[1]赵旭,李艳梅,罗建,等.基于Docker容器动态迁移数据分流框架[J].西华师范大学学报(自然科学版),2019,40(02):210-216.[doi:10.16246/j.issn.1673-5072.2019.02.017]
 ZHAO Xu,LI Yanmei,LUO Jian,et al.A Data Distribution Framework Based onDocker Container Dynamic Migration[J].Journal of China West Normal University(Natural Sciences),2019,40(02):210-216.[doi:10.16246/j.issn.1673-5072.2019.02.017]
点击复制

基于Docker容器动态迁移数据分流框架

()
分享到:

《西华师范大学学报(自然科学版)》[ISSN:1673-5072/CN:51-1699/N]

卷:
40
期数:
2019年02期
页码:
210-216
栏目:
出版日期:
2019-06-20

文章信息/Info

Title:

A Data Distribution Framework Based onDocker Container Dynamic Migration

作者:

赵旭李艳梅罗建罗金梅

(西华师范大学 计算机学院,四川 南充637009)

Author(s):

ZHAO XuLI YanmeiLUO JianLUO Jinmei

(School of Computer Science,China West Normal University,Nanchong Sichuan 637009,China)

关键词:

数据分流Docker负载均衡动态迁移云计算

Keywords:

data distributionDockerload balancingdynamic migrationcloud computing

分类号:
TP399
DOI:
10.16246/j.issn.1673-5072.2019.02.017
文献标志码:
A
摘要:

在云平台技术迅速发展的环境下,服务器的负载、维护、能耗等问题严重影响了云平台资源的管理效率。为了提高云平台资源的管理效率,本文提出一种基于Docker容器动态迁移数据分流框架策略。首先,通过对Docker实现原理和底层技术的研究,借助进程迁移检查点恢复机制和pre-copy算法实现Docker动态迁移算法的优化设计;然后,借助第三方数据管理平台和数据分流传输的策略实现Docker容器动态迁移数据分流框架。最后实验结果证明,本文提出的框架提高了Docker动态迁移的效率,降低了Docker动态迁移的数据成本,有助于实现服务器的负载均衡和错误容忍,同时降低了服务器的维护难度和管理开销。

Abstract:

Under the environment of rapid developing cloud platform technology,the load,maintenance,and energy consumption of servers seriously affect the management efficiency of the cloud platform resources.To enhance the management efficiency of cloud platform resources,this paper proposes a strategy of data distribution framework based on Docker container dynamic migration.Firstly,through the research of Docker implementation principle and underlying technology,process migration checkpoint recovery mechanism and policy algorithm are used to obtain the optimal design of Docker dynamic migration algorithm.Secondly,the Docker container dynamic migration is realized by the third-party data management platform and data offload transmission strategy.Finally,the experimental results show that the framework proposed has improved the efficiency of Docker dynamic migration,reduced the data cost of Docker dynamic migration,helped to achieve server load balancins and error tolerance,and lowered the maintenance difficulty and management overhead of servers.

备注/Memo

备注/Memo:

收稿日期:2018-11-02
基金项目:国家自然科学基金项目(61731330);四川省教育厅自然科学重点项目(18ZA0468,14ZA0123);西华师范大学英才基金项目(17YC155,17YC157);四川省科技计划资助项目(2019YFG0299)
作者简介:赵  旭(1991—),男,四川达州人,硕士研究生,主要从事云计算与大数据处理研究。E-mail:121829374@qq.com
通信作者:李艳梅(1976—),女,四川宜宾人,博士,副教授,主要从事为计算机视觉、云计算机与大数据处理研究。E-mail:ymli@cwnu.edu.cn

更新日期/Last Update: 2019-06-25