high speed networking; Click modular router; Intel DPDK; Netmap; routers; userspace I/O; NUMA; performance; fast packet I/O; multi-queue; network processing
Résumé :
[en] In recent years, we have witnessed the emergence of high speed packet I/O frameworks, bringing unprecedented network performance to userspace. Using the Click modular router, we first review and quantitatively compare several such packet I/O frameworks, showing their superiority to kernel-based forwarding.
We then reconsider the issue of software packet processing, in the context of modern commodity hardware with hardware multi-queues, multi-core processors and non-uniform memory access. Through a combination of existing techniques and improvements of our own, we derive modern general principles for the design of software packet processors.
Our implementation of a fast packet processor framework, integrating a faster Click with both Netmap and DPDK, exhibits up-to about 2.3x speed-up compared to other software implementations, when used as an IP router.
Centre de recherche :
Research Unit in Networking
Disciplines :
Sciences informatiques
Auteur, co-auteur :
Barbette, Tom ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes informatiques répartis et sécurité
Soldani, Cyril ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes informatiques répartis et sécurité
Mathy, Laurent ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes informatiques répartis et sécurité
Langue du document :
Anglais
Titre :
Fast Userspace Packet Processing
Date de publication/diffusion :
07 mai 2015
Nom de la manifestation :
Symposium on Architecture for Networking and Communications Systems
Organisateur de la manifestation :
ACM/IEEE
Lieu de la manifestation :
Oakland, Etats-Unis - Californie
Date de la manifestation :
from 07-05-2015 to 08-05-2015
Manifestation à portée :
International
Titre de l'ouvrage principal :
Proceedings of ANCS 2015
ISBN/EAN :
978-1-4673-6633-5
Peer reviewed :
Peer reviewed
Organisme subsidiant :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
K. Argyraki, S. Baset, B.-G. Chun, K. Fall, G. Iannaccone, A. Knies, E. Kohler, M. Manesh, S. Nedevschi, and S. Ratnasamy. Can softwa re routers scale? In Proceedings of the ACM Workshop on Programmable Routers for Extensible Services of Tomorrow, PRESTO '08, pages 21-26, New York, NY, USA, 2008. ACM.
T. Barbette. Click pull request #162 to enable multi-producer single-consumer mode in linuxmodule fromdevice. https://github.com/kohler/click/pull/162.
T. Ba rbette. Tom barbette's research part. http://www.tombarbette.be/research/.
A. Belay, G. Prekas, A. Klimovic, S. Grossman, C. Kozyrakis, and E. Bugnion. Ix: A protected dataplane operating system for high throughput and low latency. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14), pages 49-65, Broom eld, CO, Oct. 2014. USENIX Association.
M. Dobrescu, N. Egi, K. Argyraki, B.-G. Chun, K. Fall, G. Iannaccone, A. Knies, M. Manesh, and S. Ratnasamy. Routebricks: Exploiting parallelism to scale software routers. In Proceedings of the ACM SIGOPS 22Nd Symposium on Operating Systems Principles, SOSP '09, pages 15-28, New York, NY, USA, 2009. ACM.
N. Egi, A. Greenhalgh, M. Handley, M. Hoerdt, F. Huici, and L. Mathy. Towards high performance virtual routers on commodity hardware. In Proceedings of the 2008 ACM CoNEXT Conference, page 20. ACM, 2008.
S. Han, K. Jang, K. Park, and S. Moon. Packetshader: A GPU-Accelerated software router. In Proceedings of the ACM SIGCOMM 2010 Conference, SIGCOMM '10, pages 195-206, New York, NY, USA, 2010. ACM.
Intel. CoreTM i7-4930k processor (12m cache, up to 3.90 ghz). http://ark.intel.com/products/77780.
Intel. Data plane development kit. http://www.dpdk.org.
J. Kim, S. Huh, K. Jang, K. Park, and S. Moon. The power of batching in the click modular router. In Proceedings of the Asia-Paci c Workshop on Systems, APSYS '12, pages 14:1-14:6, New York, NY, USA, 2012. ACM.
E. Kohler, R. Morris, B. Chen, J. Jannotti, and M. F. Kaashoek. The click modular router. ACM Trans. Comput. Syst., 18(3):263-297, Aug. 2000.
I. Marinos, R. N. Watson, and M. Handley. Network stack specialization for performance. In Proceedings of the Twelfth ACM Workshop on Hot Topics in Networks, page 9. ACM, 2013.
Linux Kernel Contributors. Packet mmap. https://www.kernel.org/doc/Documentation/networking/packet-mmap.txt.
ntop. Dna vs netmap. http://www.ntop.org/pf\-ring/dna-vs-netmap/.
S. Peter, J. Li, I. Zhang, D. R. K. Ports, D. Woos, A. Krishnamurthy, T. Anderson, and T. Roscoe. Arrakis: The operating system is the control plane. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14), pages 1-16, Br oom eld, CO, Oct. 2014. USENIX Association.
L. Rizzo. Device polling support for freebsd. In BSDConEurope Conference, 2001.
L. Rizzo. netmap: A novel framework for fast packet i/o. In USENIX Annual Technical Conference, pages 101-112, 2012.
L. Rizzo, G. Lettieri, and V. Ma one. Speeding up packet i/o in virtual machines. In Proceedings of the ninth ACM/IEEE symposium on Architectures for networking and communications systems, pages 47-58. IEEE Press, 2013.
J. H. Salim, R. Olsson, and A. Kuznetsov. Beyond softnet.
Solar are. Openonload. http://www.openonload.org/.
W. Sun and R. Ricci. Fast and exible: Parallel packet processing with GPUs and Click. In Proceedings of the ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS), Oct. 2013.