In SQL Server related storage literature, it is almost univerally recommended that disk partitions be aligned either on the 32K or the 64K boundary. On this subject, I posted some test results a while back, regarding the performance impact of disk partition misalignment: http://sqlblog.com/blogs/linchi_shea/archive/2007/02/01/performance-impact-of-disk-misalignment.aspx. The results seem to be consistent with the recommendation.
Given its pervasive nature, anybody who has anything to do with SQL Server storage practices for sure knows about this recommendation. And one should therefore expect to see this practice being widely followed, especially in highly competitive benchmarks where people want to squeeze out the last drop of performance.
Well, I was surprised to find out that this is not the case in many published TPC-C benchmark results. Open one of the following HP TPC-C Full Disclosure Reports, search for partition starting offset, and you'll find that the partitions are aligned on the 31.5K boundary:
And there are more. The following TPC-C Full Disclosure Reports show that while some partitions are aligned on the 64K boundary, the others are aligned on the 31.5K bounary:
Considering how much efforts are generally put into these benchmarks, I'd think that the partitions used in these TPC-C benchmark tests are aligned as such for specific good reasons--after careful evaluation. But I'm curious about what these good reasons may be.