Computing Resource Management In Virtual Machine Based On Cloud Computing

Cloud computing is the integration of many applications and data. Ifvirtualization and computing resources can be provided to users in different areasthrough network, and users’computing demand can be met, it can be called CloudComputing, No matter by software service or Web2.0. According to AmercianNational Standards and Technology, cloud computing is a kind of dynamic andextendible computing mode, which is usually provided to users in the form of servicethrough virtualized resources on the Internet. Users do not need to know the relatedinformation inside the cloud and do not need the control of inside structure.IaaS (Infrastructure as a Service) architecture in the cloud computing is toprovide infrastructure, CPU, memory, and network, etc., for the service. Thevirtualization is to package infrastructure into a profile form to provide computingresources. This is usually a virtual environment platform, such as KVM, XEN, andVMware. In such a platform, based on the application of different computing resourcerequirements, dynamic resource adjustment in part, there are still many researchissues to be resolved, such as automated dynamic resource adjustment and allocationmechanism of calculating resources.In this thesis, a dynamic adjustment mechanism of the virtual machinecomputing resources, called dameva, in the cloud computing environment has beenproposed. It is a dynamic adjustment technique constructed under the KVM(Kernel-based Virtual Machine) virtualization architecture. By applying the proposedmechanism, when the load of a virtual machine is heavy, the number of CPUs in thevirtual machine will be increased automatically with non-stop service to increase thesystem performance. Once the system load is no longer heavy, the augmented CPUswill be released immediately to increase the overall system resource utilization. Experimental results show that by applying the proposed mechanism in a heavyloaded virtual machine, the computing performance of the virtual machine, can beimproved effectively and the response time of connection requests can also bereduced significantly.