Slashdot Mirror
Review of First 10K IDE Drive
Sivar writes "StorageReview has a review of the first 10,000 RPM IDE hard drive. Despite the speed that other technologies are improving, this is the first rotational speed increase in almost six years for standard IDE drives." The review is pretty thorough, but also warns to keep in mind that the reviewed unit is only beta hardware.
They sure can- and they do. I have been playing around with a 10k RPM SATA drive from Western Digital at work this week.
About your other question- there are a lot of factors that contribute to drive performance, but rotational speed is one of the biggest.
"The defense of freedom requires the advance of freedom" - George W Bush
Well this WD drive does sport a 1.2 million hour MTBF and 5 year warantee. It's pretty much built with reliability in mind since they are targetting entry- and mid-level servers.
-Sokie
------
Where are the slash-groupies? I distinctly remember being promised slash-groupies!
Two of my friends purchased Seagate's 40GB 7200RPM Barracuda drives. In the space of eight weeks, both began sprouting bad sectors all over the place. This is totally unacceptable, especially when you consider that the standard HDD warranty is now 1 year [from 3.]
Focus on improving reliability, not increasing rotation speeds. Or just bring on those cool holographic drives - that should fix things up
Cheers,
CD
Use ISO 8601 dates [YYYY-MM-DD]
March 5, 2003 Author: Eugene Ra
Western Digital Raptor Available Capacities
Model Number
Capacity
WD360GD
36 GB
Estimated Price: $160 (36 GB)
Manufacturer Specifications
Beta unit provided by Hypermicro.com
Remember, mention StorageReview in your HyperMicro.com order and receive free UPS ground shipping!
Introduction
StorageReview.com readers have been speculating for the better part of three years on when the industry would ratchet up the spindle speed of ATA hard drives. When would it happen? Which company would start the trend? Speculation finally gave way to a real announcement on February 10th when Western Digital officially announced its Raptor Serial ATA drive.
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!
ow-Level Results
IPEAK SPT's AnalyzeDisk assesses many low-level characteristics of hard drives. Two tests, Read Service Time and Write Service Time, each respectively conduct 25,000 random single-sector reads and writes across the entire breadth of the drive. The result is perfectly equivalent to an access time test. Results come both as an average and as a graphic that plots the percentage of accesses across the amount of time they each take to complete. For more information, please click here.
Note: Scores on top are better.
Service Time Graphs (in milliseconds)
Average Read Service Time
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 7.6 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 8.0 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 8.7 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 12.9 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 13.8 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 14.8 |
|
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.
eTesting Lab's WinBench 99 v2.0 features a test that measures a drive's read sequential transfer rates across the entire drive. The benchmark reports results both in quantitative numbers as well as in a graphic that plots the transfer rate across the capacity of the drive.
Note: Scores on top are better.
Transfer Rate Graphs (in megabytes per second)
Transfer Rate - Begin
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 70.9 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 69.0 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 59.2 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 57.6 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 56.5 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 56.2 |
|
Transfer Rate - End
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 44.1 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 40.4 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 37.6 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 33.7 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 32.8 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 30.7 |
|
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.
Desktop Performance...
Formulated utilizing IPEAK SPT's WinTrace32 and RankDisk, the StorageReview.com Desktop DriveMarks exactingly reproduce pre-recorded, contemporary access patterns on tested hard drives. For more information, please click here.
Note: Scores on top are better.
Desktop Performance Graphs (in I/Os per second)
SR Office DriveMark 2002
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 503 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 450 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 431 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 418 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 418 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 391 |
|
SR High-End DriveMark 2002
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 444 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 427 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 415 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 388 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 382 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 300 |
|
SR Bootup DriveMark 2002
Western Digital Raptor WD360GD BETA (36 GB SATA) - 455 |
|
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 422 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 391 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 386 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 348 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 307 |
|
SR Gaming DriveMark 2002
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 649 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 548 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 546 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 531 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 528 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 508 |
|
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.
Server Performance...
Server Performance
The StorageReview.com Server DriveMarks consist of IOMeter trials using predefined patterns supplied by Intel across varying load depths. The reported scores represent a normalized average of results from 1 to 64 outstanding IO/s. For more information click here.
Note: Scores on top are better.
Server Performance Graphs (in I/Os per second)
SR File Server DriveMark 2002
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 271 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 258 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 177 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 131 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 129 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 116 |
|
SR Web Server DriveMark 2002
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 261 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 255 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 181 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 134 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 119 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 115 |
|
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 Performance
eTesting 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.
Note: Scores on top are better.
Legacy Performance Graphs (in megabytes per second)
ZD Business Disk WinMark 99
Western Digital Caviar WD2000JB (200 GB ATA-100) - 16.4 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 16.1 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 15.9 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 15.7 |
|
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 12.1 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 11.7 |
|
ZD High-End Disk WinMark 99
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 44.9 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 39.2 |
|
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 38.0 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 36.9 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 33.3 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 25.0 |
|
Heat and Noise...
A Fluke thermometer and an Extech Type II SPL meter respectively deliver objective operating temperature and sound pressure measurements. Note that objective noise measurements are gathered only after subjective impressions have been penned. For more information, please click here.
Note: Scores on top are better.
Heat and Noise
Idle Noise (in dB/A @ 18mm)
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 40.1 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 40.4 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 41.0 |
|
Western Digital Caviar WD2000JB (200 GB ATA-100) - 45.5 |
|
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 47.7 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 48.5 |
|
Net Drive Temperature (in degrees celsius)
Western Digital Caviar WD2000JB (200 GB ATA-100) - 19.7 |
|
Maxtor DiamondMax Plus 9 [8MB, 80GB/plat] (160 GB ATA-133) - 19.7 |
|
Western Digital Raptor WD360GD BETA (36 GB SATA) - 20.6 |
|
IBM Deskstar 180GXP 8 MB (180 GB ATA-100) - 22.1 |
|
Seagate Cheetah 10K.6 (146 GB Ultra320 SCSI) - 24.4 |
|
Maxtor Atlas 10k IV (147 GB Ultra320 SCSI) - 30.0 |
|
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.
Conclusion...
It'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.
If they can make these beauties with a serial-ATA interface, I AM SOLD!
[snip]
Speculation finally gave way to a real announcement on February 10th when Western Digital officially announced its Raptor Serial ATA drive.
[/snip]
Did I miss something, the article says its SATA.
Estimated Price: $160 (36 GB)
Manufacturer Specifications
Beta unit provided by Hypermicro.com
Remember, mention StorageReview in your HyperMicro.com order and receive free UPS ground shipping!
Tiger Direct has 36GB Ultra160 SCSI's for only $99. Anyone know if these are some type of rejects? Google did not reveal any obvious issues with this model.
Bad boys rape our young girls but Violet gives willingly.
Uhhh, my motherboard already has integreated Serial ATA. ASUS A7N8X, nForce2 based. Also does Serial-ATA raid. And the reason they say it's quiet is likely due to the fact it only has one platter (as opposed to 2 or 3 in many of the others).
IDE drives are "dumb", and require the CPU to handle much of the work.
No longer really true. Ever since UltraDMA/33 mode, the CPU has not had much work to do with an IDE drive. SCSI drives still have a few tricks such as tagged queuing, but those features have been filtering down to IDE drives as well.
SCSI drives intended for servers cost more, and generally are better made, than IDE drives. They also come with much longer warranties (makes sense since they are made better).
steveha
lf(1): it's like ls(1) but sorts filenames by extension, tersely
Yeah, but how long till it fries itself?
I'd rather have something slow that I can trust, rather than something that goes out in a brillant ball of fire--even though it was really fast.
The reviewed drive has a 5 year warranty. How long is the warranty on your slower drive?
The Seagate Cheetah X15.3 is the world's fastest hard drive (until the Maxtor Atlas 15K is released). It is one of the most reliable drives you can buy, with an extremely high rating in StorageReview.com's reliability survey, and an excellent history in IBM, Dell, etc's enterprise servers.
"Slower is more reliable" doesn't hold water anymore, though it is true that early 7200 RPM IDE drives were less reliable than the slower 5400 RPM drives.
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
This is pretty much a dupe.
/. article has a link to an actual review of the drive, not just an announcement that it happens to exist. Analog: If a story mentions that NASA has contracted for a new space vehicle, and later there is another story that covers the actual performance, mechanics, and statistics of a completed model, those two stories would be related, but not dupes.
No. It isn't a dupe. The new
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
I've never had a problem with PCI. Sure, it's becoming outdated in terms of speed, but overall PCI has served the PC industry very well.
The move from ISA to PCI as the general PC slot was a very good step forward. Gone were the hair-pulling configuration issues, jumper settings, and "ISA Plug'n'Play" that sometimes worked.
The next "PCI" for the PC will most likely be something like 3GIO, which was recently renamed to "PCI Express." It's a new bus, but it's software-compatible with PCI. Since PCI Express is a new hardware interface (new slots) it's not just for compatibility; it's because PCI works and there's no reason to change what you don't need to change.
At any rate, this topic is IDE drives. 10K SCSI drives tend to be pretty loud and run quite hot. I think that the 10k IDE drives will probably imploy some sort of technologies to keep them quiet and cooler, since IDE drives generally live on the desktop.
- It's not the Macs I hate. It's Digg users. -
Hardware also is hideously expensive when it first hits the shelves.
Of course you are correct, but this drive is expected to be priced at $160USD, which isn't really all that bad, all things considered.
As far as reliability, the WD Raptor is targeted at servers and has a 5-yr warranty. Western Digital has experience designing SCSI drives, and I suspect that the Raptor is essentially a 10,000RPM SCSI assembly with a serial ATA--instead of SCSI--interface (as well as a few other tweaks). Certainly the mechanical characteristics appear to strongly resemble common 10,000RPM SCSI drives, such as the sub-6 millisecond access times.
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
There's no margin on a $60.00 drive. It seems to be that way, since once drives hit about the $75 mark they tend to be phased out.
I find it extremely impressive that they can get that cheap at all.
MaxtorSCSI, a SCSI engineer at Maxtor (funny, that), and a forum user on StorageReview.com, stated once that hard drives are the highest precision mechanical devices, by far, in the average person's home.
The platter has to be so flat that, spinning at thousands of RPM, the heads must float above the platter at less than 1/50 the width of a human hair, or slightly more distance than the width of an average smoke particle. And they have to survive being bumped, because if those heads touch the platters, all hell (and the heads) breaks loose.
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
http://www.tomshardware.com/technews/20030210_0836 51.html
I do have some experience hotswapping drives. Linux sort of handles it. echo `scsi remove-single-device 0 0 1 0` >
echo `scsi add-single-device 0 0 1 0` >
Adam
Would you do it for some scoobie crack?
This has been brougt up numerous times in the StorageReview.com forums. There are several companies making solid-state drives, including PCI-SDRAM drives with battery backup, and FLASH drives which need no such backup.
They're great I'm sure, but the price per GB is sky high.
Take a look at the cost/GB of Compact Flash, multiply that by "server part for server budget" marketing. You get the idea.
I'd love to provide links, but I can't remember any of the manufacturer's names, and Google doesn't bring them up. You might try a quick search in SR's forums once the server recovers for "solid state" if you're interested though--I seem to remember a 4GB SCSI FLASH drive being almost within the realm of the average geek's budget.
Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
My impressions of the drive:
-It is very heavy. It surprized me how much heavier it was than the other 7200 RPM drives.
-It has what look like a built in heatsink in it's case, and I didn't notice it feeling much hotter than other drives (maybe because of the heatsink)
-It was a noisy environment, but the drive seemed almost as quiet as the other drives (again, kind of surprizing to me)
About the speed, we mostly run proprietary traffic generation programs to the drive, so I haven't really been able to use it in a real world environment yet (no Windows or games or anything). That being the case, it is hard for me to compare.
"The defense of freedom requires the advance of freedom" - George W Bush
Hey man, I don't make the news, I just report it.
Perhaps a little googling would have enlightened you as to what exactly an MTBF is. It's not quite as simple as it sounds:
(Thus spoketh the web page:)
It is generally accepted among reliability specialists (and you, therefore, must not question it) that a thing's failure rate isn't constant, but generally goes through three phases over a thing's lifetime. In the first phase the failure rate is relatively high, but decreases over time -- this is called the "infant mortality" phase (sensitive guys these reliability specialists). In the second phase the failure rate is low and essentially constant -- this is (imaginatively) called the "constant failure rate" phase. In the third phase the failure rate begins increasing again, often quite rapidly, -- this is called the "wearout" phase. The reliability specialists noticed that when plotted as a function of time the failure rate resembled a familiar bathroom appliance -- but they called it a "bathtub" curve anyway. The units of failure rate are failures per unit of "thing-time"; e.g. failures per machine-hour or failures per system-year.
What, you may ask, does all this have to do with MTBF? MTBF is the inverse of the failure rate in the constant failure rate phase. Nothing more and nothing less. The units of MTBF are (or, should be) units of "thing-time" pre failure; e.g. machine-hours per failure or system-years per failure but the "thing" part and the "per failure" part are almost always omitted to enhance the mystique and confusion and to make MTBF appear to have the units of "time" which it doesn't. We will bow to the convention of speaking of MTBF in hours or years -- but we all know what we really mean.
What does MTBF have to do with lifetime? Nothing at all! It is not at all unusual for things to have MTBF's which significantly exceed their lifetime as defined by wearout -- in fact, you know many such things. A "thirty-something" American (well within his constant failure rate phase) has a failure (death) rate of about 1.1 deaths per 1000 person-years and, therefore, has an MTBF of 900 years (of course its really 900 person-years per death). Even the best ones, however, wear out long before that.
This example points out one other important characteristic of MTBF -- it is an ensemble characteristic which applies to populations (i.e. "lots") of things; not a sample characteristic which applies to one specific thing. In the good old days when failure rates were relatively high (and, therefore, MTBF relatively low) this characteristic of MTBF was a curiosity which created lively (?) debate at conventions of reliability specialists (them) but otherwise didn't unduly bother right-thinking people (us). Things, however, have changed. For many systems of interest today the required failure rates are so low that the MTBF substantially exceeds the lifetime (obviously nature had this right a long time ago). In these cases MTBF's are not only "not necessarily" sample characteristics, but are "necessarily not" sample characteristics. In the terms of the reliability cognoscenti, failure processes are not ergodic (i.e. you can't blithely trade population statistics for time statistics). The key implication of this essential characteristic of MTBF is that it can only be determined from populations and it should only be applied to populations.
MTBF is, therefore an excellent characteristic for determining how many spare hard drives are needed to support 1000 PC's, but a poor characteristic for guiding you on when you should change your hard drive to avoid a crash.
(An excerpt from this page.)
-Sokie
------
Where are the slash-groupies? I distinctly remember being promised slash-groupies!
it's like this:
Spindle speed and areal density have a give and take relationship, faster spindle = less areal density being the data can only be reliably read so fast by a generation of drive head and disk platter technology. Improving the head and platter designs gives you higher areal density at a given spindle speed, and sometimes a higher top spindle speed, but increasing that spindle speed will quickly reduce your areal density, sometimes to the point that the spindle speed increase can actually lower your sequential read and write speeds.
more areal density generally produces:
-faster sequential reads and writes
-higher capacities
faster spindle speed generally produces:
-faster sequential reads and writes
-less rotational latency
-lower areal density = lower drive capacities
-more noise
-more heat
Of course there are excpetions to these attributes, but generally they are cause and effect.
In general your big fast 15k SCSI drives aren't always that fast in big sequential read/write tests, at least not reletive to their spindle speed, but they generally fly in random small read/write scenarios being they're generally designed for servers and most servers require that kind of data transfer and that's where the shorter rotational latency is going to really help.
matguy(.com)
10K SCSI drives tend to be pretty loud and run quite hot.
Not any more. The latest 10K SCSI drives purr like a sleeping kitten (aww...). I just bought a Ultra160 Seagate Cheetah, and I can only hear it by putting my ear up to the computer's case. The fans are way louder.
Healthcare article at Kuro5hin