Next Article in Journal
Combined Self-Attention Mechanism for Chinese Named Entity Recognition in Military
Previous Article in Journal
Artificial Intelligence Imagery Analysis Fostering Big Data Analytics
Open AccessArticle

Impact of Modern Virtualization Methods on Timing Precision and Performance of High-Speed Applications

1
Department of Electrical, Mechanical and Industrial Engineering, Anhalt University of Applied Sciences, Bernburger Str. 55, 06366 Köthen, Germany
2
O. S. Popov Odessa National Academy of Telecommunications, Department of Higher Mathematics, Kovalska Str. 1, 65045 Odessa, Ukraine
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Future Internet 2019, 11(8), 179; https://doi.org/10.3390/fi11080179
Received: 17 July 2019 / Revised: 5 August 2019 / Accepted: 14 August 2019 / Published: 16 August 2019
(This article belongs to the Section Network Virtualization and Edge/Fog Computing)
The presented work is a result of extended research and analysis on timing methods precision, their efficiency in different virtual environments and the impact of timing precision on the performance of high-speed networks applications. We investigated how timer hardware is shared among heavily CPU- and I/O-bound tasks on a virtualized OS as well as on bare OS. By replacing the invoked timing methods within a well-known application for estimation of available path bandwidth, we provide the analysis of their impact on estimation accuracy. We show that timer overhead and precision are crucial for high-performance network applications, and low-precision timing methods usage, e.g., the delays and overheads issued by virtualization result in the degradation of the virtual environment. Furthermore, in this paper, we provide confirmation that, by using the methods we intentionally developed for both precise timing operations and AvB estimation, it is possible to overcome the inefficiency of standard time-related operations and overhead that comes with the virtualization. The impacts of negative virtualization factors were investigated in five different environments to define the most optimal virtual environment for high-speed network applications. View Full-Text
Keywords: virtualization; cloud computing; timestamps precision; timekeeping; networking; QEMU; KVM; Virtual Box; Xen; VMware ESXi virtualization; cloud computing; timestamps precision; timekeeping; networking; QEMU; KVM; Virtual Box; Xen; VMware ESXi
Show Figures

Figure 1

MDPI and ACS Style

Kirova, V.; Karpov, K.; Siemens, E.; Zander, I.; Vasylenko, O.; Kachan, D.; Maksymov, S. Impact of Modern Virtualization Methods on Timing Precision and Performance of High-Speed Applications. Future Internet 2019, 11, 179.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop