On Thu, 14 May 2009, [email protected] wrote:
I see alot of people use iozone, but I don't really understand why some of the performance numbers exceed the maximum throughput in theory for 12 SAS disks.
In order to effectively use iozone to measure "hardware" I/O you need to use huge files which are at least several times larger than available RAM. Otherwise you are measuring the effectiveness of the system caching (e.g. ARC cache) and you will find that Solaris is very effective at caching.
For testing the performance of synchronous writes you can use smaller files, but the system cache still helps quite a lot whenever some data needs to be read (such as when only part of a zfs block is updated).
Bob -- Bob Friesenhahn [email protected], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/ _______________________________________________ storage-discuss mailing list [email protected] http://mail.opensolaris.org/mailman/listinfo/storage-discuss
