Advertisement

Science China Information Sciences

, Volume 56, Issue 8, pp 1–15 | Cite as

Detecting performance anomaly with correlation analysis for Internetware

  • Tao Wang
  • Jun WeiEmail author
  • Feng Qin
  • WenBo Zhang
  • Hua Zhong
  • Tao Huang
Research Paper Special Focus

Abstract

Internetware has become an emerging software paradigm to provide Internet services. The performance anomaly of Internetware services not only affects user experience, but also causes severe economic loss to service providers. Diagnosing performance anomalies has become one of the keys to improving the quality of service (QoS) of Internetware. Existing approaches create a system model to predict performance. Then, the prediction from the model is compared with the observation; a significant deviation may signal the occurrence of a performance anomaly. However, these approaches require domain knowledge and parameterization efforts. Moreover, dynamic workloads affect the accuracy of performance prediction. To address these issues, we propose a correlation analysis based approach to detecting the performance anomaly for Internetware. We use kernel canonical correlation analysis (KCCA) to model the correlation between workloads and performance based on monitoring data. Furthermore, we detect anomalous correlation coefficients by XmR control charts, which detect the anomalous coefficient and trend without a priori knowledge. Finally, we adopt a feature selection method (Relief) to locate the anomalous metrics. We evaluated our approach on a testbed running the TPC-W industry-standard benchmark. The experimental results show that our approach is able to capture the performance anomaly, and locate the metrics relating to the cause of anomaly.

Keywords

performance anomaly anomaly detection Internetware system metrics kernel canonical correlation analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yang F, Lv J, Mei H. Technical framework for Internetware: an architecture centric approach. SCI China Ser F-Inf Sci, 2008, 51: 610–622CrossRefGoogle Scholar
  2. 2.
    Cherkasova L, Ozonat K, Mi N, et al. Automated anomaly detection and performance modeling of enterprise applications. ACM Trans Comput Syst, 2009, 27: 1–32CrossRefGoogle Scholar
  3. 3.
    Oppenheimer D, Ganapathi A, Patterson D A. Why do Internet services fail, and what can be done about it? In: Proceedings of the 4th Symposium on Internet Technologies and Systems, Seattle, 2003. 1–16Google Scholar
  4. 4.
    Koziolek H. Performance evaluation of component-based software systems: a survey. Perform Evaluation, 2010, 67: 634–658CrossRefGoogle Scholar
  5. 5.
    Zhang Q, Cherkasova L, Mathews G, et al. R-Capriccio: a capacity planning and anomaly detection tool for enterprise services with live workloads. In: Proceedings of the ACM/IFIP/USENIX International Conference on Middleware, Newport Beach, 2007. 244–265Google Scholar
  6. 6.
    Lai P L, Fyfe C. Kernel and nonlinear canonical correlation analysis. Int J Neural Syst, 2000, 10: 365–377Google Scholar
  7. 7.
    Mi N, Casale G, Cherkasova L, et al. Burstiness in multi-tier applications: symptoms, causes, and new models. In: Proceedings of the 9th International Conference on Middleware, Leuven, 2008. 265–286Google Scholar
  8. 8.
    Menasc D A. TPC-W: a benchmark for e-commerce. IEEE Internet Comput, 2002, 6: 83–87CrossRefGoogle Scholar
  9. 9.
    Chandola V, Banerjee A, Kumar V. Anomaly detection: a survey. ACM Comput Surv, 2009, 41: 1–58CrossRefGoogle Scholar
  10. 10.
    Hardoon D R, Szedmak S R, Shawe-Taylor J R. Canonical correlation analysis: an overview with application to learning methods. Neural Comput, 2004, 16: 2639–2664zbMATHCrossRefGoogle Scholar
  11. 11.
    Barnard G A. Control charts and stochastic processes. Appl Stat-J Roy Stat Soc C, 1959, 21: 239–271zbMATHGoogle Scholar
  12. 12.
    Jiang G, Chen H, Yoshihira K. Modeling and tracking of transaction flow dynamics for fault detection in complex systems. IEEE Trans Dependable Secur C, 2006, 3: 312–326CrossRefGoogle Scholar
  13. 13.
    Kononenko I. Estimating attributes: analysis and extensions of RELIEF. In: Proceedings of the European Conference on Machine Learning, Catania, 1994. 171–182Google Scholar
  14. 14.
    Wang T, Wei J, Zhang W, et al. Workload-aware anomaly detection for web applications. J Syst Softw, to be publishedGoogle Scholar
  15. 15.
    Zhang W, Wang S, Wang W, et al. Bench4Q: a QoS-oriented e-commerce benchmark. In: Proceedings of the 35th Annual Computer Software and Applications Conference, Munich, 2011. 38–47Google Scholar
  16. 16.
    Reynolds P, Killian C, Wiener J L, et al. Pip: detecting the unexpected in distributed systems. In: Proceedings of the 3rd Symposium on Network Systems Design and Implementation, San Jose, 2006. 115–128Google Scholar
  17. 17.
    Xu W, Huang L, Fox A, et al. Detecting large-scale system problems by mining console logs. In: Proceedings of the ACM SIGOPS 22nd Symposium on Operating Systems Principles, Big Sky, 2009. 117–132CrossRefGoogle Scholar
  18. 18.
    Tan Y, Nguyen H, Gu X, et al. PREPARE: predictive performance anomaly prevention for virtualized cloud systems. In: Proceedings of the 32nd International Conference on Distributed Computing Systems, Macau, 2012. 285–294Google Scholar
  19. 19.
    Chen H, Jiang G, Yoshihira K, et al. Invariants based failure diagnosis in distributed computing systems. In: Proceedings of the 29th IEEE Symposium on Reliable Distributed Systems, New Delhi, 2010. 160–166Google Scholar
  20. 20.
    Ghanbari S, Amza C. Semantic-driven model composition for accurate anomaly diagnosis. In: Proceedings of International Conference on Autonomic Computing, Chicago, 2008. 35–44Google Scholar
  21. 21.
    Chen M Y, Accardi A, Kiciman E, et al. Path-based faliure and evolution management. In: Proceedings of the 1st Symposium on Networked Systems Design and Implementation, Berkeley, 2004. 23–36Google Scholar
  22. 22.
    Barham P, Donnelly A, Isaacs R, et al. Using Magpie for request extraction and workload modelling. In: Proceedings of the 6th International Symposium on Opearting Systems Design and Implementation, San Francisco, 2004. 18–31Google Scholar
  23. 23.
    Chen H, Jiang G, Ungureanu C, et al. Failure detection and localization in component based systems by online tracking. In: Proceedings of the 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, Chicago, 2005. 750–755Google Scholar
  24. 24.
    Jiang G, Chen H, Yoshihira K. Efficient and scalable algorithms for inferring likely invariants in distributed systems. IEEE Trans Knowl Data Eng, 2007, 19: 1508–1523CrossRefGoogle Scholar
  25. 25.
    Munawar M A, Ward P A S. A comparative study of pairwise regression techniques for problem determination. In: Proceedings of the Conference of the Center for Advanced Studies on Collaborative Research, Toronto, 2007. 152–166Google Scholar
  26. 26.
    Zhen G, Jiang G, Chen H, et al. Tracking probabilistic correlation of monitoring data for fault detection in complex systems. In: Proceedings of International Conference on Dependable Systems and Networks, Philadelphia, 2006. 259–268CrossRefGoogle Scholar
  27. 27.
    Jiang M, Munawar M A, Reidemeister T, et al. System monitoring with metric-correlation models: problems and solutions. In: Proceedings of the 6th International Conference on Autonomic Computing, Barcelona, 2009. 13–22Google Scholar
  28. 28.
    Cohen I, Goldszmidt M, Kelly T, et al. Correlating instrumentation data to system states: a building block for automated diagnosis and control. In: Proceedings of the 6th Symposium on Operating Systems Design and Implementation, San Francisco, 2004. 16–29Google Scholar
  29. 29.
    Magalhes J P, Silva L M. Detection of performance anomalies in web-based applications. In: Proceedings of the 9th IEEE International Symposium on Network Computing and Applications, Cambridge, 2010. 60–67Google Scholar
  30. 30.
    Magalhes J P, Silva L M. Root-cause analysis of performance anomalies in web-based applications. In: Proceedings of the ACM Symposium on Applied Computing, Taichung, 2011. 209–216Google Scholar

Copyright information

© Science China Press and Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tao Wang
    • 1
    • 2
    • 3
  • Jun Wei
    • 1
    • 2
    Email author
  • Feng Qin
    • 4
  • WenBo Zhang
    • 2
  • Hua Zhong
    • 2
  • Tao Huang
    • 1
    • 2
  1. 1.State Key Laboratory of Computer ScienceBeijingChina
  2. 2.Institute of SoftwareChinese Academy of SciencesBeijingChina
  3. 3.University of Chinese Academy of SciencesBeijingChina
  4. 4.The Ohio State UniversityColumbusUSA

Personalised recommendations