review a look at ssd performance in windows vista

A look at SSD performance in Windows Vista

We last published an SSD round-up a month and a half ago, squaring off a six-pack of new drives against Intel’s well-established X25-M. In the end, we recommended the Intel drive, due to its all-around performance leadership, along with the homegrown and Corsair-branded versions of Samsung’s PB22-J, on the strength of that design’s solid performance, low cost per gigabyte, and modest power consumption. We weren’t particular fans of the Super Talent and OCZ SSDs based on Indilinx’s “Barefoot” SSD controller, though. The drives didn’t fare well overall, and they were painfully slow in our real-world file creation and copy tests.

Those conclusions ruffled the feathers of more than a few forum fanboys, who sprung into action to defend the upstart Indilinx controller—and, more importantly I suspect, the honor of the Vertex SSDs inside their very own systems. Insults were hurled, flames raged, and through all the noise, a few relevant concerns emerged. Exploring them has largely monopolized my benchmarking time since.

First, we started with the easy stuff: the Vertex’s firmware was updated, various drivers were freshened, and our test system’s operating system was brought up to date with the latest patches. But the Vertex’s performance didn’t improve. Curious to see whether our decision to test drives in a “used” state could shed some light on the issue, we next probed differences in fresh versus used performance with the Indilinx, Intel, and Samsung drives. The Indilinx controller proved plenty quick when the drive was in its factory-fresh state with plenty of empty flash pages available for writing, but its performance dropped by a much greater margin than the Intel and Samsung drives when tested in a used state. It looked like we’d found our culprit.

All this testing was still being conducted on an older system that, while fast enough to stress even an X25-E Extreme, wasn’t representative of the latest and greatest hardware. The system’s Windows XP operating system was perhaps the greatest concern, because its default 63-sector partition offset starts the first partition in the middle of an SSD flash page rather than at the beginning of one. This misalignment apparently creates problems for the Indilinx controller, although it’s not an issue for all SSDs. Intel says the X25-M isn’t picky about such offsets, for example.

Still, since Windows Vista drops XP’s default partition offset, we decided to test with it next. We updated our test system’s hardware, as well, combining a Core 2 processor with 4GB of memory and Intel’s most recent ICH10R south bridge SATA controller. But does this drastic overhaul change the SSD performance picture any? We’ve subjected drives based on controllers from Indilinx, Intel, and Samsung to a battery of tests in an attempt to find out.

And then there were three
We’ve narrowed our focus to three drives today because the results of our last SSD round-up nicely illustrated the fact that storage controllers (and firmware revisions) largely define SSD performance. Only a handful of different storage controllers are available, with numerous drives based on each. Intel’s X25-M, for example, is available not only directly from the chip giant, but also through partner Kingston. Samsung makes its own drives, too, and its latest controller can be found in new models from Corsair and OCZ. Indilinx’s SSD silicon may be the most promiscuous of the bunch. The company doesn’t sell its own drives, but it has numerous partners, including OCZ, Super Talent, and Patriot, just to name a few.

Today, we’ll be focusing our attention on the Intel X25-M, an OCZ Summit based on Samsung’s latest controller, and the Indilinx-based OCZ Vertex. The performance of each drive should be representative of competing models and otherwise re-badged versions of the same underlying designs. However, we should note that SSD performance is somewhat dependant on overall drive capacity. A 30GB Indilinx-based design won’t necessarily be as quick as a 120GB one. Keep that in mind if you’re looking to save a little cash on a low-capacity unit.

Capacity Cache Controller Max reads Max writes Warranty Street price

Intel X25-M
80GB 16MB Intel PC29AS21AA0 250MB/s 70MB/s 3 years

OCZ Summit
120GB 128MB Samsung S3C29RBB01-YK40 220MB/s 200MB/s 3 years

OCZ Vertex
120GB 64MB Indilinx IDX110M00-LC 250MB/s 180MB/s 3 years

The X25-M has been around longer than its direct competition, and it shows on the spec sheet. With only 16MB of cache, the drive has substantially less RAM onboard than either the Indilinx or Samsung designs, which pack 64 and 128MB, respectively. The X25-M’s write speed rating is quite a bit lower than the other drives, as well, despite the fact that all three drives use the same kind of multi-level cell (MLC) flash memory common in consumer-grade SSDs. Interestingly, Intel only clams a write speed of 170MB/s for the X25-E Extreme, which is based on pricier single-level cell (SLC) flash memory. Perhaps Intel is simply more conservative with performance ratings than its competition.

Of course, it’s important not to put too much stock into these theoretical peak ratings. We have a full suite of tests that will more clearly illustrate how these drives perform in the real world. Before getting into those results, however, I should note one important difference between these three SSD designs. While drives based on the Indilinx and Intel controllers can have their firmware upgraded by end users, SSDs based on Samsung silicon cannot. It’s unclear whether this is a hardware limitation specific to the Samsung design or whether the company simply prefers not to let users flash their own drives.

Support for user firmware flashing might not seem like an important consideration for a storage product. After all, apart from the last batch of broken Barracudas, I can’t remember the last time a mechanical hard drive maker even issued a public firmware update. New firmware releases aren’t uncommon in solid-state disks, though. We’ve already seen new firmware revisions dramatically improve the performance of some drives, and a few updates have also added new features. Enthusiasts won’t want to miss out on either.

Samsung’s lack of support for user firmware updates probably won’t bother users of Samsung-branded drives, which only seem to be available in pre-built systems from the likes of Dell and HP. However, PC enthusiasts buying versions of the drive sold by the likes of Corsair and OCZ will surely want to be able to flash their drives. What’s more, there’s currently no way for those shopping on sites like Newegg to determine which firmware revision a given drive is running. Samsung really needs to change its policy on firmware updates, if not for its own drive models, then at least for those of its partners.

The big, bad block-rewrite penalty

The block-rewrite penalty associated with flash memory is the scourge of SSD performance. This penalty arises from the very nature of flash-based memory, so it’s a tough one to avoid. Flash cells are typically arranged in 4KB pages organized into 512KB blocks. If a cell is empty, pages can be written to directly in 4KB chunks. Simple. If a cell is occupied, however, a rewrite of the entire block must be performed, even if only a single page is being written.

Before a block can be rewritten, its contents must first be read and then modified—extra steps that need not be performed when dealing with empty cells. The block write that follows also weighs in at 512KB, or 128 times the size of a 4KB page write, so there’s more to actually write. The performance loss resulting from these factors is the block-rewrite penalty.

At first blush, one might assume that simply ensuring an SSD has plenty of free capacity should avoid this calamity. But that doesn’t work because of how Windows deals with deleted files. When a file is deleted, the flash pages it occupies are marked as available, but their contents aren’t actually emptied or otherwise cleared. As a result, a solid-state drive can show plenty of available storage capacity yet still have all of its flash pages occupied. In that case, the block-rewrite penalty will hamper each and every write request.

The X25-M looking very crowded

To try to combat the block rewrite penalty’s impact on long-term drive performance, Indilinx, Intel, and Samsung have all updated their SSD firmware in the last few months. Intel released an 8820 firmware revision for the X25-M that tweaked the drive’s self-cleaning mechanism and dramatically improved file copy performance. Indilinx has been busier, issuing firmware updates for its design seemingly every other month. The latest release, version 1370, apparently improves the drive’s internal “garbage collection” scheme. Few details on this feature are available, although OCZ is promising to release a white paper on the technology soon. What we do know is that garbage collection is targeted at improving long-term drive performance.

Garbage collection has also come to Samsung-based drives via a new 18C1 firmware revision that the company will begin shipping in drives starting July 1. We’re still awaiting specifics on how—and wheter—Samsung’s approach differs from Indilinx’s. From what little has been revealed thus far, it appears the Indilinx and Samsung garbage collection schemes run automatically when the drive is idling. There’s no way to invoke these features manually, and no way to determine whether a drive has had its, er, garbage collected.

I expect there are many similarities between the self-cleaning schemes employed by the Indilinx, Intel, and Samsung SSD controllers, but we can’t be sure until more details are disclosed. There does appear to be one difference in Intel’s approach, though. The X25-M’s self-cleaning mechanism runs constantly, while the Indilinx and Samsung SSDs appear to fire up their garbage collection routines only when drive is idle.

Systems don’t idle for long in the Benchmarking Sweatshop, making it difficult to test the garbage collection schemes on the Indilinx and Samsung drives. The fact that there’s no way to verify when or even if a self-cleaning routine has completed further complicates the matter. However, a potentially better solution to the block-rewrite problem looms just over the horizon in the form of the TRIM command.

A blue PCB for the Summit

Due to be supported by Windows 7, the TRIM command promises deal with the block-rewrite penalty by emptying pages when data is deleted rather than simply marking them as available. The spec has yet to be finalized, though, and no drives currently support the command in the Windows 7 Release Candidate. Indilinx has pledged to add Windows 7-compliant TRIM support in a future firmware update. Samsung has also promised TRIM support, but Intel has been largely mum on the subject. We’d expect it to follow suit, either with entirely new drives or firmware updates for existing ones.

At the moment, those with Indilinx-powered SSDs can use a “wiper” utility to effectively TRIM their drives manually. The latest 0525 revision of this app is supposed to be more robust than an older version that didn’t work for us earlier, but problems persist. The wiper tool apparently works quickly with some configurations, taking a matter of minutes to freshen a drive, and extremely slowly with others, requiring more than a day to complete a run through a 120GB SSD. Unfortunately, our test system is one of those slow configs. More specifically, the wiper tool runs slowly when combined with Intel’s AHCI drivers.

OCZ says switching to Vista’s own AHCI drivers resolves the issue, and based on our own testing, that appears to be true. However, OCZ has been unable to tell us why the wiper utility has problems with Intel’s drivers. Lest you think Intel’s sandbagging the wiper to protect X25-M sales, OCZ notes that the app doesn’t play nicely with storage controller drivers from AMD or Nvidia, either. Indeed, it appears the only drivers that work properly with the wiper utility are the ones Microsoft built into Vista.

Switching storage controller drivers should be an easy task for any enthusiast. Still, the fact that the wiper tool doesn’t work with common, current, and WHQL-certified drivers is a major problem. This latest version may get along with very specific system configurations, but it’s not yet ready for mass consumption. As a result, we haven’t used it in our testing today.

The Vertex shows its silicon

Because the block-rewrite penalty can severely impact SSD performance, we’ve elected to test the drives in a simulated used state, with all their flash pages occupied. We don’t believe that testing SSDs in a factory-fresh state accurately represents their long-term performance, and we’re far more interested in seeing how drives handle a more typical scenario than chasing higher benchmark scores with SSDs that have been manually freshened with secure-erase tools that clear the contents of all flash pages.

Our testing methods
We’ve put together an all-new test platform for this latest SSD round-up. The most important changes here are the move to Intel’s latest ICH10R south bridge chip and Windows Vista x64 with Service Pack 2.

You’ll notice on the following pages that we’ve tested the Summit in two configurations. The first uses the 1801 firmware revision and is representative of what’s on store shelves today. We’ve also tested with the newer 18C1 firmware revision, which Samsung should be shipping to customers now.


Intel Core 2 Duo E6700 2.66GHz
System bus 1066MHz (266MHz quad-pumped)

Gigabyte EP45-DS3R
Bios revision F10
North bridge
P45 Express
South bridge Intel ICH10R
Chipset drivers
Memory size 4GB
(2 DIMMs)
Memory type

OCZ PC2-6400 Platinum Edition
at 800MHz
CAS latency (CL)
RAS to CAS delay (tRCD) 4
RAS precharge (tRP) 4
Cycle time (tRAS) 15


Realtek ALC889A with 2.24 drivers

Gigabyte GeForce 8600 GT 256MB
with ForceWare 185.85 drivers
Hard drives Intel X25-M 80GB with 8820 firmware

OCZ Summit
with 1801 and 18C1 firmware
OCZ Vertex 120GB with 1370 firmware

Windows Vista Ultimate x64
OS updates Service Pack 2

Our test system was powered by an OCZ GameXStream power supply unit.

We used the following versions of our test applications:

The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.

All the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Quantifying the block-rewrite penalty
Before digging into our benchmark results, it’s worth taking a moment to quantify the magnitude of the block rewrite penalty associated with each drive. As we’ve seen in the past, some SSDs deal with this issue better than others.

First, we used an IOMeter workload consisting exclusively of 4KB random write requests to measure the response time of each drive in its factory-fresh state, with no occupied flash pages. We then subjected each SSD to several runs through HD Tach’s “full” disk benchmark, whose write speed test fills drives with a single, contiguous file. This test neatly occupies all available flash pages, forcing a block rewrite for every subsequent write request.

With our SSDs now in a simulated used state, we ran our IOMeter random writes test once more to gather response time data.

All the drives have much quicker response times when fresh than in a simulated used state. The performance differences vary from one drive to another, though. The Vertex’s response time rises by nearly an order of magnitude, while the X25-M is only about five times slower. Neither compares to the Summit, whose used-state response times are roughly 20 times higher than with a fresh drive.

In addition to exhibiting the greatest disparity between fresh and used response times, the Summit is easily slower in each state than the Vertex and X25-M. Those two drives offer nearly identical used-state response times, although the fresh Vertex is quicker than the Intel drive in the same condition.

Based on these results, the Summit and its underlying Samsung controller seem to be the most adversely affected by the block-rewrite penalty, at least in this synthetic test. The Vertex and X25-M, on the other hand, look pretty evenly matched when in a used state. Keep in mind that the benchmark results on the following pages were all obtained with the drives running in our simulated used state.

WorldBench uses scripting to step through a series of tasks in common Windows applications. It then produces an overall score. WorldBench also spits out individual results for its component application tests, allowing us to compare performance in each. We’ll look at the overall score, and then we’ll show individual application results.

Only four points separate the fastest drive from the slowest in WorldBench overall. The X25-M and latest Summit revision share the lead, with the Vertex trailing by three points. Samsung’s latest firmware improves the Summit’s performance by a full four points here. Let’s break down the individual test results to see which applications made the difference.

Among WorldBench’s multimedia editing and encoding tests, Photoshop shows the biggest spread. There, the Vertex turns in the quickest completion time, followed nearly half a minute later by the Summit with its latest firmware. The X25-M settles for third, just ahead of the Summit with Samsung’s initial firmware release.

The Vertex enjoys a lead in the Movie Creator test, as well, but it’s a slim one at best. Note that, again, Samsung’s most recent 18C1 firmware revision improves the Summit’s performance.

The completion times in WorldBench’s office and multitasking tests are too close to call. Only a few seconds separate the fastest drives from the slowest in all three tests.

This is where things get interesting. WorldBench’s Nero test proves problematic for the Vertex, which falls well behind the leaders. The X25-M sits in second place, the meat in a Summit sandwich. Once more, Samsung’s newest firmware revision yields a decent performance boost.

In WorldBench’s WinZip test, the Vertex just edges out the X25-M for top honors. The Summits fill out the back of the pack, with the latest 18C1 firmware again delivering a notable performance advantage over the initial release.

Boot and load times
To test system boot and game level load times, we busted out our trusty stopwatch.

There’s only a one-second difference between the fastest and slowest SSD in our system boot test. That’s too close to call.

There isn’t much to see in our level load tests, either. Far Cry 2 loads slower on the Vertex than on the other drives, but the difference is only about a second. Not even that separates the pack in Call of Duty 4. Given the manual nature of our stopwatch timing, I wouldn’t get too worked up about differences of a fraction of a second here or there.

File Copy Test
File Copy Test is a pseudo-real-world benchmark that times how long it takes to create, read, and copy files in various test patterns. We’ve converted those completion times to MB/s to make the results easier to interpret.

Vista’s intelligent caching schemes make obtaining consistent and repeatable performance results rather difficult with FC-Test. To get reliable results, we had to not only drop back to an older 0.3 revision of the application and also create or own custom test patterns. During our initial testing, we noticed that larger test patterns tended to generate more consistent file creation, read, and copy times. That makes sense, because with 4GB of system memory, our test rig has plenty of free RAM available to be filled by Vista’s caching and pre-fetching mojo.

For our tests, we created custom MP3, video, and program files test patterns weighing in at roughly 10GB each. The MP3 test pattern was created from a chunk of my own archive of ultra-high-quality MP3s, while the video test pattern was built from a mix of video files ranging from 360MB to 1.4GB in size. The program files test pattern was derived from, you guessed it, the contents of our test system’s Program Files directory.

Even with these changes, we noticed a little more variability in FC-Test performance than we’d like to see. Normally we run tests three times and average the results, but for FC-Test, we’ve run each test five times before averaging. We also had to perform some additional test runs to replace obviously erroneous results that cropped up occasionally.

The Summit absolutely dominates our file creation tests. The underlying Samsung controller seems particularly well-suited to handling the larger files that make up our video test pattern, although the Summit’s performance is impressive with the program files and MP3 test patterns, as well.

Intel’s X25-M finishes a distant or, well, not quite so distant second place in all three test patterns. Only in the program files test pattern is the Intel drive threatened by the Indilinx-powered Vertex. With the video and MP3 test patterns, the Vertex trails by greater margins.

As we switch to read tests, the X25-M assumes the lead across all three test patterns. The Intel drive has a notable edge over the Summit, which in turn has an even greater advantage over the Vertex.

We’ve seen the newer 18C1 firmware improve the Summit’s performance in most tests thus far, but it doesn’t do much for the drive here. It seems the firmware’s special sauce helps with writes but not so much with reads.

Copy tests combine read and write operations. With this cocktail, the Summit leads in the program files and video test patterns. This isn’t a sweep for the Samsung controller, though. The X25-M fares quite well with the MP3 test pattern, delivering transfer rates that are 50% faster than its closest rival.

Although it eclipses the performance of both Summit configs in the MP3 test pattern, the Vertex falls to the back of the pack with the program files and video test patterns. Its transfer rates are half those of the X25-M with both test patterns—and several times slower than the leading Summit drives.

IOMeter presents a good test case for both seek times and command queuing.

Well, you certainly wouldn’t want to throw the Summit into a demanding multi-user environment. The Samsung controller doesn’t cope gracefully with our ramping IOMeter loads, as the Summit turns in much lower transaction rates than the X25-M and Vertex. Poor random write performance appears to be the culprit here, at least in part; the Summit is much worse off in the file server, database, and workstation test patterns, which are the only ones that contain write requests. With these test patterns, I’d expect mechanical hard drives to offer transaction rates in the same ballpark as the Summit.

It’s difficult to see in the graphs, but both firmware revisions for the Summit turn nearly in identical IOMeter performances.

The X25-M and Vertex are closely matched with the file server access pattern, but the Vertex pulls ahead when we switch to simulated database and workstation loads. Interestingly, the Intel drive dominates in the web server access pattern, which is made up exclusively of read operations.

The Vertex and X25-M consume more CPU cycles than the Summit, but they’re also completing more transactions. To get a clearer picture, let’s quantify IOMeter efficiency in terms of transactions per percent CPU utilization.

Although the results are certainly mixed overall, the web server results are fairly easy to interpret. With that access pattern, the X25-M delivers more transactions per CPU cycle than the Vertex and Summit.

HD Tach
We tested HD Tach with the benchmark’s full variable zone size setting.

These tests should give us a good sense of each drive’s maximum achievable sustained transfer rates. The X25-M proves the fastest in the read speed test, followed closely by the Vertex, as the Summit trails more than 20MB/s off the pace.

The X25-M falls to last place in the sustained write speed test, which shouldn’t come as a surprise given the drive’s relatively sluggish 70MB/s write speed rating. The Summit is nearly 100MB/s faster here, and the Vertex is a further 25MB/s quicker.

It’s interesting to see how much these transfer rates conflict with the results of our real-world file creation, read, and copy tests. The Vertex looks like the bee’s knees in HD Tach, but it doesn’t fare nearly as well when creating, reading, or copying actual files. This is why we don’t rely solely on synthetic benchmarks to evaluate drive performance.

The X25-M has a slight edge over the Summit in HD Tach’s burst speed test. There’s no difference in performance between Summit firmware revisions here, and there wasn’t with the sustained read and write speed tests, either.

Curiously, the Vertex only manages 186MB/s in this test. The drive’s 64MB cache should be able to keep up with a 300MB/s Serial ATA interface, suggesting that the Indilinx controller is slower than the others when handling burst transfers.

As far as HD Tach is concerned, all these drives deliver instantaneous seek times.

HD Tach’s CPU utilization scores are nearly within the app’s +/- 2% margin of error for this test. I’m going to call it a wash.

Power consumption
For our power consumption tests, we measured the voltage drop across a 0.1-ohm resistor placed in line with the 5V and 12V lines connected to each drive. We were able to calculate the power draw from each voltage rail and add them together for the total power draw of the drive. Drives were tested while idling and under an IOMeter load consisting of 256 outstanding I/O requests using the workstation access pattern.

At idle, the Summit draws half the power of the Vertex and about a third of the juice required by the X25-M. However, when subjected to a punishing IOMeter load, the OCZ drives must share the low-power limelight.

The X25-M proves to be the power-hungriest drive of the bunch, which is notable considering that it’s also packing fewer gigabytes (80 as opposed to 120) than the others. Keep that in mind if you’re looking for an SSD to extend notebook battery life.

In the last two months, I’ve tested more SSDs and firmware revisions than I’d care to remember. It’s been a grueling process, and I’ve no doubt sprouted a few grey hairs along the way. But this latest batch of performance results sheds new light on the SSD landscape, and we’ve learned some interesting things as a result.

Let’s start with the Vertex and its underlying Indilinx controller. This design isn’t at its best when faced with Windows XP’s default 63-sector partition offset, but the move to Windows Vista doesn’t appear to have helped the drive much. The Vertex is still competitive in IOMeter, again trumping the X25-M in the database and workstation test patterns. And it still boasts impressive sustained transfer rates in HD Tach’s synthetic benchmarks. However, those transfer rates don’t translate to quick file creation, read, or copy speeds in the real world. In FC-Test, the Vertex was the slowest drive in eight of nine tests, often by substantial margins.

Now, keep in mind that we tested drives in a used state—a condition that seems to be problematic for the Indilinx controller. Indilinx does have a wiper utility that can quickly restore drives to close to their factory-fresh form, provided your system’s running the right drivers. However, the wiper tool’s apparent compatibility issues with AMD, Intel, and Nvidia storage controller drivers feels sloppy for what is supposedly a finished product fit for public consumption. The Indilinx controller surely has potential, especially with TRIM support promised in the next firmware update, but it’s still very much a work in progress.

Intel’s X25-M is considerably more mature, which is to be expected from a drive that’s been selling for nearly 10 months now. The X25-M easily dominated its competition when it was launched last September, but it’s now facing considerably faster rivals. Across the range of tests we’ve explored today, I still think the X25-M has the best overall performance, but its grip on that crown is tenuous at best.

Of greater concern for prospective customers is the fact that Intel has not committed to adding TRIM support to the X25-M. Given the drive’s age, it’s entirely possible Intel will introduce an all-new SSD with TRIM under the hood rather than updating existing drives. Of course, it could also do both.

The X25-M’s toughest competition comes from the Summit and other drives based on the latest Samsung controller. The Samsung-based drive’s random write performance is more harshly affected by the block-rewrite penalty than the others. In fact, the Summit is almost an order of magnitude slower than the fastest mechanical drives in this test. Still, with peak write times below 30 milliseconds, it’s an order of magnitude faster than SSDs based on the catastrophically poor JMicron controller (which we didn’t even consider here.) In nearly all of our other real-world tests, the Summit fared quite well, even in a used state. In FC-Test, the Summit easily registered the fastest real-world file creation speeds, and it also performed well in the read and copy tests. What’s more, with the latest firmware, the Summit tied the X25-M for the lead in WorldBench. (Samsung’s latest firmware improved performance in most of our tests, so it’s a shame end users won’t be able to upgrade themselves.) Only in IOMeter did the Summit fall flat, which suggests it’s poorly suited for deployments in servers or multi-tasking-heavy workstations where multiple outstanding disk I/O requests are the norm.

The prospect of TRIM support is cramping my style a little here, because in just a few short months, Windows 7 looks set to change the SSD performance landscape, perhaps drastically. Indilinx should have a TRIM-capable firmware update soon, we’re told, but it’s not here yet. There’s no telling whether the X25-M will ever get a TRIM-capable firmware of its own. Samsung has promised to add TRIM support in another firmware update, presumably due before Windows 7 hits, but without user-applicable upgrades, TRIM support for existing drives seems doubtful at best.

If you absolutely must go out and buy an SSD today, I’d recommend the X25-M if you know you’re going to be dealing with the sort of random access patterns seen in multi-user or even heavy multitasking environments: servers, high-end workstations, and the like. Otherwise, the Summit looks like your best bet for desktops and notebooks; it delivers strong performance with typical desktop applications and real-world file operations, and it’s cheaper than the X25-M on a cost-per-gigabyte basis. The Samsung controller’s poor performance in our 4KB random write test is worrying, though. I’ll be putting a Samsung-based drive into my primary desktop to see whether the comparatively slow random writes affect real-world usage; look for an update in a week or two. That leaves us with the Vertex, which is an intriguing option if you’re willing to deal with the wiper utility’s spotty compatibility, but the sort of product I’d only recommend to seasoned enthusiasts who are looking to tinker.

Honestly, though, I wouldn’t recommend picking up any SSD until we have a clearer picture of which drives will support the TRIM command and how they’ll perform in Windows 7.

0 responses to “A look at SSD performance in Windows Vista

  1. Your real world testing was not in fact real world. Although you acknowledge that “Systems don’t idle for long in the Benchmarking Sweatshop, making it difficult to test the garbage collection schemes on the Indilinx and Samsung drives”, you went on to do the test without allowing for this cleaning. In the real world these drives idle and are cleaned through-out the week, thus these drives are rarely being operated under the false completely full “real world” conditions of your test.

    You also did not test it with the easy to use wipe.exe which does an excellent TRIM to the disk in just 2 minutes on a 256 gig drive (many of us use the Microsoft driver). Additionally, although you tested using Indilinx firmware version 1370, the much improved 1531 was already being shipped at the time of your test. Since Indilinx firmware is easily user upgradable, not using it was another non-real world handicap that materially distorted the outcome.

  2. If TR wants to create an average of 5 runs, can you include horizontal error bars showing error of the mean?

  3. I salute you, Mr. Wasson. As for M_S, well, I’d take the time to explain a thing or two about the pedigree of TR and its editors if I thought it worthwhile. Regardless, hopefully someone at the top of the pyramid at OCZ is taking a bite or two out of him for being foolish enough to publicly attack and cast doubt on TR, which makes OCZ look BAD, rather than contacting and working with TR to come to some sort of resolution that makes OCZ look GOOD. So congrats M_S, you ‘Cover Your Ass’ efforts have cast doubt on the entirety of OCZ, and I’m sure I am not the only one that feels that way.

  4. I find several things interesting here.

    I think what’s most interesting about the HDTach sustained/burst transfer rates is the fact that the OCZ Vertex delivers lower performance on the burst test than it does on the STR test, while (not to put too fine a point on it) virtually no other storage solution we have ever tested has exhibited this behavior.

    Given the other performance issues we’ve exposed and doubly confirmed with the Vertex, such a problem does not seem out a character for this troubled piece of hardware.

    I also find it interesting that OCZ’s first reaction to such an anomalous test result is to blame the test and, quite explicitly, the tester, as well.

    Yes, OCZ employees attacked us in public on their forums when we first exposed problems with the Vertex. They have since conceded a tremendous amount of ground in our conversations with them behind the scenes, since we’re pretty sure the used-state file copy performance drop is real, repeatable, and a particular problem for drives based on the Indilinx controller. We’ve taken the time and made the effort to prove it, and OCZ has retreated to recommending manual runs of a wiper utility with a history of safety and compatibility issues as a fix.

    But given that recent episode, one would think OCZ would have learned by now not to dedicate so many resources to talking down about negative reviews in public forums–and shifted its efforts toward better engineering and product validation, instead.

    Sadly, OCZ VP M_S demonstrates here that is not the case, as does Tony in OCZ’s own forums and at other public forums around the web, where he continues to criticize our Vertex coverage, while having had to concede that we have the facts right and being left to made dark implications about our testing methods and opinions, though we have explained our reasons for both in great detail in print and on our podcast.

    To be clear, we will not abandon a consumer-focused approach to testing SSDs and test new or artificially clean drives and inflate our benchmark results in order to appease drive manufacturers, even ones that take the low road and criticize us in public in lieu of expressing their concerns directly to us (we remain open to conversation via the proper channels, as we have been). We will not abandon a synthetic test like HDTach that produces reliable results for 99.9% of the storage products out there simply because the maker of a drive whose product fares poorly there has asserted, with no real evidence, that the test is flawed. (And, for the record, unlike some, we run the hours-long full test variants in HDTach, not the short ones based on fewer samples. Had M_S bothered to speak with us about this issue, he would have known that.)

    We will instead keep the burden of proof on the makers of the products we review: those products should operate properly and deliver their true performance potential when used as most folks will use them. If they cannot, while their more robust competitors can, I see no reason to recommend them, regardless of how much the company’s representatives try to persuade the world that we are somehow mistaken and dirty our reputation.

    Scott Wasson
    Editor in Chief
    The Tech Report

  5. it is really simple, the software was updated last in 2003 and doesn’t use real transfer measures but extrapolation of data based on spot checks and time stamps. Depending on the granularity of either parameter, the results are more or less (in)accurate.

    That aside, the real issue is not the software which was perfectly adequate 6 years ago but its use for reviewing current technology despite the fact that the individual results are *[

  6. And I’m sure I can show ROI for a $150,000 SAN for work. Or a private jet, or a Mercedes for the best salesperson…

    Your definition of “affordable” seems to be very narrow or very broad, I’m not sure which.

  7. Hi All

    I agree with you compltely Phez. I don’t get it either. Once the storage capacity of these drives goes up & the price comes down, I’d view these drives as a viable option. However, at present, no way.

  8. The pricegrabber links to
    “Intel X24-M 80GB Solid State Drive ”

    And leaves out newegg (possibly because of thatg{

  9. SSD’s have existed for about 31 years now, mostly in military and industrial fields. I’m curious what makes you think that this year there will be a breakthrough other than the usual lower cost of producing through economies of scaleg{

  10. Except that I wasn’t paying $120 for a hamburger not so long ago, so no, its hella expensive.

  11. I’ve parroted this numerous times so I’ll keep it brief: Most people in the services industry bill by the hour, and compete in their respective fields for business based on how quickly they can accomplish a task. A 5-15% increase in performance in operating a machine someone uses 8-10 hours a day is certainly worth it at an extra $350-$3000.

    When you look at the costs of mid-range to top-end computers in 1999, this is an even better deal.

    When you look at the inflation rates since 1999, it makes it trivial to invest in this. I daresay the $100-$200 difference in processors is so minuscule, you would be far better off just getting the best processor out at the time (if overclocking isn’t a factor,) rather than waste effort in determining best price/performance.

    I’m not saying replace HDD with SSD, but compliment it so you get lots of storage space is probably the best bet at this time. Guess that wasn’t so brief. m’bad, m’ladyg{<.<}g

  12. Wow. Congrats to Geoff for an enlightening and informative article.

    Your thoroughness and the ability to take criticism and suggestions constructively have ensured that you are my most trusted (and favourite) writer on TR.

    Awesome work, dude.

  13. Sure, it’s different for everyone. But $350 is what everyone paid for an 80GB hard drive not so long ago, so in that sense it’s very affordable.

  14. A Velociraptor and then the fastest 3.5″ drive should be thrown in for comparison. The Velociraptor does give a nice boost IMO. It feels snappier then my older 7200.10 drivers.

    But then, i go with the model that the OS and apps are on the Velociraptor, then all data is on my 4 disk raid on another server and loads over the gig ethernet. Copying files between the velociraptor and the raid just about gives me 98% utilization of the network. So right now the Velociraptor and the network are rather balanced in performance with up to120MB/s read/write. The raid on the other hand is overpowered, but thats beside the point for this exercise really.

  15. Well, if you want to really stretch what “affordable” means.

    I don’t consider a $120 hamburger “affordable” and more than a $350 80GB hard drive.

  16. I bought a Corsair M64 after seeing the larger Corsair drives did pretty well in the Tech Report review. For the last couple weeks I’ve been pretty unhappy about the constant system freezes I was experiencing. Mine was hanging the system when I was typing a simple sentence into a post like this. Firefox would freeze up and when I went to try and pull up task manager the system was frozen up for that too. That is just maddening. Then after a minute or so, the system would become fluid. Not even an IDE drive messed up that bad. They may be slow but its a constant slow. Evidently, unlike its larger Samsung controlled 128GB and 356GB siblings, the Corsair M64 has a JMicron controller. Here is a useful link that summarizes some of the available SDD’s.
    “SSD decoder ring”
    §[<<]§ Yesterday I ordered the Intel X25-M and it arrived this morning and its like night and day. Not a single stutter, so far. We'll see how it wears over time. I plan to put the M64 in a laptop with a less jazzy CPU and see if it can keep up in that slower environment.

  17. He was talking about them being affordable (which they are), not about them being relatively expensive (which they also are).

  18. how can reality be “lame” or “tired” …. well ok tired, it gets boring after more than a decade of the reality that early adopters universally get screwed…. that may be “tired” and “lame” but it’s also true.

    I bought SCSI back in 1999 and couldn’t believe the money wasted for such minimal performance boost and measly capacity….. I was debating RAID’ing the drives and while money wasn’t an issue I couldn’t shake the old proverb.

    “fool me once shame on you, fool me twice shame on me”…. so I waited and Raptors arrived to fill in the gap and could be RAID’ed for half the cost.

    I didn’t jump on SSD’s for this reason and I haven’t seen a reason yet after having repeatedly investigated that makes them compelling…… I think it’s getting close and I hope Windows 7 includes some of the answers along with new controllers but until it’s clear I’ll spend $50 for 500+ gb’s of zippy storage space instead of $300 on less than 1/4 of zippier but problematic space.

    as a side note OCZ’s whining/excuses about XP being the problem seems to have fallen apart.

  19. It’s out of proportion to the rest of the machine for what PCs sell for these days. A $1000 PC is pretty powerful in terms of how much software it will reasonably support, and what the average price is. $350 is a massive relative cost.

  20. That significant difference only happens with server-related workloads a.k.a not mainstream applications. Shaving off 3 to 5 seconds from an mainstream application that normally takes 15-30 seconds to load up on a current HDD is hardly a huge improvement. For some SSDs, they become slower then HDD due to performance degradation issue.

    You are giving current breed of SSDs far too much credit. The technology itself is still very immature. Performance degeneration issues plague all units even the Intel ones and most OS are not optimized for their usage.

  21. Well that’s a lame response. Waiting for a next gen ANYTHING device is a tired rhetoric considering what a HUGE improvement in day to day usage, an Intel SSD will bring you compared to an HD right now.


  22. They’re ALL bad, just wait for the next generation before investing in one.

  23. You can’t really make those sorts of comments about SSD’s until you have experienced a PC using one. Try it! You won’t go back to HDD’s again.

  24. Perhaps you never shelled out for SCSI drives? Once I experienced the responsiveness of a SCSI system back in 1994, there was no turning back. Even now you can get a 1000GB sata or ATAPI drive for ~$125 and that will buy you only 68GB of ultra 320 SCSI goodness. But the multitasking speed difference was worth it; especially in raids.

  25. Interesting that Geoff hasn’t responded to this; they’re the obvious questions to ask, otherwise the review isn’t useful in terms of anyone trying to assess whether to jump from HDDs to SSDs right now.

  26. As seems common in these forums, you’re assessing other people’s decisions based on your own narrow set of requirements, interests, ability-to-pay, etc.

    Maybe, juuuuuuust maybe: some people want SSDs for uses where they actually do already give a performance boost… or, some people want SSDs for other reasons besides performance gains… or, as you suggest, some people really do just want to tinker with the newest toy, and can easily afford it, so good luck to them. Etc.

  27. l[<2) HDTach: Can somebody explain the results that the burst transfer rate, i.e, the transfer rate between the drive and the system is lower than the sequential transfers. Congratulations, this is bending the laws of physics, or am I missing something?<]l who knows... either contact Indilinx or Simpli Software because while it looks like TR was first, looks like BT isn't far behind in bending the laws of physics: §[<<]§ either way if you are the VP, you might want your guys to have a look into this...

  28. SSDs will get much faster. The technology is still in its infancy.

    I agree that outside of heavy-duty I/O loads (servers/workstations). SSDs make very little sense. Spending $299+ to kill load time of a game/general application by a few seconds is hardly worth it. You can achieve similar results for far less by fine-tuning your OS.

  29. I’m still flabbergasted people are shelling out over $350 for devices that offer, by comparison, minute storage capability, and virtually unnoticeable performance increases.

    Is a couple seconds really worth paying 3x as much money for 10x less storage space?

  30. Couldn’t you say that about most all technology, especially comparisons to a decade ago, or even about 5-6 years ago for storage?

  31. I didn’t even catch that subtle change. The review is great in that everything was updated, but I must concur with one of the previous posters, you definitely need to throw in a conventional HD to make sense of it all, at least in terms of some real world tests like boot times and level loads.

  32. yeah I did. 17.8mb/s on the video create. That’s disgustingly bad. And yes video create is important to me.

  33. I personally think SSD’s are completely affordable at current pricepoints. We were paying as much for storage a decade ago, and with inflation, sound, heat, and the performance increases, we still get a great deal. It is only because mechanical drives are so much cheaper that we are spoiledg{<.<}g

  34. This is exactly why I bought a Thecus N5200Pro. 4TB, online hotspare, iSCSI and load balancing over the 2 GigE ports. Crazy fast reliable storage. I am in the process of building a new one with 2TB disks instead of the 1.5’s in my current one.

    There is something nice about having only 1 disk in all my machines and accessing all the data through the network. This type of storage and speed (for a home user) would never be possible without iSCSI.

  35. Thank you, TR, for this review. I really appreciate the work that your new testbed must have required, and the extra data is welcome.

    But no review’s perfect, and I still have a few questions.

    1) Why were no mechanical drives included in this test? Because we can’t compare these results with the previous review’s, we don’t really know how the technologies rank. I consider this a serious omission when Geoff concludes that he wouldn’t purchase any of the SSDs now. Are any of these 3 SSDs ever slower than a standard HD in the new testbed?

    2) Is there a performance difference between Vista’s native and Intel’s AHCI drivers? If wiper doesn’t like Intel’s drivers, perhaps some of the SSD benchmarks were also affected.

    3) While your concerns about wiper & TRIM make sense, I’d like to know how much performance wiper can restore. Would you please include just a couple Vertex benches post-wiper?

  36. It’s beneficial to put things like your apps on an SSD because the incredibly good random reads plus some random writes is exactly the sort of thing a modern SSD excels at, whereas even the best spinning platters can choke on a large enough number of small reads. Combined with the high price/GB there’s little most people can fit on an “affordable” SSD in my book, and I for one certainly don’t have any large frequently changing files that require fast IO – the only ones I can think of are my big fat video edits, and a RAIDed SATA enclosure gets you five times the capacity and twice the throughput of the same amount spent on SSD, and in any cases that’s usually always CPU limited.

    On top of that, OS’s seldom use the file cache sensibly. Half the time if you keep a bunch of apps open, leave your comp running an overnight backup job and all your apps and working dataset will get swapped out and not swapped back in again when the backup job is finished… and your file cache will be full of files that were backed up and you’re not going to be using. Cue the hard disc churning. Heck, if I were to keep *all* the apps I use open *all* the time, I’d need at least 32GB of RAM, but if I spend the money on an SSD I can get the “near instantaneous start” without spending a small fortune on DIMMs.

    What I’d really love is kit like my SAN at work – HDD-backed store with a write-through cache of fast flash between it and the rest of the computer. It gets colossal IOPS in our databases (95% of our database transactions happen on rows less than three hours old) due to the most recently and heavily used blocks being kept there, and our favourite use of this was setting up a bunch of flash cache for windows page files in vmware, which led to something like a 25% reduction in IO requests sent over the fibre, giving us more throughput when we needed it. Sort of what hybrid hard drives were meant to achieve but never really managed to pull off.

  37. My OS and programs typically reside in memory for 99% of the time I use my machine.

    Therefore, placing /[

  38. It would also be a turn-off to see your otherwise snappy drive perform like a slave grandmother when you copy that large file or folder once every 3 weeks or so – I say neither brand is /[

  39. Great follow up.

    I can’t say I agree with the conclusions entirely, though. I think the file copy test is a bit over emphasized. These are small drives and I don’t think it is likely they will be used that way. I find it more likely that your OS and Program Files (and maybe games) will be loaded on for the best responsiveness, while storing or shifting around large collections of video files will be left to larger mechanical drives. Next to the Summit, even the Intel drive looks so-so.

    The IO results for the Summit are interesting. After a quick glance at the 7200.12 review it looks like it even falls behind mechanical drives at the highest IO levels. I’m unsure how bad IO gets when used as an OS and Program Files drive, but I suppose the rest of the realworld tests show the Summit still does well.

    Still not pulling the trigger. I think I’ll wait for W7 gone gold and see what the landscape looks like. Still looks like the Intel drive is the safest bet for a premium on $/GB.

  40. Ever wonder how the “last access time” timestamp is updated after you’ve accessed a file?

    Give ya a clue – a very small write to the hard drive 😉

  41. Disclaimer: happy Vertex owner, not an OCZ fanboy. Alot of the people on their forums think they’re alot cleverer than they are and this was a good article.

    Would have to agree that I think the conclusion is based on different metrics than I’d warrant for a “desktop” drive – but then I’m very much in the cheapskate end of the field where I install the OS and apps on an SSD, and then use spinning bits of glass and metal for everything else (including swap). Hence sequential rates/file copying are of very little importance to me, but sequential/random reads and especially random writes are paramount – and it’s here that the Intel and Indilinx drives are still highly competitive.

    Disclaimer 2: I’ve had a 30GB vertex in my HTPC (C2D 2.6GHz, 2GB RAM, 730i + AHCI) running myth for about six months – OS and apps have a ~5GB footprint and rarely gets written to, so can’t really test for wearing out (in any case, I tend to do a bare metal restore every six months) but with ext4 + aligned partitions these things just fly. Sequential read (copy to /dev/null) nets me 230MB/s on average. I bought this thing for insta-boot and it’s been awesome in that regard.

    It’s good to see Intel finally getting some good competition on all fronts though – compare price/performance per GB with SSD’s from a year ago and it’s a pretty astonishing difference, and the samsungs are going to cause even more price drops. Yay competition!

    I still think drives like the vertex are still definitely for the tinkerer types since even I was annoyed by all the fiddling with firmware, OCZ’s idiosyncratic support (“join the forum and send a PM to a forum member to download the util to do an ATA secure erase cos we don’t want you accidentally deleting your drive” was one that stuck out, until I found out how to do the same thing with hdparm) and alot of the community quite happy to suggest, nay insist on, tweaks to make your OS use the hard drive *less* (generally to make up for the deficiencies fo the Core 1|2 range), which struck me as utterly counter-intuitive to the SSD ethos. Nice to see Samsung being more consumer-friendly.

  42. Since when does opening a program require a write?

    The Samsung may not be as fast at 4k random writes as the vertex but the difference in real terms is negliable you really won’t notice a difference between any of the 3 drives here in desktop use.

  43. Ok well the same can be said about Geoff’s conclusion !

    I’m taking into account the benches that make the most impact on Desktop use : random 4k read/write, basically small read write file operations that are very common for a desktop user. Geoff takes into account a lot more factors, BUT to recommend a drive based on a Samsung controller over the Inidilinx one for desktop use, i truly think it’s not right.


  44. Adi has a point. I don’t entirely agree with Geoff’s rec of the Samsung over the Intel drive, either. However, there is room for disagreement here, whereas the JMicrons with poor random write performance are obviously pretty much broken.

  45. If you use your desktop for copying files all day, then yes, you are correct. I, however do not do that all day. All i do is open a LOT of programs at the same time. This causes a lot of small random reads/writes. I assume that most users are my situation and therefor an SSD that performs well in 4k random write benches is better suited than the Samsung one.


  46. Winning a couple benchmarks that YOU think are important does not a sound conclusion make.

  47. We’re not trying to validate the results of the previous review. They are valid, for that particular mix of hardware and software. We updated everything this time around, including replacing our older game load tests with new ones.

    There’s such a big difference in Far Cry load times this time around because we’re using Far Cry 2 this time around.

  48. The stutter for jmicron is because of the rewrite penalty no other controller suffers from it.

  49. I am already here.

    Couple of points just for the record:

    All the drives have much quicker response times when fresh than in a simulated used state. The performance differences vary from one drive to another, though. The Vertex’s response time rises by nearly an order of magnitude, while the X25-M is only about five times slower. Neither compares to the Summit, whose used-state response times are roughly 20 times higher than with a fresh drive.

    That is an interesting way of putting it don’t you agree? Even in the used state, the Vertex is faster than the Intel drive and to hold the fact that in the new state it is way faster than the Intel drive against it to say that the Intel drive has less of a performance hit….. I am not quite sure about the logic here.

    2) HDTach: Can somebody explain the results that the burst transfer rate, i.e, the transfer rate between the drive and the system is lower than the sequential transfers. Congratulations, this is bending the laws of physics, or am I missing something?

    Otherwise, good write-up 🙂

    Best Regards

    (VP of Technology Development at OCZ Technology)

  50. File-copy test results are more appropriate for desktop use than iometer and show Samsung drives to have an advantage over Indilinx based drives.

  51. Ok, seriously, have you actually LOOKED at the benches or you just read Geoff’s conclusion at the end and that’s it ?!


  52. I don’t think a Summit will be a better choice for desktop use than a Vertex. If i were to buy an SSD right now, i’d go for the Intel drive and if i didn’t have that kind of dough, my next choice would be the Vertex.

    From the 4k random write performance bench, i really don’t see how the Summit is better suited as a Desktop SSD than the Vertex.


  53. Wrong. I think Dissonance’s conclusion is wrong. Take a look at the scores again and you’ll notice that the benches that MATTER for desktop use (4k random write and read) are the ones where the Intel and Vertex drives perform best.

    For desktop performance, the Vertex still is the second choice right after the Intel drive whether or not the reviewer admits it or not. Mind you, there are other factors to be considered but on a price/performance factor only, the Vertex is still the second choice out there.


  54. The SSDs tested are really 1-1.5X generation SSDs (ihmo). These units are really the very first ones to hit the consumers and need the feedback in order to help test/upgrade for newer models.

    Intel has the “real” 2.0 models coming (as I’m sure others are as well). Platter based storage has plenty of time left (it’ll stay popular in RAID/NAS setups), but I’m itching to get SSD for my machines at home.

  55. Thanks, Geoff for the great followup.

    Now please, we really need you doing something else here, so let’s try to move on… At least for a while until something new happens on the SSD front (perhaps Windows 7 and full TRIM support, and hopefully an updated Intel model).

  56. Benchmarks aside, it will be interesting to see what your experience is with running the Summit in your desktop for a few weeks. If Anand is right about random write performance being critical for the “feel” of SSDs, then the Summit should turn out to be a stuttering mess despite the impressive benchmark scores.

    Still feels like these things are at least 6-12 months away from being a safe purchase. Perhaps they’ll even be affordable in more useful capacities by then as well.

  57. Vertexes are quite popular, so I imagine most of them don’t die within 10 days. That may have been due to something other than the controller.

  58. I bought a couple g.skill falcons back on June 15, and they were both dead within 10 days. The more I read on forums, etc, these things aren’t ready for prime time. Check newegg’s comments on the 128gb “falcon”.

    Not sure if the issue extends to the vertex, which I understand has the same controller.

  59. The results are not comparable from the last test as this is using Vista and different base hardware. However it would have been nice if the test included the WD Black.

  60. Your boot/load tests are off and you changed a lot of stuff compared to the last round. Far cry level loads got cut in more than half (almost in three) compared to the last round of SSD testing, but the OS boot up load actually gained 10 seconds. According to you guys, between both rounds of tests, a WD black actually beats the intel X-25M in OS loading by nearly 20 seconds which is in direct contradiction with what every other reviewer is showing…

    And why would you guys do COD4 level loads when the last review you used DOOM3? If you’re trying to validate results, it only makes sense if the tests are consistent.

  61. That’s a wicked review, Geoff. And I was all set to buy a Vertex today as they’re in the latest sale. For a few bucks more, if I do buy a SSD, I’ll just get a Summit. Anyone have a recommendation on a new case – full ATX at least, I’ve got a new Powercolor Radeon HD4890 1GB card to consider. It hardly fits in my Raidmax Smilodon ATX case.

  62. And there, the Vertex has officially fallen.
    No review could have more authority than this one.

  63. For thinking that their drives’ fresh and/or HD Tach performance is worth anything.

  64. I thought it was supposed to be in the final, but isn’t in the release candidate?

  65. I criticised the benchmarks the first time because too many “problems”, but this time the benchmark is very well done. Dissonance should have done this the tests like this from the beginning so nobody could have problems with them. The problems I had with the benchmark the first time were not in the results, but in the fact that nobody could know if the results were representative of other systems, now we know the new ones are and that they make sense with how things are supposed work.

  66. Its not clear to me if in the test conditions you had AHCI enabled in the bios? That made a big difference in my system. I don’t know if its running firefox in Wow32 in XP64 or what but every little while firefox freezes up even to text input then after about 30 seconds writes what I typed in the buffer. Enabling AHCI made it bearable. With AHCI enabled Atto benchmark showed a 3 to 5 fold increase in read/write throughput for the smallest file sizes; right where it helps.

  67. Not a programmer since the days of FORTRAN but seems to me this is a driver issue. Somebody needs to man up and write a journaling file system for SDD’s that skips around like the sugar plum fairy writing 4K blocks hither and yon and does not erase a 512K block unless it needs to free up storage space and then only in a wear leveling fashion.

  68. Very good analysis! The most important part was at the end. Windows 7 changes everything for SSD’s. I am running 2 x 30GB Vertex drives RAID 0 firmware 1370 on a 780i mobo. Performance slowed very quickly on Vista. I have been running Windows 7 RC1 for a few months now and the drives are staying fast without wiper.

    Here is a good read about what the windows engineering team have to say about SSD’s §[<<]§ As people with enough cash and need for speed to buy an SSD will surely buy Windows 7. I think Vista and XP tests are a bit irrelevant. Can't wait to see you test the same drives on Windows 7!

  69. A different experience… I have used the Vertex for a couple of months and have had great experiences with it and the TRIM function on an Intel P45 chipset board. It restored the drive to new conditions without any data corruption or loss. It’s been one hell of purchase by giving me something new to use and tinker with.

    With that said, I don’t think any SSD is ready for prime-time joe-consumer consumption. It’s still in the realms of educated enthusiast. The next generation of SSDs will be very close to being ready.

  70. As expected, TR’s results were correct the first time. This kind of in-depth followup and analysis is why I don’t bother reading hardware reviews at any other site. I wonder if all of the OCZ fanboys will be back to apologize.

  71. I bought the Corsair M64 and its stuttering right now, especially when doing software installs on this system build. Huge improvement once I enabled AHCI in the bios and got Win XP64 to install the drivers. Off to read the article with great interest.

  72. Didn’t the Vista drivers work better on AMD storage controllers too? Interesting.

  73. I’ve used the Vertex and the X25-M. I really want to use the Vertex more, but the wiper utility they have for TRIM is just not where it needs to be. I had it corrupt my ICH10 AHCI 120GB drive the other night and had to rebuild. Definitely not ready for prime time.