Considering he's modeling the drive writing at the full SATA 3.0 interface speed for the entire lifespan of the drive, continuously, amplification shouldn't affect his numbers, only the perceived throughput the user receives under this workload. He mentions this is already faster than the drive can actually write: "the maximum link speed for SATA 3.0, which happens to be larger than any other relevant interface or drive speed so it's a solid upper bound."
I thought write amplification happened inside the drive (due to the drive internally working in bigger blocks than the 512-byte sectors it presents to the outside world), so the amount of data written to flash would be greater than the amount sent over the SATA link?
