What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

OCZ RevoDrive 120GB PCI-E Solid State Drive Review

Status
Not open for further replies.

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
In quite a few situations, solid state drives have hit a wall. This isn’t necessarily a performance wall because many modern SSDs have the capability to vastly outstrip the bandwidth of a SATA II interface. It is simply getting harder and harder push things to the next level with relatively slow standard interconnect standards like Serial ATA. Even the latest and greatest SATA 6GB/s standard will likely be saturated as SSD capabilities continue to grow at a break neck pace. OCZ understands this and as such as started to seriously look into different interface formats for their higher end mass market products. One such unique example is their latest RevoDrive 120GB drive which uses the PCI-E interface.

While this is not OCZ’s first foray into PCI-E solid state drives, this is the first which comes with a (somewhat) mainstream price tag. The 120GB RevoDrive is powered by a pair of Sandforce SF1200 controllers in RAID-0 which is supposed to lead to substantially increased performance when paired up with the bandwidth provided by a PCI-E interface. Unlike other non-standard SSDs, this one is available at literally every large retailer throughout North America for with a price of about $350 USD. This price actually puts it above higher-end SATA 2 SSDs which sport the same capacity.

Since this is supposed to be a PCI-E interfaced dual SandForce totting beast which is not limited by the SATA bus, it certainly is going to be interesting to see if it can justify any type of price premium over the Vertex 2s of this world. After all, the RevoDrive costs more yet doesn’t have TRIM capabilities and relies on two slower 60GB SF drives in RAID 0 to achieve its desired performance. Considering OCZ’s pedigree in SSD technology, this product has the capability to be a real barn burner.


 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
Specifications

Specifications


<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/specs.jpg" border="0" alt="" />
<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/specs2.jpg" border="0" alt="" />
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
A Closer Look at the OCZ RevoDrive 120GB

A Closer Look at the OCZ RevoDrive 120GB



The RevoDrive’s box is down right massive in comparison to those we are used to encountering with standard 2.5” SSDs. Luckily, OCZ has put all that extra space to good use as the box has all of the information one could possibly want.


When you open up the box you can see that OCZ has opted for a high-density Styrofoam cocoon which surrounds the RevoDrive’s anti-static bag.

Sadly, along with a wealth of exterior information and an excellent interior protection scheme, additional accessories are pretty much nonexistent. There are two somewhat cheesy case stickers which we would have gladly traded for a software CD with included drivers since depending on your OS of choice, you may need to find and download software for the RevoDrive to work.

While using an ancient (yet still supported) OS like XP may not fit with the high end mentality of this drive it really would have been nice if OCZ had included the necessary software RAID drivers.


The RevoDrive itself is a PCI-E x4 based device which houses a pair of SandForce SF1200 controllers, 32 NAND chips (16 per side) a, PCI-E bridge chip and a Silicone Image 3124 software RAID controller. It is interesting to note that unlike the Z Drive - which you can consider a predecessor to the RevoDrive- this unit only has two “drives” in RAID 0 opposed to it’s forefather’s 4. This was naturally done to decrease overall cost while maintaining some semblance of the higher drive’s massive performance.

<!--[if gte mso 9]><xml> <w:WordDocument> <w:View>Normal</w:View> <w:Zoom>0</w:Zoom> <w:punctuationKerning/> <w:ValidateAgainstSchemas/> <w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid> <w:IgnoreMixedContent>false</w:IgnoreMixedContent> <w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText> <w:Compatibility> <w:BreakWrappedTables/> <w:SnapToGridInCell/> <w:WrapTextWithPunct/> <w:UseAsianBreakRules/> <w:DontGrowAutofit/> </w:Compatibility> <w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel> </w:WordDocument> </xml><![endif]--><!--[if gte mso 9]><xml> <w:LatentStyles DefLockedState="false" LatentStyleCount="156"> </w:LatentStyles> </xml><![endif]--><!--[if gte mso 10]> <style> /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin:0in; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:10.0pt; font-family:"Times New Roman"; mso-ansi-language:#0400; mso-fareast-language:#0400; mso-bidi-language:#0400;} </style> <![endif]-->

As you can see, the chips and even the controller are laid out in distinctive fashion which delineates two 60GB SF drives sandwiched onto one PCB. Just as with any mundane 2.5” form factor SandForce drive, each SandForce 1200 controller is responsible for the typical 16 NAND chips, with 8 chips on each side of the PCB arrayed into two rows of four.


The NAND used on the RevoDrive are Intel 29F32G08AAMDB 32nm 32Gigabit chips which are usually used in typical 60GB Sandforce-powered drives. If you were to purchase the 240GB version you would most likely get the same NAND as found in the 120GB Vertex 2, the 80GB RevoDrive has the same chips as 40GB SF1200 SSDs and so on. This is a simple and straightforward way to enhance commonality from one product to the next in order to decrease manufacturing costs.


Underneath that big “R” is the RevoDrive’s RAID 0 controller which is a Silicon Image, SiI3124 unit with four 3Gbps SATA ports. Since this particular controller can support up to FOUR drives it is a distinct possibility that OCZ could make an even more powerful “4 drive” version of this product. This is backed up by the missing expansion port header just to the right of this controller where in theory (if it had been installed) a daughter card with an additional 2 SSDs would be connected. Hopefully, one day we will see such a beast but as it stands two SandForce drives in RAID 0 is the best this version of the RevoDrive can do.

Also worth noting is the fact that the SiI3124 is a software and not hardware-based RAID controller, so it will use up some CPU cycles when running.


Towards the bottom of the board right next to the PCI-E connectors is the PCI-E / SATA bridge chip. The SF1200 and the Sil3124 are SATA-based controllers and this Pericom PI7C9X130 is what allows communication with the PCI-E bus.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
A Look at DuraWrite, RAISE and More

A Look at DuraWrite, RAISE and More



The RevoDrive has a whopping thirty two 4GB NAND chips on board which gives it a capacity of 128GB, but is seen by the OS as 120GB. This is called “over-provisioning” and happens when a manufacturer has their drive consistently under report its size. Manufacturers use this to help increase IOPS performance and also extend life via wear levelling (as there is always free cells even when the drive is reported as “full”) and even durability since the drive has cells in reserve it can reassign sectors to as the “older” cells die.


As we said, over-provisioning is usually for wear levelling and ITGC as it gives the controller extra cells to work with for keeping all the cells at about the same level of wear. However, this is actually not the main reason SandForce sets aside so much. Wear levelling is at best a secondary reason or even just a “bonus” as this over-provisioning is mainly for the Durawrite and RAISE technology.

Unlike other solid state drives which do not compress the data that is written to them, the SandForce controller does real time loss-less compression. The upside to this is not only smaller lookup tables (and thus no need for off chip cache) but also means less writes will occur to the cells. Lowering how much data is written means that less cells have to be used to perform a given task and this should also result in longer life and even fewer controller cycles being taken up with internal house cleaning (via TRIM or ITGC).



Longevity may be a nice side effect but the real purpose of this compression is so the controller has to use fewer cells to store a given amount of data and thus has to read from fewer cells than any other drive out there (SandForce claims only .5x is written on average). The benefit to this is even at the NAND level storage itself is the bottleneck for any controller and no matter how fast the NAND is, the controller is faster. Cycles are wasted in waiting for data retrieval and if you can reduce the number of cycles wasted, the faster an SSD will be.

Compressing data and thus hopefully getting a nice little speed boost is all well and fine but as anyone who has ever lost data to corruption in a compressed file knows, reliability is much more important. Compressing data means that any potential loss to a bad or dying cell (or cells) will be magnified on these drives so SandForce needed to ensure that the data was kept as secure as possible. While all drives use ECC, to further ensure data protection SandForce implemented another layer of security.



Data protection is where RAISE (Redundant Array of Independent Silicon Elements) comes into the equation. All modern SSDs use various error correction concepts such as ECC. This is because as with any mass produced item there are going to be bad cells while even good cells are going to die off as time goes by. Yet data cannot be lost or the end user’s experience will go from positive to negative. SandForce likes to compare RAISE to that of RAID 5, but unlike RAID 5 which uses a parity stripe, RAISE does not. SandForce does not explicitly say how it does what it does, but what they do say is on top of ECC, redundant data is striped across the array. However, since it is NOT parity data there is no added overheard incurred by calculating the parity stripe.



According to SandForce’s documentation, not only individual bits or even pages of data can be recovered but entire BLOCKS of data can be as well. So if a cell dies or passes on bad data, the controller can compensate, pass on GOOD data, mark the cell as defective and if necessary swap out the entire block for a spare from the over-provisioning area. As we said, SandForce does not get into the nitty-gritty details of how DuraWrite or RAISE works, but the fact that it CAN do all this means that it most likely is writing a hash table along with the data.

SandForce is so sure of their controller abilities that they state the chances of data corruption are not only lower than that of other manufactures’ drives, but actually approaches ZERO chance of data corruption. This is a very bold statement, but only time will tell if their estimates are correct. In the mean time, we are willing to give the benefit of the doubt and say that at the very least data corruption is as unlikely with one of these products as it is on any modern MLC drive.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
Testing Methodology

Testing Methodology


Testing a drive is not as simple as putting together a bunch of files, dragging them onto folder on the drive in Windows and using a stopwatch to time how long the transfer takes. Rather, there are factors such as read / write speed and data burst speed to take into account. There is also the SATA controller on your motherboard and how well it works with SSDs to think about as well. For best results you really need a dedicated hardware RAID controller w/ dedicated RAM for SSDs to shine. Unfortunately, most people do not have the time, inclination or monetary funds to do this. For this reason our testbed will be a more standard motherboard with no mods or high end gear added to it. This is to help replicate what you the end user’s experience will be like.

Even when the hardware issues are taken care of the software itself will have a negative or positive impact on the results. As with the hardware end of things, to obtain the absolute best results you do need to tweak your OS setup; however, just like with the hardware solution most people are not going to do this. For this reason our standard OS setup is used. However, except for the XP load test times we have done our best to eliminate this issue by having the drive tested as a secondary drive. With the main drive being a WD 320 single platter drive.

For these tests we used a combination of the ATTO Disk Benchmark, HDTach, HDTune, Cystal Disk Benchmark, h2benchw and IOMeter for synthetic benchmarks.

For real world benchmarks we timed how long XP startup took, Adobe CS3 (w/ enormous amounts of custom brushes installed) took, how long a single 4GB rar file took to copy to and then from the hard drives, then copy to itself. We also used 1gb of small files (from 1kb to 20MB) with a total 2108 files in 49 subfolders.

For the temperature testing, readings are taken directly from the hottest part of the drive case using a Digital Infrared Thermometer. The infrared thermometer used has a 9 to 1 ratio, meaning that at 9cm it takes it reading from a 1 square cm. To obtain the numbers used in this review the thermometer was held approximately 3cm away from the heatsink and only the hottest number obtained was used.


Please note to reduce variables the same XP OS image was used for all the hard drives.


All tests were run 4 times and average results are represented.

Processor: AMD Phenom X4 945
Motherboard: Gigabyte 890FXA-UD5
Memory: 4GB G.Skill DDR3 12800
Graphics card: Asus 8800GT TOP
Hard Drive: 1x WD 320
Power Supply: Seasonic S12 600W


SSD FIRMWARE (unless otherwise noted):

G. Skill Titan: 0955
G.Skill Falcon: 1571 (AKA FW 1.3)
OCZ Apex: 955
OCZ Vertex: 1.3 (AKA FW 1571)
Patriot Torqx: 1571 (AKA FW 1.3)
Corsair P64: 18C1Q
OCZ Summit: 1801Q
A-Data S592: 1279 (AKA PRE 1.1 FW)
OCZ Agility EX 60GB: 1.3 (AKA 1.4 for MLC Indilinx Drives)
Kingston SSDNow V 40GB: 02G9
G.Skill Falcon 2: 1881 (AKA 1.4)
Kingston SSDNow V+ 128GB: AGYA0201
Corsair Nova: 1.0 (AKA 1916/1.5 for most other MLC Indilinx Drives)
Corsair Force F100: 0.2 (AKA bug fixed / modified 3.0.1)
OCZ Vertex 2: 1.1 (custom “full speed” SandForce 310 firmware)
G.Skill Phoneix: 305 (standard “mass production” firmware)
Patriot Inferno: 305 (standard “mass production” firmware)
OWC Mercury Extreme Pro: 310 (standard 310 firmware)
Corsair Force F120: 30CA13F0 (aka standard 310 firmware)
Corsair Force F40: 1.1 (standard SandForce 310 firmware)
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
Read Bandwidth / Write Performance

Read Bandwidth


For this benchmark, HDTach was used. It shows the potential read speed which you are likely to experience with these hard drives. The long test was run to give a slightly more accurate picture.

We don’t put much stock in Burst speed readings and this goes double for SSD based drives. The main reason we include it is to show what under perfect conditions a given drive is capable of; but the more important number is the Average Speed number. This number will tell you what to expect from a given drive in normal, day to day operations. The higher the average the faster your entire system will seem.


<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/read.jpg" border="0" alt="" />​

There is no denying this drive is a huge performer when it comes to read performance. This is to be expected as there are two SandForce Drives working together in Raid 0.


Write Performance


For this benchmark HD Tune Pro was used. To run the write benchmark on a drive, you must first remove all partitions from that drive and then and only then will it allow you to run this test. Unlike some other benchmarking utilities the HD Tune Pro writes across the full area of the drive, thus it easily shows any weakness a drive may have.

<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/write.jpg" border="0" alt="" />​

These numbers are a bit disappointing. The fact of the matter is this PCI-E based drive relies on slower 60GB drives (to be precise the slower NAND in them) and has the added overhead of the Silicon Image Controller to contend with. To be fair, the average speed of the RevoDrive is higher than the others and a minimum write speed of 157MB/s is still awfully good, but SandForce has raised the bar with their 100/120GB versions and what would have been amazing six months ago is now only mediocre.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
Crystal DiskMark / Random Access Time

Crystal DiskMark


Crystal DiskMark is designed to quickly test the performance of your hard drives. Currently, the program allows to measure sequential and random read/write speeds; and allows you to set the number of tests iterations to run. We left the number of tests at 5. When all 5 tests for a given section were run Crystal DiskMark then averages out all 5 numbers to give a result for that section.

Read



Now we really get to catch a glimpse of what this drive is made of and the sequential and even mid size numbers are awfully impressive. Sadly, the all important 4k number isn’t what we would call optimal. The fact of the matter is sequential speed is mainly for bragging rights but for OS drives the 4K number is what’s most important and here the RevoDrive gets manhandled.


Write



Once again the sequential and mid size performance of this drive is simply amazing, but once we get to the 4K test the performance plummets.


Random Access Time


To obtain the absolute, most accurate Random access time, h2benchw was used for this benchmark. This benchmark tests how quickly different areas of the drive’s memory can be accessed. A low number means that the drive space can be accessed quickly while a high number means that more time is taken trying to access different parts of the drive. To run this program, one must use a DOS prompt and tell it what sections of the test to run. While one could use “h2benchw 1 -english -s -tt "harddisk test" -w test” for example and just run the seek tests, we took the more complete approach and ran the full gamout of tests and then extracted the necessary information from the text file. This is the command line argument we used “h2benchw 1 -a -! -tt "harddisk drivetest" -w drivetest”. This tells the program to write all results in english, save them in drivetest txt file, do write and read tests and do it all on drive 1 (or the second drive found, with 0 being the OS drive).


Compared to other full speed / non-crippled firmware enabled SandForce drives the RevoDrive has about a 33% random access performance penalty which in the real world translates to…absolutely nothing. We’re talking about milliseconds of a difference between the drives and there is no way anyone would tell the difference in access time among the top products listed in the chart above.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
ATTO Disk Benchmark

ATTO Disk Benchmark


The ATTO disk benchmark tests the drive’s read and write speeds using gradually larger size files. For these tests, the ATTO program was set to run from its smallest to largest value (.5KB to 8192KB) and the total length was set to 256MB. The test program then spits out an extrapolated performance figure in megabytes per second.

<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/atto_r.jpg" border="0" alt="" />
<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/atto_w.jpg" border="0" alt="" />

As we can see ATTO simply loves the RevoDrive. Both power curves simply destroy the rest of the competition once the file size starts to increase. Of course, at smaller file sizes the RevoDrive is only slightly better than more typical SSDs we have looked at in the past.

At this point it seems like the power curves are very good in theory and Crystal DiskMark may have uncovered a weakness that may or may not manifest itself in the real world.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
IOMETER / IOMeter Controller Stress Test

IOMETER


IOMeter is heavily weighted towards the server end of things, and since we here at HWC are more End User centric we will be setting and judging the results of IOMeter a little bit differently than most. To test each drive we ran 5 test runs per HDD (1,4,16,64,128 que depth) each test having 8 parts, each part lasting 10 min w/ an additional 20 second ramp up. The 8 subparts were set to run 100% random, 80% read 20% write; testing 512b, 1k, 2k,4k,8k,16k,32k,64k size chunks of data. When each test is finished IOMeter spits out a report, in that reports each of the 8 subtests are given a score in I/Os per second. We then take these 8 numbers add them together and divide by 8. This gives us an average score for that particular que depth that is heavily weighted for single user environments.

<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/iom.jpg" border="0" alt="" />​

They say a picture is worth a thousand words and that must go double for graphs as numbers like this say it all. Just like a merely fast hard drive has a tendency to squish solid state drive performance numbers into a smudge so too does the RevoDrive out and out crush mundane Solid State Drive numbers. It really is in a league of its own.

Unfortunately, this does not shed much light on to the potential issues this drive may or may not have. We say that as the reason this drive is such a beast at IOMeter is because the SF1200 controller is not much more than a cut down SF1500 controller which is designed with the Enterprise market in mind.

This also explains why as the que depth gets deeper and deeper (and thus further away from what a consumer environment will look like) the RevoDrive’s numbers just get better and better. Obviously, IOMeter plays to the RevoDrive’s strong suit and if this is sign of things to come it is going to simply destroy our preconceptions of what “fast” really means.


IOMeter Controller Stress Test


In our usual IOMeter test we are trying to replicate real world use where reads severely outnumber writes. However, to get a good handle on how powerful the controller is we, we have also run an additional test. This test is made of 1 section at que depth of 1. In this test we ran 100% random. 100%writes of 4k size chunks of information. In the past we found this tests was a great way to check and see if stuttering would occur. Since the introduction of ITGC and / or TRIM the chances of real world stuttering happening in a modern generation SSD are next to nill; rather the main focus has shifted from predicting "stutter" to showing how powerful the controller used is. By running continuous small, random writes we can stress the controller to its maximum, while also removing its cache buffer from the equation (by overloading it) and showing exactly how powerful a given controller is. In the .csv file we then find the Maximum Write Response Time. This in ms is worst example of how long a given operation took to complete. We consider anything higher than 350ms to be a good indicator that the controller is either relying heavily on its cache buffer to hide any limitations it possess or the firmware of the controller is severely limiting it.

<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/stutter.jpg" border="0" alt="" />​

After seeing the IOMeter numbers it is not surprising in the least that the RevoDrive also dominates this test. Its combination of two SandForce drives working in conjunction is simply astounding for random access times.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,274
XP Start Up / ADOBE CS3 LOAD TIME

XP Start Up


When it comes to hard drive performance there is one area that even the most oblivious user notices: how long it takes to load the Operating System. While all the other tests were run with a streamlined XP image this particular image is the test bed's “day to day” OS and it has accumulated a lot of crud over the months from installs and removals. We chose the Anti-Virus splash screen as our finish line as it is the last program to be loaded on start up.

<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/boot.jpg" border="0" alt="" />​

When it comes to boot speed, the RevoDrive really is head and shoulders above the other drives.


Adobe CS3 Load Time


Photoshop is a notoriously slow loading program under the best of circumstances, but when you add in a bunch of extra brushes and the such you get a really great torture test which can bring even the best of the best to their knees.


<img src="http://images.hardwarecanucks.com/image/akg/Storage/revo/adobe.jpg" border="0" alt="" />​

As good as the boot time numbers are, these are simply better. This is because Adobe favours medium file performance handling abilities slightly more than it does small file abilities.
 
Last edited by a moderator:
Status
Not open for further replies.
Top