System development using Java and distributed object technology (DOT) is becoming common, and can become the standard way of doing network computing in the near future. The performance of DOTs is crucial in high-performance network computing systems. In this paper, the performance of popular DOTs for Java is evaluated in a common environment employing the fastest available PCs and 100Mbps Ethernet. We evaluate HORB, Java RMI, Voyager, two commercial CORBA IIOP implementations, and Distributed COM. For comparison a Java socket version and a C socket version are also evaluated. In order to represent the characteristics of the DOT, the performance of primitive object operations including remote object creation, remote method call, transferring arrays of objects and transferring large numerical data is measured and evaluated. No DOT won all benchmarks, but HORB showed very good performance for most benchmarks.
[1]
Nick N. Duan.
Distributed Database Access in a Corporate Environment using Java
,
1996,
Comput. Networks.
[2]
Charlie Kindel,et al.
Distributed Component Object Model Protocol -- DCOM/1.0
,
1998
.
[3]
Marc Shapiro,et al.
Structure and Encapsulation in Distributed Systems: The Proxy Principle
,
1986,
ICDCS.
[4]
H. Kodama,et al.
Prototype performance of distributed DAQ using HORB based on Java
,
1998
.
[5]
Satoshi Hirano.
HORB: Distributed Execution of Java Programs
,
1997,
WWCA.