云计算环境下的可修分布式系统可靠性分析方法

计算机与现代化 ›› 2020, Vol. 0 ›› Issue (06): 28-.

云计算环境下的可修分布式系统可靠性分析方法

（1.贵州大学计算机科学与技术学院,贵州贵阳550025；2.贵州省公共大数据重点实验室,贵州贵阳550025）

收稿日期:2020-02-06 出版日期:2020-06-24 发布日期:2020-06-28
作者简介:杨牧川(1995-),男,四川广元人，硕士研究生，研究方向：云计算，E-mail: morchyang@qq.com；吕晓丹（1970-），男，上海人，副教授，硕士，研究方向：云计算，数据分析，E-mail: lvxiaodan111@126.com；蒋朝惠（1965-），男，四川广安人，教授，硕士，研究方向：云计算，信息安全，软件工程，E-mail: jiangchaohui@126.com。
基金资助:
贵州省科技计划资助项目（黔科合基础［2017］1051）

Reliability Analysis Method for Repairable Distributed System in Cloud Compute Environment

（1. College of Computer Science and Technology, Guizhou University, Guiyang 550025, China；
2. Guizhou Provincial Key Laboratory of Public Big Data, Guiyang 550025, China）

Received:2020-02-06 Online:2020-06-24 Published:2020-06-28

摘要/Abstract

摘要： 随着云计算技术的进一步发展，越来越多的应用系统托管在云计算平台上，这就对构成云计算平台的众多分布式系统的可靠性提出了更高的要求。传统分析方法难以在系统规模较大时对可修分布式系统做可靠性分析。为了提高服务质量以及降低因违反服务水平协议而导致的经济损失，本文基于马尔可夫模型提出一种适用于可修分布式系统的可靠性分析方法。通过简化系统的状态空间，在系统运行期间对其软硬件状态进行采样，并通过对分布式系统的失效过程和修复过程进行分析，根据给定时间内的失效概率序列、修复概率序列计算分布式系统的节点状态转移矩阵，得出该马尔可夫矩阵对应的稳态向量。根据特定分布式系统的自身特性，对该稳态向量进一步分析，得出系统最终的可靠性衡量指标。最后通过实验验证了该方法的可用性和有效性。

关键词: 可靠性, 分布式系统, 马尔可夫模型

Abstract: With the further development of cloud computing technology, more and more application systems are hosted on cloud computing platforms, which puts forward higher requirements for the reliability of the many distributed systems that make up a cloud computing platform. It is difficult for traditional analysis methods to analyze the reliability of repairable distributed system when the system scale is large and dynamic. In order to improve service quality and reduce economic losses caused by violation of service level agreements, this paper proposes a reliability analysis method for repairable distributed systems based on Markov models. By simplifying the state space of the system, the software and hardware states are sampled during the system operation, and the failure process and repair process of the distributed system are analyzed. According to the failure probability sequence and repair probability sequence in a given time, the node state transition matrix of the distributed system is calculated, and the steady-state vector corresponding to the Markov matrix is obtained. Then according to the characteristics of the distributed system, the steady-state vector is further analyzed to obtain the final reliability measurement index of the system. Finally, the validity and effectiveness of the method are verified by experiments.

Key words: reliability, distributed system, Markov model

中图分类号:

TP301.6

杨牧川, 吕晓丹, 蒋朝惠, . 云计算环境下的可修分布式系统可靠性分析方法[J]. 计算机与现代化, 2020, 0(06): 28-.

YANG Mu-chuan, LYU Xiao-dan, JIANG Chao-hui, . Reliability Analysis Method for Repairable Distributed System in Cloud Compute Environment[J]. Computer and Modernization, 2020, 0(06): 28-.

参考文献

［1］ FOSTER I, ZHAO I, RAICU I, et al. Cloud computing and grid computing 360-degree compared［C］// 2008 Grid Computing Environments Workshop. 2008:1-10.
［2］段文雪,胡铭,周琼，等. 云计算系统可靠性研究综述［J］. 计算机研究与发展, 2020,57(1):102-123.
［3］ SHRESTHA R. High availability and performance of database in the cloud：Traditional master-slave replication versus modern cluster-based solutions［C］// International Conference on Cloud Computing and Services Science. 2017:413-420.
［4］ AHMED W, WU Y W. A survey on reliability in distributed systems［J］. Journal of Computer and System Sciences, 2013,79(8):1243-1255.
［5］周平. 云服务可用性和可靠性测评与优化方法［D］. 北京:北京邮电大学, 2019.
［6］陈康,郑纬民. 云计算:系统实例与研究现状［J］. 软件学报, 2009,20(5):1337-1348.
［7］ PARK M, JUNG K M, PARK D H. Optimal post-warranty maintenance policy with repair time threshold for minimal repair［J］. Reliability Engineering & System Safety, 2013,111:147-153.
［8］ MONTORO-CAZORLA D, PREZ-OCN R. A reliability system under different types of shock governed by a Markovian arrival process and maintenance policy K［J］. European Journal of Operational Research, 2014,235(3):636-642.
［9］ LIU B L, CUI L R, WEN Y Q. Interval reliability for aggregated Markov repairable system with repair time omission［J］. Annals of Operations Research, 2014,212(1):169-183.
［10］DU S J, ZENG Z G, CUI L R, et al. Reliability analysis of Markov history-dependent repairable systems with neglected failures［J］. Reliability Engineering & System Safety, 2017,159:134-142.

［11］张建华,张文博,徐继伟,等. 一种基于隐马尔可夫模型的虚拟机失效恢复方法［J］. 软件学报, 2014,25(11):2702-2714.

［12］吴佳,曾惟如,陈瀚霖,等. 基于隐马尔可夫模型的软件状态评估预测方法［J］. 软件学报, 2016,27(12):3208-3222.
［13］CUI L R, LI H J, LI J L. Markov repairable systems with history-dependent up and down states［J］. Stochastic Models, 2007,23(4):665-681.
［14］WANG L Y, CUI L R. Aggregated semi-Markov repairable systems with history-dependent up and down states［J］. Mathematical and Computer Modelling, 2011,53(5-6):883-895.
［15］WANG W G, DU S J, CUI L R. Multi-point and multi-interval availabilities for Markov repairable systems with history-dependent up and down states［J］. Journal of Shanghai Jiaotong University(Science), 2015,20(3):349-352.
［16］QIU Q G, CUI L R, SHEN J Y. Availability analysis and maintenance modelling for inspected Markov systems with down time threshold［J］. Quality Technology & Quantitative Management, 2019,16(4):478-495.
［17］DAI Y S, PAN Y, ZOU X K. A hierarchical modeling and analysis for grid service reliability［J］. IEEE Transactions on Computers, 2007,56(5):681-691.
［18］CHEN D J, SHENG M C, HORNG M S. Real-time distributed program reliability analysis［C］// IEEE Symposium on Parallel & Distributed Processing. 1993:771-778.
［19］DAI Y S, XIE M, POH K L. Reliability analysis of grid computing systems［C］// IEEE Pacific Rim International Symposium on Dependable Computing. 2002:97-104.
［20］VISHWANATH K V, NAGAPPAN N. Characterizing cloud computing hardware reliability［C］// Proceedings of the 1st ACM Symposium on Cloud Computing. 2010:193-204.
［21］KIM H, LEE H, KIM W, et al. A trust evaluation model for QoS guarantee in cloud computing［J］. International Journal of Grid and Distributed Computing, 2010,3(1):1-10.
［22］DAI Y S, YANG B, DONGARRA J, et al.Cloud service reliability: Modeling and analysis［C］// The 15th IEEE Pacific Rim International Symposium on Dependable Computing. 2009:1-17.
［23］THANAKORNWORAKIJ T, NASSAR R F, LEANGSUKSUN C, et al.A reliability model for cloud computing for high performance computing applications［C］// European Conference on Parallel Processing. 2012:474-483.
［24］YADAV N, SINGH V B, KUMARI M.Generalized reliability model for cloud computing［J］. International Journal of Computer Applications, 2014,88(14):13-16.
［25］XIE M, DAI Y S, POH K L. Computing System Reliability: Models and Analysis［M］. Springer Science & Business Media, 2004.
［26］WEIL S A, BRANDT S A, MILLER E L, et al. Ceph: A scalable, high-performance distributed file system［C］// Proceedings of the 7th Symposium on Operating Systems Design and Implementation. 2006:307-320.

[1]	陈超, 顾青峰. 面向混合负载的分布式气象数据管理系统设计[J]. 计算机与现代化, 2023, 0(12): 118-122.
[2]	姜厚海, 庄毅, 曹子宁. 一种基于改进BDD的SDN可靠性评估算法[J]. 计算机与现代化, 2023, 0(09): 64-69.
[3]	管金平, 杨晋吉, 杨成龙. 基于概率模型的Raft协议形式化验证[J]. 计算机与现代化, 2023, 0(09): 77-81.
[4]	王颖颖, 庄毅, 孙逸帆. 基于粒子群优化BP神经网络的可靠性评估模型[J]. 计算机与现代化, 2022, 0(12): 42-49.
[5]	袁嘉立, 刘梦赤. 面向信息网模型的动态数据划分算法[J]. 计算机与现代化, 2022, 0(10): 100-105.
[6]	王骞，闫夏莉，叶崛宇，张海阔，李真辉 . 面向权威DNS的数据一致性保障机制[J]. 计算机与现代化, 2020, 0(02): 36-.
[7]	麻朴方1,2，王劲林1,2，尤佳莉1,2. 一种基于马尔可夫模型的加速ICN路径收敛性的方法[J]. 计算机与现代化, 2020, 0(01): 28-.
[8]	卫津逸，徐珞，戴文博. 基于脆弱点分析的故障注入技术[J]. 计算机与现代化, 2019, 0(12): 39-.
[9]	李思雨 . 基于极限学习机的组合软件可靠性模型研究[J]. 计算机与现代化, 2019, 0(11): 44-.
[10]	韦海龙,孙宁,张杰,武张. 水声传感网中基于网络编码的协作传输算法[J]. 计算机与现代化, 2019, 0(06): 24-.
[11]	王关祥,李义勇,夏亚东,王志献. 基于多层次评价模型的高校网络运行可靠性分析[J]. 计算机与现代化, 2019, 0(06): 98-.
[12]	肖楚琬1，邓力2，张真3. 无失效数据机载多余度EWIS可靠性研究[J]. 计算机与现代化, 2019, 0(04): 98-.
[13]	郭鑫，闫连山，李洪赭，张晓薇. 基于SD-WSN的高危仓储无线监测系统[J]. 计算机与现代化, 2018, 0(10): 84-.
[14]	张志国. 基于工业以太网的高速列车通信网络仿真[J]. 计算机与现代化, 2017, 0(9): 1-6.
[15]	刘维维，庄毅，李蜜. 一种嵌入式软件可靠性建模与评估方法[J]. 计算机与现代化, 2017, 0(8): 78-.