SAS drives can address multiple IO operations from a single platter revolution if the data happens to be where the head is already positioned. How can you measure whether this actually makes a difference, comparing SATA vs. SAS, especially with a good raid card?
I have a Dell PE with a Perc 5, eight drive SATA raid. I can either replace SATA with SAS and the same raid card or replace the raid card and purchase new SATA drives. I have other servers that have SAS and wanted to know how I could measure (or if software exists to measure) the actual benefit of SAS over SATA?