An Autonomic Self-management Mechanism for High-available Ubiquitous Computing System

고가용성 유비쿼터스 컴퓨팅 시스템을 위한 오토노믹 자가 관리 메커니즘

  • 최창열 (아주대학교 정보통신전문대학원) ;
  • 김성수 (아주대학교 정보통신전문대학원)
  • Published : 2005.12.01

Abstract

A ubiquitous computing system could be constructed not only with one computer but with networks of computers (or ether devices with computing power) embedded in everyday objects. For this, dependability must be guaranteed for each single component of a system and for the whole system which might be more than just a sum of its components. This paper proposes an autonomic self-management mechanism that ran operate for 24 hours/day with the minimum human intervention. In addition, we validate the autonomic fault management scheme based on a workload model derived from the system log analysis.

유비쿼터스 컴퓨팅은 네트워크로 상호연결된 프로세서로 구성되며, 하나 이상의 컴퓨터로 이루어진다. 따라서 한 시스템의 단일 컴포넌트 뿐만 아니라 전체 시스템의 가용도를 유지할 수 있어야만 한다. 본 연구에서는 사람의 간섭을 최소화하면서 예기치 못한 결함이 발생하여도 서비스를 지속적으로 제공할 수 있는 능력을 시스템에 부여하기 위한 오토노믹 자가 관리 기법을 제안하고 설계한다. 또한 시스템 로그 분석 결과를 통한 서비스 부하 모델을 근간으로 제안한 메커니즘의 효율성을 검증한다.

Keywords

References

  1. M. Satyanarayanan. 'Pervasive Computing: Visioin and Challenges,' IEEE Personal Communications, Aug, 2001 https://doi.org/10.1109/98.943998
  2. Sun_Microsystems: J2EE Platform Specification (2002) http://java.sun.com/j2ee/
  3. Microsoft: The Microsoft .NET Framework. Microsoft Press (2001)
  4. Garg S., Moorsel A., Vaidyanathan K, Trivedi K: A Methodology for Detection and Estimation of Software Aging. Proceedings of 9th IEEE International Symposium on Software Reliability Engineering (1998) 282-292 https://doi.org/10.1109/ISSRE.1998.730892
  5. Sullivan M., Chillarehe R: Software Defects and Their Impact on System Availability-A Study of Field Failures in Operating Systems. Proceedings of 21 st IEEE International Symposium on FaultTolerant Computing (1991) 2-9 https://doi.org/10.1109/FTCS.1991.146625
  6. Scott D.: Making Smart Investments to Reduce Unplanned Downtime. Tactical Guidelines Research Note TG-07-4033, Gartner Group (1999)
  7. Huang Y., Kintala C., Kolettis N., Fultion N.: Software Rejuvenation: Analysis, Module and Applications. Proceedings of 25th IEEE International Symposium on Fault-Tolerant Computing(1995) 318-390 https://doi.org/10.1109/FTCS.1995.466961
  8. Trivedi K., Vaidyanathan K., Popstojanova K.: Modeling and Analysis of Software Aging and Rejuvenation. Proceedings of IEEE 33rd Annual Simulation Symposium (2000) 270-279 https://doi.org/10.1109/SIMSYM.2000.844925
  9. Park K.. Kim S.: Availability Analysis and Improvement of Active/Standby Cluster Systems using Software Rejuvenation. The Journal of Systems Software, Vol. 61, No.2. (2002) 121-128 https://doi.org/10.1016/S0164-1212(01)00107-8
  10. Choi C, Kim S.: Self-configuring Algorithm for Software Fault Tolerance in (n, k)-way Cluster Systems. Lecture Notes in Computer Science, Springer, Vol. 2667, No. 1. (2003) 742-751
  11. J. Arlat, et al.: Dependability of COTS Microkernel-based Systems. IEEE Transactions on Computers, Vol. 51, No.2. (2002) 138-163 https://doi.org/10.1109/12.980005
  12. Lanfranchi G., et al.: Toward a New Landscape of Systems Management in An Autonomic Computing Environment. IBM System Journal, Vol. 42, No. 1. (2003) 119-128 https://doi.org/10.1147/sj.421.0119
  13. DMTF Inc.-Common Information Model. http://www.dmtf.org/standards/cim/
  14. 최창열, 김성수, '유비쿼터스 컴퓨팅 환경의 자동적인 결함 허용 기법 설계', 2004년 한국정보과학회 추계학술발표대회, 한국정보과학회, 31(2), pp. 379-381, 2004. 10
  15. Kleinrock, L..: Queueing Systems Volume I: Theory. Wiley (1975)
  16. H. Chen and P. Mohapatra, 'Session-Based Overload Control in QoS-Aware Web Servers,' IEEE INFOCOM 2002, pp. 516-524, June 2002 https://doi.org/10.1109/INFCOM.2002.1019296
  17. V. Cardellini, E. Casalicchio, M. Colajanni, and M. Mambelli, 'Web Switch Support for Differentiated Services,' ACM Performance Evaluation Reviews, Vol. 29, No.2, pp. 14-19,2001 https://doi.org/10.1145/572317.572320
  18. Crovell M. E. and Bestavros A.: Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes, IEEE/ ACM Transactions on Networking, Vol. 5, No.6. (1997) 835-846 https://doi.org/10.1109/90.650143