期刊文献+

I/O密集型虚拟机的域间通信优化方法 被引量:2

Inter-domain Communication Optimization Method of I/O Intensive Virtual Machines
下载PDF
导出
摘要 I/O密集型虚拟机需要频繁地进行域间通信,为解决现有虚拟机域间通信效率低、延迟大的问题,提出一种基于双环形缓冲区的用户域与驱动域域间通信优化方法。在用户域中建立与驱动域共享的双环形缓冲区,由虚拟机监控器依据I/O任务表对驱动域的访问权限进行控制,减少处理器模式切换和内存映射开销。实验结果表明,与原虚拟机域间通信机制相比,使用该优化方法后的域间通信机制具有更高的吞吐率和更低的延迟,大幅提高了用户域与驱动域的域间通信性能。 The virtual machines which are I/O intensive need to communicate with each other frequently.In order to solve the problems of low efficiency and big latency in inter-domain communication of virtual machines,an inter-domain communiaction optimization method between driver domain and user domain based on Double Ring Buffer (DRB) is proposed.Two ring buffers in user domain are built to be shared with a driver domain,and the access rights of the driver domain is controlled by the virtual machines monitor according to I/O task tables,which reduces the overhead of processor mode switching and memory mapping.Experimental results show that the inter-domain communication mechanism after using the optimization method has higher throughput and lower delay compared with original interdomain virtual machine communication mechanism,and it greatly improves the inter-domain communication performance of the user domain and drive domain.
出处 《计算机工程》 CAS CSCD 北大核心 2017年第1期1-7,共7页 Computer Engineering
基金 国家"973"计划项目(2011CB311801)
关键词 I/O密集型虚拟机 域间通信 双环形缓冲区 共享内存 授权表 I/O intensive virtual machine inter-domain communication shared memory grant table
  • 相关文献

参考文献4

二级参考文献50

  • 1董耀祖,周正伟.基于X86架构的系统虚拟机技术与应用[J].计算机工程,2006,32(13):71-73. 被引量:63
  • 2英特尔开源软件技术中心,复旦大学并行处理研究所.系统虚拟化--原理与实现[M].北京:清华大学出版社,2009.
  • 3Meergen M F, Uhlig V, Krieger O, et al. Virtualization for high-performance computing[J]. ACM SIGOPS Operating Systems Review, 2006, 40(2): 8-11.
  • 4Barham P, Dragovic B, Fraser K, et al. Xen and the art of virtualization[C]//Proceedings of the 19th ACM Sympo- sium on Operating Systems Principles (SOSP '03). NewYork, NY, USA: ACM, 2003: 164-I77.
  • 5Zhang Xiaolan, Mclntosh S, Rohatgi P, et al. XenSocket: a high-throughput interdomain transport for virtual ma- chines[C]//Proceedings of the ACM/IFIP/USENIX 2007 International Conference on Middleware (Middleware '07). New York, NY, USA: Springer-Verlag New York, Ir~c, 2007: 184-203.
  • 6Wang Jian, Wright K-L, Gopalan K. XenLoop: a trans- parent high performance inter-VM network loopback[C]// Proceedings of the 17th International Symposium on High Performance Distributed Computing (HPDC '08), Boston, Massachussets, June 2008. New York, NY, USA: ACM, 2008: 109-118.
  • 7Burtse A, Srinivasan K, Radhakrishnan R et al. Fido: fast inter-virtual-machine communication for enterprise appli- ances[C]//Proceedings of the 2009 USENIX Annual Tech- nical Conference (USENIX '09), San Diego, June 2009. Berkeley, CA, USA: USENIX Association, 2009: 25.
  • 8Bellard F. QEMU, a fast and portable dynamic transla- tor[C]//Proceedings of the 2005 USENIX Annual Tech- nical Conference (USENIX '05), Marriott Anaheimm, April 2005. Berkeley, CA, USA: USENIX Association, 2005: 41.
  • 9Kivity A, Kamay Y, Laor D, et al. KVM: the Linux virtual machine monitor[C]//Proceedings of the Linux Sympo- sium, Ottawa, Ontario, 2007: 225-230.
  • 10Li Shengzhao, Hao Qinfen, Xiao Limin, et al. Optimizing network virtualization in kernel-based virtual machine[C]// Proceedings of the 1st IEEE International Conference on Information Science and Engineering (ICISE '09). Wash- ington, DC, USA: 1EEE Computer Society, 2009: 282- 285.

共引文献19

同被引文献26

引证文献2

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部