Evaluating CORBA Latency and Scalability Over High-Speed ATM Networks

Conventional implementations of CORBA communication middleware incur significant overhead when used for performance-sensitive applications over high-speed networks. As gigabit networks become pervasive, inefficient middleware will force programmers to continue using lowerlevel mechanisms to achieve necessary transfer rates and end-to-endlatency. Thisis aserious problem formission/lifecritical applications(such as real-time avionics, process control systems, and medical imaging). This paper provides two contributions to the study of CORBA performance over high-speed networks. First, we measure the latency of various types and sizes of oneway and twoway client requests using a pair of widely used implementations of two C++ implementations of CORBA – Orbix 2.1 and VisiBroker 2.0. Second, we use Orbix and VisiBroker to measure the scalability of CORBA servers in terms of the number of objects they can support efficiently. These experiments extend our previous work on CORBA performanc...

• Type: Conference
• Year: 1997
• Where: ICDCS
• Authors: Douglas C. Schmidt, Aniruddha S. Gokhale
• Keywords: CORBA, CORBA Implementations, CORBA Performance, Distributed And Parallel Computing, ICDCS 1997