eWEEK Labs has just completed one of the most comprehensive, real-world style tests of Linux, open source and .NET application stacks. The results were, from a Linux fans point of view, annoying.
The tests showed that such vanilla LAMP (Linux, Apache, MySQL, PHP/Python/PERL) stacks as SLES (SUSE Enterprise Linux Server) 9, Zope, ZODB, and PHP and a pure LAMP based on SLES, produced "C" results.
They werent bad, but they werent anywhere near as good as an out of the box .NET stack based on Windows Server 2003, IIS (Internet Information Server), SQL Server 2005, ASP (Active Server Pages) and SharePoint Portal Server 2003.
Now, having created and run just such tests myself, I know exactly why these benchmarks produced their results.
Indeed, eWEEK Labs agrees with me and points these factors out. For example, all their tests were based on standard portal configuration setups. So, youre not really testing the stacks themselves, youre testing the portals.