基于预传输的虚拟机双机热备可用性研究

doi:10.3969/j.issn.1000-3428.2012.15.006

计算机工程 ›› 2012, Vol. 38 ›› Issue (15): 20-22,27. doi: 10.3969/j.issn.1000-3428.2012.15.006

基于预传输的虚拟机双机热备可用性研究

郑志蕴?，任振芳，李钝，李伦

(郑州大学信息工程学院，郑州 450001)

收稿日期:2012-02-20 出版日期:2012-08-05 发布日期:2012-08-05
作者简介:郑志蕴(1962－)，女，教授、博士，主研方向：虚拟化，分布式计算；任振芳，硕士；李钝，讲师、博士；李伦，讲师、硕士
基金资助:
河南省自然科学基金资助项目(2008A520025, 2010A520039)

Research on Availability of Virtual Machine Hot Standby Based on Pre-transfer

ZHENG Zhi-yun, REN Zhen-fang, LI Dun, LI Lun

(School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China)

Received:2012-02-20 Online:2012-08-05 Published:2012-08-05

摘要/Abstract

摘要：

针对虚拟机双机热备中传统拷贝技术导致的虚拟机低可用性问题，提出一种基于分段挑选最近未使用(SSNUR)算法的预传输方法。在虚拟机运行阶段预先传输被使用的内存页，减少停机阶段需要拷贝的内存页数量，使用SSNUR算法挑选预传输页面，以降低预传输和停机传输的重复率。实验结果表明，与XEN4.0中典型的虚拟机双机热备系统Remus相比，基于预传输的Remus系统在重负载和长间隔时间状态下停机时间明显减少，最高可达23.37%。

关键词: 虚拟机, 双机热备, 可用性, XEN技术, 预传输, Remus系统

Abstract:

A pre-transfer method based on Segment Selection Not Used Recently(SSNUR) algorithm is presented to solve low availability caused by the traditional copy technology in the virtual machine hot standby. The used memory pages are pre-transferred in the running phase of the virtual machine, in order to reduce the number of memory pages to copy in the shutdown phase, and SSNUR algorithm is proposed to select the pages need to copy in order to reduce the repetition rate of pre-transfer and stop-transfer. Experimental results show that the pre-transfer Remus compred with the original method has obvious advantages when the virtual machines have heavy load and long intervals, and downtime can be reduced up to 23.37%.

Key words: virtual machine, hot standby, availability, XEN technology, pre-transfer, Remus system

中图分类号:

TP319

郑志蕴?, 任振芳, 李钝, 李伦. 基于预传输的虚拟机双机热备可用性研究[J]. 计算机工程, 2012, 38(15): 20-22,27.

ZHENG Zhi-Wen-?, LIN Zhen-Fang, LI Dun, LI Lun. Research on Availability of Virtual Machine Hot Standby Based on Pre-transfer[J]. Computer Engineering, 2012, 38(15): 20-22,27.

https://www.ecice06.com/CN/Y2012/V38/I15/20

参考文献

[1] 金海. 计算系统虚拟化——原理与应用[M]. 北京: 清华大学出版社, 2008.
[2] Malik S, Huet F. Adaptive Fault Tolerance in Real Time Cloud Computing[C]//Proc. of IEEE World Congress on Services. Washington D. C., USA: IEEE Press, 2011.
[3] 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.
[4] Liu Haikun, Jin Hai, Liao Xiaofei. Optimize Performance of Virtual Machine Checkpointing via Memory Exclusion[C]//Proc. of the 4th China Grid Annual Conference. Yantai, China: IEEE Press, 2009.
[5] Ibrahim K, Hofmeyr S, Iancu C, et al. Optimized Pre-copy Live Migration for Memory Intensive Applications[C]//Proc. of International Conference for High Performance Computing, Networking, Storage and Analysis. Seattle, USA: IEEE Press, 2011.
[6] Lu Maohua, Chiueh T. Fast Memory State Synchronization for Virtualization-based Fault Tolerance[C]//Proc. of IEEE/IFIP International Conference on Dependable Systems and Networks. Lisbon, Portugal: IEEE Press, 2009.
[7] Cully B, Lefebvre G, Meyer D, et al. Remus: High Availability via Asynchronous Virtual Machine Replication[C]//Proc. of the 5th USENIX Symposium on Networked Systems Design and Implementation. San Francisco, USA: USENIX Press, 2008.
[8] Tamura Y, Sato K, Kihara S, et al. Kemari: Virtual Machine Synchronization for Fault Tolerance[C]//Proc. of USENIX Annual Technical Conference. Boston, USA: USENIX Press, 2008.
[9] Cui Wenchao, Ma Dianfu, Wo Tianyu. Enhancing Reliability for Virtual Machines via Continual Migration[C]//Proc. of Interna- tional Conference on Parallel and Distributed Systems. Shenzhen, China: IEEE Press, 2009.
[10] Zhu Jun, Dong Wei, Jiang Zhefu. Improving the Performance of Hypervisor-based Fault Tolerance[C]//Proc. of the 26th IEEE International Parallel and Distributed Processing Symposium. Shanghai, China: IEEE Press, 2010.
[11] Sun M H, Blough D M. Fast, Lightweight Virtual Machine Checkpointing[D]. Atlanta, USA: Georgia Institute of Technology, 2010.
[12] Liu Haikun, Jin Hai, Liao Xiaofei, et al. Live Virtual Machine Migration via Asynchronous Replication and State Synchroni- zation[J]. IEEE Transactions on Parallel and Distributed Systems, 2011, 22(12): 1986-1999.
[13] Barham P, Dragovic B, Fraser K, et al. Xen and the Art of Virtualization[C]//Proc. of the 19th ACM Symposium on Operating Systems Principles. New York, USA: ACM Press, 2003.

[1]	赵徐炎, 崔允贺, 钱清, 郭春, 申国伟. 基于虚拟扩展网络的虚拟机及路由路径联合部署[J]. 计算机工程, 2023, 49(8): 154-162.
[2]	汪小勇, 董德存, 欧冬秀. 车载TBTC-CBTC系统降级场景下的CPN建模与仿真[J]. 计算机工程, 2022, 48(7): 189-198.
[3]	谷青竹, 董红斌. PPDM中面向k-匿名的MI Loss评估模型[J]. 计算机工程, 2022, 48(4): 143-147.
[4]	高子轩, 郑烇. NDMANET中基于内容优先级的缓存策略研究[J]. 计算机工程, 2021, 47(3): 190-195.
[5]	俞庆英, 王燕飞, 叶梓彤, 张双桂, 陈传明. 基于优化局部抑制的轨迹数据发布隐私保护算法[J]. 计算机工程, 2020, 46(8): 112-118.
[6]	孙志勇, 季新生, 游伟, 李英乐. 一种基于冗余跳变的虚拟机动态迁移方法[J]. 计算机工程, 2020, 46(2): 21-27,34.
[7]	梅浩, 代红兵, 刘静. 嵌入式Forth操作系统多任务空间复用算法[J]. 计算机工程, 2020, 46(1): 208-215,221.
[8]	臧韦菲,兰巨龙,胡宇翔,陈文涛. 基于多目标离散差分进化的网络感知虚拟机放置算法[J]. 计算机工程, 2019, 45(6): 96-102.
[9]	郭良敏,高俊杰,胡桂银. 一种基于机器学习的虚拟机放置方法[J]. 计算机工程, 2019, 45(5): 135-142.
[10]	谭宏楠,石京燕,邹佳恒,杜然,姜晓巍,孙震宇. 应用于JUNO实验的容器技术研究[J]. 计算机工程, 2019, 45(4): 1-5.
[11]	刘开南. 云数据中心基于任务映射的虚拟机选择策略[J]. 计算机工程, 2019, 45(10): 33-39.
[12]	全力,傅明. 云计算中任务调度优化策略的研究[J]. 计算机工程, 2018, 44(8): 14-18.
[13]	王小强,顾乃杰. 基于操作码合并的Python程序防逆转算法[J]. 计算机工程, 2018, 44(5): 113-118.
[14]	丁祥武,张东辉. Hadoop平台的安全加固方案[J]. 计算机工程, 2018, 44(12): 94-101.
[15]	王正,许德武,韩建民,鲁剑锋. 一种高阶权限指派约束的安全性与一致性验证[J]. 计算机工程, 2018, 44(1): 171-175,181.

选择文件类型/文献管理软件名称

选择包含的内容

基于预传输的虚拟机双机热备可用性研究

Research on Availability of Virtual Machine Hot Standby Based on Pre-transfer

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于预传输的虚拟机双机热备可用性研究

Research on Availability of Virtual Machine Hot Standby Based on Pre-transfer

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价