Few drives have generated as much buzz as Western Digital’s upcoming Raptor, the first ATA drive to feature a 10,000 RPM spindle speed. Long-time SR sponsor Hyper Microsystems has made it possible to put an early pre-production Raptor through our standard battery of tests.
When reading the preview and perusing the figures, please remember that these results have been culled from a pre-production drive. Performance figures on the final shipping product may differ substantially. Though SR has traditionally refrained from presenting pre-production figures, HyperMicro’s gracious gesture combined with the SR readership’s insatiable curiosity has pushed this preview forward.
|
Western Digital is in many ways the perfect company to lead ATA to a next-generation spindle speed. Ever since it introduced the Caviar WD400BB, WD has consistently led the field when it came to ATA performance. That’s a 2.5-year run at the top- very impressive in the competitive computer hardware field. More importantly, however, the firm has no SCSI business to protect. The last thing that established SCSI powerhouses such as Seagate, IBM, and Maxtor want to see is the erosion of the relatively cushy margins associated with SCSI drives. Now that WD has opened this veritable Pandora’s Box, the competition is sure to follow.
According to WD, the key factor holding back higher spindle speeds was parallel ATA’s lack of specification-level hot swap functionality. To be successful (initially, at least), any 10k RPM ATA drive must gun for the enterprise market. And in the enterprise, a sector that views outages as unacceptable, the ability to swap out a failed drive for another unit with minimal downtime is crucial. Serial ATA provides for such hot-swap functionality. Now that SATA is trickling into the channel, WD believes 10k RPM ATA’s time has come.
The Raptor comes in just a single configuration- a single 36-gigabyte platter. WD specifies the drive’s seek time at just 5.2 milliseconds, solidly within SCSI territory. An 8-megabyte buffer accompanies the drive. Some folks may be disappointed with the drive’s relatively paltry capacity- after all, today’s SCSI drives deliver 147 GB of storage in a low-profile chassis. Much like its namesake made popular by 1993’s Jurassic Park, however, WD envisions Raptors in multiple-drive configurations running off of relatively inexpensive SATA RAID controllers. Reflecting its enterprise orientation, the Raptor claims a 1.2 million hour MTBF spec and features a five-year warranty.
It is important to note that the market for the Raptor is primarily the entry- and mid-level server markets and not the enthusiast desktop sector. When Western Digital raised the bar nearly 1.5 years ago, we repeatedly pointed out that the Special Edition (JB series) Caviar was what readers really wanted when they speculated over 10,000 RPM ATA drives. Equipped with an 8-megabyte buffer and accompanying firmware aggressively tuned for single-user scenarios, the WD1000JB easily matched and even exceeded the performance that the best 10k RPM SCSI drives of the era delivered when it came to desktop performance. While SCSI drives feature superior mechanics, their server orientation forces them to trade away firmware optimized for highly-localized patterns in favor of strategies that maximize returns in random access scenarios. In the Raptor, WD faces much of the same quandary. With its enterprise-class warranty and seek time, however, its clear that server performance is WD’s first priority for the Raptor.
The drive tested for this review is a beta unit provided by longtime SR sponsor HyperMicro.com rather than Western Digital itself. With a handful of exceptions, SR generally has not published performance figures for products this early in the development cycle. Please remember the final Raptor product may deliver results substantially different from those that follow.
Keeping that in mind, let’s see what kind of performance this beta sample delivers!
Low-Level ResultsFor diagnostic purposes only, StorageReview measures the following low-level parameters: Average Read Access Time– An average of 25,000 random accesses of a single sector each conducted through IPEAK SPT’s AnalyzeDisk suite. The high sample size permits a much more accurate reading than most typical benchmarks deliver and provides an excellent figure with which one may contrast the claimed access time (claimed seek time + the drive spindle speed’s average rotational latency) provided by manufacturers. WB99 Disk/Read Transfer Rate – Begin– The sequential transfer rate attained by the outermost zones in the hard disk. The figure typically represents the highest sustained transfer rate a drive delivers. WB99 Disk/Read Transfer Rate – End– The sequential transfer rate attained by the innermost zones in the hard disk. The figure typically represents the lowest sustained transfer rate a drive delivers. |
For more information, please click here.
|
Note: Scores on top are better. |
|
||||||||||
|
WD360GD (BETA) Average Read Service Time |
|||||||||
|---|---|---|---|---|---|---|---|---|---|---|
The beta Raptor delivers a measured average access time of 8.7 milliseconds. Subtracting 3.0 ms to account for the rotational latency of a 10k RPM spindle speed yields a measured seek time of 5.7 ms. While excellent for an ATA drive, the score is a bit off of the manufacturer’s 5.2 ms claim as well as a bit higher than what we’ve come to expect from 10k SCSI drives.
The use of an external controller (the Promise SATA150 TX4) and its associated driver unfortunately makes it more difficult to consistently disable write caching which unfortunately precludes us from presenting average write access times.
|
Note: Scores on top are better. |
|
|||||||||||||||||||
|
|
||||||||||||||||||
WD360GD (BETA) Transfer Rate |
|||||||||||||||||||
Despite its higher spindle speed, the Raptor’s outer-zone transfer rates aren’t much better than today’s top 7200 RPM units. Its score of 57.6 MB/sec narrowly beats the Caviar WD2000JB and slightly trails the DiamondMax Plus 9. Thanks to its smaller platter diameter, the Raptor exhibits a bit less decay as it moves towards its inner zones. Its minimum score of 37.6 MB/sec tops other ATA drives yet still fails to reach the levels of a Cheetah or Atlas.
Single-User PerformanceStorageReview uses the following tests to assess non-server use: StorageReview.com Office DriveMark 2002– A capture of 30 minutes of actual computer productivity use that exactingly recreates a typical office-style multitasking environment. The applications include: Outlook XP, Word XP, Excel XP, PowerPoint XP, Calypso (a freeware e-mail client), SecureCRT v3.3 (a telnet/SSH client), CuteFTP Pro v1.0 (an FTP/SSH client), ICQ 2000b), Palm Hotsync 4.0, Gravity 2.3 (a Usenet/newsgroups client), PaintShop Pro v7.0, Media Player v8 for the occasional MP3, and Internet Explorer 6.0. StorageReview.com High-End DriveMark 2002– A capture of VeriTest’s Content Creation Winstone 2001 suite. Applications include Adobe Photoshop v5.5, Adobe Premiere v5.1, Macromedia Director v8.0, Macromedia Dreamweaver v3.0, Netscape Navigator v4.73, and Sonic Foundry Sound Forge v4.5. Unlike typical productivity applications, high-end audio- and video- editing programs are run in a more serial and less multitasked manner. The High-End DriveMark includes significantly more sequential transfers and write (as opposed to read) operations. |
StorageReview.com Bootup DriveMark 2002– A capture of the rather unusual Windows XP bootup process. Windows XP’s boot procedure involves significantly different access patterns and queue depths than those found in other disk accesses. This test recreates Windows XP’s bootup from the initial bootstrap load all the way to initialization and loading of the following memory-resident utilities: Dimension4 (a time synchronizer), Norton Antivirus 2002 AutoProtect, Palm Hotsync v4.0, and ICQ 2000b.
StorageReview.com Gaming DriveMark 2002– A weighted average of the disk accesses featured in five popular PC games: Lionhead’s Black & White v1.1, Valve’s Half-Life: Counterstrike v1.3, Blizzard’s Diablo 2: Lord of Destruction v1.09b, Maxis’s The Sims: House Party v1.0, and Epic’s Unreal Tournament v4.36. Games, of course, are not multitasked- all five titles were run in a serial fashion featuring approximately half an hour of play time per game.
For more information, please click here.
|
Note: Scores on top are better. |
|
|||||||||||||||||||
|
|
||||||||||||||||||
|
|
||||||||||||||||||
The beta Raptor turns in a StorageReview.com Office DriveMark 2002 of 418 I/Os per second. While such a score places it among the top ATA drives, the Raptor fails to match WD’s own Caviar WD2000JB. A top-level 10k SCSI unit such as Maxtor’s Atlas 10k IV substantially outpaces the Raptor.
Differences become more glaring in the High-End DriveMark. At just 300 I/Os per second, the Raptor places in the middle of a pack of 7200 RPM drives equipped with 2-megabyte buffers. Here the WD2000JB outscores the WD360GD by a substantial 43% margin.
The Windows XP bootup process recorded in the SR Bootup DriveMark 2002 features an unusually high average queue depth for a desktop scenario. In this test, the Raptor stretches its legs, easily besting all comparable ATA and SCSI disks.
Finally, in the SR Gaming DriveMark 2002, the Raptor delivers 531 I/Os per second, a figure comparable to a top-end ATA drive yet trailing the Atlas 10k IV by a significant margin.
To be fair, we should point out that the 36-gigabyte Raptor faces flagship drives of much greater capacity in our tests. The margins between the Raptor and smaller ATA or SCSI drives would likely not be as pronounced since the competition would then be forced to work across a greater percentage of its platter zones.
Multi-User PerformanceStorageReview uses the following tests to assess server performance: StorageReview.com File Server DriveMark 2002– A mix of synthetically-created reads and writes through IOMeter that attempts to model the heavily random access that a dedicated file server experiences. Individual tests are run under loads with 1 I/O, 4 I/Os, 16 I/Os, and 64 I/Os outstanding. The Server DriveMark is a convenient at-a-glance figure derived from the weighted average of results obtained from the four different loads. StorageReview.com Web Server DriveMark 2002– A mix of synthetically-created reads through IOMeter that attempts to model the heavily random access that a dedicated web server experiences. Individual tests are run under loads with 1 I/O, 4 I/Os, 16 I/Os, and 64 I/Os outstanding. The Server DriveMark is a convenient at-a-glance figure derived from the weighted average of results obtained from the four different loads. For more information click here. |
|
Note: Scores on top are better. |
|
|||||||||||||||||||
|
|
||||||||||||||||||
In the SCSI-stronghold of random, server-oriented performance, the Raptor, while delivering scores significantly better than traditional ATA drives, nonetheless falls behind contemporary SCSI drives by a significant margin. Even older drives such as the Seagate Cheetah 36ES (not represented; see the performance database to create custom comparisons) unquestionably trounce the WD360GD. The beta Raptor delivers the server performance that one would expect from a good 7200 RPM SCSI drive- definitely a cut above standard ATA, but not up to 10k RPM levels.
Legacy PerformanceeTesting Lab’s WinBench 99 Disk WinMark tests are benchmarks that attempt to measure desktop performance through a rather dated recording of high-level applications. Despite their age, the Disk WinMarks are somewhat of an industry standard. The following results serve only as a reference; SR does not factor them into final judgments and recommends that readers do the same. |
|
Note: Scores on top are better. |
|
|||||||||||||||||||
|
|
||||||||||||||||||
Heat and NoiseIdle Noise– The sound pressure emitted from a drive measured at a distance of 18 millimeters. The close-field measurement allows for increased resolution between drive sound pressures and eliminates interactions from outside environmental noise. Note that while the measurement is an A-weighted decibel score that weighs frequencies in proportion to human ear sensitivity, a low score does not necessarily predict whether or not a drive will exhibit a high-pitch whine that some may find intrusive. Conversely, a high score does not necessarily indicate that the drive exhibits an intrusive noise envelope. Net Drive Temperature– The highest temperature recorded from a 16-point sample of a drive’s top plate after it has been under heavy load for 80 minutes. The figures provided are net temperatures representing the difference between the measured drive temperature and ambient temperature. For more information, please click here. |
|
Note: Scores on top are better. |
|
|||||||||||||||||||
|
|
||||||||||||||||||
Objectively speaking, the beta Raptor turns in impressively low noise floors, likely due to its single-platter design. A score of 40.4 approaches the noise floor delivered by the latest Barracuda ATA drives. Subjectively speaking, however, our sample emits an irritating high-pitched squeal reminiscent of early 10k RPM SCSI disks. The whine was audible even over the testbed’s relatively loud drive cooler fans.
Seek noises land somewhere between today’s louder ATA disks and a typical reviewed SCSI unit. While the Raptor features random seeks similar to that of 10k RPM SCSI, it features just a single platter contrasted with the four typically found in today’s flagship units. The resultant actuator noise is quite unobtrusive.
The Raptor’s single-platter configuration also yields a relatively low operating drive temperature. Our measurements reached 20.6 degrees Celsius above ambient room temperature- on the high side for an ATA drive but well below the typical SCSI disk.
ReliabilityThe StorageReview.com Reliability Survey aims to amalgamate individual reader experiences with various hard disks into a comprehensive warehouse of information from which meaningful results may be extracted. A multiple-layer filter sifts through collected data, silently omitting questionable results or results from questionable participants. A proprietary analysis engine then processes the qualified dataset. SR presents results to readers through a percentile ranking system. According to filtered and analyzed data collected from participating StorageReview.com readers, the |
Note that the percentages in bold above may change as more information continues to be collected and analyzed. For more information, to input your experience with these and/or other drives, and to view comprehensive results, please visit the SR Drive Reliability Survey.
ConclusionIt’s very difficult to draw firm conclusions on a drive that is obviously far from its final state. Firms manufacture pre-release units not for performance demonstrations but rather for system-integration purposes- resellers need to qualify the unit in their systems for extended periods of time before the drive hits general availability. Many readers may be disappointed with the Raptor’s relatively lackluster desktop performance. For various reasons, enthusiasts view an increased spindle speed as the largest factor in single-user performance. The reality, however, is that desktop usage predominately consists of highly-localized patterns and is affected more by caching strategies than marginal mechanical improvements. Western Digital’s JB series may very well continue to stand as the premiere choice for those seeking the ultimate in single-user speed. |
We’re more concerned with the Raptor’s server performance. While it is definitely a step above standard 7200 RPM ATA drives, the beta Raptor trails today’s 10k RPM SCSI drives by substantial margins. If WD and SATA are to have a chance at cracking the enterprise market, the Raptor’s multi-user performance must approach the levels delivered by Cheetahs and Atlases.
Again, all figures, analyses, and conclusions have been drawn from an early pre-production sample. It is likely that the performance delivered by the final product will differ significantly from what we’ve seen today. We wish WD the best, and eagerly await the opportunity to officially put the Raptor through its paces.
