Multi Queue Approach for Network Services Implemented for Multi Core CPUs

• Autorzy: Hasse M. , Nowicki K. , Woźniak J.
• Języki publikacji: EN

Abstrakty

EN

Multiple core processors have already became the dominant design for general purpose CPUs. Incarnations of this technology are present in solutions dedicated to such areas like computer graphics, signal processing and also computer networking. Since the key functionality of network core components is fast package servicing, multicore technology, due to multi tasking ability, seems useful to support packet processing. Dedicated network processors characterize very good performance but at the same time high cost. General purpose CPUs achieve incredible performance, thanks to task distribution along several available cores and relatively low cost. The idea, analyzed in this paper, is to use general purpose CPU to provide network core functionality. For this purpose parameterized system model has been created, which represents general core networking needs. This model analyze system parameters influence on system performance.

Słowa kluczowe

EN

generic purpose CPU; multi-core; networks; queue; network services

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2011
• Tom: nr 3
• Strony: 57--62
• Opis fizyczny: Bibliogr. 25 poz., rys.

Twórcy

autor

Hasse M.

autor

Nowicki K.

autor

Woźniak J.

• Gdańsk University of Technology, G. Narutowicza st 11/12, 80-952 Gdańsk, Poland,

Bibliografia

• [1] “Intel IXP4XX product line of network processors”, http://www.intel.com
• [2] “OCTEON Multi-Core Processor Family”, http://www.cavium.com/OCTEON MIPS64.html
• [3] “Semiconductors overview”, http://www.freescale.com/
• [4] “Improving network performance in multi-core systems”, in Intel Corporation White Paper, http://www.intel.com
• [5] “Intel CPU documentation”, in Intel CPU, http://www.intel.com/design
• [6] “Press release”, in Intel Corporation, March 2007, http://www.intel.com/pressroom
• [7] L. Shimpi, “AnandTech”, June 2008, in The Nehalem Preview: Intel Does It Again, http://www.intel.com
• [8] “Intel Core i7” in The Nehalem Preview: Intel Does It Again, http://www.intel.com
• [9] M. Hasse and K. Nowicki, Linux Scheduler Improvement for Time Demanding Network Applications, Running on Communication Platform Systems. Gdańsk, Polska: Politechnika Gdańska, 2011.
• [10] P. Barham et al., “Xen and the art of virtualization”, in Proc. ACM Symp. Operat. Sys. Principles, New York, USA, 2003.
• [11] A. Gavrilovska et al., “High-performance hypervisor architectures: virtualization in HPC systems”, in Proc. 1st Worksh. System-level Virtu. High Perform. Comput. HPCVirt 2007, Lisbon, Portugal, 2007.
• [12] “A Performance comparison of hypervisors”, in VMWare Performance Study, Technical paper VMWare.
• [13] “Guide to virtualization on Red Hat enterprise Linux”, in Virtualization Guide, http://docs.redhat.com
• [14] “Virtual box reference”, in Sun xVM Virtual Box, http://www.virtualbox.org
• [15] C. Pitter and M. Schoeber, “Time predictable CPU and DMA shared memory access”, in Proc. FPL 2007, Amsterdam, The Netherland, 2007, pp. 317–322.
• [16] K. Kolyshkin, “Virtualization in Linux”, September 2006, http://www.pdfmob.com
• [17] R. Ennals, R. Sharp, and A. Mycroft, “Task partitioning for multicore network processors”, in Proc. Eur. Symp. Programming ESOP, LNCS, 2005, vol. 3443, SpringerLink.
• [18] L. Moddelmog and P. Johnson, “Poisson distribution”, February 2006 [Online]. Available: http://pj.freefaculty.org/stat/Distributions/Exponential v2.lyx
• [19] I. Al Ajarmeh, J. Yu, and M. Amezzine, “Framework of applying a non-homogeneous Poisson process to model VoIP traffic on tandem networks”, in Proc. 10th WSEAS Int. Conf. Applied Informatics and Communications AIC 2010, Taipei, Taiwan, 2010, pp. 164–169.
• [20] V. Paxson and S. Floyd, “Wide-area traffic: the failure of Poisson modeling”, IEEE/ACM Trans. Netw., vol. 3, no. 3, pp. 226–244, 1995.
• [21] W. Leleand, M. Taqqu, W. Willinger, and D. Wilson, “On the self similar nature of Ethernet traffic”, IEEE/ACM Trans. Netw., vol. 2, no. 1, pp. 1–15, 1994.
• [22] G. Munz, H. Dai, L. Braun, and G. Carle, “TCP traffic classification using Markov models”, in Proc. Traffic Monitoring and Analysis Workshop TMA 2010, Zurich, Switzerland, 2010, pp. 127–140.
• [23] A. Nogueira, P. Salvador, R. Valadas, and A. Pacheco, “Modeling self-similar traffc through Markov modulated Poisson processes over multiple time scales”, Telecommun. Sys., vol. 17, no. 1–2, pp. 185–211, 2001.
• [24] S. Scott and P. Smyth, The Markov Modulated Poisson Process and Markov Poisson Cascade with Applications to Web Traffic Modeling. Oxford University Press 2003.
• [25] J. F. Brady, “Virtualization and CPU wait times in a Linux guest environmnet”, January 2008.