Performance Analysis of Cloud Service Considering Reliability

Cloud computing is one technology developed for large-scale resource sharing and service-oriented computing. Since, cloud computing is a service-oriented computing, performance analysis of cloud service becomes an important issue. Due to the complexity of the cloud computing system, it is difficult to analyze the service performance. Although there exist some researches on cloud service, very few of them addressed the issues of reliability and its impact on service performance in the virtual resources pool constructed by heterogeneous physical resources. In order to analyze performance considering reliability, this paper presents a reliability-performance correlation model. By using the Markov model, the universal generating function and the Markov reward model, the correlation model first analyzes performance with considering physical machine failures and VM failures simultaneously in a heterogeneous environment. In addition, compared with traditional models, our model is realistic model that can support dividing a job into many subtasks (e.g., MapReduce). And the performance index of efficient service rate can be obtained. Numerical examples are presented to verify the validity of our model.

[1]  Kishor S. Trivedi.  Probability and Statistics with Reliability, Queuing, and Computer Science Applications , 1984 .

[2]  Jelena V. Misic,et al.  A Fine-Grained Performance Model of Cloud Computing Centers , 2013, IEEE Transactions on Parallel and Distributed Systems.

[3]  Xiaobo Zhou,et al.  Automated and Agile Server Parameter Tuning with Learning and Control , 2012, 2012 IEEE 26th International Parallel and Distributed Processing Symposium.

[4]  Yi Pan,et al.  A Hierarchical Modeling and Analysis for Grid Service Reliability , 2007, IEEE Transactions on Computers.

[5]  Yuan-Shun Dai,et al.  Performance evaluation of cloud service considering fault recovery , 2011, The Journal of Supercomputing.

[6]  Rajkumar Buyya,et al.  Article in Press Future Generation Computer Systems ( ) – Future Generation Computer Systems Cloud Computing and Emerging It Platforms: Vision, Hype, and Reality for Delivering Computing as the 5th Utility , 2022 .

[7]  Rajesh Gupta,et al.  Hardware/software co-design , 1996, Proc. IEEE.

[8]  Jon W. Mark,et al.  Approximation of the Mean Queue Length of an M/G/c Queueing System , 1995, Oper. Res..

[9]  Shigeru Yamada,et al.  Codesign-Oriented Performability Modeling for Hardware-Software Systems , 2011, IEEE Transactions on Reliability.

[10]  Sairaj V. Dhople,et al.  A Stochastic Hybrid Systems framework for analysis of Markov reward models , 2014, Reliab. Eng. Syst. Saf..

[11]  Dong Seong Kim,et al.  End-to-End Performability Analysis for Infrastructure-as-a-Service Cloud: An Interacting Stochastic Models Approach , 2010, 2010 IEEE 16th Pacific Rim International Symposium on Dependable Computing.

[12]  Randy H. Katz,et al.  A view of cloud computing , 2010, CACM.

[13]  Randy H. Katz,et al.  Above the Clouds: A Berkeley View of Cloud Computing , 2009 .

[14]  Jelena V. Misic,et al.  Performance Analysis of Cloud Computing Centers Using M/G/m/m+r Queuing Systems , 2012, IEEE Transactions on Parallel and Distributed Systems.

[15]  James MacGregor Smith,et al.  M/G/c/K blocking probability models and system performance , 2003, Perform. Evaluation.

[16]  Xiaodong Liu,et al.  A queuing model considering resources sharing for cloud service performance , 2015, The Journal of Supercomputing.