Impact of Machine Virtualization on Timing Precision for Performance-critical Tasks

2nd International Conference on Measurement Instrumentation and Electronics

物理学;无线电电子学

Karpov, Kirill^1 ; Fedotova, Irina^1 ; Siemens, Eduard^1

Anhalt University of Applied Sciences, Faculty of Electrical, Mechanical and Industrial Engineering, Bernburger Str. 57, Köthen

06366, Germany^1

关键词: Critical applications;    Critical tasks;    Hardware virtualization;    Host-based;    Measurement study;    Sleep operations;    Statistical parameters;    Timing behaviors;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/870/1/012007/pdf
DOI  :  10.1088/1742-6596/870/1/012007

来源: IOP

【 摘 要 】

In this paper we present a measurement study to characterize the impact of hardware virtualization on basic software timing, as well as on precise sleep operations of an operating system. We investigated how timer hardware is shared among heavily CPU-, I/O- and Network-bound tasks on a virtual machine as well as on the host machine. VMware ESXi and QEMU/KVM have been chosen as commonly used examples of hypervisor- and host-based models. Based on statistical parameters of retrieved distributions, our results provide a very good estimation of timing behavior. It is essential for real-time and performance-critical applications such as image processing or real-time control.