Improving the Resource Availability in Virtual Cloud Environment

Abstract

The past decade has seen a great paradigm shift to cloud computing in the IT industry. The active participation of such major IT companies as Amazon, Google, and Microsoft significantly stimulates the prosperity of this new generation of service model. These cloud services leverage virtualizations to achieve high resource utilization as well as performance isolation among co-located VMs (virtual machines). Virtualization has attained mainstream status in big business IT industry. In spite of it’s across the board appropriation, it is known that virtualization likewise presents non-paltry overhead when executing undertakings on a virtual machine (VM).Specifically, a consolidated impact from device virtualization overhead and CPU booking dormancy can cause performance degradation when calculation concentrated undertakings and I/O intensive tasks are co-located on a VM. Such an impedance causes extra energy consumption, too. In this paper, we have used Hylics with IPS, a novel solution that provides the efficient data traverse paths for both I/O and reduce the workloads in a safer manner. This is achieved with the arrangement of in-memory file framework and network service at the hypervisor level. Several important design issues are pinpointed and tended to amid our model execution, including efficient intermediate information sharing, network service offloading, and QoS-mindful memory use management. This design also alleviates the existing virtualization overhead and normally optimizes the overall energy efficiency.