Impact of virtualization on timing precision under stressful network conditions

Abstract

The impact of cloud computing and sharing physical resources simultaneously between several virtual instances can be crucial for the designing real-time and time-critical applications. This especially applicable to cases when the target is to deliver reliable network services. In this paper, we primarily aim at investigating the timing behavior in the cloud environments where the resources are shared among up to 50 instances. Moreover, we extend the previously performed experiment with the simulation of various background tasks where the key use-case is the deployment of secure and reliable network applications in virtualized environments. The measurements have been performed on host-based model QEMU/KVM and include different method for time acquisitions and waiting operations. Providing detailed statistical data, we have been analyzed the performance of timing part for the general network application and found some interesting phenomena about the behavior of Linux standard sleep calls. Considering these results, corresponding recommendations about using timing mechanisms have been offered.