Abstract
Nuclear disaster early warning systems are based on simulations of the atmospheric dispersion of the radioactive pollutants that may have been released into the atmosphere as a result of an accident at a nuclear power plant. Currently the calculation is performed by a series of 9 enchained FORTRAN and C/C++ sequential simulation codes. The new requirements to our example early warning system we focus on in this paper include a maximum response time of 120 seconds whereas currently computing a single simulation step exceeds this limit. For the purpose of improving performance we propose a pipeline parallelization of the simulation workflow on a multi-core system. This leads to a 4.5x speedup with respect to the sequential execution time on a dual quad-core machine. The scheduling problem which arises is that of maximizing the number of iterations of the dispersion calculation algorithm while not exceeding the maximum response time limit. In the context of our example application, a static scheduling strategy (e.g., a fixed rate of firing iterations) proves to be inappropriate because it is not able to tolerate faults that may occur during regular use (e.g., CPU failure, software errors, heavy load bursts). In this paper we show how a simple PI-controller is able to keep the realized response time of the workflow around a desired value in different failure and heavy load scenarios by automatically reducing the throughput of the system when necessary, thus improving the system’s fault tolerance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Burns, A., Wellings, A.: Real-Time Systems and Programming Languages, 4th edn. Addison Wesley, Reading (2009)
Misra, J.: Distributed discrete-event simulation. ACM Computing Surveys 18, 39–65 (1986)
Lazowska, E.D., Zahorjan, J., Graham, G.S., Sevcik, K.C.: Quantitative system performance: computer system analysis using queueing network models. Prentice-Hall, Inc., Englewood Cliffs (1984)
Legg, B.J., Raupach, M.R.: Markov-chain simulation of particle dispersion in inhomogeneous flows: The mean drift velocity induced by a gradient in eulerian velocity variance. Boundary-Layer Meteorology 24, 3–13 (1982)
Åström, K.J., Hägglund, T.: Advanced PID Control. ISA (2006)
Eker, J., Janneck, J., Lee, E., Liu, J., Liu, X., Ludvig, J., Neuendorffer, S., Sachs, S., Xiong, Y.: Taming heterogeneity – the ptolemy approach. Proceedings of the IEEE 91, 127–144 (2003)
Woltman, G.: Prime95 v25.9 (2009), http://www.mersenne.org/freesoft/
Hollot, C., Misra, V., Towsley, D., Gong, W.: On designing improved controllers for aqm routers supporting tcp flows. Technical report, University of Massachusetts, Amherst, MA, USA (2000)
Kelly, F.: Mathematical modelling of the internet. In: Proceedings of the 4th Int. Contr. on Industrial and Applied Mathematics (2000)
Abdelzaher, T., Lu, C.: Modeling and performance control of internet servers. In: Proceedings of the 39th IEEE Conference on Decision and Control, pp. 2234–2239 (2000)
Sha, L., Liu, X., Lu, Y., Abdelzaher, T.: Queueing model based network server performance control. In: Proceedings of the 23rd Real-Time Systems Symposium, pp. 81–90 (2002)
Lu, C., Stankovic, J., Son, S., Tao, G.: Feedback control real-time scheduling: Framework, modeling, and algorithms. Real-Time Systems 23, 85–126 (2002)
Benoit, A., Kosch, H., Rehn-Sonigo, V., Robert, Y.: Multi-criteria scheduling of pipeline workflows (and application to the jpeg encoder). The International Journal of High Performance Computing Applications 23, 171–187 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ionescu, T.B., Laurien, E., Scheuermann, W. (2010). Applying Classic Feedback Control for Enhancing the Fault-Tolerance of Parallel Pipeline Workflows on Multi-core Systems. In: Keller, R., Kramer, D., Weiss, JP. (eds) Facing the Multicore-Challenge. Lecture Notes in Computer Science, vol 6310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16233-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-16233-6_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16232-9
Online ISBN: 978-3-642-16233-6
eBook Packages: Computer ScienceComputer Science (R0)