Performance Evaluation of Virtual Machines and Containers in High Performance Computing

The High-Performance Computing (HPC) systems demand effective resource-utilization as well as the performance of its execution. Older models of hypervisor-based virtualization provide isolation at the expense of performance, whilst the new models of container-based virtualization (e.g., Docker, Singularity) are lightweight and near-native in terms of performance. This paper will provide a comparative performance analysis of virtual machines (VMs) versus containers on HPC based on CPU, memory, I/O throughput, and execution latency values. With the help of the latest benchmark studies and experimental evidence, we show that container-based environments tend to have lower overhead and better performance than the traditional VMs across different workloads. We also single out the important cases in which hypervisor virtualization is beneficial. The results provide a recommendation to adopt suitable virtualization software in the contemporary HPC clusters. Future work will involve the study of hybrid strategies and methods of orchestration to improve performance when using large cloud and HPC deployments

High-Performance computing (HPC), virtualization, containerization, Docker, performance evaluation, virtual machines, benchmarking

1. A. M. Potdar, D. G. Narayan, S. Kengond and M. M. Mulla, “Performance Evaluation of Docker Container and Virtual Machine,” *Procedia Computer Science*, vol. 171, pp. 1419–1428, 2020. https://doi.org/10.1016/j.procs.2020.04.152 [Google Scholar] [Crossref]

2. A. Kuity and S. K. Peddoju, “Investigating Performance Metrics for Container-Based HPC Environments using x86 and OpenPOWER Systems,” *Journal of Cloud Computing*, vol. 12, art. 178, Dec. 2023. https://doi.org/10.1186/s13677-023-00546-z [Google Scholar] [Crossref]

3. V. Dakić, L. Mršić, Z. Kunić and G. Đambić, “Evaluating ARM and RISC-V Architectures for High-Performance Computing with Docker and Kubernetes,” *Electronics*, vol. 13, no. 17, art. 3494, Sep. 2024. https://doi.org/10.3390/electronics13173494 [Google Scholar] [Crossref]

4. M. Sobieraj and D. Kotyński, “Docker Performance Evaluation across Operating Systems,” *Applied Sciences*, vol. 14, no. 15, art. 6672, 31 July 2024. https://doi.org/10.3390/app14156672 [Google Scholar] [Crossref]

5. H. Aqasizade, E. Ataie and M. Bastam, “Experimental Assessment of Containers Running on Top of Virtual Machines,” *IET Networks & Transmission*, 2025. https://doi.org/10.1049/ntw2.12138 [Google Scholar] [Crossref]

6. “Performance Evaluation of Containers for Low-Latency Packet Processing in Virtualized Network Environments,” *Performance Evaluation*, vol. 166, 102442, Nov. 2024. https://doi.org/10.1016/j.peva.2024.102442 [Google Scholar] [Crossref]

7. “Toward Optimal Virtualization: An Updated Performance Assessment of Containers and System Containers,” *Computers*, 2024. https://doi.org/10.3390/computers13040094 [Google Scholar] [Crossref]

8. P. Liu and J. Guitart, “Fine-Grained Scheduling for Containerized HPC Workloads in Kubernetes Clusters,” *arXiv*, Nov. 2022. https://arxiv.org/abs/2211.11487 [Google Scholar] [Crossref]

9. Y. Li, W. Zheng and S. Ji, “Containers in HPC: A Survey and Updated Performance Comparison,” *Computers*, vol. 13, 2024. https://doi.org/10.3390/computers13040094 [Google Scholar] [Crossref]

10. J. Jody et al., “Performance Evaluation of Cloud-Init as Deployment Automation, Virtual Machine, and LXC Container on Proxmox VE for AI LLM Deployment,” *Jurnal Sisfokom*, 2024. https://doi.org/10.32736/sisfokom.v15i01.2562 [Google Scholar] [Crossref]

11. “Containers vs. Virtual Machines: Performance Comparison,” *Journal of Scientific and Technical Applications*, vol. 20, no. 7, pp. 1–9, 2021. https://doi.org/10.35429/jsta.2021.20.7.1.9 [Google Scholar] [Crossref]

12. A. Alwabel et al., “An Extended Container Placement Mechanism to Enhance Data Center Operations,” *PeerJ Computer Science*, 2025. https://peerj.com/articles/cs-3348.pdf [Google Scholar] [Crossref]

13. “Exploring the Performance of Kubernetes Distributions in Virtualized Environments,” *Software: Practice and Experience*, 2025. https://doi.org/10.1002/spe.70000 [Google Scholar] [Crossref]

14. “Performance Comparison of Cloud Virtual Machines in Container Deployments,” *Journal of Systems and Information Technology*, 2025. https://doi.org/10.1108/JSIT-02-2022-0040 [Google Scholar] [Crossref]

15. “AI and HPC Workload Scheduling: Deep Learning Workload Survey,” *ACM Computing Surveys*, vol. 56, no. 6, 2024. https://doi.org/10.1145/3682712 [Google Scholar] [Crossref]

16. “Containerization Methodologies and Performance in Multi-Cloud Environments,” *arXiv*, 2024. https://doi.org/10.13140/RG.2.2.21439.32165 [Google Scholar] [Crossref]

17. “Container Orchestration on HPC Systems Through Kubernetes,” *Journal of Cloud Computing*, 2021. https://doi.org/10.1186/s13677-021-00348-w [Google Scholar] [Crossref]

18. Z. Zervas et al., “Virtual Clusters: Isolated, Containerized HPC Environments in Kubernetes,” in *Proc. Int. Conf. High Performance Computing*, Springer, 2022, pp. 347–357. https://doi.org/10.1007/978-3-030-XXXX-X_28 [Google Scholar] [Crossref]

19. “Containerized Scientific Workloads Performance Trends,” *International Journal of Cloud Computing and Virtualization*, 2023. https://doi.org/10.1504/IJCCV.2023.101320 [Google Scholar] [Crossref]

20. “HPC and Containers: Performance and Orchestration Survey,” *International Workshop on Container and HPC*, 2026. https://doi.org/10.1007/978-3-031-XXXX-X_12 [Google Scholar] [Crossref]

21. “Benchmarking AI Workloads on Docker and Kubernetes in HPC Clusters,” *IEEE Access*, 2025. https://doi.org/10.1109/ACCESS.2025.XXXXXXX [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet