The Impact of Spare Area on SandForce, More Capacity At No Performance Loss?
Final Words
Unless I’m missing something here, it looks like SandForce can definitely improve its price/performance ratio by reducing the overprovisioning percentage on its consumer drives.
Based on current Agility 2 pricing, here’s how things could change with this new firmware:
| Pricing Comparison | |||||||
| Drive | NAND Capacity | User Capacity | Drive Cost | Cost per GB of NAND | Cost per Usable GB | ||
| OCZ Agility 2 (28% OP) | 128GB | 93.1GB | $399 | $3.117 | $4.286 | ||
| OCZ Agility 2 (13% OP) | 128GB | 111.8GB | $399 (est) | $3.117 | $3.569 | ||
| Corsair Nova V128 | 128GB | 119.2GB | $369 | $2.882 | $3.096 | ||
| Crucial RealSSD C300 | 128GB | 119.2GB | $419 | $3.273 | $3.515 | ||
| Intel X25-M G2 | 160GB | 149.0GB | $450 | $2.813 | $3.020 | ||
By moving to 13% over provisioning you drop the cost per usable GB to roughly 83% of what it is on current SF-1200 drives at virtually no impact to performance in typical workloads. It’s still not as cheap as an X25-M in terms of dollars per GB, but you are getting better performance. And the best part? It doesn’t even require a different chip - only different firmware.
If they choose to, existing SF-1200 drive manufacturers could load this firmware on their drives and give their customers more user capacity up front. It could even be a user configurable option if a manufacturer wanted to enable it. Unfortunately there's no guarantee that we'll see this made available at no extra charge. Vendors could be particularly evil and charge more for a simple change in the amount of spare area you get on a drive. I'd highly recommend against it though.
The Rest of the Tests
In our standard tests without unfairly penalizing the drive, the special Agility 2 performs similarly to the standard shipping drive. The only real exception is PCMark Vantage's HDD test which saw a ~4.6% increase in performance. Without knowing what other changes exist in the firmware it's difficult to pinpoint the cause. It's a little large to be normal benchmark variance so there could be other optimizations in this version of the firmware.
For those who want the standard comparison charts, I've included those results on the following pages.
I've trimmed down some of our charts, but as always if you want a full rundown of how these SSDs compare against one another be sure to use our performance comparison tool: Bench.
| CPU | Intel Core i7 965 running at 3.2GHz (Turbo & EIST Disabled) |
| Motherboard: | Intel DX58SO (Intel X58) |
| Chipset: | Intel X58 + Marvell SATA 6Gbps PCIe |
| Chipset Drivers: | Intel 9.1.1.1015 + Intel IMSM 8.9 |
| Memory: | Qimonda DDR3-1333 4 x 1GB (7-7-7-20) |
| Video Card: | eVGA GeForce GTX 285 |
| Video Drivers: | NVIDIA ForceWare 190.38 64-bit |
| Desktop Resolution: | 1920 x 1200 |
| OS: | Windows 7 x64 |
Originally published at https://www.anandtech.com/show/3690/the-impact-of-spare-area-on-sandforce-more-capacity-at-no-performance-loss (Wayback Machine).