For the better part of two decades, the standard for hard drive chassis has rested with the 3.5″ form factor. In an effort to integrate more spindles per cubic foot, however, industry-giant Seagate has started shifting its enterprise-oriented offerings towards a more svelte 2.5″ standard. How does the firm’s first implementation stack up? Let’s take a closer look at the Savvio 10K.1!
Note: Since the publication of this review, this drive has been retested under Testbed4, a newer hardware/software/benchmark platform. Please see this article for updated results. This review remains for reference purposes only.
|
Beforehand, the predominant metric when it came to server-class drives was the classic cost per gigabyte (a paradigm that still drives most of the desktop market). While continuous movement to electronic forms of storage fueled capacity requirements, the need to serve information to more and more users simultaneously requesting data also grew. From this environment grew a newer model, cost per I/O transaction serviced. With their faster spindle speeds and smaller-diameter platters (reduced from the standard 3.5 inches to just under 3 inches), 10,000 RPM drives such as the Cheetah quickly displaced their 7200 RPM ancestors in the modern data center.
A few more years passed; the need for speed grew. Industry research indicated that to satisfy the need for swifter random I/O, many system administrators intentionally used only a portion of their drives’ capacity in an attempt to shave even more from access times. Terabytes of space went unused. Finally, Seagate was again first to address the issue with the Cheetah X15, a drive that yet again reduced platter diameters (this time to about 2.6 inches) as well as bumping up spindle speeds to an awesome 15,000 RPM.
Today, many in the industry argue that another fundamental paradigm shift is taking place. The total cost of ownership when it comes to maintaining drive arrays includes not only the drives themselves but also supporting chassis, racks, cooling, and data center space. While firms gain improvements in random I/O performance through “short stroking” drives, they do not realize any savings when in power, space, and cooling requirements. The drive remains just as large and just as warm as when it brings its full capacity to bear. But, if applications exist that nonetheless demand short-stroking to maximize I/O speeds, why not design a drive’s casing around the smaller-sized platter? As demonstrated in the summer’s take on RAID arrays, high-depth, highly-random applications benefit from the use of multiple spindles. If one can fit more spindles into an equal amount of space, multiple gains arise.
A smaller platter, of course, yields better random access times. Multiple spindles deliver more I/Os per second. If such an array does not demand more space, power, or cooling, a net savings arises in the total cost per transaction.
Seagate’s Savvio (pronounced “sah-vee-oh,” as in “savvy I/O”) aims to address this market. Rather than focusing on cost per gigabyte or even cost per I/O, the Savvio attempts to tackle a more complex cost per transaction per cubic foot equation. The first-generation Savvio 10K.1 features a diminutive 2.5 inch chassis about the size of a deck of playing cards and nets a 70% savings in space when contrasted with a traditional low-profile, 3.5″ form factor drive. It combines a workhorse 10,000 RPM spindle speed with two platters to yield a flagship capacity of 73 gigabytes. Seagate specs the Savvio’s seek time at 4.1 milliseconds and equips the drive with a standard eight-megabyte buffer.
In addition to saving space, Seagate claims that the drive’s smaller profile and two-platter design consumes about half the power and thus generates half the heat of a traditional SCSI drive. The shorter, more rigid actuator arms permit increased reliability through reduction of unintended head-surface contact. The firm backs the drive with a five-year warranty.
The Savvio is currently available equipped with Ultra320 single-connector (80-pin) and fibre channel interfaces. It is important to note that the drive’s small size (and perhaps its target market- the server arena) precludes a desktop-friendly 68-pin Ultra320 version.
Though currently available only with 73 gigabytes of storage and only with a 10,000 RPM spindle speed, Seagate is sure enough of the 2.5″ form factor that they have already stated the upcoming 3.5″ 10K.7 will be the last of the venerable Cheetah 10K line. Does the Savvio have what it takes to fill some (literal and figurative) big shoes?
In the following tests, the 73 GB Seagate Savvio 10K.1 is compared against the following drives for the following reasons:
| Fujitsu MAP3147 (147 GB) | 3.5″ competing unit |
| Hitachi/IBM Ultrastar 146Z10 (147 GB) | 3.5″ competing unit |
| Maxtor Atlas 10K V (300 GB) | 3.5″ competing unit |
| Seagate Cheetah 10K.6 (147 GB) | Manufacturer’s 3.5″ unit |
| Western Digital Raptor WD740GD (74 GB) with TCQ enabled | Enterprise-oriented 10K RPM 3.5″ SATA drive |
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. |
|
||||||||||||||||||||
|
ST973401LC Average Read Service Time |
|||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
The smaller platters allow Seagate to shave a few extra milliseconds off of the Savvio 10K.1’s average random access time for a score of 7.3 ms, the fastest we’ve yet recorded for a 10,000 RPM drive. Subtracting 3.0 ms to account for the rotational latency of a 10K RPM spindle yields a net average seek time of 4.3 ms. Seagate claims an average seek time of 4.1 ms- the Savvio misses its mark ever so slightly.
It is important to note again that the lower seek time predominately arises from the smaller distances that the Savvio’s actuator must travel rather than from the actuator sporting more power. The other 10,000 RPM designs listed above would approach or even beat the Savvio’s score were they short-stroked down to 73 gigs. They would, however, remain just as bulky as always, relatively speaking.
|
Note: Scores on top are better. |
|
|||||||||||||||||||||||||||||||||||||||
|
|
||||||||||||||||||||||||||||||||||||||
ST973401LC Transfer Rate |
|||||||||||||||||||||||||||||||||||||||
Smaller-diameter platters translate into less linear density as less sectors can be packed into each of the outer-zone tracks. The Savvio tops out at 61.8 MB/sec, a sedate rate compared to the competition. As data moves in towards the inner tracks, however, things equalize as the Savvio bottoms at a respectable 42.3 MB/sec. Like 15K RPM units (which also feature narrow platters), the Savvio’s rates feature less net decay (that is, the difference between the maximum and minimum score) than other drives.
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. |
Seagate’s lilliputian delivers just 295 I/Os per second in the SR Office DriveMark, an abysmal score for a 10K RPM drive. In fact, all 7200 RPM drives manufactured within the last three years (save only the Maxtor DiamondMax Plus 8– not shown, but as always, readers may create custom comparisons through the SR Performance Database) handily trounce the Savvio 10K.1 in this replay of actual desktop use.
The situation does not improve with the other DriveMarks. Whether High-End, Bootup, or Gaming, the Savvio lags behind the competition by huge margins. It remains painfully obvious that the Savvio is not intended for use in non-server scenarios.
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. |
|
|||||||||||||||||||||||||||||||||||||||
|
|
||||||||||||||||||||||||||||||||||||||
Remember that even the most demanding of single-user setups features disk accesses quite different from the truly random I/O generated by server use. Hence, though the Savvio does quite poorly in a desktop or workstation setup, server performance unfolds quite differently.
It is in the SR File Server DriveMark that the Savvio 10K1 shines. At 283 I/Os per second, the Savvio bests Seagate’s own 3.5 inch Cheetah 10K.6 by a respectable 10% margin and even tops the category-leading Maxtor Atlas 10K V by 3%.
Unlike the File Server DriveMark, the SR Web Server DriveMark emphasizes reads only rather than a mix of reads and writes. Here the Savvio slips by just a bit but nonetheless remains a competitive player when contrasted with traditional 3.5″ offerings.
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. TTTTT |
|
|||||||||||||||||||||||||||||||||||||||
|
|
||||||||||||||||||||||||||||||||||||||
A combination of FDB motors, a two-platter assembly, and a diminutive form factor combine to make the Savvio 10K.1 the quietest drive we have yet measured. Objective sound pressure readings peg the Seagate at just 37.4 dB/A at a distance of 18 millimeters, even lower than the manufacturer’s own 5400 RPM U6 (not shown, see the SR Performance Database for more details). Subjective impressions concur- this is a remarkably silent drive when idle.
The lighter and smaller actuator also attenuates noise when the drive seeks. The Savvio’s noise envelope when seeking is similar to that of a 7200 RPM drive- that is to say, noticeably quieter than today’s other 10K RPM units.
Though it is undeniable that the Savvio is one of the quietest units around, it is heat generation rather than noise that remains all-important. Seagate’s key selling point of packing more spindles into less space requires a significantly lower temperature reading per spindle to ensure that cooling costs remain constant at a given volume. Here the Savvio delivers, reading just 15.8 degrees Celsius above ambient room temperature after extended heavy operation.
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.
ConclusionLast June, Seagate issued a press release in which they trumpeted the introduction of no less than eleven different products. A prevailing theme in the release is that “one size does not fit all,” that multiple products and increased product differentiation are necessary to properly address varying market segments. This remains an idea quite different than the misconception under which many still labor, that certain drives, due to their mechanics or their interface, are automatically better than others regardless of the intended application. The Savvio 10K.1 hammers home this message. It is slower than any contemporary 7200 RPM drive for non-server use. In fact, as StorageReview will soon demonstrate, today’s 5400 RPM notebook drives, sharing the same form factor as the Savvio, give the drive a run for its money. Perhaps it is fortunate that the drive does not come in a native desktop-friendly 68-pin configuration. |
Server use, on the other hand, is an entirely different story. The Savvio’s swift access time propels it to the top when it comes to multi-user disk accesses. Further, its low power consumption, heat generation, and small size indeed fulfill Seagate’s promise to pack more spindles (and thus more I/Os for multi-user scenarios) in a given amount of space. The Savvio 10K.1 is a formidable entry in the enterprise market.
Its cost, however, is staggering. Pricing the 10K.1 yields figures in the neighborhood of $850 for a 73 GB drive, more than four times that of the 73 GB Cheetah 10K.6. Certainly some savings are realized when total cost of ownership is factored in; still, we hope the cost of entry for the Cheetah 10K’s ordained successor will become less severe as time passes.
Addendum 11/9/04: Though older Seagate offerings such as the Cheetah 10K.6 and Cheetah 15K.3 demonstrate small differences as best, the Savvio 10K.1 (as well as the Cheetah 10K.7 and Cheetah 15K.4) delivers substantial differences when SCSI page mode settings related to buffer segmentation are toggled between desktop-oriented and server-oriented settings. Briefly, the Savvio delivers considerable gains in single-user performance while regressing a bit under multi-user loads when segmentation strategies change. Because the Savvio is firmly marketed towards the enterprise server market, the figures in this article represent the performance one may expect from the drive “out of box,” that is, oriented towards multi-user applications. Readers may nonetheless examine the difference through the SR Performance Database. A full look at the segmentation options provided by the firm’s SeaTools Enterprise utility will follow in the future.
