ABSTRACT
Cloud computing is a resource of significant value to computational science, but has proven itself to be not immediately realizable by the researcher. The cloud providers that offer a Platform-as-a-Service (PaaS) platform should, in theory, offer a sound alternative to infrastructure-as-a-service as it could be easier to take advantage of for computational science kinds of problems. The objective of our study is to assess how well the Azure platform as a service can serve a particular class of computational science application. We conduct a performance evaluation using three approaches to executing a high-throughput storm surge application: using Sigiri, a large scale resource abstraction tool, Windows Azure HPC scheduler, and Daytona, an Iterative Map-reduce runtime for Azure. The differences in the approaches including early performance measures for up to 500 instances are discussed.
- R. Barga, J. Jackson, N. Araujo, D. Guo, N. Gautam, and Y. Simmhan. The Trident scientific workflow workbench. IEEE International Conference on eScience, 0:317--318, 2008. Google ScholarDigital Library
- Daytona iterative map-reduce framework. http://research.microsoft.com/en-us/projects/daytona/.Google Scholar
- D. de Oliveira, E. Ogasawara, F. BaiaÌCo, and M. Mattoso. Scicumulus: A lightweight cloud middleware to explore many task computing paradigm in scientific workflows. In 2010 IEEE 3rd International Conference on Cloud Computing. IEEE, 2010. Google ScholarDigital Library
- B. Glahn, A. Taylor, N. Kurkowski, and W. Shaffer. The Role of the SLOSH Model In National Weather Service Storm Surge Forecasting. National Weather Digest, 33(1):3--14, 2009.Google Scholar
- C. A. Goble and D. C. De Roure. myexperiment: social networking for workflow-using e-scientists. In WORKS '07: Proceedings of the 2nd workshop on Workflows in support of large-scale science, pages 1--2, New York, NY, USA, 2007. ACM. Google ScholarDigital Library
- T. Gunarathne, T.-L. Wu, and G. J.Qiu. Cloud Computing Paradigms for Pleasingly Parallel Biomedical Applications. In HPDC, 2010. Google ScholarDigital Library
- S. Jensen and B. Plale. Trading consistency for scalability in scientific metadata. In 6th International IEEE Conference on e-Science, pages 292--299. IEEE Computer Society Press, 2010. Google ScholarDigital Library
- J. Li, D. Agarwal, M. Humphrey, C. van Ingen, K. Jackson, and Y. Ryu. eScience in the Cloud: A MODIS Satellite Data Reprojection and Reduction Pipeline in the Windows Azure Platform. In Proceedings of the 24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010). IEEE, 2010.Google ScholarCross Ref
- W. Lu, J. Jackson, and R. Barga. Azureblast: a case study of developing science applications on the cloud. In Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, HPDC '10, pages 413--420, New York, NY, USA, 2010. ACM. Google ScholarDigital Library
- W. Lu, J. Jackson, J. Ekanayake, R. S. Barga, and N. Araujo. Performing large science experiments on azure: Pitfalls and solutions. In CloudCom, pages 209--217, 2010. Google ScholarDigital Library
- Azure hpc scheduler. http://msdn.microsoft.com/en-us/library/windowsazure/hh545593.aspx.Google Scholar
- What's new in windows azure. http://msdn.microsoft.com/en-us/library/windowsazure/gg441573.aspx.Google Scholar
- NOAA SLOSH display program. http://slosh.nws.noaa.gov/sloshPub/\#sloshDsp.Google Scholar
- S. Pandey, D. Karunamoorthy, and R. Buyya. Workflow Engine for Clouds. In Cloud Computing, Principles and Paradigms, Wiley Series on Parallel and Distributed Computing, pages 321--344, 2011.Google ScholarCross Ref
- B. Plale, E. C. Withana, C. Herath, K. Chandrasekar, and Y. Luo. Effectiveness of hybrid workflow systems for computational science. In International Conf on Computational Science (ICCS). To appear Procedia Computer Science, Elsevier, 2012.Google ScholarCross Ref
- Y. Simmhan, R. Barga, C. V. Ingen, E. Lazowska, and A. Szalay. On Building Scientific Workflow Systems for Data Management in the Cloud. In Fourth IEEE International Conference on eScience. IEEE, 2008. Google ScholarDigital Library
- Windows azure queue. https://www.windowsazure.com/en-us/home/tour/storage/.Google Scholar
- E. C. Withana and B. Plale. Sigiri: Uniform research abstraction for grids and clouds. To appear Concurrency and Computation: Practice and Experience; Early view to DOI: 10.1002/cpe.2823 Feb 2012, 2012. Google ScholarDigital Library
Index Terms
- Middleware alternatives for storm surge predictions in Windows Azure
Recommendations
Early observations on the performance of Windows Azure
HPDC '10: Proceedings of the 19th ACM International Symposium on High Performance Distributed ComputingA significant open issue in cloud computing is performance. Few, if any, cloud providers or technologies offer quantitative performance guarantees. Regardless of the potential advantages of the cloud in comparison to enterprise-deployed applications, ...
Storm surge simulation and load balancing in Azure cloud
HPC '13: Proceedings of the High Performance Computing SymposiumCloud computing platforms are drawing increasing attention of the scientific research communities. By providing a framework to lease computation resources, cloud computing enables the scientists to carry out large-scale experiments in a cost-effective ...
A Framework and Middleware for Application-Level Cloud Bursting on Top of Infrastructure-as-a-Service Clouds
UCC '13: Proceedings of the 2013 IEEE/ACM 6th International Conference on Utility and Cloud ComputingA core idea of cloud computing is elasticity, i.e., enabling applications to adapt to varying load by dynamically acquiring and releasing cloud resources. One concrete realization is cloud bursting, which is the migration of applications or parts of ...
Comments