Exploratory Study on the Linux OS Jitter
Abstract
We present the results of an experimental study that quantifies the effects of different sources of OS Jitter in the Linux operating system. We found that the processor topology, especially regarding the shared processor cache, has the most significant influence in terms of OS Jitter. Also, we found that in order to reduce the impact of OS Jitter on a given application, the number of computational phases in the algorithm is significantly more important than the number of distributed processes or compute nodes.References
Agarwal, S., Garg, R., and Vishnoi, N. K. (2005): The impact of noise on the scaling of collectives: a theoretical approach. In Proc. of IEEE Int’l Conf. on High Performance Comp., Goa, India, Dec. 280–289.
De, P., Kothari, R., and Mann, V. (2007): Identifying sources of operating system jitter through fine-grained kernel instrumentation. In Proc. of the IEEE International Conference on Cluster Computing, Washington, USA, 331–340.
Garg, R. and De, P. (2006): The impact of noise on the scaling of collectives: an empirical evaluation. In Proc. of 13th IEEE International Conference on High Performance Computing (HiPC), Bangalore, India.
Gioiosa, R., Petrini, F., Davis, K., and Lebaillif-Delamare, F. (2004): Analysis of system overhead on parallel computers. In Proc. of IEEE Symposium of Signal Processing and Information Tech, 387–390.
R. Jain (1991): The Art of Computer Systems Performance Analysis: Techniques for Experimental Design, Measurement, Simulation, and Modeling. Wiley-Interscience, New York, NY.
Jones, T. R., Brenner, L. B., Fier, J. M. (2003): Impacts of operating systems on the scalibility of parallel applications. Tech. Rep. UCRL-MI-202629, Lawrence Livermore National Laboratory.
D. C. Montgomery (2000): Design and Analysis of Experiments. John Wiley, 3rd edition.
Tsafrir, D., Etsion, Y., Feitelson, D. G., and Kirkpatrick, S. (2005): System noise, os clock ticks, and fine-grained parallel applications. In Proc. of Int’l Conf. on Supercomputing, New York, NY, USA 303–312.
Vam, P.H. and Vidakovic, B. (2007): Nonparametric Statistics With Applications to Science and Engineering. Wiley-Interscience.
De, P., Kothari, R., and Mann, V. (2007): Identifying sources of operating system jitter through fine-grained kernel instrumentation. In Proc. of the IEEE International Conference on Cluster Computing, Washington, USA, 331–340.
Garg, R. and De, P. (2006): The impact of noise on the scaling of collectives: an empirical evaluation. In Proc. of 13th IEEE International Conference on High Performance Computing (HiPC), Bangalore, India.
Gioiosa, R., Petrini, F., Davis, K., and Lebaillif-Delamare, F. (2004): Analysis of system overhead on parallel computers. In Proc. of IEEE Symposium of Signal Processing and Information Tech, 387–390.
R. Jain (1991): The Art of Computer Systems Performance Analysis: Techniques for Experimental Design, Measurement, Simulation, and Modeling. Wiley-Interscience, New York, NY.
Jones, T. R., Brenner, L. B., Fier, J. M. (2003): Impacts of operating systems on the scalibility of parallel applications. Tech. Rep. UCRL-MI-202629, Lawrence Livermore National Laboratory.
D. C. Montgomery (2000): Design and Analysis of Experiments. John Wiley, 3rd edition.
Tsafrir, D., Etsion, Y., Feitelson, D. G., and Kirkpatrick, S. (2005): System noise, os clock ticks, and fine-grained parallel applications. In Proc. of Int’l Conf. on Supercomputing, New York, NY, USA 303–312.
Vam, P.H. and Vidakovic, B. (2007): Nonparametric Statistics With Applications to Science and Engineering. Wiley-Interscience.
Published
2013-07-23
How to Cite
VICENTE, Elder; MATIAS JR., Rivalino.
Exploratory Study on the Linux OS Jitter. In: THESIS AND DISSERTATION CONTEST (CTD), 26. , 2013, Maceió/AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2013
.
p. 47-52.
ISSN 2763-8820.
