After the initial configuration and installation, we created a disk image that will be used to test every drive.
Automated updates were disabled for all programs. This ensures that—for every review—each drive uses the same settings without any interference from previous testing.
Our disk image consumes around 150 GB—we re-sized the partition to fill all available space on the drive.
Partitions are properly aligned.
In order to minimize random variation, each real-life performance test is run twelve times with reboots in-between tests to minimize the impact of disk cache. We use the average of the last ten runs as the final score.
All application benchmarks run the actual application and do not replay any disk traces.