Workload characterization and autoscaling in Cloud environments

Cloud computing is becoming a successful key factor in many types of business, because it enables an efficient model for resource provisioning. Even though resources can be provisioned on demand, they need to adapt quickly and in a seamless way to the workload intensity and characteristics and satisfy at the same time the desired performance levels. Autoscaling policies are devised for these purposes. In this thesis work, we apply a state-of-the-art reactive autoscaling policy to assess the effects of deploying the HTTP/2 server push mechanism in Cloud environments. A simulation environment based on the CloudSim simulation toolkit has been designed and developed to exploit a Web workload on a realistic Cloud infrastructure. Workload characterization based on measurements collected on a real Web server has been carried out to derive workload model to be used for workload description in the simulation experiments. These experiments have shown that the autoscaling mechanism is beneficial for web servers even though pushing a large number of objects might lead to server overload.