
In practice, SandForce based drives running a desktop workload do very well and typically boast an average write amplification below 1 (more writes to the device than actual writes to NAND). My personal SF-1200 drive had a write amplification of around 0.6 after several months of use. However if subjected to a workload composed entirely of incompressible writes (e.g. tons of compressed images, videos and music) you can back the controller into a corner.
To simulate this I filled the drive with incompressible data, ran a 4KB (100% LBA space, QD32) random write test with incompressible data for 20 minutes, and then ran AS-SSD (another incompressible data test) to see how low performance could get:
| OCZ Vertex 3 240GB - Resiliency - AS SSD Sequential Write Speed - 6Gbps | |||||
| Clean | After Torture | After TRIM | |||
| OCZ Agility 3 240GB | 238.6 MB/s | 206.1 MB/s | 213.2 MB/s | ||
| OCZ Vertex 3 240GB | 284.4 MB/s | 278.5 MB/s | 286.3 MB/s | ||
The 240GB Agility 3 behaves similarly to the Vertex 3, although it does lose more ground after our little torture session. There's a sharp drop after about 60 minutes of random writes on these 240GB drives, so performance can definitely go lower if you torture for longer - most users should be just fine though.
One benefit of the asynchronous NAND is much lower power consumption. The Agility 3 posted the lowest idle power draw of any modern drive we've tested and load power is better than any other SF-2200 drive.



A lot of us are waiting for a non-ocz sandforce 6 GBs drive.