The Fujitsu MAS3735 has held the distinction as the “world’s fastest drive” for nearly two years. As a result, expectations run high for the MAS’s successor, the 147-gigabyte Fujitsu MAU3147. Join StorageReview as we examine how the MAU rates when compared to drives such as its predecessor and Seagate’s new Cheetah 15K.4.
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.
|
Like competitors Seagate, Maxtor, and Hitachi, however, Fujitsu’s climb to the next plateau of capacity and performance has been a long one. Increasingly prominent limitations in media and head technology along with the need to maintain the rock-solid reputation of enterprise-oriented SCSI offerings have stayed the hands of all players and kept drives such as the MAS and the Cheetah 15K.3 in the spotlight for an unprecedented length of time.
Last week, Seagate’s Cheetah 15K.4 met Testbed3. With its user-toggleable buffer segmentation strategy set to a static, desktop-oriented setting, the 15K.4 managed to slightly improve upon the single-user performance marks set by the last generation. However, even with segmentation settings switched to the default “server-oriented mode”, the 15K.4’s multi-user scores actually retreated from the levels obtained by the older 73-gigabyte flagships.
Fujitsu’s MAU3147 is next up to the plate. The specs of the Japanese conglomerate’s new 15,000 mainstay read identically to that of the Cheetah 15K.4- four 37-gigabyte platters to top out at 147 GB of storage, a 3.3 millisecond access time, and an eight-megabyte buffer. Fujitsu warrants the drive with standard five-year protection.
Initial shipments of the MAU3147 will include standard parallel Ultra320 and Fibre Channel interfaces. Serial Attached SCSI (SAS)’s time is almost upon us however- it is not unreasonable to expect an SAS version of the drive once controllers and other support infrastructure hit the market.
As a new-breed 15,000 RPM drive, the MAU targets the most demanding storage applications around: heavy-load file and web servers, data mining/warehousing, busy transaction servers, and other uses where best-of-breed random access performance is mandatory. In the following tests, the MAU3147 will be compared against the following drives for the following reasons:
Fujitsu MAS3735 (73 GB) | Manufacturer’s previous-generation unit |
Hitach Ultrastar 15K73 (73 GB) | Previous-generation competing unit |
Maxtor Atlas 15K (73 GB) | Previous-generation competing unit |
Seagate Cheetah 15K.4 (147 GB) | Current-generation competing unit |
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. |
|
|||||||||||
|
MAU3147NP Average Read Service Time
|
||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
The Fujitsu MAU3147 delivers an average random access time of 5.7 milliseconds. Subtracting 2 ms to account for the rotational latency of a 15,000 RPM spindle leaves a measured average seek time of 3.7 milliseconds. Fujitsu misses its mark by 0.4 ms (incidentally, by the same margin the Cheetah 15K.4 misses its own claim). An access time of 5.7 ms also places the MAU ever so slightly behind the older MAS3735.
|
Note: Scores on top are better. |
|
|||||||||||||||||||||||||
|
|
||||||||||||||||||||||||
MAU3147NP Transfer Rate
|
|||||||||||||||||||||||||
With an outer-zone transfer rate of 93.8 megabytes per second, the MAU3147 barely slides by the Cheetah to best a record set only days ago by Seagate’s drive. The MAU’s rates decay more gracefully than the Cheetah as one moves towards inner cylinders, finally bottoming at just under 64 MB/sec. Interestingly, however, the MAU’s inner-zone scores fail to beat that of its predecessor, which more or less matches the newer drive’s minimum rate.
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. |
|
|||||||||||||||||
|
|
||||||||||||||||
|
|
||||||||||||||||
At 714 I/Os per second, the Fujitsu MAU3147 finally delivers the first truly significant advance in StorageReview’s single-user cornerstone measure, the SR Office DriveMark. The MAU blows past the previously set record, held for nearly two years by Maxtor’s Atlas 15K, by a margin of 15%.
In the High-End DriveMark, Fujitsu also sets a new standard at 645 I/Os per second; the MAU improves upon the MAS’s score by 23%. Here, however, the previous top dog was Western Digital’s Raptor WD740GD (not shown- as always, readers may create their own custom comparisons with the StorageReview Drive Performance Database). The MAU’s improvement over the Raptor is a more modest yet still significant 12%.
The Bootup DriveMark provides the MAU3147’s greatest showcase for improvement where it tops its forerunner by a staggering 28% margin. Ironically, however, this test ranks among the least important of the DriveMarks, especially for an enterprise-class drive that ostensibly will find a home in systems that boast uptimes measured in months if not years.
Finally, the MAU3147 refuses to take prisoners even in the Gaming DriveMark. Fujitsu’s screamer continues its tear with a score of 909 I/Os per second, shattering the Atlas 15K’s score by 15%.
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. |
|
|||||||||||||||||||||
|
|
||||||||||||||||||||
The Fujitsu MAU3147 hits a weighted File Server average of 342 I/Os per second. While its enough to squeak past the Cheetah 15K.4 by a tiny 1% margin, the score actually falls short of the 366 I/Os per second record currently held by Fujitsu’s own MAS3735. The score also trails Maxtor’s second-place Atlas 15K.
Results are similar in the read-only Web Server average. Although it virtually matches the Atlas 15K, the MAU nonetheless falls short of the MAS3735’s record 355 I/Os per second.
These patterns mimic the gaps between Seagate’s newer 15K.4 and previous-generation Cheetah 15K.3 (not shown, see the SR Performance Database). As we did with the Cheetah, we should note that the relatively synthetic nature of IOMeter’s tests prevent it from taking capacity differences into account. The MAU3147 stores about twice as much per cylinder as the MAS3735 and thus would enjoy significantly shorter strokes were these highly random tests confined to the MAU’s first 73 gigabytes. Further, the MAU’s higher density enables a 73 GB capacity utilizing only two actuator arms and four heads rather than the four and eight respectively required by the MAS. The subsequently lighter assembly could thus seek faster and would perhaps erase some of the margin.
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. |
|
|||||||||||||||||||||||||
|
|
||||||||||||||||||||||||
Fujitsu’s incorporation of FDB motors into its 15K RPM line results in a low, unobtrusive noise floor for the MAU3147. With an objective measurement of just 46.6 dB/A, it ranks among the lowest pressures we have witnessed for a 15,000 RPM disk. The measurement bears out in subjective listening- at idle the MAU is noticeably quieter than the Cheetah 15K.4. Seek noises, on the other hand, rumble away, albeit in the admittedly satisfying manner that one comes to expect from a drive equipped with an ultra-powerful actuator.
A 15,000 RPM spindle speed, 5.7 millisecond access times, and four platters do not add up to a quiet, low-power drive. The MAU’s top plate reaches 30.7 degrees Celsius above ambient room temperature after extended heavy use. This is a drive intended for a well-cooled, well-ventilated server room rather than a cramped case with poor airflow.
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 |
According to filtered and analyzed data collected from participating StorageReview.com readers, a predecessor of the
Fujitsu MAU3147NP, the
Fujitsu MAS3735
, 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.
ConclusionNon-server scores fall within expectations- that is, they blow away anything we have seen in the past by comfortable margins. Those seeking the ultimate in desktop and workstation performance will find it (albeit at a dear cost) in the MAU3147. Multi-user scores, on the other hand, fall short of the levels set by the two-year old MAS3735, a trend we also saw when contrasting the new Cheetah 15K.4 with the older 15K.3. Perhaps this is yet another side effect of the increasingly laborious advances in areal density- despite featuring actuators just as swift as the previous generation, these 37 GB/platter drives must settle on tracks packed up top twice as close to each other while maintaining the reliability standards set by their predecessors. |
Two down, two to go. Can Maxtor or Hitachi buck the trend and deliver across-the-board performance improvements? We shall see.
