TheServerSide.NET has done a performance benchmark specifically around benchmarks comparing the following four configurations against each other:
- Sun JWSDP 1.5 / Sun HTTP Server 6.1
- IBM WebSphere 6.0 / IBM HTTP Server 6.0
- .NET 1.1 / IIS 6.0
- .NET 2.0 / IIS 6.0
They said, extensive time was taken to tune all the above following each vendor’s best practices and iterative testing to get the best result. For all configurations, tracing, logging, authentication and session state was switched off. Also the Java heap sizes and thread settings were tuned for max. performance. And, all tests were run on the same hardware (in this case a AMD Opteron 1.8 ghz).
Read up the full details of the wbeservices tested, including further breakdown of the statistics and also a discussion of the test methodologies used.
Conclusion: The results indicate that Web Service performance is roughly 25% better in .NET 2.0 than .NET 1.1 when the soap object size is large and hence deserialization/serialization operations are more intensive. The difference is even more dramatic for smaller SOAP message sizes, with the echostruct size 20 test showing .NET 2.0 beta2 performance to be roughly 40% better than .NET 1.1. In all cases using the 50-client methodology (read on their site for the webservice details), .NET outperforms both SunOne and IBM Websphere 6.0, often by wide margins.