October 19th, 2005 by eugene
Western Digital Caviar RE2 WD4000YR
This "ATA specialist" of sorts, however, has been noticeably slow in migrating from the older parallel ATA standard to the new serial ATA interface. Though the firm supplied the Caviar "JD" series, these drives remained PATA designs retrofit for SATA operation via a bridged design. It is only over the summer, with the arrival of the SE16 series, that WD finally caught up to its competitors with the introduction of a drive designed from the ground up for the SATA interface. And though the Caviar WD2500KS featured a 300 MB/sec SATA interface, the drive lacked the Native Command Queuing feature found on drives such as the Seagate Barracuda and Maxtor MaXLine. Taken with the firm's relative lag in capacity and the lack of significant performance increases since the original 8 MB buffer drives, WD's once glamorous drives eventually became rather pedestrian.
Thus we turn to WD's latest entry, the Caviar RE2. The original Caviar RE (Raid Edition) was built on the firm's long-standing PATA Caviar blueprint. A tightening of manufacturing tolerances and improved error handing combined to represent WD's first foray into the nearline enterprise storage sector, one where cost per gigabyte is a metric more important than raw I/Os per second. The RE2, however, is a totally new beast. Although it features a 7200 RPM spindle speed and though it is equipped with native SATA electronics, the RE2 leverages much of its physical engineering from WD's 10,000 RPM Raptor. In fact, the RE2 borrows so much from the Raptor family that the firm seriously considered a name such as "Raptor 7200."
As a four-platter setup, however, the Caviar RE2 far outstrips the Raptor's 73 GB capacity. Four 100 GB platters combine to yield 400 GB of storage, a size that finally matches the flagships of the competition. WD specs the Caviar's average seek time at 8.9 milliseconds, a standard figure recited for some time now. The RE2's buffer conforms to the newer, roomy 16 MB standard.
The RE2's consumer-oriented counterpart, the Caviar SE16, boasts an SATA-2 style 300 MB/sec interface but lacks Native Command Queuing (NCQ). While command queuing's value is undisputed in the server world, WD argues that its inclusion in a drive hinders desktop performance... hence its omission on the SE16. At this point, the disadvantage NCQ lends to single-user operation is debatable. Seagate's Barracuda 7200.8 often performs better with queuing disabled yet Maxtor's MaXLine III demonstrates improvement across the board with queuing enabled. At any rate, as an enterprise-aimed part, the RE2 reverses situation- it incorporates NCQ but maintains a more conservative 150 MB/sec transfer rate.
WD pulls no punches when it comes to claimed reliability. Unlike competing nearline products that also feature 1 million+ hours of MTBF, the firm boasts that the Raptor-leveraged RE2 is capable of a 24x7 100% duty cycle... no "eight hours a day" stuff here. As a result, in addition to eyeing the nearline sector itself, the RE2 solidly targets the first-line entry-level server drive sector. In fact, WD touts the drive's "Time Limited Error Recovery" (TLER) ability, a feature that enables better drive-controller coordination in mutually handling drive errors (see here for more information). The drawback, however, is that the RE2 expects to operate off of a RAID controller and is as a result not recommended for use in a standard desktop system. An enterprise-class 5-year warranty backs the drive.
On paper, at least, the Caviar RE2 addresses many of the areas in which WD has come up short lately. Does it truly deliver? Let's turn to our tests and find out! The 400 GB Caviar RE2 WD4000YR will be compared against the following drives in the tests that follow:
|Hitachi Deskstar 7K400 (400 GB)||Previous-generation competing unit|
|Maxtor MaXLine III (300 GB)||Current-generation competing unit|
|Samsung SpinPoint P80 (160 GB)||Previous-generation desktop unit|
|Seagate Barracuda 7200.8 (400 GB)||Current-generation competing unit|
Access Time and Transfer Rate
For diagnostic purposes only, StorageReview measures the following low-level parameters:
Average Read Access Time- An average of 25,000 random read 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.
Average Write Access Time- An average of 25,000 random write 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. Due to differences in read and write head technology, seeks involving writes generally take more time than read accesses.
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.
The Caviar RE2 weighs in with a read access time of 13.3 milliseconds. When accounting for the average rotational latency of a 7200 RPM spindle (4.2 ms), the Caviar's measured read seek time is 9.1 milliseconds, missing the manufacturer's claim by a relatively insignificant 0.2 ms. Average writes come in at 14.2 ms, just under a millisecond higher than average reads.
Equipped with 100 GB platters, the RE2's outer-zone transfer rates hit 64.7 MB/sec, placing it in the middle of today's pack. As we move inwards, however, sustained rates decay relatively gracefully and bottom out at a very respectable 40.8 MB/sec. For a closer look at the drive's transfer rates, click here.
It is important to remember that seek time and transfer rate measurements are mostly diagnostic in nature and not really measurements of "performance" per se. Assessing these two specs is quite similar to running a processor "benchmark" that confirms "yes, this processor really runs at 2.4 GHz and really does feature a 400 MHz FSB." Many additional factors combine to yield aggregate high-level hard disk performance above and beyond these two easily measured yet largely irrelevant metrics. In the end, drives, like all other PC components, should be evaluated via application-level performance. Over the next few pages, this is exactly what we will do. Read on!
StorageReview uses the following tests to assess non-server use:
StorageReview.com Office DriveMark 2006- A capture of VeriTest's Business Winstone 2004 suite. Applications include Microsoft's Office XP (Word, Excel, Access, Outlook, and Project), Internet Explorer 6.0, Symantec Antivirus 2002 and Winzip 9.0 executed in a lightly-multitasked manner.
StorageReview.com High-End DriveMark 2006- A capture of VeriTest's Multimedia Content Creation Winstone 2004 suite. Applications include Adobe Photoshop v7.01, Adobe Premiere v6.5, Macromedia Director MX v9.0, Macromedia Dreamweaver MX v6.1, Microsoft Windows Media Encoder 9.0, Newtek Lightwave 3D 7.5b, and Steinberg Wavelab 4.0f run in a lightly-multitasked manner.
For more information, please click here.
WD's latest turns in a very strong showing in StorageReview's newly-revised productivity benchmark. With a score of 826 I/Os per second when NCQ is disabled, the Caviar RE2 WD4000YR easily bests all other 7200 RPM drives and even tops the company's own 10,000 RPM Raptor (not shown, see here). Enabling NCQ slides the drive's score down to 787 I/Os per second for a net loss of about 5%. While nothing to sneeze at in an absolute sense, it is interesting to note that WD's implementation of NCQ remains more like the Seagate's Barracuda (where NCQ occasionally hurts the drive) as opposed to Maxtor's MaXLine III (where scores are usually better with NCQ enabled).
The Caviar's 621 I/Os per second (with NCQ disabled) in the new High-End DriveMark dominates the competition by a margin even larger than that of the Office DriveMark. The gap between the Caviar and next place Hitachi's Deskstar 7K400 increases to a sizable 18%. Here too, however, the enabling of NCQ on the WD4000YR causes the drive's score to fall by about 6%. The resulting 585 I/Os per second, however, is still enough to maintain a healthy lead over the competition.
Three decidedly different entertainment titles cover gaming performance in StorageReview's test suite.
FarCry, a first-person shooter, remains infamous for its lengthy map loads when switching levels.
The Sims 2, though often referred to as a "people simulator," is in its heart a strategy game and spends considerable time accessing the disk when loading houses and lots.
Finally, World of Warcraft represents the testbed's role-playing entry; it issues disk accesses when switching continents/dungeons as well as when loading new textures into RAM on the fly.
For more information, please click here.
WD's latest churns through our FarCry trace and delivers an impressive 735 I/Os per second with NCQ disabled, enough to claim the top 7200 RPM slot by a comfortable margin. Enabling NCQ causes the RE2 to slide by a fairly significant 11%, though it still retains enough speed to offer a tenacious third-place showing.
The Caviar keeps up the pace in the Sims2 test with 781 I/Os per second and again captures the top spot. With NCQ enabled, the drive once more slips just behind the second-place Hitachi Deskstar 7K400.
595 I/Os per second while playing World of Warcraft is enough for the Caviar, an "enterprise-class/nearline product", to sweep our new gaming tests. Here, though it exhibits a 9% drop in performance, WD's drive maintains a lead over the competition even with NCQ enabled.
Unlike single-user machines (whether a desktop or workstation), servers undergo highly random, non-localized access. StorageReview simulates these multi-user loads using IOMeter. The IOMeter File Server pattern balances a majority of reads and minority of writes spanning requests of varying sizes.
IOMeter also facilitates user-configurable load levels by maintaining queue levels (outstanding I/Os) of a specified depth. Our tests start with the File Server pattern with a depth of 1 and double continuously until depth reaches 128 outstanding I/Os.
Drives with any sort of command queuing abilities will always be tested with such features enabled. Unlike single-user patterns, multi-user loads always benefit when requests are reordered for more efficient retrieval.
For more information click here.
Out of the gate, with a queue depth of 1, the Caviar RE2 WD4000YR starts at the top of the heap with 79 I/Os per second. WD's implementation of NCQ scales well, peaking the Caviar at 143 I/Os per second under queue depths of 32 and greater. Regardless of load, the RE2's strong showing fends off the competition from Maxtor and Hitachi. In fact, tt's only under a load featuring 128 outstanding I/Os that the drive is matched (but not outperformed) by the legacy TCQ-equipped Deskstar 7K400.
Noise and Power Measurements
Idle Noise- The sound pressure emitted from a drive measured at a distance of 3 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 profile.
Operating Power Dissipation- The power consumed by a drive, measured both while idle and when performing fully random seeks. In the relatively closed environment of a computer case, power dissipation correlates highly with drive temperature. The greater a drive's power draw, the more significant its effect on the chassis' internal temperature.
Startup (Peak) Power Dissipation- The maximum power dissipated by a drive upon initial spin-up. This figure is relevant when a system features a large number of drives. Though most controllers feature logic that can stagger the spin-up of individual drives, peak power dissipation may nonetheless be of concern in very large arrays or in cases where a staggered start is not feasible. Generally speaking, drives hit peak power draw at different times on the 5V and 12V rails. The 12V peak usually occurs in the midst of initial spin-up. The 5V rail, however, usually hits maximum upon actuator initialization.
For more information, please click here.
Objectively speaking, the Caviar WD4000YR hits an idle sound pressure of 45.2 decibels and places at the bottom of the chart when contrasted with other drives. As often is the case, however, this single number does not tell the whole story. The drive's measured sound pressure oscillates regularly and predictably between 42 and 45.2 dB/A and indicates a steady rise and fall of sound levels at a certain frequency. Subjectively, however, we hear no such noise even in the very quiet room in which we take sound measurements. Rather, the drive's noise floor remains quite low, similar to that turned in by the Seagate Barracuda 7200.8. Seeks are very quiet. With some ambient noise present, one must concentrate to hear the drive's actuator undergoing activity.
As a four-platter design, the WD4000YR can't match the relatively lower power dissipation figures turned in by the two-disk Samsung SpinPoint P80. In absolute terms, however, the Caviar's idle draw of 8.6 watts and seek power consumption of 12.0 watts remains well the expected range and below that of, say, the three-platter Maxtor MaXLine III.
At 28.4 watts, the Caviar's peak power dissipation is on the high side when contrasted with other 7200 RPM drives. Ensure an adequate source of power and/or be certain an array of drives staggers their power-on from a cold start.
The 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 Western Digital Caviar RE2 WD4000YR is more reliable than of the other drives in the survey that meet a certain minimum floor of participation.
According to filtered and analyzed data collected from participating StorageReview.com readers, a predecessor of the Western Digital Caviar RE2 WD4000YR, the Western Digital Raptor WD740GD , is more reliable than of the other drives in the survey that meet a certain minimum floor of participation.
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.
In the end, the Caviar RE2 WD4000YR sweeps our high-level performance tests across the board. Equipped with a solid NCQ implementation, the drive's multi-user scores never falter and top the competition whether in a light, a medium, or a heavy load scenario. Combined with the drive's presumed (given the 5-year warranty, 1.2m MTBF, and Raptor-leveraged heritage) reliability, the WD4000YR emerges as today's preeminent 7200 RPM offering for server use.
With NCQ disabled, the RE2 also tops the competition in all of our new single-user benchmarks. In fact, the prowess displayed by the unit hearkens back to the glory days of the firm's original "Special Edition" Caviar and even manages to give their solid but aging 10,000 RPM Raptor a real run for its money. Despite this stellar performance, however, WD cautions against using the RE2 in a desktop system. The drive's TLER feature expects to be paired with a RAID controller. In the event of an unlikely but possible error situation, the RE2 may not make every attempt to recover when operating on a regular controller as a standard SATA drive would..
Our look at the RE2 does not end here. In the past, we have examined how WD's own Raptor and Seagate's Cheetah scale when incorporated into multi-drive arrays. In the near future we will launch StorageReview's expanded multi-drive coverage with a look at the WD4000YR's RAID performance. It is, after all, WD's first NCQ-equipped drive, a unit that squarely targets the enterprise sector, and last but not least, called the "Raid Edition." ;)