Mitigation technique for performance degradation of virtual machine owing to GPU pass-through in fog computing

Jihun Kang, Heonchang Yu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.

Original languageEnglish
Article number8437206
Pages (from-to)257-265
Number of pages9
JournalJournal of Communications and Networks
Volume20
Issue number3
DOIs
Publication statusPublished - 2018 Jun 1

Fingerprint

Fog
Degradation
Graphics processing unit
Virtual machine
Program processors

Keywords

  • Fog computing
  • general purpose computing on graphic processing unit (GPGPU)
  • performance isolation
  • virtualization

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications

Cite this

Mitigation technique for performance degradation of virtual machine owing to GPU pass-through in fog computing. / Kang, Jihun; Yu, Heonchang.

In: Journal of Communications and Networks, Vol. 20, No. 3, 8437206, 01.06.2018, p. 257-265.

Research output: Contribution to journalArticle

@article{0a42a908ced1426aa37722e8f3dfbb28,
title = "Mitigation technique for performance degradation of virtual machine owing to GPU pass-through in fog computing",
abstract = "As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.",
keywords = "Fog computing, general purpose computing on graphic processing unit (GPGPU), performance isolation, virtualization",
author = "Jihun Kang and Heonchang Yu",
year = "2018",
month = "6",
day = "1",
doi = "10.1109/JCN.2018.000038",
language = "English",
volume = "20",
pages = "257--265",
journal = "Journal of Communications and Networks",
issn = "1229-2370",
publisher = "Korean Institute of Communication Sciences",
number = "3",

}

TY - JOUR

T1 - Mitigation technique for performance degradation of virtual machine owing to GPU pass-through in fog computing

AU - Kang, Jihun

AU - Yu, Heonchang

PY - 2018/6/1

Y1 - 2018/6/1

N2 - As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.

AB - As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.

KW - Fog computing

KW - general purpose computing on graphic processing unit (GPGPU)

KW - performance isolation

KW - virtualization

UR - http://www.scopus.com/inward/record.url?scp=85052338825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052338825&partnerID=8YFLogxK

U2 - 10.1109/JCN.2018.000038

DO - 10.1109/JCN.2018.000038

M3 - Article

AN - SCOPUS:85052338825

VL - 20

SP - 257

EP - 265

JO - Journal of Communications and Networks

JF - Journal of Communications and Networks

SN - 1229-2370

IS - 3

M1 - 8437206

ER -