Western Digital’s Caviar Green 3TB hard drive

There are two kinds of data in this world: that which we need to access quickly and that which mostly just needs to be stored. In the PC world, the former is typically made up of files associated with one’s applications, games, and operating system. You want that data on the fastest drive possible—ideally, a solid-state disk better equipped than mechanical storage to handle the random access patterns commonly associated with OS and application files.

If SSDs were cheap, we’d be using them to store everything. However, flash memory remains an exceedingly expensive proposition next to capacious platters that cost a couple of orders of magnitude less per gigabyte. When you need a lot of capacity for data that mostly just needs to be stored, be it gigabytes of RAW family photos, an MP3 collection fueled by years of rampant piracy, or the complete collection of Sex and the City episodes you ostensibly downloaded for your better half but have yet to delete, only a mechanical hard drive will do. Folks who have already upgraded to an SSD for their OS and application files will want to seek out one of a new breed of low-power hard drives spawned by Western Digital’s Caviar GP, which went on to become the Caviar Green.

Introduced more than three years ago, the Caviar GP compromised performance in the name of reduced power consumption and noise levels, while delivering what was at the time a generous terabyte of capacity. SSDs were an even more indulgent luxury back then, but the soon-to-be Caviar Green became an attractive option for folks building home-theater PCs and those in need of quiet, power-efficient secondary storage for their desktops. A new class of hard drive was born, and today, Hitachi, Samsung, and Seagate all have their own spin on the Green recipe.

However, none of them have a drive that can match the latest Green’s three-terabyte capacity. Although Seagate was first to reach the 3TB threshold with an external drive released this summer, the hard disk that lives within isn’t being offered as a bare Barracuda. Western Digital announced its own 3TB external drive earlier this month, and already, an internal version has become available.

Breaking new ground on the capacity front is nothing new for the Caviar Green family. Back in February of last year, it became the first drive line to reach the 2TB mark. Jumping from two to three terabytes over a year and a half puts one more nail in the coffin of Kryder’s law, which predicted a doubling of areal density, and thus hard drive capacity, every year. Western Digital seems intent on being secretive about the areal density of the new platters that fuel its 3TB monster. However, it has confirmed that each one packs 750GB—a 50% increase over the 500GB platters that reside in 2TB Caviars. Those last-gen platters have an areal density of 400 Gb/in², so the new ones are probably squeezing at least 600 gigabits into every square inch of platter surface area.

With 750GB apiece, only four platters are needed to hit three terabytes. A 2.5TB variant is also on the way, but no three-platter model is planned at 2.25TB.

Like previous Caviar Greens, this one rotates its high-tech magnetic turntable at about 5,400 RPM. Western Digital has always been reticent to reveal exact spindle speeds for Caviar Greens, which it says are fine-tuned for each capacity point (or, more likely, each platter config) to hit specific power and acoustic targets. However, the company has conceded that this is essentially a 5,400-RPM drive.

Somewhat surprisingly for a product that doesn’t aspire to better than “solid” performance, the new Green comes equipped with a substantial 64MB of DRAM cache memory. Western Digital isn’t moving the Green line into 6Gbps Serial ATA territory, though. The drive’s 3Gbps interface is more than fast enough considering that the spec sheet quotes a maximum disk transfer rate of 110MB/s. However, I wouldn’t put too much stock into that number given that the same one is listed for every member of the Caviar Green family, including drives with lower-density platters.

Higher areal densities lead to faster sequential transfers because more data pass under the drive head in a given moment as the platter spins. Thus, the Caviar Green 3TB’s 750GB platters should offer higher transfer rates than the 2TB drive’s 500GB discs. The amount of available outer-edge area—the fastest portion of a platter—can also affect transfer rates. Since they’re both four-platter designs, the 2TB and 3TB Caviar Greens should be even in that department.

Of course, performance is hardly the Caviar Green’s raison d’être. This drive is all about quiet, power-efficient storage, and its specs are certainly impressive on that front. We’ll test noise levels and power consumption a little later in the review to see how the new Green measures up to the competition.

Like much of that competition, the Caviar Green 3TB is covered by a three-year warranty. That’s sufficient, I suppose, but the five-year warranties attached to premium 7,200-RPM hard drives would be a welcome addition to the Caviar Green line. Despite the fact that longer warranty coverage doesn’t guarantee a lower failure rate, it would be nice to have the extra coverage for the added peace of mind, however irrational. 3TB is a heck of a lot of data to lose, and reliability is one thing we can’t test without delaying this review well beyond the point of irrelevance.

Complications on the road to 3TB
The Caviar Green 3TB makes use of Advanced Format to use the capacity it has available more efficiently. Rather than breaking platters up into 512-byte blocks, Advanced Format relies on 4KB sectors that waste less storage capacity on overhead. Advanced Format is new enough to create compatibility issues with some software, which is why the Caviar Green uses 4KB sectors internally but presents itself as a drive with 512-byte sectors thanks to an emulation scheme WD dubs 512e.

Using 512e is all well and good on drives with capacities less than 2.19TB, but you run into problems with anything larger because Master Boot Record partition tables can only address up to 2³² blocks. With 512-byte sectors, that adds up to a maximum capacity of 2.19TB, or considerably less than the 3TB offered by the new Caviar Green. The storage industry’s answer to the MBR’s addressing limitation is the GUID Partition Table, or GPT, which can address up to 2⁶⁴ sectors. Windows XP doesn’t work with GPT partitions, so Western Digital isn’t supporting the drive under that OS, although it notes that users may be able to find workarounds using third-party controllers and drivers.

There are issues for users running Windows 7 and Vista, as well. Both support GPT and will detect a full 3TB of capacity when the Green is run as secondary storage. However, if you want to use the Caviar as a boot drive, you’ll need a 64-bit version of either OS and a motherboard with a Unified Extensible Firmware Interface (UEFI) BIOS. Motherboards equipped with UEFI BIOSes are few and far between, so Western Digital is shipping this Caviar with a HighPoint RocketRAID 62X Serial ATA card with a PCI Express x1 interface. Folks with motherboards that lack UEFI BIOSes will be able to boot off the drive if it’s connected to the HighPoint card, but they’ll still need to be running a 64-bit version of Vista or Windows 7 to exploit all three terabytes.

Interestingly, the Caviar Green had no problem booting into Windows 7 x64 when connected to our test system’s P55 storage controller. However, this system’s motherboard doesn’t have a UEFI BIOS, so we couldn’t tap the drive’s full capacity. 746GB was inaccessible even with the drive converted to GPT, although we didn’t run in to any issues getting at all 3TB of capacity with the Green installed as a secondary hard drive.

That was with the Microsoft AHCI drivers built into Windows 7. We had more trouble with Intel’s latest 9.6.0.1014 RST storage controller drivers, which came out way back in March and are apparently unprepared to cross the 2.19TB threshold. When running the Caviar Green as a boot drive, we could only see 746GB of storage capacity, presumably from the portion of the disk beyond the 2.19TB mark. Even worse, that same 746GB was all that was available when running the Green as secondary storage! Intel is aware of the issue and has committed to address it with an updated RST driver that will be released this quarter. However, you’ll still need a motherboard with a UEFI BIOS or a compatible auxiliary storage controller to boot off the Green’s full 3TB capacity.

Or you need a Mac. The Cult of Jobs can rejoice knowing that Apple’s Intel-based systems have UEFI BIOSes and that OS X 10.5 and 10.6 both support GPT partitions. Those folks should be able to plug in the 3TB Green and use it however they wish.

Watch for motherboard makers to pounce on what looks like an opportunity to differentiate their boards with gaudy “3TB-ready” stickers. Asus has already developed an application that creates a virtual drive to give users access to the Green’s full capacity, even under Windows XP. Old XP licenses are great for closet file servers, which seem like a natural home for the first 3TB Caviar.

Our testing methods
Before dipping into pages of benchmark graphs, let’s set the stage with a quick look at other the players we’ve assembled for comparative reference. We’ve called up a wide range of competitors, including a selection of desktop hard drives, traditional notebook drives, Seagate’s Momentus XT hybrid, and a stack of pure solid-state goodness. Below is a chart highlighting some of the key attributes of the contenders we’ve lined up to face the Caviar Green 3TB.

Obviously, the SSD and mobile hard drive results won’t be as relevant to our discussion of the new Caviar Green. You’ll want to pay particular attention to how the Green compares to its 2TB predecessor and Seagate’s low-power Barracuda LP. The LP tops out at 2TB, which is as big as you can get Seagate’s internal hard drives at the moment.

On the SSD front, we’ve collected all the other relevant players, including drives based on Indilinx, Intel, JMicron, Marvell, SandForce, and Toshiba controllers. Although it might not seem like a fair fight, we’ve also thrown in results for a striped RAID 0 array built using a pair of Intel’s X25-V SSDs. The X25-V only runs a little more than $100 online, making multi-drive RAID arrays affordable enough to be tempting for desktop users. Our X25-V array was configured using Intel’s P55 storage controller, the default 128KB stripe size, and the company’s latest 9.6.0.1014 Rapid Storage Technology drivers.

The block-rewrite penalty inherent to SSDs and the TRIM command designed to offset it both complicate our testing somewhat, so I should explain our SSD testing methods in greater detail. Before testing the drives, each was returned to a factory-fresh state with a secure erase, which empties all the flash pages on a drive. Next, we fired up HD Tune and ran full-disk read and write speed tests. The TRIM command requires that drives have a file system in place, but since HD Tune requires an unpartitioned drive, TRIM won’t be a factor in those tests.

After HD Tune, we partitioned the drives and kicked off our usual IOMeter scripts, which are now aligned to 4KB sectors. When running on a partitioned drive, IOMeter first fills it with a single file, firmly putting SSDs into a used state in which all of their flash pages have been occupied. We deleted that file before moving onto our file copy tests, after which we restored an image to each drive for some application testing. Incidentally, creating and deleting IOMeter’s full-disk file and the associated partition didn’t affect HD Tune transfer rates or access times.

Our methods should ensure that each SSD is tested on an even, used-state playing field. However, differences in how eagerly an SSD elects to erase trimmed flash pages could affect performance in our tests and in the real world. Testing drives in a used state may put the TRIM-less Plextor SSD at a disadvantage, but I’m not inclined to indulge the drive just because it’s using a dated controller chip.

To make our massive collection of results a little easier to interpret, we’ve colored our bar charts by drive type. This color coding separates the SSDs from 2.5″ and 3.5″ mechanical drives and marks low-RPM versions of the latter, allowing the Caviar Green to stand out from the crowd, at least visually.

Most of our tests run on drives connected as secondary storage, so we were able to use the Caviar Green’s full 3TB with our test system’s default configuration, which uses the Microsoft AHCI drivers built into Windows 7. For the few tests that required booting off the Green, we elected to stick with the same config, since moving to the HighPoint card would’ve made the results less comparable—we’d be switching storage controllers, as well. The impact of running the Green at slightly less than full capacity should be negligible considering that our boot and system partition only amounts to 100GB, most of which is unused.

With few exceptions, all tests were run at least three times, and we reported the median of the scores produced. We used the following system configuration for testing:

You can read more about the hardware that makes up our twin storage test systems on this page of our VelociRaptor VR200M review. Thanks to Gigabyte for providing the twins’ motherboards and graphics cards, OCZ for the memory and PSUs, Western Digital for the system drives, and Thermaltake for SpinQ heatsinks that keep the Core i5s cool.

We used the following versions of our test applications:

• WorldBench 6
• Intel IOMeter 2006.07.27
• Xbit Labs File Copy Test 0.3
• HD Tune 4.01
• Visual Studio 2008 with 03-23-2010 Firefox source
• Call of Duty: Modern Warfare 2
• Crysis Warhead

The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at a 75Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.

Most of 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.

HD Tune
We’ll kick things off with HD Tune, our synthetic benchmark of choice. Although not necessarily representative of real-world workloads, HD Tune’s targeted tests give us a glimpse of a drive’s raw capabilities. From there, we can explore whether the drives live up to their potential.

I’ve removed the SSDs from the line graphs because the data is too densely packed to be readable. Plus, Excel really doesn’t have enough colors. If you’d like an idea of how the SSD transfer-rate profiles look in comparison, check out this page of our 7,200-RPM terabyte round-up.

First, a quick primer on color coding for the bar graphs. The Caviar Green 3TB is, as one might expect, green. Low-power desktop drives are dressed in a more evergreen hue, while blue highlights the pack of 7,200-RPM desktop drives and 10k-RPM VelociRaptors. We’ve greyed out the results for the 2.5″ crowd, with separate shades for SSDs and mechanical notebook models.

Let this first graph set your expectations for the rest of our performance results. The Caviar Green probably won’t be particularly quick in the realm of mechanical hard drives, which means it’s going to be quite a bit slower than the solid-state offerings that dominate the top of the standings.

The 3TB Green’s sustained read rate is, however, much faster than 2TB’s—by 18MB/s if we look at the averages. Seagate’s Barracuda LP is quicker than the 2TB Green but not fast enough to catch the 3TB model.

If you look at the line graph, you’ll notice that the ‘cuda’s read rates level and then plummet in a stair-step fashion across the length of the disk. The Caviar Green’s reads follow a similar profile, but the steps are less pronounced, particularly through the middle of the drive’s capacity.

Our write-speed results play out much like the reads. The Green is once again quicker than its 2TB cousin and the Barracuda LP, and this time it even beats Intel’s flagship X25-M SSD. Don’t get too excited, though. The X25-M line is notorious for its comparatively slow write rates.

Next up: some burst-rate tests that should test the cache speed of each drive. We’ve omitted the X25-V RAID array from the following results because it uses a slice of system memory as a drive cache.

The Green’s slow spindle speed doesn’t hamper short burst transfers to and from the drive’s hefty 64MB cache. While certainly not the quickest drive of the bunch, the 3TB Caviar finds itself nicely in the middle of the pack. It’s ahead of the 2TB Green but 12MB/s short of the Barracuda LP.

Our HD Tune tests conclude with a look at random access times, which the app separates into 512-byte, 4KB, 64KB, and 1MB transfer sizes. Let’s start with reads.

Betcha didn’t expect that. No, not the SSDs dominating. I’m talking about the 3TB Green edging out a couple of 7,200-RPM Seagates in random reads, at least up to the 64KB transfer size. All the drives slow considerably with 1MB random reads, but the 3TB Green still edges out the 2TB model and ties with the Barracuda LP.

The Caviar isn’t nearly as competitive with writes, where it’s well behind all of the 3.5″ desktop offerings. Only the Scorpio Blue, a 2.5″ notebook drive with a similar 5,400-RPM spindle speed, has slower access times with random writes. This is why you probably don’t want the Caviar Green as your system drive, at least on a desktop PC.

File Copy Test
Since we’ve tested theoretical transfer rates, it’s only fitting that we follow up with a look at how each drive handles a more typical set of sequential transfers. 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.

Windows 7’s intelligent caching schemes make obtaining consistent and repeatable performance results rather difficult with FC-Test. To get reliable results, we had to drop back to an older 0.3 revision of the application and create our 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 Windows 7’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 obviously erroneous results pop up every so often. Additional test runs were performed to replace those scores.

Given its strong sustained write rates in HD Tune, I expected better from the 3TB Green in these file creation tests. The Caviar is particularly sluggish with the MP3 file set, but it’s more competitive with the other two, at least when compared with the 2TB Green. That said, the Barracuda LP has notably faster file creation speeds across all three file sets.

Switching to reads gives the Seagate drives fits with the MP3 and program file sets. The 3TB Green doesn’t have any issues with read performance, and it maintains a healthy lead over its 2TB counterpart throughout. Notice that the latest Caviar is only a little bit slower than the last-gen VelociRaptor, which has a blistering 10k-RPM spindle speed.

These copy tests combine read and write operations, so it’s not surprising to see the 3TB Caviar faltering with the MP3 file set. The drive otherwise manages to best its 2TB predecessor, although it’s still slower than the Barracuda LP across the board.

File copy speed
Although FC-Test does a good job of highlighting how quickly drives read, write, and copy different types of files, the app is antiquated enough to completely ignore the command queuing logic built into modern hard drives and SSDs. FC-Test only uses a queue depth of one, while Native Command Queuing can stack up to 32 I/O requests when asked. To get a better sense of how these drives react when moving files around in Windows 7, we performed a set of hand-timed copy tests with 7GB worth of documents, digital pictures, MP3s, movies, and program files. These files were copied from the drive to itself to eliminate any other bottlenecks.

We run this test on SSDs in a factory fresh and simulated used state since there are often performance differences between those two conditions. To put our SSDs into a simulated used state, I run our IOMeter workstation access pattern with 256 concurrent I/O requests for 30 minutes before launching into a second batch of copy tests.

IOMeter creates a massive test file that spans the entirety of a drive’s capacity, and deleting it to make room for a batch of copy tests nicely puts solid-state disks into a tortured used state. What we’ve essentially done here is filled all of an SSD’s flash pages, subjected the drive to a punishing workload with a highly-randomized access pattern, and then marked all of the flash pages as available to be reclaimed by garbage-collection or wear-leveling routines.

Mechanical hard drives aren’t subject to the block-rewrite penalty that causes SSD performance degradation as flash pages become occupied, so there’s no difference between their fresh- and used-state performance. We’ve double-checked to be sure. To avoid confusing the issue, we’ve omitted the fresh-state copy speeds of the SSDs in the graph below.

This real-world file copy test shows the Caviar Green 3TB in a more positive light than FC-Test. Here, the Green is just a smidgen ahead of our low-power 2TB drives. The 7,200-RPM desktop models are quite a bit quicker, of course, with the Spinpoint F3 boasting a copy speed 67% faster than the new Caviar’s.

Application performance
We’ve long used WorldBench to test performance across a broad range of common desktop applications. The problem is that few of those tests are bound by storage subsystem performance—a faster hard drive isn’t going to improve your web browsing or 3ds Max rendering speeds. A few of WorldBench’s component tests have shown favor to faster hard drives in the past, though, so we’ve included them here.

Just because the 3TB Green offers largely equivalent performance to the others in most of our application tests doesn’t make it a good app drive. As the Nero test nicely illustrates, the Green is substantially slower than its 3.5″ counterparts with higher spindle speeds, including the Barracuda LP. The 3TB Green does have a sizable advantage over the 2TB model in that particular test, though.

Boot and load times
Our trusty stopwatch makes a return for some hand-timed boot and load tests. When looking at the boot time results, keep in mind that our system must initialize multiple storage controllers, each of which looks for connected devices, before Windows starts to load. You’ll want to focus on the differences between boot times rather than the absolute values.

This boot test starts the moment the power button is hit and stops when the mouse cursor turns into a pointer on the Windows 7 desktop. For what it’s worth, I experimented with some boot tests that included launching multiple applications from the startup folder, but those apps wouldn’t load reliably in the same order, making precise timing difficult. We’ll take a look at this scenario from a slightly different angle in a moment.

Once again, the 3TB Green is quicker than its 2TB cousin but slower than the Barracuda LP. The difference between the three only amounts to a couple of seconds, which is longer than it’ll take to figure out what your system needs to access the Green’s full capacity as a boot drive.

A faster hard drive is not going to improve frame rates in your favorite game (not if you’re running a reasonable amount of memory, anyway), but can it get you into the game quicker?

If you’re worried about games spilling over from your solid-state system drive and into secondary storage, pay attention to these results. The 3TB Green loads our two gaming scenarios several seconds slower than 7,200-RPM desktop drives. Seagate’s 5,900-RPM Barracuda has a lead of nearly five seconds in Modern Warfare 2, but the gap shrinks to less than two seconds in Crysis. Versus the 2TB Green, the 3TB drive saves about a second in each gaming test.

Disk-intensive multitasking
TR DriveBench allows us to record the individual IO requests associated with a Windows session and then play those results back on different drives. We’ve used this app to create a new set of multitasking workloads that should be representative of the sort of disk-intensive scenarios folks face on a regular basis.

Each workload is made up of two components: a disk-intensive background task and a series of foreground tasks. The background task is different for each workload, but we performed the same foreground tasks each time.

In the foreground, we started by loading up multiple pages in Firefox. Next, we opened, saved, and closed small and large documents in Word, spreadsheets in Excel, PDFs in Acrobat, and images in Photoshop. We then fired up Modern Warfare 2 and loaded two special-ops missions, playing each one for three minutes. TweetDeck, the Pidgin instant-messaging app, and AVG Anti-Virus were running throughout.

For background tasks, we used our Firefox compiling test; a file copy made up of a mix of movies, MP3s, and program files; a BitTorrent download pulling seven Linux ISOs from 800 connections at a combined 1.2MB/s; a video transcode converting a high-def 720p over-the-air recording from my home-theater PC to WMV format; and a full-disk AVG virus scan.

DriveBench produces a trace file for each workload that includes all IOs that made up the session. We can then measure performance by using DriveBench to play back each trace file. During playback, any idle time recorded in the original session is ignored—IOs are fed to the disk as fast as it can process them. This approach doesn’t give us a perfect indicator of real-world behavior, but it does illustrate how each drive might perform if it were attached to an infinitely fast system. We know the number of IOs in each workload, and armed with a completion time for each trace playback, we can score drives in IOs per second.

Below, you’ll find an overall average followed by scores for each of our individual workloads. The overall score is an average of the mean performance score in each multitasking workload.

DriveBench doesn’t produce reliable results with Microsoft’s AHCI driver, forcing us to obtain the following performance results with Intel’s 9.6.0.1014 RST drivers. We couldn’t get DriveBench to play nicely with our the X25-V RAID config, either, which is why it’s not listed in the graphs below. The app will only run on unpartitioned drives, so we tested drives after they’d completed the rest of the suite.

As we’ve mentioned, Intel’s current RST drivers don’t properly support 3TB hard drives. Instead of detecting the Green’s full capacity, we were limited to the latter 746GB of the drive. That’s still enough capacity to run our DriveBench workloads, but given that the Intel drivers aren’t handling the Green properly, I’m hesitant to draw too many conclusions from the results.

Looking at the overall DriveBench scores, we see the 3TB Caviar just barely ahead of the 2TB model. That’s not a surprise, nor is the fact that the Barracuda LP is out ahead of both. The ‘cuda’s margin of victory here is particularly impressive, though; it’s 20% quicker than the Greens.

Let’s break down the overall average into individual test results to see if anything stands out.

The Caviar’s performance with the virus-scanning workload certainly jumps out, but not in a good way. The Green is particularly slow, finishing dead last in a pack that includes a 5,400-RPM notebook model. Given the fact that drives churn out fewer IOps with the virus-scanning workload than any other, I suspect it’s our most demanding multitasking test.

Curious to see whether removing the multitasking element of these tests would have any bearing on the standings, I recorded a control trace without a background task.

Nope. Nothing to see here.

DriveBench lets us start recording Windows sessions from the moment the storage driver loads during the boot process. We can use this capability to take another look at boot times, again assuming our infinitely fast system. For this boot test, I configured Windows to launch TweetDeck, Pidgin, AVG, Word, Excel, Acrobat, and Photoshop on startup.

The 3TB Green puts a little more distance between itself and the 2TB model, but both are still slower than the Barracuda LP.

IOMeter
Our IOMeter workloads are made up of randomized access patterns, presenting a good test case for both seek times and command queuing. The app’s ability to bombard drives with an escalating number of concurrent IO requests also does a nice job of simulating the sort of demanding multi-user environments that are common in enterprise applications.

SSDs are orders of magnitude faster than mechanical hard drives in this test, and that makes graphing the results rather challenging. So we didn’t. The graphs below only have results from the mechanical hard drives. If you’d like to see how the SSDs compare, scroll down this page of our four-way 7,200-RPM terabyte comparison.

Western Digital’s newest Caviar Green has mostly been faster than the 2TB model, and that holds true with three of four IOMeter access patterns. With the file server access pattern, the 3TB Green’s transaction rates lag behind those of its predecessor by a decent margin.

Both Caviars outclass the Barracuda LP with the file server, workstation, and database access patterns. In those tests, the ‘cuda’s transaction rates flat-line until we hit 32 outstanding I/O requests—the queue depth for Native Command Queuing—before ramping up aggressively. The LP’s transaction rates scale more linearly with the web server access pattern, which is made up entirely of read requests.

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.

Finally, the Caviar Green gets to play on its native turf, and it shines, drawing fewer watts under load than any other 3.5″ desktop drive (the VelociRaptors have 2.5″ form factors inside 3.5″ sleds). The Green’s idle power draw is also impressively low, although not quite as sparing as the Barracuda LP or terabyte Deskstar. Given its capacity, the Caviar would look even better on a watts-per-terabyte scale.

Noise levels
Noise levels were measured with a TES-52 Digital Sound Level meter 1″ from the side of the drives at idle and under an HD Tune seek load. Drives were run with the PCB facing up.

Our noise level and power consumption tests were conducted with the drives connected to the motherboard’s P55 storage controller.

I’ve consolidated the solid-state drives here because they’re all completely silent. The SSD noise level depicted below is a reflection of the noise generated by the rest of the test system, which has a passively-cooled graphics card, a very quiet PSU, and a nearly silent CPU cooler.

The 3TB Caviar is far from quietest mechanical drive of the bunch. However, drives with fewer platters tend to generate less noise than those with more, and the Green is quieter than any other four-platter model. Under a seek load, only a couple of two-platter terabyte drives generate less noise than the 3TB Caviar. The new Green has quieter seek acoustics than the 2TB model, as well.

Most mechanical hard drives have an Automatic Acoustic Management (AAM) value that can be set between 128 and 254. Manipulating this setting tends not to affect idle noise levels, but it can dramatically impact seek noise and access times. To get an idea of the sort of performance and acoustic range available with our collection of mechanical drives, we’ve tested the seek noise level and random access time of each at the extremes of the AAM scale. By default, all of the mechanical drives had AAM disabled or set to 254, which is the most aggressive seek setting. AAM doesn’t appear to work at all on the Barracuda XT.

Fiddling with AAM levels will only cut a decibel from the 3TB Green’s seek noise levels. That’s not enough to get the drive into Spinpoint territory, and my ears were hard pressed to notice the difference from a couple of feet away. Is there much of a performance penalty to the less aggressive AAM setting?

Oh yes. The Green’s seek time jumps by a third when we push the AAM slider back to 128. Even with the drive deployed as secondary storage, I probably wouldn’t bother messing with the default AAM setting.

The value perspective
After spending pages rifling through a stack of performance graphs, it’s time to broaden our horizons a little and take each drive’s price into consideration. First, we’ll look at capacity per dollar.

To establish an even playing field for all the contenders, we’re using Newegg pricing for all the drives. Mail-in rebates weren’t included in our calculations. Rather than relying on manufacturer-claimed capacities, we gauged each drive’s capacity by creating an actual Windows 7 partition and recording the total number of bytes reported by the OS. Having little interest in the GB/GiB debate, I simply took that byte total, divided by a Giga (10⁹), and then by the price. The result is capacity per dollar that, at least literally, is reflected in gigabytes.

In part because it sets a new standard for overall capacity, the Caviar Green 3TB commands a rather hefty price premium compared to other mechanical desktop drives. The drive’s $240 asking price includes the HighPoint controller, of course, but that doesn’t add any gigabytes to the equation. Flagship capacity points have always been a costly proposition, so the Green’s position isn’t unexpected.

Overall performance per dollar is up next, but before we get there, we need to come up with an overall performance score for each drive. Using a single number to represent a drive’s performance across a range of different benchmark tests can be tricky business. After reading through numerous papers on the subject, we’ve settled on calculating a harmonic mean of all the results you’ve seen today. A harmonic mean can be useful for quantifying overall performance for a benchmark suite when individual test results can be compared to a reference baseline, and it’s not prone to being skewed by the fact that we have performance differences of several orders of magnitude in some cases. We just happen to have a full suite of results normalized to a performance baseline provided by an ancient 2.5″, 4,200-RPM IBM Travelstar mobile drive, and as you’ll see in a moment, the harmonic mean generates an overall score that nicely tracks with expectations based on the performance we’ve observed thus far.

I should note that we considered using an arithmetic average to calculate our overall score. However, this simple mean is easily skewed by the enormous performance gaps in IOMeter and HD Tune’s random access time tests, which are several orders of magnitude larger than the performance deltas in the other tests. The resulting overall score doesn’t track with expectations based on the performance we’ve already quantified. Weighting the average to account for those orders-of-magnitude differences would have been arbitrary at best, so we’ve settled on a harmonic mean, which seems to provide useful results.

Our overall score includes individual results for DriveBench and IOMeter rather than the averages we presented in the first set of value graphs. There are five DriveBench multitasking loads and four IOMeter access patterns, giving us a total of 19 test results from which to calculate the harmonic mean. This collection of tests is a little biased towards random access patterns rather than sequential transfers, but we think it strikes a good balance for drives that will store a system’s OS and applications. The power-efficiency and noise-level results have been left out to keep this a strictly performance-per-dollar affair.

Because they had to sit out at least one of the tests that make up our overall average, the PX-128M1S and X25-V RAID array haven’t been included in the graphs below. We wouldn’t recommend the former, anyway, and with two drives at its disposal, the RAID config would’ve had an unfair advantage—you know, like it’s had all day already.

Our overall performance index isn’t particularly friendly to the new Caviar Green. The drive’s slow random-write access times and poor performance with DriveBench’s virus-scanning workload certainly don’t help, as the 3TB Green lags behind all other desktop drives, including the 2TB model.

SSDs obviously have a huge advantage when we consider overall performance. However, capacity is an equally important component of any storage device. We’ve divided each drive’s overall performance score by its cost per gigabyte to get a look at overall performance per dollar per gigabyte. Try saying that five times fast.

I’ve omitted SSDs from the scatter plots for the sake of readability. Once more, if you’re curious to see how the solid-state field compares, consult this section of our last hard drive round-up.

With room to spread out, the mechanical drives make for an interesting scatter plot all on their own. The Caviar Green is the slowest of the desktop drives, and much better performance can be had without moving up much on the price axis. In fact, you can step up in performance and spend a fair bit less on both the Caviar Green 2TB and the similarly sized Barracuda LP.

Another way to look at this data is to divide each drive’s performance by the cost of a complete system built around it. The aim here is to determine whether spending a little (or a lot) more makes sense when the price premium is absorbed as part of the cost of a complete system. The step up from a $70 drive to a $95 one is hardly daunting to start, and once you factor in the cost of a complete build, the price difference practically disappears.

For our system price calculations, we’ve used our test rig as the inspiration for a base config, to which the price of each drive will be added. Our example system includes a Core i5-750, a P55-based ASUS P755D-E motherboard, 4GB of DDR3-1333 memory, a passively-cooled Radeon HD 4850, Antec’s Sonata III enclosure, and Windows 7. Its base price is $814.94, although you’ll probably want to tack on the cost of secondary mass storage for configurations that will use an SSD.

The Caviar’s relatively high price does it no favors here. Once more, the 3TB Green looks like a relatively poor value, at least from a performance perspective. Of course, you shouldn’t be buying a Caviar Green for its performance.