While modern storage controllers can make available immense amount of space, in a real-life scenario, workloads actively use only a fraction of the total available storage space known as the footprint. Generally speaking, for random workloads, for a given cache size, the larger the footprint, the smaller the hit ratio, and vice versa. In this paper, we will use the following two different back-end configurations in conjunction with the SPC-1 Like workload:
| ASU-1 | ASU-2 | ASU-3 | |
| (percentages) | 45 | 45 | 10 |
| cache-sensitive (GB) | 45 | 45 | 10 |
| cache-insensitive (GB) | 1443 | 1443 | 320 |