Hopes and facts in evaluating the performance of HPC-I/O on a cloud environment

Authors

  • Pilar Gómez Sánchez Computer Architecture and Operating Systems Department (CAOS), Universität Autónoma de Barcelona, Bellaterra (Barcelona), Spain
  • Sandra Méndez High Performance Systems Division Leibniz Supercomputing Centre (LRZ), Garching (Munich), Germany.
  • Dolores Rexachs del Rosario
  • Emilio Luque Computer Architecture and Operating Systems Department (CAOS), Universität Autónoma de Barcelona, Bellaterra (Barcelona), Spain

Keywords:

application I/O model, I/O system, Cloud Cluster, I/O phases, I/O access pattern, I/O configuration

Abstract

Currently, there is an increasing interest about the cloud platform by the High Performance Computing (HPC) community, and the Parallel I/O for High Performance Systems is not an exception. In cloud platforms, the user takes into account not only the execution time but also the cost, because the cost can be one of the most important issue. In this paper, we propose a methodology to quickly evaluate the performance and cost of Virtual Clusters for parallel scientific application that uses parallel I/O. From the parallel application I/O model automatically extracted with our tool PAS2P-IO, we obtain the I/O requirements and then the user can select the Virtual Cluster that meets the application requirements. The application I/O model does not depend on the underlying I/O system. One of the main benefits of applying our methodology is that it is not necessary to execute the application to select the Virtual Cluster on cloud. Finally, costs and performance-cost ratio for the Virtual Clusters are provided to facilitate the decision making on the selection of resources on a cloud platform.

Downloads

Download data is not yet available.

References

[1] M. Liu, J. Zhai, Y. Zhai, X. M a, and W. Chen, “One Opti­mized I/O Configuration Per HPC Application: Leveraging the Configurability of Cloud,” in Proceedings o f the Second Asia-Pacific Workshop on Systems. ACM, 2011, pp. 15:1-15:5.
[2] R. Exposito, G. Taboada, S. Ramos, J. Gonzalez-Dominguez, J. Tourino, and R. Doallo, “Analysis of I/O Perform ance on an Amazon EC2 Cluster Com pute and High I/O Platform,” Journal of Grid Computing, vol. 11, no. 4, pp. 613-631.
[3] G. Juve, E. Deelman, G. B. Berrim an, B. P. Berm an, and P. Maechling, “An Evaluation of the Cost and Performance of Scientific Workflows on Am azon EC2,” J. Grid Comput., vol. 10, no. 1, pp. 5-21, Mar. 2012.
[4] M. Liu, Y. Jin, J. Zhai, Y. Zhai, Q. Shi, X. M a, and W. Chen, “ACIC: Automatic Cloud I/O Configurator for HPC Applications,” in Proceedings o f the Int. Conf. on High Performance Computing, Networking, Storage and Analysis , ser. SC’13. ACM, 2013, pp. 38:1-38:12.
[5] P. Wong and R. F. V. D. Wijngaart, “Nas parallel benchmarks i/o version 2.4,” Computer Sciences Corporation, NASA Ad­vanced Supercomputing (NAS) Division, Tech. Rep., 2003.
[6] J. H. Chen, A. Choudhary, B. de Supinski, M. DeVries, E. R. Hawkes, S. Klasky, W. K. Liao, K. L. M a, J. Mellor-Crummey, N. Podhorszki, R. Sankaran, S. Shende, and C. S. Yoo, “Terascale direct numerical simulations of turbulent combustion using S3D,” Computational Science & Discov­ery, vol. 2, no. 1, p. 015001, 2009.
[7] StarCluster. (2014) An Open Source Cluster-Computing Toolkit for Amazon’s Elastic Compute Cloud (EC2). [Online]. Available: http://star.m it.edu/cluster/
[8] S. Mendez, J. Panadero, A. Wong, D. Rexachs, and E. Luque, “A New approach for Analyzing I/O in Parallel Scientific Applications,” in CACIC12, 2012, pp. 337-346.
[9] S. M endez, D. Rexachs, and E. Luque, “Modeling Parallel Scientific Applications through their Input/Output Phases,” in Cluster Computing Workshops, 2012 IEEE Int. Conf. on, Sept 2012, pp. 7-15.
[10] W. D. Norcott. (2006) IOzone Filesystem Benchmark. [Online]. Available: http://www.iozone.org/
[11] W. Loewe, T. McLarty, and C. Morrone. (2012) IOR Benchmark. [Online]. Available: https://github.com /chaos/ior/blob/m aster/doc/USER_GUIDE
[12] CESGA. (2014) Finisterrae of the centre of supercomputing of galicia (CESGA). [Online]. Available: https://www.cesga.es
[13] W CSS. (2014) Supernova of the Wroclaw Centre for Networking and Supercomputing (WCSS). [Online]. Available: https://www.wcss.pl
[14] AWS-EC2. (2014) Amazon Elastic Compute Cloud, Instance Types. [Online]. Available: http://docs.aws.amazon.com /AWSEC2/latest/UserGuide/instance-types.html

Downloads

Published

2015-04-01

How to Cite

Gómez Sánchez, P., Méndez, S., Rexachs del Rosario, D., & Luque, E. (2015). Hopes and facts in evaluating the performance of HPC-I/O on a cloud environment. Journal of Computer Science and Technology, 15(01), p. 23–29. Retrieved from https://journal.info.unlp.edu.ar/JCST/article/view/528

Issue

Section

Original Articles

Most read articles by the same author(s)