An experimental study of DCE performance in an ATM environment

ABSTRACT

Many factors affect distributed system performance. With new opportunities and challenges presented by high speed network technologies, previous design or implementation decisions based on low speed networks might have become inappropriate over high speed networks. This research focuses on OSF DCE RPC performance in an ATM LAN environment. By measuring performance over both Ethernet and ATM, the study investigates what impact an ATM network has on DCE RPC performance. The study addresses factors that affect DCE RPC performance, how they affect it, and how much they affect it. It reveals aspects of distributed system design and implementation that may need reconsideration in order to gain the performance improvement expected from a move to a high speed network.

REFERENCES

• 1: {1} Y. An. Performance implications of high speed networks for distributed systems. M.Sc. thesis, Department of Computer Science, University of Saskatchewan, June 1998.
• 2: M. A. Bauer , R. B. Bunt , A. El Rayess , P. J. Finnigan , T. Kunz , H. L. Lutfiyya , A. D. Marshall , P. Martin , G. M. Oster , W. Powley , J. Rolia , D. Taylor , M. Woodside, Services supporting management of distributed applications and systems, IBM Systems Journal, v.36 n.4, p.508-526, 1997
• 3: {3} D. Berding. Distributed performance of IBM AIX 2.1 DCE RPC for AIX version 4.1. Technical report, IBM DCE Development, Austin, TX, May 1996. http://www.ibm.com/.
• 4: Philip A. Bernstein, Middleware: a model for distributed system services, Communications of the ACM, v.39 n.2, p.86-98, Feb. 1996 [doi>10.1145/230798.230809]
• 5: Andrew D. Birrell , Bruce Jay Nelson, Implementing remote procedure calls, ACM Transactions on Computer Systems (TOCS), v.2 n.1, p.39-59, February 1984 [doi>10.1145/2080.357392]
• 6: {6} M. Carter. Adding 50,200 entries to a DCE namespace: A comparison of OSF DCE V1.0.2 and IBM DCE/6000 V1.2. Technical Report CITI-TR-93-12, Center for Information Technology Integration, University of Michigan, December 1993.
• 7: {7} M. Carter. Adding 50,200 entries to a DCE registry: A comparison of OSF DCE V1.0.2 and IBM DCE/6000 V1.2. Technical Report CITI-TR-94-1, Center for Information Technology Integration, University of Michigan, February 1994.
• 8: {8} S. Chung, E. Lazowska, D. Notkin, and J. Zahorjan. Performance implications of design alternative for remote procedure call stubs. In Proceedings of the 9th International Conference on Distributed Computing Systems, pages 36-41, Newport Beach, CA, June 1989.
• 9: {9} D. Comer and J. Lin. TCP buffering and performance over an ATM network. Internetworking: Research and Experience, 6(1):1-14, March 1995.
• 10: {10} C. Corn, T. Li, R. Pekowski, and B. Santeford. Performance of key functions in DCE for OS/2. IBM Personal Systems Technical Solutions, pages 60-70, January/February 1994.
• 11: B. Dasarathy , Khalid Khalil , David E. Ruddock, Some DCE Performance Analysis Results, Proceedings of the International DCE Workshop on DCE - The OSF Distributed Computing Environment, Client/Server Model and Beyond, p.47-62, October 07-08, 1993
• 12: {12} R. Friedrich and J. Rolia. Performance evaluation of a distributed application performance monitor. In Proceeding of International Conference on Distributed Platforms , 1996.
• 13: {13} J. Howe. An environment for "sniffing" DCE-RPC traffic. Technical Report CITITR-93-4, Center for Information Technology Integration, University of Michigan, June 1993.
• 14: {14} R. Jain. The Art of Computer Systems Performance Analysis: Techniques for Experimental Design, Measurement, Simulation, and Modeling. John Wiley & Sons, Inc, 1991.
• 15: A. M. Khandker , P. Honeyman , T. J. Teorey, Performance of DCE RPC, Proceedings of the 2nd International Workshop on Services in Distributed and Networked Environments, p.2, June 05-08, 1995
• 16: Joseph J. Martinka , Richard J. Friedrich , Peter M. Friedenbach , Traci F. Sienknecht, A Performance Study of the DCE 1.0.1 Cell Directory Service: Implications for Application and Tool Programmers, Proceedings of the International DCE Workshop on DCE - The OSF Distributed Computing Environment, Client/Server Model and Beyond, p.63-77, October 07-08, 1993
• 17: Kjersti Moldeklev , Per Gunningberg, How a large ATM MTU causes deadlocks in TCP data transfers, IEEE/ACM Transactions on Networking (TON), v.3 n.4, p.409-422, Aug. 1995 [doi>10.1109/90.413215]
• 18: {18} B. Nelson. Remote procedure call. Technical Report CSL-81-9, Xero Palo Alto Research Center, Palo Alto, CA, 1981.
• 19: {19} G. Oster and R. Bunt. Monitoring DCE runtime performance using shim technology. In Proceeedings CASCON'97, pages 96-107, Toronto, ON, November 1997.
• 20: {20} B. Perry and B. Russell. Distributed performance characteristics of IBM DCE for OS/2. IBM Personal Systems Technical Solutions, pages 50-58, January/February 1994.
• 21: {21} B. Perry and B. Russell. IBM DCE for OS/2 multiuser application performance. IBM Personal Systems Technical Solutions, pages 50-58, January/February 1994.
• 22: Ward Rosenberry , David Kenney , Gerry Fisher, Understanding DCE, O'Reilly & Associates, Inc., Sebastopol, CA, 1992
• 23: {23} B. Russell. DCE performance study. http://www.ibm.com/dce/performance, November 1994.
• 24: {24} B. Russell. DCE cell performance: High water marks. IBM Personal Systems Technical Solutions, pages 57-62, November/December 1995.
• 25: {25} Y. Sun. Measuring and modelling RPC performance in OSF DCE. M.Sc. thesis, Department of Computer Science, University of Saskatchewan, November 1997.
• 26: Ying Sun , Rick Bunt , Greg Oster, Measuring RPC Traffic in an OS/2 DCE Environment, Proceedings of the 5th International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, p.51, January 12-15, 1997
• 27: {27} J. White. A high-level framework for network-based resource sharing. In Proceedings of the National Computer Conference , June 1976.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.4 PERFORMANCE OF SYSTEMS
      Subjects: Performance attributes

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.4 Parallel Architectures
          Subjects: Distributed architectures
  C.2 COMPUTER-COMMUNICATION NETWORKS
      C.2.1 Network Architecture and Design
          Subjects: Distributed networks
      C.2.5 Local and Wide-Area Networks
          Subjects: High-speed (e.g., FDDI, fiber channel, ATM)

  D. Software
  D.4 OPERATING SYSTEMS
      D.4.7 Organization and Design
          Subjects: Distributed systems

General Terms:
Algorithms, Design, Experimentation, Measurement, Performance, Theory