For our today’s SSD test session we put together a system on an Intel H67 based mainboard. This chipset provides support for two SATA 6 Gbit/s ports, which we use to connect the tested SSDs.
We are going to compare Kingmax SMP35 Client 480 GB against a few different SSDs with the similar storage capacity supporting contemporary SATA 6 Gbps interface. They are a SF-2281 based SSD with typical synchronous ONFI memory (OCZ Vertex 3), as well as a pair of SSDs on Everest and Everest 2 chips (OCZ Octane and OCZ Vertex 4).
Overall our testbed was configured as follows:
- Intel Core i5-2400 (Sandy Bridge, 4 cores, 3.1 GHz, EIST and Turbo Boost turned off);
- Foxconn H67S mainboard (BIOS A41F1P03);
- 2 x 2 GB DDR3-1333 SDRAM DIMM 9-9-9-24-1T;
- Crucial m4 256 GB system disk (CT256M4SSD2);
- Tested SSDs:
- Kingmax SMP35 Client 480 GB (KM480GSMP35, firmware version L0306);
- OCZ Octane 512 GB (OCT1-25SAT3-512G, firmware version 1.13);
- OCZ Vertex 3 480 GB (VTX3-25SAT3-480G, firmware version 2.22);
- OCZ Vertex 4 512 GB (VTX4-25SAT3-512G, firmware version 1.4).
- Microsoft Windows 7 SP1 Ultimate x64
- Intel Chipset Driver 18.104.22.1689;
- Intel Graphics Media Accelerator Driver 22.214.171.12422;
- Intel Rapid Storage Technology 126.96.36.1996.
Random and Sequential Read/Write
We use CrystalDiskMark 3.0.1 benchmark to test the random- and sequential read and write speed. This benchmark is convenient to work with as it can measure the speed of an SSD with both incompressible random and fully compressible recurring data. This feature is important for testing SSDs based on SF-2281/2282 controller, which tries to compress the data before writing it into memory. So, there are two numbers in the diagrams below that reflect the maximum and minimum SSD speed. The real-life performance of an SSD is going to be in-between those two numbers depending on how effective the controller data compression is.
Note that the performance tests in this section refer to SSDs in their “Fresh Out-of-Box” state (FOB). No degradation could have taken place yet.
The Kingmax SMP35 Client 480GB can serve as a good illustration of the performance of second-generation SandForce controllers. You can see that its speed depends greatly on whether data are compressible or not.
When processing compressible files, the SSD is fast and competes with the Vertex 3. In other words, the SMP35 Client can match the best SATA III SSDs at sequential operations and when reading with a short request queue. But when it comes to incompressible data, the SandForce magic evaporates, exposing the low bandwidth of the asynchronous flash memory interface and making the SMP35 Client 480GB the worst SSD in this test.
Thus, the Kingmax is going to be always slower than SandForce-based SSDs with synchronous flash, such as the Vertex 3. Its standing relative to other SSDs is going to depend on the particular load. We'll check the SML35 Client out in real-life applications shortly. Right now let’s run our performance degradation tests.