Our Test Methodologies: Under each test condition, the Solid State Drives tested here were installed as secondary volumes in our testbed, with a standard spinning hard disk for the OS and benchmark installations. Our testbed's motherboard was updated with the latest BIOS available as of press time and AHCI (or RAID) mode was enabled. The SSDs were secure erased and left blank without partitions wherever possible, unless a test required them to be partitioned and formatted, as was the case with our ATTO, PCMark 7, and CrystalDiskMark benchmark tests. Windows firewall, automatic updates and screen savers were all disabled before testing. In all test runs, we rebooted the system, ensured all temp and prefetch data was purged, and waited several minutes for drive activity to settle and for the system to reach an idle state before invoking a test.
|
HotHardware Test System |
Intel Core i7 and SSD Powered |
|
Processor -
Motherboard -
Video Card -
Memory -
Audio -
Hard Drives -
|
Hardware Used:
Intel Core i7-2600K
Asus P8Z6-V Pro
(Z68 Chipset, AHCI Enabled)
NVIDIA GeForce GTX 285
4GB Kingston DDR3-1600
Integrated on board
WD Raptor 150GB (OS Drive)
Samsung SSD 830 (256GB)
OCZ Vertex 3 (480GB)
Corsair Force GT (240GB)
Crucial M4 (256GB)
OCZ Octane (512GB)
Intel SSD 520 (240GB)
OCZ Vertex 4 (256GB & 512GB) |
OS -
Chipset Drivers -
DirectX -
Video Drivers -
|
Relevant Software:
Windows 7 Ultimate SP1 x64
Intel 9.2.0.1030, iRST 10.5.1027
DirectX 11
NVIDIA GeForce 275.33
Benchmarks Used:
IOMeter 1.1.0 RC
HD Tune v4.61
ATTO v2.47
AS SSD
CrystalDiskMark v3.01 x64
PCMark 7
SiSoftware Sandra 2011
|
|
IOMeter |
I/O Subsystem Measurement Tool |
|
As we've noted in previous SSD articles, though IOMeter is clearly a well-respected industry standard drive benchmark, we're not completely comfortable with it for testing SSDs. The fact of the matter is, though our actual results with IOMeter appear to scale properly, it is debatable whether or not certain access patterns, as they are presented to and measured on an SSD, actually provide a valid example of real-world performance for the average end user. That said, we do think IOMeter is a reliable gauge for relative available throughput within a given storage solution. In addition, there are certain higher-end workloads you can place on a drive with IOMeter that you can't with most other storage benchmark tools currently available.
In the following tables, we're showing two sets of access patterns; our custom Workstation pattern, with an 8K transfer size, 80% reads (20% writes) and 80% random (20% sequential) access and IOMeter's default access pattern of 2K transfers, 67% reads (34% writes) and 100% random access.
On the Default test, our 128GB Vertex 4 easily bested the field in terms of IOps, MBps, average response time, and maximum response time. CPU utilization, unfortunately, was comparatively high at nearly 12%.
Our custom Workstation test tells a different story. The CPU utilization is much better, although it still isn’t exactly stellar, and again the maximum response time is tops by a longshot. However, the 128GB Vertex 4 struggled to keep up in IOps and MBps, posting the lowest scores in each area.
|
SiSoft SANDRA 2011 |
Synthetic HDD Benchmarking |
|
Next we ran SiSoft SANDRA, the the
System
ANalyzer,
Diagnostic and
Reporting
Assistant. Here, we used the Physical Disk test suite and provided the results from our comparison SSDs. The benchmarks were run without formatting and read and write performance metrics are detailed below.
This SiSoft SANDRA score is a bit of a head-scratcher; the bigger Vertex 4 SSDs we tested posted lack-luster read scores but comparatively stellar write scores, and the 128GB Vertex 4 shows the opposite. Its write score is not very good at all, and although the read score is much better--higher than both of the larger Vertex 4s--it’s still unimpressive compared to the rest of the field. We'll chalk that up to the firmware update the 128GB Vertex 4 enjoys that the other Vertex 4s here did not; the update was supposed to, in part, fix the problem of poor sequential read speeds.