Date: August 23, 2010
Author(s): Robert Tanner
Looking to upgrade your PC with a fast SSD? How fast do you want it? If you answered “ultra fast”, then OCZ’s RevoDrive is worth a look. With read speeds of 500MB/s and beyond, a PCI Express interface, and a modest price premium, this SSD is hard to ignore. We’re on the bleeding-edge here, though, so this drive isn’t without a few caveats.
Large capacity hard drives with PMR tend to be surprisingly fast compared to drives as recent as five years ago, but as any enthusiast can attest, a 10,000RPM VelociRaptor hard drive is faster still. And even many non-enthusiasts have taken notice that SSDs are faster than them all, in both throughput and latency. So then that begs the question… what is faster than a SSD? Why two of them in RAID 0 of course!
It didn’t take long for hardcore enthusiasts to capitalize on the SSD phenomenon, and even less time to go one step further. Some keen consumers noted that by combining two small 30-40GB SSDs together in a RAID 0 array they could fix two of the largest issues with small SSDs and mitigate a third. Namely, that doing so would almost double the lower-than-typical SSD performance experienced on these cut-down solid-state drives, while doubling the minuscule capacity they offered.
Yet most of all, with a keen eye a consumer could pick up two 30-40GB boot drives for the same as or even less than the cost of a single SSD with the same total capacity, and end up with better performance at the same time.
SSD manufacturers also were quick to take notice and over the past couple of years have introduced a small variety of solid-state drives that were in effect two (or more) SSDs combined into one package. The obvious caveats crept back in though, with the resulting dual or quad SSD designs fetching a price premium over two stand-alone SSDs of equal capacity.
This is what sets the OCZ RevoDrive apart. OCZ Technology is no stranger to combination SSD devices; look no further than the PCIe based Z-Drive or the SATA-based Colossus, for example. With the RevoDrive, OCZ aims to rectify this issue, and states that models will cost marginally more than two discrete OCZ solid-state drives of equal capacity.
There are quite a few benefits for buying a single RevoDrive in place of two SSDs, particularly that the RAID array remains self-contained onboard the PCIe card. This has the dual effect of making the RAID setup transparent to the user. No drivers, software, or BIOS settings need to be configured to enable RAID… it all happens behind the scenes.
Additionally, while admittedly a minor issue for some chipsets, the SATA bus will not have to deal with overhead or data saturation, and finally, users won’t have to shell out more money for a decent performance RAID controller card, or settle for putting their data at unnecessary risk by using Intel’s software RAID controller.
The RevoDrive itself is fairly innocuous looking, at least until peering closer. The slot bracket is a classy black chrome that matches the nearly black PCB. Upon closer inspection we can see the two SandForce SF-1200 controllers, and the PI7C9X130 PCI to PCI Express switch. Although the RAID controller is unmarked save for a holographic R, the Windows 7 installation driver files indicate that it is a Silicon Image SiI 3124.
OCZ Revo drives will range as small as 50GB to as large as 480GB ensuring there should be a model for every price range. Again it is worth mentioning this is a PCI Express x4 drive and can be installed into any x4 or larger slot, therefore completely avoiding the issue of SATA 3Gbit/s versus SATA 6Gbit/s slots and bottlenecks.
The RevoDrive remains bootable, although during the Windows installation process users will need to copy a few RAID drivers to a USB drive and load them before the Windows 7 setup can detect the drive for installation. MLC NAND flash is utilized, and although this is a RAID 0 device, the RevoDrive retains a full three-year warranty.
At Techgage, we strive to make sure our results are as accurate and real-world applicable as possible. We list most of the steps and processes involved in setting up and conducting our benchmarking process below, but in the interests of brevity we can’t mention every last detail. If there is any pertinent information that we’ve inadvertently omitted or you have any thoughts, suggestions, or critiques, then please feel free to email us or post directly in our forums. This site exists for readers like you and we value your input.
The table below lists the hardware used in our current storage-testing machine, which remains unchanged throughout all of our testing, with the obvious exception of the storage device. Each drive used for the sake of comparison is also listed here.
Techgage Hard Drive Test System
Intel Core 2 Quad Q6600 – 2.4GHz Quad-Core
4GB Corsair 800MHz CAS 4
Foxconn 8800 GTS 320MB
Corsair Nova V128 128GB
Intel X25-M G1 80GB
Kingston SSDNow V Series 40GB
Kingston SSDNow V Series 128GB
Kingston SSDNow V+ Series 128GB
OCZ RevoDrive 120GB PCI Express
OCZ Summit 60GB
OCZ Vertex Turbo 120GB
OCZ Vertex 2 100GB
Seagate Barracuda 7200.10 320GB
Western Digital SiliconEdge Blue 256GB
PC Power & Cooling Quad Silencer 750W
Arctic Freezer 7 Pro
Windows 7 Ultimate 64-bit
Our Windows 7 Desktop for SSD Testing
When preparing our SSD testbed for testing we follow these guidelines:
All solid-state drives start in a factory fresh or HDDErase fresh state prior to testing. Windows 7 is manually installed and then SYSmark 2007 Preview is installed. Due to the nature of SYSmark, Windows 7 must be reinstalled upon completion of testing in order for many programs to function normally and benchmark consistently. As not all SSDs support TRIM technology, this process is important and ensures all of the drives are in a “dirtied” state before we collect the benchmark results.
For the time-being, cloned test images are not used as these can result in non-aligned partitions, which if it occurs will result in degraded SSD performance. Just as with Windows XP’s default sector offset causing degraded SSD performance, non-intelligent cloning software can have the same effect.
For testing, we ran all tests five times, dropping the highest and lowest results to finally average the middle three. And who said that college statistics class wouldn’t prove useful? If any anomalous results were seen, the test was run again. Given the complexities of modern computers, and especially today’s operating systems, we feel this provides the most accurate results possible.
Finally, we are seeking to constantly improve and expand upon our SSD testing methodology. We are activity seeking real-world workload scenarios that are bottlenecked by hard drives, so if you have any suggestions whatsoever or there is a program you would like to see included in our SSD content, then please drop by our forums and let us know! We are always looking to expand our SSD benchmarks and provide more useful and real-world results, and not just synthetic numbers.
There are few PC enthusiasts who are unfamiliar with the name “Futuremark”, as the Finland-based developer has been producing quality benchmarks to help us gauge our computer’s worth for years. Originally known as Madonion, Futuremark has expanded its focus to go beyond its bread and butter, graphics and gaming, and tackle other areas, such as full system performance. That’s where PCMark comes into play.
The company’s most recent addition to the PCMark family is Vantage. For most users, a full suite would be run, but because we’re focused on storage performance only, we instead run only the storage-specific tests. Fortunately, Futuremark makes this easy for us to do as it has split up the entire suite into seven separate sub-tests, one being the aptly named “HDD Suite”.
PCMark’s HDD Suite may look simple on the surface, but it’s actually quite exhaustive. While the benchmark does deliver a simple “overall” result, it actually tests I/O performance based on a variety of scenarios, from adding music to Windows Media Player, to loading applications in succession, to editing video, to running a malware scanner, and more. It even includes metrics to evaluate a simulated Windows Vista boot time, so Futuremark has done a fine job of combining many useful scenarios into a single button press.
Before jumping into the results, keep in mind that the SiliconEdge Blue uses the identical JMicron drive controller as the SNV425. The only difference is Western Digital wrote its own custom firmware. To date all other SSD manufacturers that use JMicron’s controllers use the firmware supplied by that company. Therefore while it would be easy to dismiss the controller outright, the SiliconEdge Blue results do show what optimized firmware can do with this controller.
With that over with, onto the results!
We suspect the results speak for themselves. The increase in the overall PCMark Vantage score is significant, but when focusing solely on the HDD suite score, the RevoDrive makes the Vertex 2 seem like yesterday’s news. We should mention this is highly ironic given the Revo uses the same SandForce SF-1200 controller as the Vertex 2… the only difference being two are utilized in a RAID 0 configuration.
Performance jumps as significant as these are a rarity in the computer hardware realm, where successive processor and graphics card launches bring reasonable but moderate gains of at most 20% or less, on average. By comparison, a single solid-state drive such as the Vertex 2 is able to offer a 43% jump in performance over its already solid-performing Indilinx Barefoot predecessor, yet a contraption such as the RevoDrive is able to trump that by offering a 29% jump over the Vertex 2! Or in other words, the 120GB OCZ RevoDrive delivers an 85% increase in PCMark Vantage over the original 120GB Vertex SSD.
Originally developed by Intel, and since given to the open-source community, Iometer (pronounced “eyeawmeter”, like thermometer) is one of the best storage-testing applications available, for a couple of reasons. The first, and primary, is that it’s completely customizable, and if you have a specific workload you need to hit a drive with, you can easily accomplish it here. Also, the program delivers results in IOPS (input/output operations per second), a common metric used in enterprise and server environments.
The level of customization cannot be understated. Aside from choosing the obvious figures, like chunk sizes, you can choose the percentage of the time that each respective chunk size will be used in a given test. You can also alter the percentages for read and write, and also how often either the reads or writes will be random (as opposed to sequential). I’m just touching the surface here, but what’s most important is that we’re able to deliver a consistent test on all of our drives, which increases the accuracy in our results.
Because of the level of control Iometer offers, we’ve created profiles for three of the most popular workloads out there: Database, File Server and Workstation. Database uses chunk sizes of 8KB, with 67% read, along with 100% random coverage. File Server is the more robust of the group, as it features chunk sizes ranging from 512B to 64KB, in varying levels of access, but again with 100% random coverage. Lastly, Workstation focuses on 8KB chunks with 80% read and 80% random coverage.
Because these profiles aren’t easily found on the Web, with the same being said about the exact structure of each, we’re hosting the software here for those who want to benchmark their own drives with the exact same profiles we use. That ZIP archive (~3.5MB) includes the application and the three profiles in an .icf file.
Scenarios such as these are pretty much the bane of hard drives and illustrate why 15,000RPM SCSI drives exist. Ironically, despite Iometer and these tests being created well before SSDs began entering the desktop market, the nature of the tests are going to inherently favor them due to their rapid, near-instantaneous random access times. While we do not have a 15,000RPM or VelociRaptor drive to use for reference, the numbers generated by them would only be little better than the desktop drive results.
If looking for a perfect test to illustrate the potential strengths of random access, this would be it. That said, the large number of 512B to 4KB mixed reads and writes in the File Server scenario will also be the anathema of any SSD controller that was designed primarily for large sequential read & write performance. We can gauge which candidates have the highest potential to suffer from performance stuttering with these tests. Very small, random file operations are the worst offenders as they stress the controller the most.
If the SSD controller becomes backlogged, it will exacerbate the stuttering, causing file operations that should take milliseconds to instead take up to a full second or more to complete, thereby only compounding the problem. Of course when there are not one but two SF-1200 SandForce controllers that can evenly divide the workload, it becomes much harder to saturate the drive. The sheer power of the SF-1200 controller combined with two of them to split the workload means even these daunting workloads are easily taken in stride.
As the name might hint, AS SSD is a nifty little program written exclusively for SSDs. It can be run on mechanical hard drives, but be warned that what should take minutes will take over an hour to benchmark! This handy little tool provides several read/write tests at important file sizes, but also includes a benchmark to simulate the transfer of three types of large files.
We selected this program for its precision, ability to generate large file sizes on the fly, and that it is written to bypass Windows 7’s automatic caching system. The tool does not bypass any onboard cache.
Although several of the results are close, the RevoDrive again walks away with the final score results. Here’s a good point to mention that access times like these are the reason why a mechanical disk RAID array can never be the equal of any good quality SSD. Adding mechanical drives together in RAID does not decrease the initial access latency involved. Concurrent file accesses in RAID can better hide the latency penalty, but it doesn’t actually remove it. In the same way the same is true of the Revo, although two SF-1200 controllers are present in RAID 0, the access times are identical to that of the single SF-1200 controller found in the Vertex 2 SSD.
Synthetic benchmarks have typically been favored for performance testing, but the results they provide can be fairly abstract, and the methods they use to assign their scores can be dubious at times. By contrast, real-world application benchmarks provide performance metrics that apply directly to real-world usage, and we endeavor to apply both in our performance comparisons.
SYSmark 2007 Preview from BAPCO is a special case, because its synthetic scores are derived from tests in real-world applications. However, we still believe that synthetic benchmarking scores are best used to directly compare the performance of one piece of hardware to another, and not for developing an impression of real-world performance expectations. SYSmark is more useful than most synthetic benchmarking programs in our opinion, because its tests emulate tasks that people actually perform, in actual software programs that they are likely to use.
The benchmark is hands-free, using scripts to execute all of the real-world scenarios identically, such as video editing in Sony Vegas and image manipulation in Adobe Photoshop. At the conclusion of the suite of tests, five scores are delivered: an E-learning score, a Video Creation score, a Productivity score, and a 3D Performance score, as well as an aggregated ‘Overall’ score. These scores can still be fairly abstract, and are most useful for direct comparisons between test systems.
A quick note on methodology: SYSmark 2007 requires a clean install of Windows 7 64-bit to run optimally. Before any testing is conducted, the hard drive is first wiped clean, and then a fresh Windows installation is conducted, then lastly, the necessary hardware drivers are installed.
SYSmark’s exhaustive battery of recorded real-world usage tests is an important factor when trying to precisely gauge drive performance. According to BAPCo, differences of 3 points in the final scoring should be considered meaningful. Given the age of this test suite, the “Preview” part of the benchmark’s name, however, is definitely not.
Perhaps most impressive is that even with the OCZ RevoDrive, the overall SYSmark score peaks at 178. While still an impressive feat, it serves as a reminder that not all programs are disk bottlenecked, and in fact most programs simply are not. Short of a disk benchmark or another type of workload that is primarily bottlenecked by the storage medium, it is clear we would see a much larger gain by upgrading the test platform itself before we upgraded from a capable SSD to a drive such as the Revo.
HD Tune has long been one of our favorite storage benchmarks, thanks in part to its ease-of-use, and its ability to deliver consistent results (which is obviously important). Since we are using HD Tune on storage devices that also house our OS, we’re unable to test the write performance, so here, we stick to both Read and Access Times.
Once again the Revo takes the top spot across the various file sizes in the read testing. And again we show the access times as these are the hallmark of solid-state drives, which can’t be underscored enough. Three milliseconds to read a 1MB file sounds like a long time by SSD standards, but in actuality it’s the quickest time here. The lone mechanical drive requires ten times as long to access the same size file by comparison. Latency isn’t just a flat value, it is determined by the size of the file operation as well as the type.
HD Tach is a program similar to HD Tune, and although it hasn’t been updated in a few years, it’s still decent for testing SSDs. It offers a different method for calculating burst rates, as well as offering access time measurements below 0.1ms, which is unfortunately the limit for HD Tune. With a massive new program rewrite in the works, we look forward to seeing what the upcoming new version can do.
HD Tach might be showing its age here, as it is the only program not updated to work natively in Vista or Windows 7. We can only hope that the announced future rewrite of the program will bring it up-to-date with storage technology as well as current operating systems. The RevoDrive’s results ranks in just above the old Summit drive, but given the best read results are held by a JMicron based drive and other similarly fast drives also fared poorly we aren’t going to give this benchmark too much credence.
With this we reach the first of our real-world tests where there are no unusual testing or scoring algorithms to leave us scratching our heads! First we start with a simple file transfer from one part of the same drive to another. Please note that straight file transfers to a different destination would post even higher results.
For this test we took a 7.16GB Dual-layer DVD image and timed how long was required to transfer it to a different 10GB partition created on the same drive. Keep in mind with a hard disk, this requires the actuator arm to seek back and forth between the source and destination sectors of the disk platter, while any SSD can instantly read and write to multiple flash chips at once. Still, this is not a test of the raw write speeds of a SSD as the SSD controller cannot read & write to the same parts of the NAND flash simultaneously.
Although the results aren’t the landslide victory we might’ve expected, the OCZ RevoDrive manages to post a new quickest time of 79 seconds so there isn’t any reason to complain. Especially if we were upgrading from an older model mechanical drive, which posted an embarrassing time of over six minutes by comparison.
For this test we utilize 500 large RAW files, and import them into Lightroom. We time how long it takes the program to import the files, cache them, and build the image library.
Somewhat interesting is that the results are split into two main groups with the Summit only able to tie the hard drive, while the other SSDs clump together around the 3 minute mark. It appears the Lightroom test is not demanding enough, and another system component (likely the CPU) has become the bottleneck here rather than the storage. Remember, Lightroom only utilizes two cores when loading and creating its image library, so it is not fully utilizing our slower quad-core CPU.
This should go to show that not all workloads are bottlenecked by storage, and that to get the most out of a fast SSD it will require an equally matched processor and system as to avoid any system (or even software) bottlenecks.
This test is perhaps the most important in our battery of benchmarks as it gives us truly real-world results. It is designed to simulate three kinds of multi-tasking scenarios in order to see how well the storage drive can cope with concurrent workloads. The better a drive performs here, the quicker and more responsive it should feel in everyday tasks. It shouldn’t need to be said that this is where SSDs shine and where traditional HDD bottlenecks are most directly experienced.
In addition to stressing the controller with a demanding, large queue to sort through (NCQ support helps here), this test will give any weak controller a complete panic attack by overwhelming it with simultaneous random read/write operations to juggle with large sequential writes, which is the Achilles’ heel of many cheaper SSDs.
Queue depth and IOPs optimizations have long been a strength of Intel’s own SSDs, however, there is enough differing types of workloads here that regardless of drive, every SSD should see some part of the workload playing to its own unique strengths and weaknesses in some fashion. A good-quality SSD should allow the system to remain responsive as the tasks are carried out in the background at all times. (Please for your own safety don’t try this at home on your HDD!)
Our Medium test consists of the following:
Our Heavy test consists of all-the-above in addition to a full Anti-Virus scan running concurrently in the background with the start of the test. The AV scan uses a static, unchanging 5.1GB test folder that contains 19,748 files and 2,414 sub-folders created from the Program Files directory.
Granted, even with a Core i7 processor, no computer user would be performing all of these tasks concurrently unless they wish to see their computer go unresponsive for up to 30 minutes at a time, but with an SSD, this is almost child’s play! If you think we are exaggerating then just look at what a fairly typical SATA HDD is able to offer, which is a representative sample for any other desktop HDD.
Last but not least, the Light test changes things slightly. This test is a batch file dropped into the Startup folder designed to load several programs as soon as Windows 7 reaches the desktop. This light test will open four websites in Firefox, load five images in Photoshop CS4, start playing our favorite 8 minute (56MB FLAC) music file in Winamp, and open a single large Word, Excel, and PowerPoint document, in addition to a single PDF file. For this specific test in particular, we start measuring from the moment the power button is pressed to the moment the last program and all files have been fully loaded ready for use.
In the time required for a regular hard disk drive computer to boot, it is possible for an SSD to boot and have fully loaded a multitude of programs and files that you regularly use, as the nearly two and a half minutes for the HDD clearly illustrates. For the test platform base level boot time is typically a rather sedate 55 seconds. Loading several Microsoft Office documents in addition to Photoshop only adds an average of 12-15 seconds, in contrast to the mechanical drive which sees its load time more than double by comparison.
Then we have a drive such as the Revo, which one-ups the average SSD and manages to complete the Light load scenario in less than one minute. The average computer user is lucky to have a responsive desktop by one minute, let alone all of their regular programs already loaded and running!
Moving on to the Medium workload scenario the Revo has no trouble shaving a bit over 40 seconds from the best times, which is more impressive considering the test platform is contributing to the bottleneck here. Just as with the Iometer results, it is apparent the Revo’s dual-controller advantage makes it the best choice for intensive I/O workloads.
To add a little perspective, in a little over four minutes the RevoDrive is able to almost halve the time required by the X25-M G1 SSD, partly due to the X25-M G1’s 80MB/s write limitation and lack of TRIM support , yet the competition fairs even worse. The discontinued 40GB V series drive only has half of the normal 10 flash channels and this, as well as the small drive capacity, limit it to a time more than double that (9:11) of the V+ series 128GB SSD. For those like me that are too lazy to do the math, the outclassed mechanical hard disk drive completes the identical scenario in not quite 14 minutes. That’s nearly 10 minutes of time saved just by upgrading to a good quality SSD right there.
As mentioned above the heavy test uses the exact same scenario as the medium test, but includes a concurrent anti-virus scan of a static test folder. Predictable or not, in a five minutes and thirty-two seconds the OCZ RevoDrive sets a new record here as well, knocking 99 seconds off the previous best result. Five and a half minutes is far more palatable than the platter-based drive time which on average required an eye-watering 23 minutes and 42 seconds to complete the same workload.
One thing not shown by our graphs that we like to address is both result consistency and system responsiveness. With the medium scenario the Revo performed all five runs with results that were consistent, although due to the inability for TRIM to pass through the RAID array results did vary a bit more than seen by either the Vertex, Vertex 2, or Nova drives which all support TRIM. As one might expect the Revo never suffered a loss in system responsiveness. Weaker controllers such as the “V” drive’s JMicron controller by comparison had some results differing by as much as several minutes between ones in addition to the system becoming unresponsive, which was clear evidence the controller was becoming overwhelmed from the workload.
Primarily what to take away from these results are which SSD controllers are best suited for high drive I/O workloads. Even with the most brutal of scenarios where several gigabytes of data are simultaneously accessed and written to the drive, SSDs have little to no trouble juggling the loads while maintaining a responsive system. The 120GB OCZ RevoDrive has no trouble stomping over all other single-controller drives in our graphs, and even after reaching a thoroughly “dirty” state results still easily outpaced the competition.
This is a test that any Windows 7 user can perform on their own system without needing to download anything. For those curious, Vista should allow the same, but we can’t guarantee the results will be directly comparable due to changes made in the WinSAT program. To run the program, hit the Windows Key + R at the same time, and type cmd into the run box. In the command prompt window type (or right-click and paste) the following without quotes: “cd c:windowssystem32” and hit enter. Once there input, again without quotes: “winsat disk -drive c -ran -write -count 10” and enter again.
This command runs a small portion of the Windows Experience Index’s drive assessment, specifically it uses small random writes and calculates how fast in MB/s the drive can sustain it. As we mentioned before with the HD Tune results, regardless of what drive is in question, its actual performance depends on what file size is being referred to. The smaller the file size, generally the lower the performance for a hard disk drive. So again, the small random file writes will be brutal.
Windows 7 appears to simply love the OCZ Revo and gives it a rating for 216MB/s for small file writes, well above that of the Vertex 2 and easily 210MB/s quicker than the poor platter-based hard drive.
For the boot test, we perform a cold boot, with the stopwatch starting the moment the power button is pressed until the last systray icon has finished loading. A large number of factors can change how fast a computer boots, from motherboard to just the BIOS configuration, so these times should not be used as an expectation of how fast the SSD will boot in your respective system. With some newer motherboards condensing the time taken in the boot process, boot times could reach significantly lower than these.
We have long concluded that our test platform was the primary bottleneck for faster boot times, but the Revo decided to show there was still room for improvement. With an average of 47 seconds the Revo saves eight seconds off the best boot times, breaking the previous four way tie.
It is worth pointing out that current motherboard designs on the market feature quite a few optimizations for faster booting than the P35 motherboard in our test rig. As a quick test in an X58 motherboard cold boot times averaged 37 seconds, and warm boots (reboots) were as quick as 28 seconds to reach the desktop. Results will primarily depend upon the BIOS configuration, such as if “Quick Boot” is enabled for Gigabyte motherboards, if SATA drives configured with AHCI are present, and other factors.
Last, but certainly not least, are the game level-loading times. SSDs tend to improve application load times significantly over their mechanical brethren, and games are no exception.
Crysis is still infamous for how well it could stress the entire PC, and although Crysis Warhead was a significant improvement and much better optimized than its predecessor, it still makes for one of the better gaming benchmarks to use. For this test, we timed how long it took to load the first level, Ambush. We also figured we would use the newer Left 4 Dead 2 game, for its slightly longer-than-average load times. Here, we timed how long it took to load the final chapter in the Hard Rain campaign.
While the difference between the best SSD and the typical HDD almost exactly halves the game loading time, that 15 seconds really doesn’t seem like much in L4D2, or 30 seconds in Crysis Warhead. At least until considering that each level load is one of many, then halving the load time really starts to add up. Some games involve quite a few load points or build them directly into the level (Half Life 2 being a good example), and smoother, more fluid transitions will greatly preserve game the immersion. In which case, for some gamers the answer becomes a definite yes.
Finally, we reach the most important of our benchmarks! Okay, maybe those were actually the batch workload tests, but still games are admittedly more interesting! Choosing almost any SSD results in an immediate near-halving of load times over a mechanical drive, but the truth is most games are not demanding enough to see any improvement between a good quality SSD and the best SSD available. If this was the case most games would become intolerable to play for the majority of gamers that use mechanical drives, which is something no game developer is going to want.
That said, after having made the transition personally to an SSD in my gaming system I can attest those differences of ten seconds (or more) are definitely noticed and I could never go back to a mechanical drive for gaming.
When I very first heard about the OCZ RevoDrive, truth be told I was a bit of a skeptic. I figured just like past PCIe SSDs, it wouldn’t be bootable, and later when I was told that it was in fact bootable, I then naturally assumed the price would ensure it would remain in the realm of luxury. Yet again, with OCZ’s assurance that pricing would fall in line slightly above two stand-alone drives, that assumption was proven wrong.
What makes OCZ’s RevoDrive series so exciting is not just the pricing, but the near doubling in performance in any high disk usage workloads. OCZ is furthermore going to start off with 50GB and 80GB RevoDrives. While there are no 25GB SSDs to get a price from, 50GB models can be found for below $150 after rebate, giving us hope that we will see these retail for slightly above that price.
As impressive as the RevoDrive series is, there are a few issues worth mentioning. Although SandForce controllers support TRIM, because they are in a RAID 0 configuration here the TRIM command is not passed onto the individual controllers. This is in fact an issue with anyone’s SSD configured in a RAID array, and is not exclusive to the Revo.
At this time it does not appear background garbage collection is working, either. Although these controllers are resilient, after running our battery of tests we reran HD Tach and observed the following result:
Let’s be clear, even with this issue present it did not hamper the RevoDrive from delivering the best results we’ve seen to date in our benchmarks. This condition shouldn’t change much further than this, but we can see that performance is no longer the same as it was with the drive in its factory fresh state.
Additionally, because of the RAID controller, users cannot secure erase the drive (such as with HDD Erase) to restore the “new” factory fresh state. OCZ is reportedly working on software tool that will allow manual TRIMing of RevoDrives and Z-Drives, but there is no idea when this tool will be become available for use.
For current SSD owners there is little reason to upgrade to a RevoDrive. The real-world performance differences shouldn’t be easily noticeable, unless perhaps the SSD in question is JMicron or Samsung based, or is a first generation Intel X25-M. There is a marked improvement in performance in every disk intensive benchmark in our testing, but unless the RevoDrive will be used in intensive disk usage scenarios where the hard drive is the primary bottleneck, there isn’t sufficient reason to recommend upgrading from a traditional SSD.
For hard drive owners we strongly recommend upgrading to any good quality SSD, as the differences would be plain as day during normal computer usage. If considering a RevoDrive as the potential SSD upgrade, then the simple fact of the matter is that the performance is top-notch and is impossible to beat at this time with a single “drive”.
Until the next wave of controllers and NAND flash arrive, as they inevitably will, OCZ’s RevoDrive simply is the most affordable solid-state drive featuring two SandForce SF-1200 drives in RAID 0, and by far the best performing SSD we have tested to date. After making short work of our tests we can easily recommend OCZ’s RevoDrive if seeking one of the fastest and more affordable solid-state drive configurations currently available on the market.
Have a comment you wish to make on this article? Recommendations? Criticism? Feel free to head over to our related thread and put your words to our virtual paper! There is no requirement to register in order to respond to these threads, but it sure doesn’t hurt!
Copyright © 2005-2020 Techgage Networks Inc. - All Rights Reserved.