Limits to low-latency communication on high-speed networks
ACM Transactions on Computer Systems (TOCS)
Virtual memory mapped network interface for the SHRIMP multicomputer
ISCA '94 Proceedings of the 21st annual international symposium on Computer architecture
U-Net: a user-level network interface for parallel and distributed computing
SOSP '95 Proceedings of the fifteenth ACM symposium on Operating systems principles
Measuring the performance of communication middleware on high-speed networks
Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Fast RPC on the SHRIMP virtual memory mapped network interface
Journal of Parallel and Distributed Computing - Special issue on workstation clusters and network-based computing
Flick: a flexible, optimizing IDL compiler
Proceedings of the ACM SIGPLAN 1997 conference on Programming language design and implementation
Measuring and Optimizing CORBA Latency and Scalability Over High-Speed Networks
IEEE Transactions on Computers
The Coign automatic distributed partitioning system
OSDI '99 Proceedings of the third symposium on Operating systems design and implementation
Fast Messages: Efficient, Portable Communication for Workstation Clusters and MPPs
IEEE Parallel & Distributed Technology: Systems & Technology
Fast, Optimized Sun RPC Using Automatic Program Specialization
ICDCS '98 Proceedings of the The 18th International Conference on Distributed Computing Systems
A Software Architecture for Zero-Copy RPC in Java
A Software Architecture for Zero-Copy RPC in Java
WINSYM'98 Proceedings of the 2nd conference on USENIX Windows NT Symposium - Volume 2
Detours: binary interception of Win32 functions
WINSYM'99 Proceedings of the 3rd conference on USENIX Windows NT Symposium - Volume 3
Hi-index | 0.00 |
In this paper, we describe an approach to build high-performance, commercial distributed object systems over system area networks (SANs) with user-level networking. The specific platforms we use in this study are the Virtual Interface Architecture (VIA) and Microsoft's Distributed Component Object Model (DCOM). We give a detailed functional and performance analysis of DCOM and apply optimizations at several layers to take full advantage of modern high-speed networks. Our optimizations preserve the full set of DCOM features including security, alternative threading models, and Microsoft Transaction Server (MTS). Through extensive runtime, transport and marshaling optimization, our system achieves round-trip latencies of 72 microseconds for DCOM calls and 174 microseconds for MTS calls, and an application bandwidth of 86.1 megabytes per second. We also examine the performance gains in real applications.