An Approach to Model Resources Rationalisation in Hybrid Clouds through Users Activity Characterisation

In recent years, some strategies (e.g., server consolidation by means of virtualisation techniques) helped the managers of large Information Technology (IT) infrastructures to limit, when possible, the use of hardware resources in order to provide reliable services and to reduce the Total Cost of Ownership (TCO) of such infrastructures. Moreover, with the advent of Cloud computing, a resource usage rationalisation can be pursued also for the users applications, if this is compatible with the Quality of Service (QoS) which must be guaranteed. In this perspective, modern datacenters are “elastic”, i.e., able to shrink or enlarge the number of local physical or virtual resources from private/public Clouds. Moreover, many of large computing environments are integrated in distributed computing environment as the grid and cloud infrastructures. In this document, we report some advances in the realisation of a utility, we named Adaptive Scheduling Controller (ASC) which, interacting with the datacenter resource manager, allows an effective and efficient usage of resources, also by means of users jobs classification. Here, we focus both on some data mining algorithms which allows to classify the users activity and on the mathematical formalisation of the functional used by ASC to find the most suitable configuration for the datacenter’s resource manager. The presented case study concerns the SCoPE infrastructure, which has a twofold role: local computing resources provider for the University of Naples Federico II and remote resources provider for both the Italian Grid Infrastructure (IGI) and the European Grid Infrastructure (EGI) Federated Cloud.