|OCZ SATA-II 32GB 2.5-Inch SSD OCZSSD2-1S32G|
|Reviews - Featured Reviews: Storage|
|Written by Olin Coles|
|Tuesday, 13 May 2008|
Page 8 of 10
ATTO Disk Benchmark Results
EDITORS NOTE: Please read Solid State Drive (SSD) Benchmark Performance Testing to understand how the benchmarks used in this article should be interpreted.
Normally ATTO Disk Benchmark is not my first choice for drive testing tools. To be honest, I think it makes for a poor scientific comparison of products because the settings allow for a large range of results. But since the Intel ICH9 and ICH9R southbridge has a bug that prohibits SSD bandwidth beyond 80 MBps I cannot use my all-time favorite System Speed Test software. The ICH chipset has an available DOS driver, but the JMicron JMB363 controller used for testing does not which left us without our favorite testing tool.
The ATTO Disk Benchmark program is free, and offers a comprehensive set of test variables to work with. In terms of disk performance, it measures interface transfer rates at several different user-specified intervals and reports read and write speeds. The drives seek and access times are not statistics made available in this application, which makes this a considerably basic tool. Bandwidth results are indicated as the transfer rate in the images below.
Our testing starts with the Western Digital Raptor (WD740ADFD) 10,000 RPM Hard Disk Drive. Based on the transfer size results, the Raptor HDD reaches a plateau around 16 KB and remains steady up to 1 MB. Western Digital's Raptor is a very good product for the money, but its time has come. With a performance delta around 16 Kb, the Raptor doesn't offer much performance to users wanting to move larger file chunks.
Next up, we tested the MemoRight GT MR25.2-064S. The GT does very well at performing very near to the 120 MBps advertised maximum rate throughout the bandwidth test results. From 64.0 KB to 1 MB the read and write transfer bandwidth is virtually identical, with the 64 Kb file size appearing to be the delta. Since most applications have taken advantage of larger drive capacity, the size of program files has also grown. This makes drives such as Western Digital's Raptor less desirable than the MemoRight GT shown below.
As I mentioned in the beginning of this section, ATTO Disk Benchmark is not among my favorite test tools. A clear example is shown below, which dramatically reduces the read bandwidth results for OCZ's SATA-II SSD compared to those of HD Tach, and raises the OCZSSD2's write bandwidth numbers. Take it for what it's worth, since we've chose to include this information for your comparison.
Based on this results, the OCZ SATA-II SSD plateau's around 64 KB transfer chucks, and produces nearly identical read and write transfer rates of 94 MBps.
Since there are bandwidth results for each transfer file size from .5 KB to 1 MB, we decided to use the 1 MB statistic in our chart below. In this chart, I have organized the products using the sum of their read and write bandwidth speeds. The MemoRight GT MR25.2-064S appears well ahead of the pack, but the Seagate 7200.11 hard drive gets the closest in terms of performance. Training behind is the Mtron Pro and MOBI, followed by the Raptor in last place. Access time is the key benefit for Raptor owners, but with 32MB of cache buffer in the 7200.11 it won't be long before other hard drives are within reach. For now it looks like there is some real promise in the linear read and write speeds of MemoRight's GT.
Originally I hadn't planned on including the ATTO Disk Benchmark results in this article. While the software is decent enough to mention, it was merely included because almost all SSD manufacturers test with it... and for very good reason. After several tests had been completed, I began to see why they decided on this particular software for benchmarks. What I like least about this software is how you can manipulate the settings to produce extremely different results. As an example, if you reduce the total test length size from 32 MB (used in our testing configuration) to one of the smaller sizes the benchmark results are more than 30% different. That reason alone is enough for manufacturers to tweak their own tests for self-benefit.
Nevertheless, in regard to our ATTO tests the MemoRights GT series has proven itself capable of producing superior performance on every level... at a cost of nearly $2000. Yet with cache buffers growing larger and larger, perhaps there's a reasonable middle ground that will provide the best of both worlds. I suspect that hybrid drives could play an important role in this argument very soon.
In our next section, we address the collection of test results and give our conclusion on the OCZ SATA-II 32 GB SSD OCZSSD2.