Test Setup, IOMeter 1.1, Compression Tests
Our Test Methodologies: Under each test condition, the Solid State Drives tested here were installed as secondary volumes in our testbed, with a separate drive used for the OS and benchmark installations. Out testbed's motherboard was updated with the latest BIOS available at the time of publication and AHCI (or RAID) mode was enabled.
The SSDs were secure erased prior to testing, and left blank without partitions for some tests, while others required them to be partitioned and formatted, as is the case with our ATTO, PCMark, SANDRA, 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, waited several minutes for drive activity to settle and for the system to reach an idle state before invoking a test.
Video Card -
Intel Core i7-6700K
Asus Z170 Deluxe
(Z170 Chipset, AHCI Enabled)
Intel HD 430
16GB Corsair DDR4-2666
Integrated on board
Corsair Force GT (OS Drive)
Intel SSD 750
Toshiba OCZ RD400 (1TB & 512GB)
Samsung SSD 850 EVO M.2
Samsung SSD 950 PRO M.2 NVMe
Kingstin HyperX Predator
Chipset Drivers -
Video Drivers -
Windows 10 Pro x64
Intel 10.1.19, iRST 188.8.131.521
Intel HD 184.108.40.20648
IOMeter 1.1.0 RC
HD Tune v5.60
CrystalDiskMark v5.0.2 x64
SiSoftware Sandra 2015 SP3
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--the access patterns we tested may not reflect your particular workload. 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 available currently.
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 a 4K access pattern with a 4K transfer size, comprised of 67% reads (34% writes) and 100% random access.
The Toshiba OCZ RD400 series drives finished about in the middle of the pack here. Most of the drives are grouped relatively close together, except for the Intel SSD 750 which pulls well head as the queue depth is increased.
The overall bandwidth numbers show the Toshiba OCZ RD400 series drives trailing the Samsung and Intel offerings, with the access patterns we used to test. Bandwidth here just misses the 1GB/s mark in the workstation access pattern.
The compressibility of data being transferred on the Toshiba OCZ RD400 series drives is not supposed to affect performance, but we saw some wild swings in this test, that were confirmed by our contacts at OCZ. Take a look...
Normally you'd see a relatively flat line here for both reads and writes, but there are some significantly valleys with the Toshiba OCZ RD400 series drives at the beginning of the test and just after the 50% mark. The RD400 doesn't use a compression engine, so the best explanation for what's happening here is that parts of the test happen at different block sizes and/or queue depths and hit different parts of the RD400 performance curve.