浏览全部资源
扫码关注微信
面向网络性能优化的虚拟计算资源调度机制研究
Study on virtual computing resource scheduling for network performance optimization
- 通信学报 2016年37卷第8期 页码：105-118
- 作者机构：
1. 中国科学院计算技术研究所，北京
2. 中国科学院大学，北京 100049
3. 中国联合网络通信集团有限公司，北京 100032
1.1.中国科学院计算技术研究所，北京 100190;2.中国科学院大学，北京 100049;3.中国联合网络通信集团有限公司，北京 100032
- 作者简介：
[ "王煜炜（1980-），男，河北唐山人，中国科学院博士生、助理研究员，主要研究方向为未来网络、虚拟化技术和云计算。" ]
[ "刘敏（1976-），女，河南郑州人，博士，中国科学院研究员、博士生导师，主要研究方向为移动管理、网络测量和移动计算。" ]
[ "房秉毅（1980-），男，山东泰安人，博士，中国联合网络通信集团有限公司高级工程师，主要研究方向为下一代网络、移动核心网和云计算。" ]
[ "秦晨翀（1991-），男，山西临汾人，中国科学院硕士生，主要研究方向为虚拟化技术、下一代网络、移动计算。" ]
[ "闫小龙（1990-），男，安徽阜阳人，中国科学院硕士生，主要研究方向为虚拟化技术、下一代网络、移动计算。" ]
- 基金信息：国家自然科学基金资助项目;The National Natural Science Foundation of China(61132001);国家自然科学基金资助项目;The National Natural Science Foundation of China(61120106008);国家自然科学基金资助项目;The National Natural Science Foundation of China(61472402);国家自然科学基金资助项目;The National Natural Science Foundation of China(61472404);国家自然科学基金资助项目;The National Natural Science Foundation of China(61272474);国家自然科学基金资助项目;The National Natural Science Foundation of China(61202410)
DOI：10.11959/j.issn.1000-436x.2016161
中图分类号： TP302-
网络出版日期：2016-08，
纸质出版日期：2016-08-58
- 稿件说明：
移动端阅览
王煜炜, 刘敏, 房秉毅, 等. 面向网络性能优化的虚拟计算资源调度机制研究[J]. 通信学报, 2016,37(8):105-118.
Yu-wei WANG, Min LIU, Bing-yi FANG, et al. Study on virtual computing resource scheduling for network performance optimization[J]. Journal on communications, 2016, 37(8): 105-118.
王煜炜, 刘敏, 房秉毅, 等. 面向网络性能优化的虚拟计算资源调度机制研究[J]. 通信学报, 2016,37(8):105-118. DOI： 10.11959/j.issn.1000-436x.2016161.
Yu-wei WANG, Min LIU, Bing-yi FANG, et al. Study on virtual computing resource scheduling for network performance optimization[J]. Journal on communications, 2016, 37(8): 105-118. DOI： 10.11959/j.issn.1000-436x.2016161.
摘要
针对基于Xen的vCPU调度机制对虚拟机网络性能的影响进行了深入研究和分析。提出一种高效、准确、轻量级的网络排队敏感类型虚拟机（NSVM）识别方法，可根据当前虚拟机I/O传输特征将容易受到影响的虚拟机进行准确识别和区分。进而设计一种新型虚拟计算资源调度和分配机制 Diff-Scheduler，将不同类型虚拟机的vCPU实施分池隔离调度，同时提高NSVM类型虚拟机vCPU的调度频率。原型系统实验结果表明，相比Xen默认的调度机制，Diff-Scheduler能够大幅提高虚拟机网络性能，同时保证计算资源分配的公平性。
Abstract
A deep insight into the relationship between vCPU scheduling and I/O transmit in Xen was provided.Then an effective and lightweight recognition method
through which could identify the so-called NSVM (network queuing sensi-tive virtual machine) that was more vulnerable to the congestion in I/O transmit was put forward.Furthermore
a novel mechanism for resource assignment and scheduling called Diff-Scheduler was proposed.It could schedule the vCPU of the NSVM more frequently than other VM in different pools independently.Evaluations based on a prototype of Xen platform featured Diff-Scheduler show that the proposed mechanism significantly improves the network performance of VM.Specifically
comparing with the default mechanism of Xen
Diff-Scheduler proposed jointly enhances throughput
latency remarkably and ensures the fairness of resource allocation at the same time.
关键词
Keywords
references
Amazon elastic compute cloud [EB/OL ] . http://aws.amazon.com/ec2/. http://aws.amazon.com/ec2/. .
Google cloud platform [EB/OL ] . http://cloud.google.com. http://cloud.google.com. .
Microsoft server and cloud platform [EB/OL ] . http://www.microsoft. http://www.microsoft. .
Aliyun.com [EB/OL ] . http://appcloud.aliyun.com. http://appcloud.aliyun.com. .
Wo cloud [EB/OL ] . http://www.wocloud.cn. http://www.wocloud.cn. .
Ecloud [EB/OL ] . http://ecloud.10086.cn/. http://ecloud.10086.cn/. .
E Cloud [EB/OL ] . http://www.ctyun.cn/. http://www.ctyun.cn/. .
The XEN project [EB/OL ] . http://www.xenproject.org/. http://www.xenproject.org/. .
OSTERMANN S , IOSUP A , YIGITBASI N , et al . A performance analysis of EC2 cloud computing services for scientific comput-ing [C ] // International Conference on Cloud Computing . c 2010 : 115 - 131 .
WHITEAKER J , SCHNEIDER F , TEIXEIRA R . Explaining packet delays under virtualization [J ] . ACM Sigcomm Computer Communica-tion Review , 2011 , 41 ( 1 ): 38 - 44 .
WANG G , NG T . The impact of virtualization on network performance of amazon EC2 data center [C ] // The 29th IEEE International Confer-ence on Computer Communications . c 2010 : 1 - 9 .
SHEA R , WANG F , WANG H , et al . A deep investigation into network performance in virtual machine based cloud environments [C ] // The 33th IEEE International Conference on Computer Communications . c 2014 : 1285 - 1293 .
GAMAGE S , KANGARLOU A , KOMPELLA R R , et al . Opportunis-tic flooding to improve TCP transmit performance in virtualized clouds [C ] // The 2nd ACM Symposium on Cloud Computing . c 2011 : 24 - .
KANGARLOU A , GAMAGE S , KOMPELLA R R , et al . vSnoop:improving TCP throughput in virtualized environments via acknowl-edgement offload [C ] // The 2010 ACM/IEEE International Conference for High Performance Computing,Networking,Storage and Analysis . c 2010 : 1 - 11 .
XU C , GAMAGE S , RAO P N , et al . vSlicer:latency-aware virtual machine scheduling via differentiated-frequency CPU slicing [C ] // The 21st International Symposium on High-Performance Parallel and Dis-tributed Computing . c 2012 : 3 - 14 .
XU Y , MUSGRAVE Z , NOBLE B , et al . Bobtail:avoiding long tails in the cloud [C ] // The USENIX Conference on Network Systems De-sign and Implementation . c 2013 : 329 - 341 .
XU Y . Characterizing and mitigating virtual machine interference in public clouds [D ] . Michigan:University of Michigan , 2014 .
XU Y , BAILEY M , NOBLE B , et al . Small is better:avoiding latency traps in virtualized data centers [C ] // The 4th Annual Symposium on Cloud Computing . c 2013 .
Credit2 scheduler [EB/OL ] . http://wiki.xen.org/wiki/Credit2_Scheduler_Development#Status http://wiki.xen.org/wiki/Credit2_Scheduler_Development#Status .
Iperf [EB/OL ] . http://iperf.sourceforge.net/ http://iperf.sourceforge.net/ .
Sysbench [EB/OL ] . http://sysbench.sourceforge.net/ http://sysbench.sourceforge.net/ .
0
浏览量
1
下载量
0
CSCD
- 网络PDF下载
- XML下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
- 总访问量：127741 今日访问量：6