Performance Evaluation of Hypervisors and the Effect of Virtual CPU on Performance

被引:6
|
作者
Rahman, Hafiz Ur [1 ]
Wang, Guojun [1 ]
Chen, Jianer [1 ]
Jiang, Hai [2 ]
机构
[1] Guangzhou Univ, Sch Comp Sci & Technol, Guangzhou 510006, Guangdong, Peoples R China
[2] Arkansas State Univ, Dept Comp Sci, State Univ, AR 72467 USA
基金
中国国家自然科学基金;
关键词
cloud computing; hypervisor; virtual CPU mapping; CPU utilization;
D O I
10.1109/SmartWorld.2018.00146
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Organizations are adopting virtualization technology to reduce the cost while maximizing the productivity, flexibility, responsiveness, and efficiency. There are a variety of vendors for the virtualization environments, all of them claim that their virtualization hypervisor is the best in terms of performance. Furthermore, when a system administrator or a researcher want to deploy a virtual machine in a cloud environment, which vCPU-VM configuration is the best for better performance? In this paper, prior to evaluating the latest version of hypervisors (commercial and open source), the best virtual CPU to virtual machine (vCPU-VM) configuration as well as the effect of virtual CPUs on performance is analyzed for each hypervisor. We used Phoronix Test Suite (PTS) benchmarking tool as a traffic generator and analyzer. The results have shown that commercial and open source hypervisors have similar performance. As per our observation, the performance of a system would degrade by improper allocation of vCPUs to VMs, or when there is a massive over-allocation of vCPUs.
引用
收藏
页码:772 / 779
页数:8
相关论文
共 50 条
  • [31] Performance evaluation of CPU isolation mechanisms in a multimedia OS kernel
    Yau, DKY
    MULTIMEDIA COMPUTING AND NETWORKING 2001, 2001, 4312 : 62 - 74
  • [32] Performance Evaluation Benchmark of General-Purpose CPU: A Survey
    Shi H.-K.
    Wang Z.-S.
    Zhang S.-Z.
    Gao X.
    Zhao Y.-J.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2023, 51 (01): : 246 - 256
  • [33] Performance characterization and profiling of chained CPU-bound Virtual Network Functions
    Troia, Sebastian
    Savi, Marco
    Nava, Giulia
    Zorello, Ligia Maria Moreira
    Schneider, Thomas
    Maier, Guido
    COMPUTER NETWORKS, 2023, 231
  • [34] A holistic model of the performance and the energy efficiency of hypervisors in a high-performance computing environment
    Guzek, Mateusz
    Varrette, Sebastien
    Plugaru, Valentin
    Pecero, Johnatan E.
    Bouvry, Pascal
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2014, 26 (15): : 2569 - 2590
  • [35] Comparative Performance Study of Lightweight Hypervisors Used in Container Environment
    Li, Guoqing
    Takahashi, Keichi
    Ichikawa, Kohei
    Iida, Hajimu
    Thiengburanathum, Pree
    Phannachitta, Passakorn
    CLOSER: PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND SERVICES SCIENCE, 2021, : 215 - 223
  • [36] Design and Performance Evaluation of Multispectral Sensing Algorithms on CPU, GPU, and FPGA
    Menon, Vivek V.
    Siddiqui, Saquib A.
    Rao, Sanil
    Schmidt, Andrew
    French, Matthew
    Chirayath, Ved
    Li, Alan
    2021 IEEE AEROSPACE CONFERENCE (AEROCONF 2021), 2021,
  • [37] Evaluation of high performance thermal greases for CPU package cooling applications
    Stern, MB
    Gektin, V
    Pecavar, S
    Kearns, D
    Chen, T
    Twenty-First Annual IEEE Semiconductor Thermal Measurement and Management Symposium, Proceedings 2005, 2005, : 39 - 43
  • [38] On-line performance evaluation of RAID 5 using CPU utilization
    Jin, H
    Yang, HN
    Zhang, JL
    SIGNAL AND DATA PROCESSING OF SMALL TARGETS 1998, 1998, 3373 : 498 - 509
  • [39] Accurate Emulation of CPU Performance
    Buchert, Tomasz
    Nussbaum, Lucas
    Gustedt, Jens
    EURO-PAR 2010 PARALLEL PROCESSING WORKSHOPS, 2011, 6586 : 5 - 12
  • [40] Performance evaluation of image smoothing on CPU and GPU using multithreading - An experimental apwwWroach in High Performance Computing
    Gopalakrishnan, Anantharaman
    Narayanasamy, Senthil Anand
    Sethumadhavan, Gopalakrishnan
    2016 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH, 2016, : 786 - 790