Endurance Testing
SSD vendors selling SandForce-based drives are incredibly enthusiastic about differentiating their offerings. There are three aspects of solid-state storage that affect performance: the controller, the NAND, and the firmware. We all know that these drives center on the same firmware. We've seen that the flash does have some affect on performance, though two drives with the same configuration are pretty much comparable. So, they try to sell us on custom firmware with home-brewed optimizations not offered by other vendors.
Can we create of list of what those tweaks entail? Unfortunately not. No SSD vendor has ever gotten specific with us about what its "golden" or "purely in-house" firmware includes that other vendors don't have.
What we do know is that the basic core of SandForce’s compression technology cannot be altered. We tested for this in Intel SSD 520 Review: Taking Back The High-End With SandForce by measuring endurance by writing highly compressible data. What we found were close to identical values for write amplification. When write amplification is similar, then we know that two drives (in this case, the oldest and newest SandForce-based SSDs) are benefiting from the same level of compression.
128 KB Compressible Sequential Write1 Hour, QD=1 | Intel SSD 52060 GB | OCZ Vertex 360 GB |
---|---|---|
Host Writes | 1258 GB | 1301 GB |
NAND Writes | 176 GB | 182 GB |
Write Amplification | 0.13990 | .139892 |
In the time between publishing our SSD 520 review and now, we've seen similar results from all of the 60 GB SF-22xx-based SSDs in our lab, suggesting that every vendor using SandForce's technology enjoys the same degree of compression, which most influentially affects the performance of these drives.