 |
 |
 |
||
|
|
||||
 |
|
|
| Introduction and Specifications | ||||||
| Back in April, we ran a pair of OCZ Vertex 4 SSDs (256GB and 512GB) through the benchmark grinder to see what they could do and also told you everything you ever wanted to know about them in the process. Today, we’re testing another brother in the family, the 128GB OCZ Vertex 4. When we first tested the aforementioned drives, we found that the latest generation of the Vertex series delivered somewhat uneven performance. In some workloads, the drives more or less smoked the competition, while they stumbled a bit in others. The bottom line was that the OCZ Vertex 4 SSDs were mostly impressive, but they didn’t demonstrate quite the upgrade from the previous-generation Vertex 3s that we would have liked. Between then and now, however, OCZ has tended to the Vertex 4 SSD line by upgrading its firmware. On the pages ahead we’ll get a gander at how the updated 128GB OCZ Vertex 4 stacks up against other drives with similar capacities and see if it can demonstrate a greater performance enhancement over the competition than the 256GB and 512GB versions did. We’ll also check in on how (or if) pricing has changed over the last few months; in April, the Vertex 4s were going for about $1.47 per GiB, which put them right around of the middle of the competition in terms of cost. First, though, let’s have a look at the 128GB OCZ Vertex 4’s specs. ;) OCZ Vertex 4 SSD 128GB
Before the firmware update, the 128GB Vertex 4 was rated for 535MBps/200MBps read/write times, but now OCZ promises 560MBps/430MBps performance; that’s a huge leap forward (more than double) for the SSD’s write performance. The 128GB Vertex 4 also features 90,000/85,000 random 4k read/write IOPS, with a maximum of 120,000 IOPS and a SATA III (6Gbps) interface. ;) ;) ;) ;) A closer look at the actual PCB reveals the same Indilinx Everest 2 (IDX400M00-BC) controller we saw in the 256GB and 512GB Vertex 4s, which supports up to 8 channels and 16-way Interleaving (and lacks the compression limitations found in the SandForce controllers OCZ previously used in some of its SSDs.) ;) ;) The actual NAND and DRAM chips are different; the 128GB version of the Vertex 4 has sixteen Intel 25nm 8GB synchronous MLC flash chips (29F64G08ACME2), and eight each are stamped on the top and bottom of the PCB. That happens to be the same NAND that OCZ used in the 128GB Vertex 3 SSDs. This SSD also has 1GB of DRAM courtesy of a pair of Micron. |
| Test Setup, IOMeter 1.1 RC, and SANDRA | ||||||||||||||||
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.
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.
 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.
|
| 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.
  In the read tests, the 128GB Vertex 4 hung with the pack for the most part, posting speeds within shouting distance of the top performer, and it actually bested the other Vertex 4s by a hair in most of the transfers. Write performance is another story; in those tests, our SSD climbed up to over 191MBps quickly but then plateaued a notch behind the performance of the other drives in our test.
|
| 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.
    Just as in the SANDRA test, the 128GB Vertex 4 posted mixed scores compared to the other Vertex 4s; in the Average Transfer Rate test, it again delivered a relatively low write score but a read score that was slightly faster than its bigger brothers. All of the Vertex 4s lagged behind the field in that one.
The SandForce-equipped SSDs did well in the Burst Rate test, while the Vertex 4s competed in a second-tier bracket with the Crucial M4. Looking at Access Time, all three Vertex 4s had nearly identical scores, and they trounced the competition. Only the read scores of three of the other drives were even in the same ballpark. The 128GB Vertex 4 in particular cleaned up in the CPU Usage test. |
| CrystalDiskMark Benchmarks | ||||
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.
    We have a theme developing here; the 128GB Vertex 4 had another inverted score, this time in three of the CrystalDiskMark tests.
The Sequential Transfer test and 512K Transfer tests have nearly identical charts; the 128GB Vertex 4 beats out the Corsair and Patriot Pyro SE drives in the write tests and posts decent reads. In the 4K Transfer test and 4K QD32 Transfer test, we see the 128GB Vertex 4 suddenly come to life, posting the best numbers across the board in both read and write tests (except for a modest score in the 4K QD32 write test). |
| 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.
  Once we hit the 50% Compressible mark on the read test, all the drives in our test bank deliver stable and closely grouped numbers; unfortunately, our Vertex 4 128GB SSD tanked this one, offering up just 381MBps, while the next-closest drive was at 484MBps.
The write test shows an interesting pattern, which is that SandForce SSDs start the test low with incompressible data and scale high as data is more compressible, while the Crucial M4 with its Marvell controller and all three Indilinx-infused Vertex 4s kept steady numbers. Stability aside, the 128GB Vertex 4 again brought up the rear by a wide margin. |
| 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.
 There’s not much to see here; all the drives had closely-grouped scores, although the 128GB Vertex 4 was the slowest by a nose and all four of the highest scores were posted by SandForce-driven SSDs.
 The scores here are borne out in the individual PCMark 7 scores. None of the drives do much to separate themselves from one another but performance is robust all around.
|
| Our Summary and Conclusion | ||||
| Performance Summary: To put it succinctly, the 128GB Vertex 4 delivered somewhat of a mixed bag of performance results. In some tests it bested the field, while in others it couldn't keep pace. Like the previous Vertex 4s, the 128GB version didn’t do very well in SANDRA, a couple of the HD Tune tests, or the ATTO write test, but it shined like a jewel in most of the CrystalDiskMark tests and the Default IOMeter test, while it held its own in PCMark 7. Then again, PCMark is a better indicator of real world desktop performance versus the former synthetic tests. We also noticed that the percentage difference in the drive’s read and write performance compared to the other SSDs we tested (or specifically to the other Vertex 4s) often varied greatly. For example, in a given benchmark test, the Vertex 4 would hit a particularly strong read score and notably weak write score. This is especially apparent in the ATTO and CrystalDiskMark tests. ;) The 128GB OCZ Vertex 4  The 128GB Vertex 4 enjoys the same strong performance in certain areas that the 256GB and 512GB Vertex 4s did, and the weakness in sequential reads has apparently been resolved with the firmware updates over the last couple of months. Write speeds, however, seem comparably soft. The bottom line is that the 128GB Vertex 4 will deliver strong performance, and it will be better in some areas than versus competitive SSDs and weaker in others.  Of course, when it comes right down to it, you have to talk price-for-performance. As you can see from the street prices we dug up, the 128GB Vertex 4 offers the best cost-per-GiB in the list (with the 256GB version a penny behind), and it can be yours for $99.99, which is almost nothing these days; if you drive a pickup truck or SUV, that might be less than the cost of a tank of gas.
However, if you’re looking the best value for performance, the 256GB Vertex 4 might be your best bet. With updated firmware, it will perform better than the 128GB version, and it costs almost the same per GiB. Regardless, considering that the 128GB Vertex 4 delivers the performance it does (a few weak synthetic scores notwithstanding) and costs so little, this drive is a great deal. Remember also that OCZ offers an impressively lengthy 5-year warranty on these drives as well, so they're standing firmly behind the product. 
|
