|Introduction and Specifications|
OCZ already offers a wide array of popular, high performance SSDs, but to the company’s credit, it’s not resting on its laurels. After employing SandForce controllers on some of the earlier Vertex SSDs, OCZ snapped up Indilinx and is using what is now its own proprietary silicon in many of its drives. Thus, the brand new OCZ Vertex 450 SSD we'll be showing you here today with an Indilinx Barefoot 3 M10 series controller inside is very much a “vertical” effort, with the Indilinx and OCZ-owned PLX teams building both the silicon and firmware.
OCZ will be selling Vertex 450s in capacities of 128GB, 256GB, and 512GB. The 128GB version will offer 525/290 MBps sequential read/write speeds with 75,000/70,000 4KB random read/write IOPS. The larger-capacity versions offer markedly better performance specifications that are almost identical, with the only difference being that the 512GB model is rated for an additional 5MBps in sequential write speeds.
This Barefoot 3 M10 controller features an ARM Cortex core with an OCZ Aragon co-processor, a SATA 6Gbps interface, AES 256-bit encryption, ECC engine, and a power-optimized clock generator. The 2.5-inch Vertex 450 also offers TRIM support, bundled cloning software, and a suite of flash management tools designed to bolster both durability and reliability.
One physical difference between the Vertex 450 and the Vertex 4 is height; OCZ shaved 2.5mm off of the Z-Height with this new drive, which is now just 7mm high. Further, the casing looks decidedly more like an OCZ Vector drive than a Vertex, with a chunky-looking white rim and a black top with “Indilinx Infused” stamped on one corner.
Peering at the guts of the Vertex 450, you can see the Micron DRAM cache and 16 total (8 each on the top and bottom of the PCB) 16GB NAND flash chips that equal 256GB in total. In the Vertex 450, OCZ went with 20nm IMFT (a joint venture between Intel and Micron) MLC NAND flash chips over the previous Vertex’s 25nm flash.
Note that we’ve included some photos of and benchmark scores from the 240GB OCZ Vertex 3.20 in this review as well; OCZ released this drive a few weeks back, so we decided to include it here for reference. In short, this drive sports a SandForce 2281 controller and also features that 20nm synchronous MLC NAND flash (which helps reduce cost over previous models).
Going all-in on yourself is a bold move, but OCZ has fully embraced the risk--especially with another new Vertex on hand built with an alternative controller. The question is, did the bet pay off? Let’s dig into some benchmarks and suss it out.
|Test Setup, IOMeter 1.1 RC|
Our Test Methods: 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. Out testbed's motherboard was updated with the latest UEFI available as of press time and AHCI (or RAID) mode was enabled. The SSDs were secure erased before testing 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.
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 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 another with 4K transfers, 100% random, 100% writes.
In the default access pattern test, the OCZ Vertex 450 starts out in the middle of the pack, although as the concurrent I/Os ramp up, the drive performance improves. That pushes it past the Corsair Neutron into third place behind the OCZ Vector and Vertex 4. (It’s worth noting that the new SandForce-equipped Vector 3.20 performed poorly compared to the rest of the field in this test.)
It’s more of the same in total transfers, with the Vertex 450 finishing in third place in both the default and workstation access tests.
|SiSoft SANDRA 2013|
|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 (which is a requirement for the write test) and read and write performance metrics are detailed below.
In SiSoft SANDRA, the Vertex 450 delivers outstanding performance, besting the field in both read and write speeds. Perhaps most revealing is the gaping delta between the Vertex 450 and the Vertex 4.
|ATTO Disk Benchmark|
|ATTO is another "quick and dirty" type of disk benchmark that measures transfer speeds across a specific volume length. It measures raw transfer rates for both reads and writes and graphs them out in an easily interpreted chart. We chose .5kb through 8192kb transfer sizes and a queue depth of 6 over a total max volume length of 256MB. ATTO's workloads are sequential in nature and measure raw bandwidth, rather than I/O response time, access latency, etc. This test was performed on blank, formatted drives with default NTFS partitions in Windows 7 x64.
The Vertex 450 carves a quirky path through our ATTO chart, spiking and then dipping sharply at the 16KB and 32KB transfer sizes, respectively, in both the read and write tests.
In any case, however, the drive performed well, coming in what is essentially a three-way tie for first in the write test with the Corsair Force GT and the OCZ Vertex 3.20, leaving all but the OCZ Vector behind.
Things were much more tightly grouped in the read test, with four drives scoring within just a few MBps of one another and only one SSD (the Corsair Neutron) delivering less than 500MBps.
|HD Tune Benchmarks|
|EFD Software's HD Tune is described on the company's web site as such: "HD Tune is a hard disk utility with many functions. It can be used to measure the drive's performance, scan for errors, check the health status (S.M.A.R.T.), securely erase all data and much more." The latest version of the benchmark added temperature statistics and improved support for SSDs, among a few other updates and fixes.
As we’ve seen so far, the OCZ Vertex 450 is a formidable drive in most of our tests, and indeed the trend continues here as the SSD beats the field in the average transfer rate and burst rate tests. It also had the second-best access time, bowing only to the Vertex 4.
The SandForce-powered Vertex 3.20 didn't fare quite as well and offered middling performance in this group of tests.
CrystalDiskMark is a synthetic benchmark that tests both sequential and random small and mid-sized file transfers using incompressible data. It provides a quick look at best and worst case scenarios with regard to SSD performance, best case being larger sequential transfers and worse case being small, random transfers.
SandForce-based drives have performed well in CrystalDiskMark’s sequential transfers (including apparently the Vertex 3.20, which also posted a strong write score), and the Vertex 450 didn’t catch them all, but it got a lot closer than the Vertex 4 did. The drive also topped the field in the 512K transfer write test (coming in a close third in the read test), giving the SandForce based drives a run for their money.
|AS-SSD Compression Test|
Next up we ran the Compression Benchmark built-into AS SSD, an SSD specific benchmark being developed by Alex Intelligent Software. This test is interesting because it uses a mix of compressible and incompressible data and outputs both Read and Write throughput of the drive. We only graphed a small fraction of the data (1% compressible, 50% compressible, and 100% compressible), but the trend is representative of the benchmark’s complete results.
In the AS-SSD read test, the Vertex 450, like all of the other drives, posted extremely consistent scores--except for the Vertex 3.20, which had a rough start due to the 1% compressible data.
|PCMark 7 Storage Benchmarks|
|We really like PCMark 7's Secondary Storage benchmark module for its pseudo real-world application measurement approach to testing. PCMark 7 offers a trace-based measurement of system response times under various scripted workloads of traditional client / desktop system operation. From simple application start-up performance, to data streaming from a drive in a game engine, and video editing with Windows Movie Maker, we feel more comfortable that these tests reasonably illustrate the performance profile of SSDs in an end-user / consumer PC usage model, more so than a purely synthetic transfer test.
SandForce drives seem to do well in PCMark 7’s secondary storage benchmark, but the Vertex 450 put up a very strong score and finished second best in the group.
The deltas separating the scores in PCMark 7 are relatively miniscule, but even so, the Vertex 450 scored among the top two or three drives in every sub-test.
|Our Summary and Conclusion|
Performance Summary: There’s no question that OCZ has a really nice drive on its hands with the 256GB Vertex 450 SSD. In most of our benchmark tests, it either beat the competition or hung close to the top two or three drives. Regardless, the Vertex 450 showed solid consistency and great bandwidth across all workloads. Of particular note is the remarkable improvement over the previous-gen Vertex 4 in terms of write speeds, which rival or exceed the SandForce-based SSDs in our test bank. And unlike SandForce SSDs, the Indilinx-based Vertex 450 didn’t have any issues with compression-related performance penalties.
Generationally, the Vertex 450 seems to mostly fit the profile of the original Vertex 3--consistent and high-performance. OCZ should be relieved to see its homegrown SSD faring so well versus some of the market's top competitors. However, for as solid a drive as the Vertex 450 is, it doesn't always outshine the competition in every test--there are even one or two in which the Vertex 4 actually does better.