OWC Mercury Extreme Pro 6G SSD Review (120GB)
by Anand Lal Shimpi on May 5, 2011 1:45 AM ESTI still don't get how OWC managed to beat OCZ to market last year with the Mercury Extreme SSD. The Vertex LE was supposed to be the first SF-1500 based SSD on the market, but as I mentioned in our review of OWC's offering - readers had drives in hand days before the Vertex LE even started shipping.
I don't believe the same was true this time around. The Vertex 3 was the first SF-2200 based SSD available for purchase online, but OWC was still a close second. Despite multiple SandForce partners announcing drives based on the controller, only OCZ and OWC are shipping SSDs with SandForce's SF-2200 inside.
The new drive from OWC is its answer to the Vertex 3 and it's called the Mercury Extreme Pro 6G. Internally it's virtually identical to OCZ's Vertex 3, although the PCB design is a bit different and it's currently shipping with a slightly different firmware:
OWC's Mercury Extreme Pro 6G 120GB
OCZ's Vertex 3 120GB
Both drives use the same SF-2281 controller, however OCZ handles its own PCB layout. It seems whoever designed OWC's PCB made an error in the design as the 120GB sample I received had a rework on the board:
Reworks aren't uncommon for samples but I'm usually uneasy when I see them in retail products. Here's a closer shot of the rework on the PCB:
Eventually the rework will be committed to a PCB design change, but early adopters may be stuck with this. The drive's warranty should be unaffected and the impact on reliability really depends on the nature of the rework and quality of the soldering job.
Like OCZ, OWC is shipping SandForce's RC (Release Candidate) firmware on the Mercury Extreme Pro 6G. Unlike OCZ however, OWC's version of the RC firmware has a lower cap on 4KB random writes. In our 4KB random write tests OWC's drive manages 27K IOPS, while the Vertex 3 can push as high as 52K with a highly compressible dataset (39K with incompressible data). OCZ is still SandForce's favorite partner and thus it gets preferential treatment when it comes to firmware.
OWC has informed me that around Friday or Monday it will have mass production firmware from SandForce, which should boost 4KB random write performance on its drive to a level equal to that of the Vertex 3. If that ends up being the case I'll of course post an update to this review. Note that as a result of the cap that's currently in place, OWC's specs for the Mercury Extreme Pro 6G aren't accurate. I don't put much faith in manufacturer specs to begin with, but it's worth pointing out.
| OWC Mercury Extreme Pro 6G Lineup | |||||
| Specs (6Gbps) | 120GB | 240GB | 480GB | ||
| Sustained Reads | 559MB/s | 559MB/s | 559MB/s | ||
| Sustained Writes | 527MB/s | 527MB/s | 527MB/s | ||
| 4KB Random Read | Up to 60K IOPS | Up to 60K IOPS | Up to 60K IOPS | ||
| 4KB Random Write | Up to 60K IOPS | Up to 60K IOPS | Up to 60K IOPS | ||
| MSRP | $319.99 | $579.99 | $1759.99 | ||
OWC is currently only shipping the 120GB Mercury Extreme Pro 6G SSD. Given our recent experience with variable NAND configurations I asked OWC to disclose all shipping configurations of its SF-2200 drive. According to OWC the only version that will ship for the foreseeable future is what I have here today:
There are sixteen 64Gbit Micron 25nm NAND devices on the PCB. Each NAND device only has a single 64Gbit die inside, which results in lower performance for the 120GB drive than 240GB configurations. My review sample of OCZ's 120GB Vertex 3 had a similar configuration but used Intel 25nm NAND instead. In my testing I didn't notice a significant performance difference between the two configurations (4KB random write limits aside).
OWC prices its 120GB drive at $319.99, which today puts it at $20 more than a 120GB Vertex 3. The Mercury Extreme Pro 6G comes with a 3 year warranty from OWC, identical in length to what OCZ offers as well.
Other than the capped firmware, performance shouldn't be any different between OWC's Mercury Extreme Pro 6G and the Vertex 3. Interestingly enough the 4KB random write cap isn't enough to impact any of our real world tests.
The Test
| CPU | Intel Core i7 965 running at 3.2GHz (Turbo & EIST Disabled) Intel Core i7 2600K running at 3.4GHz (Turbo & EIST Disabled) - for AT SB 2011, AS SSD & ATTO |
| Motherboard: | Intel DX58SO (Intel X58) Intel H67 Motherboard |
| Chipset: | Intel X58 + Marvell SATA 6Gbps PCIe Intel H67 |
| Chipset Drivers: | Intel 9.1.1.1015 + Intel IMSM 8.9 Intel 9.1.1.1015 + Intel RST 10.2 |
| Memory: | Qimonda DDR3-1333 4 x 1GB (7-7-7-20) |
| Video Card: | eVGA GeForce GTX 285 |
| Video Drivers: | NVIDIA ForceWare 190.38 64-bit |
| Desktop Resolution: | 1920 x 1200 |
| OS: | Windows 7 x64 |
Facebook
Twitter
RSS
44 Comments
View All Comments
altermaan - Thursday, May 5, 2011 - link
nice review though I'll most likely buy either the vertex 3 120GB max iops or the crucial m4 128GB. speaking of which: are there any plans of reviewing those two drives in the near future? I (and I think I'm might not be the only one) am desperately waiting for this as I don't wanna spend $300 for the wrong drive.greets
A
Nicolas Pillot - Thursday, May 5, 2011 - link
I see from the graphs, that- sequential read are faster than sequencial write, which seems ok
- random write are faster than random read, which seems illogical
That's the case for each and every ssd drive (well as far as i have checked)
Could somebody please explain this to me ?
Nihility - Thursday, May 5, 2011 - link
I'm not promising that this is the 100% correct reason, however it's possible that the random writes are being made to the cache (SSD's RAM) so that's quicker. While the reads have to be made from the actual flash storage.andymcca - Thursday, May 5, 2011 - link
Caching is another possible explanation, but if you run a test for any length of time (and I'm guessing the reviewers here do) logic dictates that your buffer will fill up if input rate > output rate.7Enigma - Thursday, May 5, 2011 - link
Makes sense to me. Writing to the drive only requires knowing where to put the data (ie is this block of space free or not). It's basically a limitation of how fast the cpu can deliver write requests to the SSD (so only 2 variables essentially).Random read on the other hand has an added variable of first FINDING the data on the SSD after the read request is made by the CPU. The latency of finding that data (as compared to writing in a free block) is where the performance difference occurs. This is why mechanical drives are so much slower than SSD's, but there still is an overhead on the "finding" part.
andymcca - Thursday, May 5, 2011 - link
Writes on SSDs are to wherever the drive wants to put them (not to a pre-defined physical location). Reads have to come from a pre-defined location, since that is where the data was already put. Basically, SSDs have to hunt for your read data, but put your write data somewhere convenient.JasonInofuentes - Thursday, May 5, 2011 - link
Could the power differences be a result of binning? Could be part of the perk of being Sandforce's favorite client.Thanks.
Jason
andymcca - Thursday, May 5, 2011 - link
My guess is that it has to do more with the memory and less with the controller, but IANAexpertaraczynski - Thursday, May 5, 2011 - link
I don't mean this as a stupid question (apologies if it is) but why not include a traditional platter driver in the ATStorageBench2011? Sometimes comparing apples to apples doesn't have the impact as when you also throw in an orange into the mix to help visualize what you're seeing.average MB/s of 100-200 on a certain bench doesn't mean much to me personally when i don't know how it compares to a traditional drive.
MilwaukeeMike - Thursday, May 5, 2011 - link
I agree. I like the Velociraptor included on some graphs because I own one, and know what the comparison is. These charts help us realize which SSD might suit our purposes best, but the question many of us are really wondering is 'should I upgrade to one at all?'The easy answer is 'yes', but having MS Word open in 1 second instead of 2 doesn't matter to me. Having my games load in 5 seconds instead of 25 does. But without an old school drive on the benchmark table we can't quantify SSD to HDD.
Review is great for SSD to SSD, don't get me wrong :)