategies able to meet the dynamically-changing traffic demands of instantiated Virtual Machines. This paper presents the architectural design of an SDN-based orchestrator for dynamic computing and communication resources chaining, able to assure better than best effort VMs data exchanges across Cloud Data Centers. Moreover, the paper evaluates a number of different chaining strategies able to dynamically compose proper pool of resources based on their variable load. Such strategies are compared against specific management objectives using both simulations and experiments showing their effectiveness in terms of resource usage and service provisioning rate.
An SDN Orchestrator for Resources Chaining in Cloud Data Centers
A. Sgambelluri;GHARBAOUI, Molka;CASTOLDI, Piero
2014-01-01
Abstract
The oversubscription of intra-Data Center links and the high volatility of Virtual Machine deployments require a flexible and agile control of the Data Center network infrastructure, possibly coordinated with computing and storage resources control. In this scenario, the Software-Defined Networking paradigm opens up new opportunities to design orchestrated resources control strategies able to meet the dynamically-changing traffic demands of instantiated Virtual Machines. This paper presents the architectural design of an SDN-based orchestrator for dynamic computing and communication resources chaining, able to assure better than best effort VMs data exchanges across Cloud Data Centers. Moreover, the paper evaluates a number of different chaining strategies able to dynamically compose proper pool of resources based on their variable load. Such strategies are compared against specific management objectives using both simulations and experiments showing their effectiveness in terms of resource usage and service provisioning rate.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.