THE SQL Server Blog Spot on the Web

Welcome to - The SQL Server blog spot on the web Sign in | |
in Search

Linchi Shea

Checking out SQL Server via empirical data points

Disk Partition Alignment in the Published TPC Benchmarks

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: 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.


Published Thursday, July 19, 2007 1:49 PM by Linchi Shea

Comment Notification

If you would like to receive an email when updates are made to this post, please register here

Subscribe to this post's comments using RSS



WesleyB said:

Interesting material Shea.  You made me curious too now :-(

July 19, 2007 2:44 PM

Chuck said:

Dude, you are the best.


July 19, 2007 11:43 PM

Leave a Comment


About Linchi Shea

Checking out SQL Server via empirical data points

This Blog


Privacy Statement