Western Digital’s RE2 750GB hard drive

PC enthusiasts are famous for poaching enterprise-class hardware for their personal systems. New technologies tend to debut for server and workstation markets first—just look at the latest processor launches from AMD and Intel—and we don’t like having to wait for those developments to trickle down to desktop parts. Even after the latest new hotness has a change to percolate through desktop lineups, enterprise-class hardware can still hold the promise of faster performance, better reliability, and longer warranty coverage: a trifecta of goodness that’s hard for any enthusiast to ignore.

Of course there’s another element to our penchant for enterprise-class hardware: the sense of almost smug satisfaction we get from deploying otherwise button-down business hardware in systems that are tweaked and overclocked to within inches of their lives, most of which are spent playing games. It’s much easier to justify spending money on a system you can legitimately call a workstation, too.

Lately, enterprise-class hard drives have become increasingly popular in enthusiast systems. The 10K-RPM Raptor is perhaps the best example of this trend, but not the only one. Western Digital’s RE2 line of 7,200-RPM drives has also become favored among enthusiasts for its delicate balance of performance, capacity, and a five-year warranty. And now there’s a new one.

Based on a Caviar SE16 750GB foundation that we already know delivers phenomenal performance with low noise levels, the latest RE2 benefits from tweaked firmware, RAID optimizations, more extensive reliability testing, and extended warranty coverage. Read on to see if those extras are enough to elevate this enterprise drive above not only its desktop counterpart, but also the fastest drives on the market.

The drive
Before diving into the RE2, we must first separate it from the desktop Caviar SE16. That’s not as easy as one might expect, in part because the drives are cosmetically identical.

The Caviar SE16 and RE2: I can’t see the difference. Can you see the difference?

These drives are similar in more than just their appearance, as well. 750GB flavors of the Caviar SE16 and RE2 are mechanically identical.

Only upon consulting the drive’s label can we discern between the SE16 and RE2. Drives with model number WD7500AYYS are RE2s, while those tagged with WD7500AAKS are Caviar SE16s.

Making an arbitrary distinction between drives that are mechanically identical seems unnecessary, but there’s a method to Western Digital’s madness here. One needs only to dig through the drives’ specifications to get a hint at where the RE2 starts to differ from its desktop counterpart.

On the surface, the specs look comparable, as they should be for drives that share 300MB/s Serial ATA interfaces, 188GB platters, 7,200RPM spindle speeds, and 16MB caches. Yet despite all those similarities, there are a few deviations worth noting. The RE2 manages to shave 1.3 milliseconds off the Caviar SE16’s write seek time, for example. 1.3 milliseconds doesn’t seem like much, but within the confines of a modern PC where bits flip at gigahertz clock speeds, it’s actually quite a long time.

A more aggressive algorithm may make the RE2 seek a little faster, but that optimization is not without cost. The RE2’s seek acoustics are at least a decibel higher than those of the SE16, suggesting Western Digital hasn’t been shy about optimizing for performance at the expense of silence. That’s a sensible trade-off for a drive like the RE2—a single decibel will easily be lost in the droning hum of most enterprise environments.

In addition to running a little louder than its desktop cousin, the RE2 is also rated for higher power consumption, particularly under load. The drive does attempt to cut power use by employing Western Digital’s IntelliSeek just-in-time actuator mechanism, though. Rather than darting the drive head back and forth between data points as fast as possible, IntelliSeek takes advantage of the rotational latency inherent to spinning platters and only moves the drive head as fast as necessary to get it into position for the next time the data point is scheduled to come ’round on the platter. Western Digital is adamant that IntelliSeek still gets the drive head into position on time, so while vibration and power consumption are reduced by the slower drive head movement, seek times don’t suffer.

The RE2 inherits IntelliSeek from the Caviar SE16, but that’s not all. RE2 drives also brings the SE16’s SecurePark head parking mechanism, improving the drive’s tolerance of non-operational shock. The SE16’s StableTrack motor makes its way to the RE2, as well. This motor’s shaft is secured at both ends, which Western Digital says improves the drive’s ability to withstand environmental vibration.

Environmental vibration is actually a major concern for enterprise drives because they’re often grouped in RAID arrays that are packed like sardines into tight enclosures. With that in mind, the RE2 employs a couple of unique features that you won’t find in the Caviar SE16. The first of these features is Rotary Acceleration Feed Forward, or RAFF. RAFF uses accelerometers in the hard drive to sense rotational vibration and adjusts the position of the drive head to maintain a safe distance from the platter. According to Western Digital, this feature allows the drive to sustain higher transfer rates in vibration-rich environments.

With an eye towards RAID applications, the RE2 also features Time-Limited Error Recovery (TLER). Hard drives typically perform error-recovery on their own, occasionally pausing for longer periods of time to save data that would otherwise be lost. Those pauses aren’t an issue for single-drive environments, but they can be problematic when multiple drives are combined in a RAID array. RAID controllers prefer to be in charge of error recovery, and they can be a little impatient. If a single drive in an array pauses for too long trying to recover an error on its own, a RAID controller may mark the drive as failed and drop it from the array. To prevent this kind of array degradation, TLER reduces the amount of time that a drive will attempt error recovery, ensuring that RAID controllers don’t prematurely assume that a drive has gone off the reservation.

In the past, Western Digital has warned against using drives with TLER in single-disk environments. However, no such warning accompanies the 750GB RE2, which WD says can be used all by its lonesome.

With RAFF and TLER, the RE2’s enterprise orientation starts to come into focus. And there’s one more acronym of importance to tackle: MTBF. Western Digital estimates the mean time between failures for its RE2 at 1.2 million hours, which is typical for an enterprise-class hard drive. MTBF data isn’t available for the Caviar SE16, although since it’s mechanically identical to the RE2, one would assume that’s its reliability is comparable. Western Digital does say that the RE2 receives more extensive testing than its desktop drives, though.

Perhaps that more extensive testing makes it easier for Western Digital to step the RE2’s warranty up to five years. Five-year warranties are typical for enterprise drives, of course, but the desktop Caviar SE16 is at best covered for only three years.

Test notes
We’ll be comparing the performance of the RE2 750GB with that of a slew of competitors, including some of the latest and greatest Serial ATA drives from Hitachi, Maxtor, Samsung, Seagate, and Western Digital. These drives differ when it comes to external transfer rates, spindle speeds, cache sizes, platter densities, NCQ support, and capacity, all of which can have an impact on performance. Keep in mind the following differences as we move through our benchmarks:

Note that the 250GB Caviar SE16 and the Raptor WD740GD lack support for Native Command Queuing. The WD740GD does support a form of command queuing known as Tagged Command Queuing (TCQ), but host controller and chipset support for TCQ is pretty thin. Our Intel 955X-based test platform doesn’t support TCQ.

We have test results from several versions of Western Digital’s Caviar SE16 and RE2. To avoid confusion, we’ll be listing their capacities in parentheses in each of our graphs.

Since Seagate makes versions of the 7200.7 both with and without NCQ support, the 7200.7 in our tests appears as the “Barracuda 7200.7 NCQ” to clarify that it’s the NCQ version of the drive. The other drives aren’t explicitly labeled as NCQ drives because they’re not available without NCQ support.

Finally, we should note that our WD1500ADFD has a slightly newer firmware revision than the Raptor X sample we’ve had since February, 2006. The drives still share identical internals, but firmware optimizations could give our newer Raptor an edge over the X in some tests.

Performance data from such a daunting collection of drives can make our graphs a little hard to read, so I’ve highlighted the RE2 750GB in bright yellow and its high-capacity competitors—the Barracuda 7200.10 and ES, the Deskstar 7K1000, and the Caviar SE16 750GB—in pale yellow to set them apart from the others. Since the RE2 is an enterprise drive, I’ve highlighted the 10K-RPM Raptor WD1500ADFD’s performance in light yellow, as well. We also have two sets of IOMeter graphs: one with all the drives, and another with just the Deskstar and its 750GB rivals. Most of our analysis will be limited to how the 7K1000 compares with its direct rivals, so it should be easy to follow along.

Our testing methods
All tests were run three times, and their results were averaged, using the following test system.

Thanks to the folks at Newegg for hooking us up with the DiamondMax 11 we used for testing. Also, thanks to NCIX for getting us the Deskstar 7K1000.

Our test system was powered by OCZ PowerStream power supply units. The PowerStream was one of our Editor’s Choice winners in our last PSU round-up.

We used the following versions of our test applications:

• WorldBench 5.0
• Intel IOMeter v2004.07.30
• Xbit Labs File Copy Test v1.0 beta 13
• TCD Labs HD Tach v3.01
• Far Cry v1.3
• DOOM 3
• Intel iPEAK Storage Performance Toolkit 3.0

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.

WorldBench overall performance
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.

Our first look at the RE2’s performance shows the drive neck and neck with its SE16 desktop counterpart at the head of the pack, but do any of WorldBench’s individual application tests separate the two?

Multimedia editing and encoding

MusicMatch Jukebox

Windows Media Encoder

Adobe Premiere

VideoWave Movie Creator

Not through WorldBench’s multimedia editing and encoding tests. It’s worth noting that few of these apps separate the field, and the RE2 turns in the quickest times in three of four tests.

Image processing

Adobe Photoshop

ACDSee PowerPack

ACDSee gives the drives some room to stretch their legs, and while the Caviar SE16 and RE2 manage to distance themselves a little from the rest of the field, they can’t outrun each other.

Multitasking and office applications

Microsoft Office

Mozilla

Mozilla and Windows Media Encoder

WorldBench’s office and multitasking tests are largely a wash.

Other applications

WinZip

Nero

Things get more interesting with WinZip and Nero, though. In the former, the RE2 ties the SE16 at the head of the class, followed closely by several of its competitors. However, in Nero, the RE2 has a good 15 seconds on the SE16, and even more over the rest of the pack.

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

Boot times are quick for both the SE16 and RE2, with only one one hundredth of a second separating the two.

Our game level load tests knock the Western Digital drives back some, and the RE2 actually pulls up slower than the SE16 in Far Cry. Of course, that still puts the RE2 in the top five, with two of those places occupied by 10K-RPM Raptors.

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. File copying is tested twice: once with the source and target on the same partition, and once with the target on a separate partition. Scores are presented in MB/s.

To make things easier to read, we’ve busted out our FC-Test results into individual graphs for each test pattern. We’ll tackle file creation performance first.

The RE2 goes four for five with FC-Test’s file creation tests. Through the first four test patterns, the drive is not only faster than the SE16, but also quicker than any other Serial ATA drive we’ve tested. Only with the Windows test pattern, which is dominated by a large number of smaller files, does the RE2 fall to third place overall, just short of the SE16.

FC-Test’s read, er, tests provide a little intrigue. The SE16 and RE2 go back and forth here, with the enterprise drive coming out on top with programs and Windows test patterns that include larger numbers of smaller files, and the SE16 reigning supreme with the others, which are made up of smaller numbers of larger files. Overall, the RE2 is at or just shy of the top spot throughout FC-Test’s read workloads.

FC-Test – continued
Next, File Copy Test combines read and write tasks with some, er, copy tests.

Copy tests find the RE2 at the front of the field in all but one test pattern. The RE2 isn’t much faster than the SE16 here, but it does enjoy a consistent performance advantage. Only Hitachi’s terabyte 7K1000 has the throughput to edge ahead of the RE2 in the Windows test pattern.

FC-Test’s second wave of copy tests involves copying files from one partition to another on the same drive.

Hitachi’s rare moment in the sun doesn’t last; when we move to FC-Test’s partition copy workloads, the RE2 finishes atop the podium with each test pattern. The RE2 doesn’t run away from the SE16, but its throughput is consistently faster.

iPEAK multitasking
We’ve developed a series of disk-intensive multitasking tests to highlight the impact of command queuing on hard drive performance. You can get the low-down on these iPEAK-based tests here. The mean service time of each drive is reported in milliseconds, with lower values representing better performance.

The RE2 doesn’t dominate our first wave of iPEAK workloads, but the drive still manages to stay a step ahead of the 750GB SE16. Our dual file copy workload is the only one that takes the RE2 out of the top three.

iPEAK multitasking – con’t

Through the first couple of tests in this second wave of iPEAK workloads, the RE2 manages to maintain its position in the top three. However, once we introduce workloads that include Outlook import operations, the RE2 falls back a few places. It’s still consistently faster than the SE16, though.

IOMeter – Transaction rate
IOMeter presents a good test case for command queuing, so the NCQ-less Western Digital Caviar SE16 250GB and Raptor WD740GD should have a slight disadvantage here under higher loads. To keep things easy to read, we’ve busted out two sets of graphs here. The first includes the Deskstar 7K1000 and its closest competitors, while the second has results for all the drives we’ve tested. With close to 20 drives, those latter graphs are a little difficult to read, so we’ll focus our attention on the first set and the Deskstar’s direct rivals.

At more relaxed loads with fewer concurrent I/O requests, the RE2 runs neck and neck with the SE16. However, once the load scales upwards, the RE2 begins to pull away. Obviously, it has a long way to go before it can catch the 10K-RPM Raptor. But the RE2 has five times the Raptor’s capacity, and it’s the fastest 7,200-RPM drive in these tests.

Good luck with these, folks.

IOMeter – Response time

Response times favor the RE2, but it only pulls away from the SE16 under heavier multi-user loads. As we saw with IOMeter’s transaction rate results, the RE2 may be the quickest 7,200-RPM drive of the lot, yet it’s still in a different class than the Raptor under these kinds of workloads.

IOMeter – CPU utilization

CPU utilization is below half a percent for the RE2 and all its close competitors.

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

Registering the fastest sustained transfer rates we’ve seen from a Serial ATA hard drive, the RE2 tops HD Tach’s read and write speed tests. The drive is between 1.4 and 1.9MB/s faster than its Caviar cousin and even quicker than Western Digital’s fastest Raptors.

Despite its dominance of HD Tach’s sustained transfer rate tests, the RE2 isn’t quite as impressive in the burst speed test. Here, it’s more than 20MB/s off the pace set by Seagate’s Barracuda 7200.10 and even a little slower than the SE16.

Western Digital claims slightly quicker seek times for the RE2, and HD Tach’s random access time test bears that out by a hair. The RE2 is only 0.2 milliseconds faster than the SE16 here, though, and that relegates it to the middle of the pack.

CPU utilization results are within HD Tach’s +/- 2% margin of error for this test.

Noise levels
Noise levels were measured with an Extech 407727 Digital Sound Level meter 1″ from the side of the drives at idle and under an HD Tach seek load. Drives were run with the PCB facing up.

The Caviar SE16 isn’t particularly quiet at idle, and the RE2 is barely an improvement on that front. There’s a bigger delta between the two drives under a seek load, where the RE2 is more than a decibel louder.

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. Through the magic of Ohm’s Law, we were able to calculate the power draw from each voltage rail and add them together for the total power draw of the drive.

Considering its capacity, the RE2’s power consumption is actually quite reasonable. The drive does pull more juice than the SE16, which is to be expected, but under a seek load it still consumes less power than 750GB and 1TB drives from Seagate and Hitachi, respectively.

Conclusions

With the 750GB Caviar SE16 already offering arguably the most attractive blend of performance, noise levels, and power consumption of any desktop Serial ATA drive, Western Digital’s latest RE2 couldn’t start with a better foundation. Built upon that foundation is a drive that’s been tweaked and massaged with enterprise environments in mind. Additions like RAFF and TLER will no doubt come in handy for those looking to deploy a stack of RE2s in RAID, and the drive’s slight performance advantage over the SE16—particularly under heavy multi-user loads—more than makes up for the modest increase in noise levels.

Of course, the RE2’s slightly higher noise levels probably won’t make this drive a favorite among PC enthusiasts. Neither will its price; the RE2 current starts at $260 online while its desktop counterpart can be had for as little as $190. $70 is a lofty premium to scale considering just how close these drives are in terms of performance. An extra two years of warranty coverage surely isn’t worth that much, either.

So the RE2 doesn’t unseat the Caviar SE16 as the best 7,200-RPM Serial ATA hard drive for PC enthusiasts. Instead, it establishes a new high-water mark for enterprise-class 7,200-RPM SATA drives. In fact, unless the environment demands low access times or involves heavy multi-user loads, the RE2 may even be a better alternative than a 10K-RPM Raptor. The RE2 certainly has the edge in terms of capacity—an important consideration if you’re trying to squeeze as much storage as possible into a given rack or enclosure. In many instances, the RE2 beats the Raptor on performance, too.