A new approach to performance optimization of mashups via data flow refactoring

ABSTRACT

Mashup tools allow end users graphically build complex mashups using pipes to connect web data sources into a data flow. Because end users are of poor technical expertise, the designed data flows may be inefficient. This paper targets on enhancing the performance of mashups via automatically refactoring the structure of its data flows. First a set of operational semantics features are selected for annotating the operators in data flows and refactoring rules are defined to generate all candidate semantics equivalent data flows. Then a heuristic algorithm is described for accurately searching the data flow of minimal execution time by constructing a partially ordered set of data flows based on their cost estimation. This approach is applicable to general mashup data flows without knowing complete operational semantics of their operators and the efficiency improvement is demonstrated by experiments.

References

1. Sebastien, M., Franck, C., Mireille, B. et al.: Web Services Composition: Mashups Driven Orchestration Definition. In: International Conference on Computational Intelligence for Modelling, Control and Automation, pp. 284--289. IEEE Computer Society, Los Alamitos, CA, USA (2008)
2. Yahoo Pipes, http://pipes.yahoo.com
3. Alkis, S., Panos, V., Timos, S.: State-Space Optimization of ETL Workflows. IEEE Transactions on Knowledge and Data Engineering. 17(10), 1404--1419 (2005)
4. Alkis, S., Kevin, W., Umeshwar, D. et al.: Optimizing ETL Workflows for Fault-Tolerance. In: 26th IEEE International Conference on Data Engineering, pp. 385--396. IEEE Press, New York (2010)
5. Giusy, D. L., Hakim, H., Hye-young, P. et al: Data integration in mashups. SIGMOD Record. 38(1), 59--66 (2009)
6. Serge, A., Ohad, G., Tova, M.: Modeling the mashup space. In: 10th ACM workshop on Web information and data management, pp. 87--94. ACM, New York (2008)
7. Serge, A., Ohad, G., Tova, M.: Autocompletion for mashups. In: 25th IEEE International Conference on Data Engineering, pp. 1479--1482. ACM, New York (2009)
8. Biorm, B., Cesare, P.: Let It Flow: Building Mashups with Data Processing Pipelines. In: ICSOC 2007 Workshops, pp. 15--28. Springer-Verlag, Berlin, Heidelberg (2007)
9. Osama, A. H., Lakshmish, R., John, A. M.: MACE: A Dynamic Caching Framework for Mashups. In: 7th IEEE International Conference on Web Service, pp. 75--82. IEEE Computer Society, Washington, DC, USA (2009)
10. Eric, W., Peng, L., Brett, C.: Web service mashup middleware with partitioning of xml pipelines. In: 7th IEEE International Conference on Web Service, pp. 91--98. IEEE Computer Society, Washington, DC, USA (2009)
11. Dong, L., Ralph, D.: The Reverse C10K Problem for Server-Side Mashups. In: ICSOC 2008 International Workshops, pp. 166--177. Springer-Verlag, Berlin, Heidelberg (2008)
12. Tsangaris, M., Kakaletris, G., Kllapi, H. et al.: Dataflow Processing and Optimization on Grid and Cloud Infrastructures. Bulletin of the Technical Committee on Data Engineering. 32(1), 67--74 (2009)

Index Terms

• General and reference

  • Cross-computing tools and techniques

    • Performance

• Social and professional topics

  • Professional topics

    • Management of computing and information systems

      • Software management

        • Software selection and adaptation

• Software and its engineering

  • Software organization and properties

    • Extra-functional properties

      • Software performance