Journal of KIISE (정보과학회 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

PathSavanna: Realistic Packet Routing using GPGPU on the Xen-based Virtual Router

PathSavanna: Xen 기반 가상 라우터에서의 GPGPU를 이용한 실제적인 패킷 라우팅

  • 박근영 (고려대학교 임베디드소프트웨어학과) ;
  • 이치영 (고려대학교 컴퓨터전파통신공학과) ;
  • 유혁 (고려대학교 정보대학)
  • Received : 2015.01.13
  • Accepted : 2015.09.29
  • Published : 2016.01.15
⟨ Previous Next ⟩

Abstract

As the need for a flexible Internet grows, research for software and virtual routers has increased. Although software routers and virtual routers provide Internet flexibility, they have low performance compared with existing hardware routers. In addition, the low performance problem is intensified in virtual routers because they have virtualization overheads. GPU routing is one method of improving the performance of software routers. However, previous GPU routing is based on native software routers, which are not virtualized, and presents experimental simulation results only. In this paper, we examine the effect of GPU routing on a virtual router using PathSavanna. Our GPU routing is implemented on the virtual router and forwards real packets to another machine, which is connected by a network.

최근, 다양한 인터넷 환경을 제공하는 유연성을 가진 소프트웨어 기반의 라우터 연구가 활발하게 진행되고 있다. 특히, 소프트웨어 라우터에 확장성을 더하기 위해 라우터를 가상화하려는 연구가 증가하고 있다. 하지만, 소프트웨어 라우터를 가상화하면, 가상화로 인한 오버헤드로 인해 성능 저하가 더욱 심화된다. 게다가, 기존의 소프트웨어 라우터에서 제안된 GPU 기반 packet routing 기법들은 native 환경에서의 연구거나 실제 네트워크 상에 적용되지 않은 단점이 있다. 따라서, 기존의 연구로는 GPU routing이 가상 라우터에서 어떤 효과를 보일지를 예측하기 어렵다. 본 논문은 실제로 가상 라우터를 구축하고, 실제 네트워크 패킷을 전송함으로써 가상 라우터에서의 GPU routing의 영향을 보인다. 이를 위해, GPU를 가상화하는 Savanna와 가상 라우터 역할의 Pathfinder를 구현하고, 가상 라우터와 연결된 외부 머신으로부터 패킷을 전송한다.

Keywords

Acknowledgement

Grant : SDN 2.0 실현을 위한 네트워크 가상화 플랫폼 핵심 기술 및 서비스 연구, (SW 스타랩) 성능 및 보안 SLA 보장이 가능한 차세대 클라우드 인프라SW 개발

Supported by : 정보통신기술진흥센터

References

  1. J. Pan, S. Paul, and R. Jain, "A survey of the research on future internet architectures," IEEE Communications Magazine, Vol. 49, No. 7, pp. 26-36, 2011.
  2. M. Dobrescu et al., "RouteBricks: exploiting parallelism to scale software routers," Proc. of the ACM SIGOPS 22nd symposium on Operating systems principles, 2009.
  3. L. Rizzo, "netmap: A Novel Framework for Fast Packet I/O," Proc. of USENIX Annual Technical Conference, 2012.
  4. J. Zhao et al., "Exploiting graphics processors for high-performance IP lookup in software routers," INFOCOM, 2011 Proceedings IEEE. IEEE, 2011.
  5. Y. Li et al., "GAMT: a fast and scalable IP lookup engine for GPU-based software routers," Proc. of the ninth ACM/IEEE symposium on Architectures for networking and communications systems, 2013.
  6. S. Han et al., "PacketShader: a GPU-accelerated software router," ACM SIGCOMM Computer Communication Review, Vol. 41, No. 4, pp. 195-206, 2011.
  7. Y. Lee et al., "Fast forwarding table lookup exploiting GPU memory architecture," Proc. of IEEE International Conference on Information and Communication Technology Convergence (ICTC), 2010.
  8. Yoo-kyung Uh, "Savanna: GPGPU Virtualization through the Xen-based Communication Mechanism with Minimum Overheads," Master's thesis, Department of Convergence Information Technology, Korea University, Feb. 2014.
  9. SungWon Ahn, "Toward High-performance and Scalability for Software based Virtual Router," Ph.D.'s Thesis, Department of Computer Science and Radio Communication Engineering, Korea University, Feb. 2014.
  10. J. Smith and R. Nair, "Virtual Machines: Versatile Platforms for Systems and Processes(The Morgan Kaufmann Series in Computer Architecture and Design)," San Francisco, CA, Morgan Kaufmann Publishers Inc., 2005.
  11. D. Chisnall, "The definitive guide to the xen hypervisor," Pearson Education, 2008.
  12. P. Barham, B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, R. Neugebauer, I. Pratt, and A. Warfield, "Xen and the Art of Virtualization," Proc. 19th ACM Symp. Operating Systems Principles (SOSP '03), pp. 164-177, Oct. 2003.
  13. Xen Community, "PV on HVM," http://wiki.xenproject.org/wiki/PV_on_HVM
  14. W. S. Ou, C. T. Yang, Y. T. Liu, C. H. Hsu, and H. Y. Wang, "On implementation of GPU virtualization using PCI pass-through," Proc. the 4th IEEE International Conference on Cloud Computing Technology and Science (CloudCom), Dec. 2012, pp. 711-716.
  15. J. Sanders and E. Kandrot, "CUDA by example: an introduction to general-purpose GPU programming," Addison-Wesley Professional, 2010.
  16. PCI-SIG, "Single Root I/O Virtualization," http://www.pcisig.com/specifications/iov/single_root