The Transactions of the Korea Information Processing Society (한국정보처리학회논문지)

Korea Information Processing Society (한국정보처리학회)
권호 표지

Implementation of High Performance Messaging Layer for Multi-purpose Clustering System

다목적 클러스터링 시스템을 위한 고속 메시징 계층 구현

  • Published : 2000.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

High sped messaging layer for application's feeling of low level network performance is needed by Clustering System based on high speed network fabrics. It should have the mechanism to directly pass messages between network card and application space, and provide flexible affodabilities for many diverse applications. In this paper, CROWN (Clustering Resources On Workstations' Network) which is designed and implemented for multi-purpose clustering system will be introduced briefly, and CLCP(CROWN Lean Communication Primitives)which is the high speed messaging layer for CROWN will be followed. CLCP consists of a firmware for controlling Myrinet card, device drier, and user libraries. CLCP supports various application domains as a result of pooling and interrupt receive mechanism. In case of polling based receive, 8 bytes short message, and no other process, CLCP has 262 micro-second response time between two nodes, and IM bytes large message, it shows 442Mbps bandwidth.

Keywords

References

  1. J. H. Park. K D. Moon. T. Kim, G. H. Cho, 'Performance Characteristics of Polling and Interrupt for a Clustered Video Server,' Proceedings of ICMTM'98. pp.470-478. 1998
  2. 박준희，문경덕，김태근，조기환， '클러스터 기반 멀티미디어 서버를 위한 고속 통신 프리미티브 설계' 한국통신학회 추계 학술대회 학술지，1998
  3. 박준회, 문경덕，김태근，박창순，'워크스테이션 클러스터링 시스템의 초고속 통신 프리미티브 설계' 한국 정보과학회 추계 학술대회 학술지, 1997
  4. B. N. Chun, A. M. Mainwaring and D. E. Culler, 'Virtual Network Transport Protocols for Myrinet,' IEEE Micro Special Issue, Jan/Feb, 1998. http://now.cs.berkeley.edu/AM/active_messages,html https://doi.org/10.1109/40.653035
  5. L. A. Giannini and A. A. Chien, 'A Software Architecture for Global Address Space Communication on Clusters: Put/Get on Fast Messages,' In Proc. Of HPDC98, 1998. http://www-csag.cs.uiuc.edu/projects/comm/fm.html https://doi.org/10.1109/HPDC.1998.710019
  6. R Bhoedjang, T. Ruhl and H. E. Bal, 'Design Issues for User-Level Network Interface Protocols on Myrinet,' IEEE Computer, Nov. 1998. http://www. cs.vu.nl/~bal/das.html https://doi.org/10.1109/2.730737
  7. L. Prylli and B. Tourancheau, 'BIP : A New Protocol Designed for High Performance Networking on Myrinet,' In Workshop PC-NOW, IPPS/SPDP98, 1998. http://www.bip,univ-lyonl.fr/overview.html
  8. Basu, A, Buch, V., Vogels, W. and Eicken, T., 'UNet: A User-Level Network Interface for Parallel and Distributed Computing,' 15thACM Symposium on Operating Systems Principles, Copper Mountain, CO, USA, pp.40-53, 1995
  9. Boden, N., Cohen, D., Felderman R and Kulawik, A, 'Myrinet : A Gigabit-per-second Local Area Network,' IEEE-Micro, 15(1), pp.29-36, 1995 https://doi.org/10.1109/40.342015
  10. Culler, D., Arpaci-Dusseau, A, Arpaci-Dusseau, R, Chun, B., Lumetta, S., Mainwaring, A, Martin, R, Yoshikawa and C, Wong, F., 'Parallel Computing on the Berkeley NOW,' 9th Joint Symposium on Parallel Processing, Kobe, Japan, 1997
  11. Damianakis, S., Chen, Y. and Felten, E., 'Reducing Waiting Costs in User-Level Communication,' 11th International Parallel Processing Symposium, 1997
  12. Felten, E., Alpert, R, Bilas, A, Blumrich, M., Clark, D., Damiankis, S., Dubnicki, C., Iftode, L., and Li, K., 'Early Experience with Message- on the SHRIMP Multicomputer,' 23rd Annual International Symposium on Computer Architecture, 1996 https://doi.org/10.1145/232974.233004
  13. Maquelin, O., Gao, G., Hum, H., Theobald K. and Yia, X., 'Polling Watchdog: Combining Polling and Interrupts for Efficient Message Handling,' 23th International Symposium on Computer Architecture, pp.179-188, 1996 https://doi.org/10.1145/232973.232992
  14. Martin, R., Vahdat, A, Culler, D. and Anderson, T., 'Effects of Communication Latency, Overhead, and Bandwidth in a Cluster Architecture,' 24th Annual International Symposium on Computer Ardlitecture, Denver, CO, USA, 1997 https://doi.org/10.1145/264107.264146
  15. Park. J., Moon, K., Kim, T., and Park, C' 'A UserLevel Fast Message Receiving Technique by Maintaining Common Available Memory Pages Information in Network Interface,' 3rd Asia-Pacific Conference on Communications, Sydney, Australia, 1997
  16. Pakin, S., Karamcheti V. and Chien, A, 'Fast Messages (PM) : Efficient, Portable Communication for Workstation Clusters and Massively-Parallel Processors,' IEEE Concurrency, 5 (2), pp.60-73, 1997 https://doi.org/10.1109/4434.588295
  17. Tezuka, H., Hori, A, Ishikawa, Y. and Sato, M., 'PM : An Operating System Coordinated High Performance Communication Library,' Vol.1225 of Lecture Notes in Computer Science, pp.708-717, 1997
  18. Thomas E. Anderson, David E. Culler, David A Patterson, 'A Case for Networks of Workstations: NOW,' IEEE Micro, 1995 https://doi.org/10.1109/40.342018
  19. Barak A and La'adan O., 'The MOSIX Multicomputer Operating System for High Performance Cluster Computing,' Journal of Future Generation Computer Systems, Vol.13, No.4-5, pp.361-372, March 1998 https://doi.org/10.1016/S0167-739X(97)00037-X