gMig

Author:

Ma Jiacheng1,Zheng Xiao2,Dong Yaozu3,Li Wentai4,Qi Zhengwei4,He Bingsheng5,Guan Haibing4

Affiliation:

1. Shanghai Jiao Tong University and Intel Corporation

2. Intel Corporation and Alibaba Group

3. Intel Corporation

4. Shanghai Jiao Tong University

5. National University of Singapore

Abstract

This paper introduces gMig, an open-source and practical GPU live migration solution for full virtualization. By taking advantage of the dirty pattern of GPU workloads, gMig presents the One-Shot Pre-Copy combined with the hashing based Software Dirty Page technique to achieve efficient GPU live migration. Particularly, we propose three approaches for gMig: 1) Dynamic Graphics Address Remapping, which parses and manipulates GPU commands to adjust the address mapping to adapt to a different environment after migration, 2) Software Dirty Page, which utilizes a hashing based approach to detect page modification, overcomes the commodity GPU's hardware limitation, and speeds up the migration by only sending the dirtied pages, 3) One-Shot Pre-Copy, which greatly reduces the rounds of pre-copy of graphics memory. Our evaluation shows that gMig achieves GPU live migration with an average downtime of 302 ms on Windows and 119 ms on Linux. With the help of Software Dirty Page, the number of GPU pages transferred during the downtime is effectively reduced by 80.0%.

Funder

National NSF of China

National Key Research & Development Program of China

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design,Software

Reference35 articles.

1. 2015. Intel graphics virtualization technology (intel gvt). https://01.org/igvt-g. (2015). 2015. Intel graphics virtualization technology (intel gvt). https://01.org/igvt-g. (2015).

2. 2016. AMD Multiuser GPU: Hardware-Enabled GPU Virtualization for a True Workstation Experience. http://www.amd.com/Documents/Multiuser-GPU-White-Paper.pdf. (2016). 2016. AMD Multiuser GPU: Hardware-Enabled GPU Virtualization for a True Workstation Experience. http://www.amd.com/Documents/Multiuser-GPU-White-Paper.pdf. (2016).

3. 2016. GRID VIRTUAL GPU User Guide. http://images.nvidia.com/content/grid/pdf/GRID-vGPU-User-Guide.pdf. (2016). 2016. GRID VIRTUAL GPU User Guide. http://images.nvidia.com/content/grid/pdf/GRID-vGPU-User-Guide.pdf. (2016).

4. 2016. Introducing Amazon EC2 P2 Instances the largest GPU-Powered virtual machine in the cloud. https://aws.amazon.com/aboutaws/whats-new/2016/09/introducing-amazon-ec2-p2-instances-the-largest-gpu-powered-virtual-machine-in-the-cloud/. (2016). 2016. Introducing Amazon EC2 P2 Instances the largest GPU-Powered virtual machine in the cloud. https://aws.amazon.com/aboutaws/whats-new/2016/09/introducing-amazon-ec2-p2-instances-the-largest-gpu-powered-virtual-machine-in-the-cloud/. (2016).

5. 2017. Elastic GPU Service. https://www.alibabacloud.com/product/gpu. (2017). 2017. Elastic GPU Service. https://www.alibabacloud.com/product/gpu. (2017).

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3