DOI QR코드

DOI QR Code

VDI deployment and performance analysys for multi-core-based applications

멀티코어 기반 어플리케이션 운용을 위한 데스크탑 가상화 구성 및 성능 분석

  • Received : 2022.08.31
  • Accepted : 2022.09.13
  • Published : 2022.10.31

Abstract

Recently, as Virtual Desktop Infrastructure(VDI) is widely used not only in office work environments but also in workloads that use high-spec multi-core-based applications, the requirements for real-time and stability of VDI are increasing. Accordingly, the display protocol used for remote access in VDI and performance optimization of virtual machines have also become more important. In this paper, we propose two ways to configure desktop virtualization for multi-core-based application operation. First, we propose a codec configuration of a display protocol with optimal performance in a high load situation due to multi-processing. Second, we propose a virtual CPU scheduling optimization method to reduce scheduling delay in case of CPU contention between virtual machines. As a result of the test, it was confirmed that the H.264 codec of Blast Extreme showed the best and stable frame, and the scheduling performance of the virtual CPU was improved through scheduling optimization.

최근 VDI(Virtual Desktop Infrastructure)가 오피스 업무 환경뿐만 아니라 고사양의 멀티코어 기반 어플리케이션을 사용하는 워크로드에도 많이 사용되면서 VDI에 대한 실시간성과 안정성에 대한 요구 사항이 증대되고 있다. 그에 따라 VDI에서 원격접속에 사용되는 디스플레이 프로토콜과 가상머신의 성능 최적화 또한 중요성이 높아졌다. 본 논문에서는 멀티코어 기반 어플리케이션 운용을 위한 데스크탑 가상화 구성을 위해 두 가지를 제안한다. 첫 번째는 멀티 프로세싱으로 인한 고부하 상황에서 최적의 성능을 가진 디스플레이 프로토콜의 코덱 구성을 제안한다. 두 번째는 가상머신 간 CPU 경합 시 스케쥴링 지연을 줄이기 위한 가상 CPU 스케쥴링 최적화 방안을 제안한다. 시험 결과 Blast Extreme의 H.264 코덱이 가장 좋고 안정적인 프레임을 보여줬으며 스케쥴링 최적화를 통해 가상 CPU의 스케쥴링 성능이 개선됨을 확인하였다.

Keywords

References

  1. VMware, "Best practices for performance tuning of latencysensitive workloads in vSphere VMs," VMware White Paper, Sep. 2013.
  2. VMware, "Media and Entertainment Workloads on vSphere 6.7," VMware White Paper, Mar. 2019.
  3. J. Y. Lim and D. S. Kim, "Performance Evaluation of Virtualization Solution for Next Generation Naval Combat Systems," Journal of The Institute of Electronics and Information Engineers, vol. 56, no. 2, pp. 41-49, Feb. 2019.
  4. K. S. Song, "A Study of Feasibility and Performance Analysis of VDI based on GPU Acceleration for Naval Combat System," Journal of The Institute of Electronics and Information Engineers, vol. 58, no. 11, pp. 86-93, Nov. 2021. https://doi.org/10.5573/ieie.2021.58.11.86
  5. J. S. Shin and H. Y. Kim, "Event Routing Scheme to Improve I/O Latency of SMP VM," Journal of Korean Institute of Information Scientists and Engineers, vol. 42, no. 11, pp. 1322-1331, Nov. 2015.
  6. VMware, "vSphere Monitoring and Performance," VMware White Paper, Apr. 2020.
  7. VMware, "The CPU Scheduler in VMware vSphere 5.1," VMware White Paper, Jan. 2013.
  8. VMware Digital Workspace Tech Zone. VMware Blast Extreme Optimization Guide [Internet]. Available: https://techzone.vmware.com/resource/vmware-blast-extre me-oprimization-guide.
  9. VMware End-User Computing Blog. Delivering a Transformational User Experience with NVIDIA GRID & VMware Horizon 7 [Internet]. Available: https://blogs.vmware.com/euc/2016/05/transform-user-experience-nvidia-grid-vmware-horizon-7.html.
  10. S. Y. Kim, T. H. Lee, and Y. I. Eom, "Performance Analysis of NUMA-aware Locks in Virtualized Systems," Journal of KIISE Transactions on Computing Practices, vol. 27. no. 2, pp. 107-109, Feb. 2021.
  11. Nutanix portal. Intermittent CPU ready time due to NUMA action affinity on VMware ESXi [Internet]. Available: https://portal.nutanix.com/page/documents/kbs/details?targetId=kA07V000000LXAwSAO.
  12. VMware Docs. esxtop data [Internet]. Available: https://docs.vmware.com/en/VMware-Smart-Assurance/10. 1.0/ip-manager-delopment-guide-101/GUID-8F62BA71-5 C6B-41DE-9B9B-0BF24ADD743B.html.
  13. PassMark portal. PerformanceTest [Internet]. Available: https://www.passmark.com/products/performancetest/index.php.