Abstract
Standard user-level networking architecture such as Virtual Interface (VI) Architecture enables distributed applications to perform low overhead communication over System Area Networks (SANs). This paper describes how high-level communication paradigms like stream sockets and remote procedure call (RPC) can be efficiently built over user-level networking architectures. To evaluate performance benefits for standard client-server and multi-threaded environments, our focus is on off-the-shelf sockets and RPC interfaces and commercially available VI Architecture based SANs. The key design techniques developed in this research include credit-based flow control, decentralized user-level protocol processing, caching of pinned communication buffers, and deferred processing of completed send operations. The one-way bandwidth achieved by stream sockets over VI Architecture was 3 to 4 times better than the same achieved by running legacy protocols over the same interconnect. On the same SAN, high-performance stream sockets and RPC over VI Architecture achieve significantly better (between 2-3x) latency than conventional stream sockets and RPC over standard network protocols in Windows NTTM 4.0 environment. Furthermore, our high-performance RPC transparently improved the network performance of Distributed Component Object Model (DCOM) by a factor of 2 to 3.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bilas, A., Felten, E.W.: Fast RPC on the SHRIMP Virtual Memory Mapped Network Interface. J. of Parallel and Distributed Computing 40(1), 138–146 (1997)
Blumrich, M., et al.: A Virtual Memory Mapped Network Interface for the Shrimp Multicomputer. In: Proceedings of the 21st Annual Symposium on Computer Architecture, pp. 142–153 (1994)
Chang, C.-C., von Eicken, T.: A Software Architecture for Zero-Copy RPC in Java. CS Technical Report 98-1708, Cornell University (1998)
Damianakis, S.N., Dubnicki, C., Felten, E.W.: Stream Sockets on SHRIMP. In: Proceedings of 1st International Workshop on Communication and Architectural Support for Network-Based Parallel Computing (1997)
DCOM Architecture. Microsoft Corporation (1997)
Dunning, D., et al.: The Virtual Interface Architecture: A Protected, Zero Copy, User-level Interface to Networks. IEEE MICRO 18(2), 66-76 (1998)
von Eicken, T., et al.: U-Net: A User-Level Network Interface for Parallel and Distributed Computing. In: Proceedings of the 15th ACM Symposium on Operating System Principles. 40-53 (1995)
GigaNet Incorporated. GigaNet cLAN Product Family, http://www.giga-net.com/products
JavaTM Remote Method Invocation Specification, ftp://ftp.javasoft.com/docs/jdkl.2/rmi-spec-JDKL2.pdf
Madukkarumukumana, R.S., Pu, C., Shah, H.V.: Harnessing User-level Networking Architectures for Distributed Object Computing over High-Speed Networks. In: Proc. of 2nd USENIX Windows NT Symposium, pp. 127-135 (1998)
Muller, G., et al.: Fast, Optimized Sun RPC Using Automatic Program Specialization. In: Proceedings of the International Conference on Distributed Computing Systems, ICDCS-18, pp. 240-249 (1998)
Object Management Group: The Common Object Request Broker: Architecture and Specification. 2.0 Edition (1995)
Pakin, S., Karamcheti, V., Chien, A.A.: Fast Messages: Efficient, Portable Communication for Workstation Clusters and MPPs. IEEE Concurrency 5(2), 60–73 (1997)
Rodrigues, S.H., Anderson, T.E., Culler, D.E.: High-Performance Local Area Communication with Fast Sockets. In: USENIX 1997 Conference (1997)
Virtual Interface Architecture Specification. Version 1.0 (1997), http://www.viarch.org/
Windows Sockets 2 Service Provider Interface, ftp://ftp.microsoft.com/bussys/winsock/winsock2/
Zelesko, M.J., Cheriton, D.R.: Specializing Object-Oriented RPC for Functionality and Performance. In: Proceedings of the International Conference on Distributed Computing Systems, ICDCS-16 (1996)
Zimmer, O.M., Chien, A.A.: The Impact of Inexpensive Communication on a Commercial RPC System. In: Concurrent System Architecture Group Memo, University of Illinois at Urbana-Champaign and University of California at San Diego (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shah, H.V., Pu, C., Madukkarumukumana, R.S. (1999). High Performance Sockets and RPC over Virtual Interface (VI) Architecture. In: Sivasubramaniam, A., Lauria, M. (eds) Network-Based Parallel Computing. Communication, Architecture, and Applications. CANPC 1999. Lecture Notes in Computer Science, vol 1602. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10704826_7
Download citation
DOI: https://doi.org/10.1007/10704826_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65915-0
Online ISBN: 978-3-540-48869-9
eBook Packages: Springer Book Archive