No abstract

<p class="CAbstract"><span>The performance of servers at the data centers is affected when the servers are overloaded. To overcome this problem, the workload at the overloaded servers has to be redistributed to other servers which is possible with live VM migration. Live migration plays a crucial role in handling the overload at the data centers without service interruption. However, live migration also incurs some performance loss and energy overhead. The energy consumption at the data centers is a matter of utmost concern both in terms of economy and ecology. In this paper we are proposing a novel approach to find the most suitable server for VM placement. We have introduced an Optimal VM Allocation Framework (OVAF) in which the hosts at the source requests the destination for their available slots. Based on the response from the available servers, the utilization factor is calculated and the selection of appropriate destination for VM placement is done. Simulations carried out have shown 10% improvement in energy saving.</span></p>

Increasing demand of computing resources and the popularity of cloud computing have led the organizations to establish of large-scale data centers. To handle varying workloads, allocating resources to Virtual Machines, placing the VMs in the most suitable physical machine at data centers without violating the Service Level Agreement remains a big challenge for the cloud providers. The energy consumption and performance degradation are the prime focus for the data centers in providing services by strictly following the SLA. In this paper we are suggesting a model for minimizing the energy consumption and performance degradation without violating SLA. The experiments conducted have shown a reduction in SLA violation by nearly 10%.

In virtualized servers, with live migration technique pages are copied from one physical machine to another while the virtual machine (VM) is running. The dynamic migration of virtual machines encumbers the data center which in turn reduces the performance of applications running on that particular physical machine. A considerable number of studies have been carried out in the area of performance evaluation during live VM migration.  However, all the aspects related to the migration process have not been examined for the performance assessment. In this paper, we propose a novel approach to evaluate the performance during migration process in different types of coupled machine environment. It is presented here that the state of art VM migration technology requires further improvement in realizing effective migration by monitoring comprehensive performance value. We introduced the parameter, θ, to compare performance value which can be used for controlling and halting unsuccessful migration and save significant amount of time in migration operation.  Our model is capable of analyzing real time scenario of cloud performance assessment targeting VM migration strategies. It also offers the possibility of further expanding to universal models for analyzing the performance variations that occurs as a result of VM migration.