Abstract

Active-passive cluster systems are commonly used in distributed computing to improve system availability and fault tolerance. In this work, Semi-Markov model is used to analyze the availability and dependability of the system. A state transition diagram is used to represent the state behavior which includes active unit failure, standby unit failure, coverage, and failure detection. System availability is evaluated by calculating the steady-state probabilities. The impact of the active unit failure rate on availability is analyzed using parametric evaluation and graphical results. The results show us that the availability decreases when the failure rate increases, which highlights the importance of component reliability. The model presented can help in the design and evaluation of highly available cluster system.

References

• D. Clitherow, M. Brookbanks, N. Clayton, and G. Spear, "Combining High Availability and Disaster Recovery Solutions for Critical IT Environments," IBM Systems Journal, vol. 47, no. 4, pp. 563–575, 2008.
• D. Chen and K. S. Trivedi, "Optimization for Condition-Based Maintenance with Semi-Markov Decision Process," Reliability Engineering & System Safety, 2005.
• S. W. Hunter and W. E. Smith, "Availability Modeling and Analysis of a Two Node Cluster," in Proc. International Conference on Information Systems, 1999.
• Th. Lumpp et al., "From High Availability and Disaster Recovery to Business Continuity Solutions," IBM Systems Journal.
• M. Malhotra and A. Reibman, "Selecting and Implementing Phase Approximations for Semi-Markov Models," IEEE Transactions on Reliability, 1993.
• G. F. Pfister, In Search of Clusters: The Coming Battle in Lowly Parallel Computing. Prentice Hall, 1998.
• H. Song, C. Leangsuksun, and R. Nassar, "Availability Modeling and Evaluation on High Performance Cluster Computing Systems," Journal of Research and Practice in Information Technology, 2006.
• K. S. Trivedi, R. Vasireddy, D. Trindade, S. Nathan, and R. Castro, "Modeling High Availability Systems," Pacific Rim Dependability Conference, 2006.
• K. S. Trivedi, Probability and Statistics with Reliability, Queueing and Computer Science Applications. John Wiley & Sons, 2002.
• A. L. Reibman, "Modeling the Effect of Reliability on Performance," IEEE Transactions on Reliability.
• E. J. Henley and H. Kumamoto, Probabilistic Risk Assessment: Reliability Engineering, Design, and Analysis. IEEE Press, 1992.
• S. A. Doyle, J. B. Dugan, and M. A. Boyd, "Combinatorial Models and Coverage: A Binary Decision Diagram Approach," Reliability and Maintainability Symposium.
• S. A. Doyle, J. B. Dugan, and M. A. Boyd, "Combining Imperfect Coverage with Digraph Models."
• J. B. Dugan, B. Venkataraman, and R. Gulati, "DIFtree: A Software Package for the Analysis of Dynamic Fault Tree Models."
• R. Gulati and J. B. Dugan, "A Modular Approach for Analyzing Static and Dynamic Fault Trees."
• J. B. Dugan, K. S. Trivedi, M. K. Smotherman, and R. M. Geist, "The Hybrid Automated Reliability Predictor."
• G. Ciardo, "Analysis of Large Stochastic Petri Net Models."
• M. A. Boyd, "Converting Fault Trees to Markov Chains for Reliability Prediction."
• S. J. Bavuso and J. B. Dugan, "HiRel: Reliability/Availability Integrated Workstation Tool."
• T. T. Lwin and T. Thein, "High Availability Cluster System for Local Disaster Recovery with Markov Modeling Approach."