Western Digital Working On a 20,000 RPM Drive

MrKaos writes "Western Digital seems to be preparing for the onslaught of solid-state drives set to impact its market by developing a 20,000 rpm hard drive. Similar to the VelociRaptor line of drives, the new drives are speculated to be offering lower capacity as a tradeoff for faster seek and write times." This report out of Taipei is the only word on the rumored WD 20K drive. It's said to be a 2.5" drive in a 3.5" enclosure, for efficiency of cooling — the arrangement the Register enjoyed poking fun at when the 10K drive was upgraded last month.

Comments

They should work on a 20,001 RPM drive

[Anonymous Coward]

The equivalent of going to 11

Re:They should work on a 20,001 RPM drive

[MostAwesomeDude]

20001: A Speed Odyssey.

Sorry, couldn't resist.

Re:They should work on a 20,001 RPM drive

[dave420]

Or redefine what M is in RPM. Or R. Or P, come to think about it. :)

Re:They should work on a 20,001 RPM drive

[Anonymous Coward]

Revolutions Per Minute.

Re:They should work on a 20,001 RPM drive

[xlcus]

Revolutions Per Month!

Re:They should work on a 20,001 RPM drive

[hostyle]

Relatives (in charge) Per Marriage

Re:They should work on a 20,001 RPM drive

[pxlmusic]

glad you appreciate good humor.

Seagate responds

[Leuf]

We've taken the next step by mounting our 15,000 rpm drives in an external enclosure which then spins the drive at a further 10,000 rpms, for a total system speed of 25,000 rpms. Initial benchmarks are very promising!

Re:Seagate responds

[sunami]

We've taken the next step by mounting our 15,000 rpm drives in an external enclosure which then spins the drive at a further 10,000 rpms, for a total system speed of 25,000 rpms. Initial benchmarks are very promising!
Pretty sure this is a general relativity question, so it would be less than 25,000. Come on get your science right.

Re:Seagate responds

[Anonymous Coward]

They would be foolish to say that, as everyone knows that when you spin a platform on which someone else is spinning, the RPMs are not the sum of the two due to the Theory of Relativity.

Re:Seagate responds

[Firehed]

Before now, nobody understood why I have all of my computers sitting on top of turntables. Now I'll just point them to your post, since they couldn't fathom what I meant when I said it makes it run faster.

I had also tried mounting them in a paint can shaker to get at least another 15Hz out of the CPU, but I couldn't stand the noise.

Re:Seagate responds

[Anonymous Coward]

Actually it would be 15,000 times 10,000. Come on get your pedantry right.

Re:Seagate responds

[Fastball]

When you play games do the bad guys sound like chipmunks?

Re:Seagate responds

[EdIII]

Come on get your science right.

You don't get +5 Funny for "getting your science right".

Re:Seagate responds

[Anonymous Coward]

Actually, it wouldn't.

Relative velocities are additive. Even angular ones

Re:Seagate responds

[davester666]

I find putting my computers on a treadmill makes them run even faster than on a turntable. As a bonus, treadmills are much sturdier than turntables, so they last much longer before they need repair.

I also have stopped getting dizzy trying to look at the pulsing light on my MacBook Pro to see if it's sleeping or not since switching to a treadmill.

Re:Seagate responds

[Anonymous Coward]

The trouble with turntables is the wires get all tangled. The trick is to snip them all and solder wifi antennas on all the ends. No more tangle. Be careful with the power cable, it HURTS but it's worth it.

Re:Seagate responds

[Enderandrew]

http://funroll-loops.info/

Paint flames on it, install Gentoo, and use --omg-optimized

Re:Seagate responds

[Squalish]

That's an urban myth. Laptops can't run faster than a treadmill - they take off.

Re:Seagate responds

[Anonymous Coward]

You, sir, are an idiot.

Re:Seagate responds

[Anonymous Coward]

I noticed that you failed to offer the correct answer. It looks like you're the idiot.

Re:Seagate responds

[Swiper]

Thank goodness they introduced that wireless thingammybob. Before that we would rotate clockwise one day and anti-clockwise the next. That made a real mess of the databases

Re:Seagate responds

[repka]

Wouldn't angular velocity stay the same but radius/circumference shrink? Any relativity geeks around to clear this up?

immovable object?

[seeker_1us]

I wonder if these really fast hard disks will have to be kept stationary. More specifically: I wonder if conservation of angular momentum (manifested, for example, in gyroscopic precession) becomes a real issue if any torques were put on a spinning disk.

Re:immovable object?

[Anonymous Coward]

Considering that these are top o' the line enterprise drives for servers, I don't think the stationary requirement would be a detriment to its usage. Management frowns on horseplay near the hardware. Were not allowed to duplicate the nerf basketball court that google has set up in their cages.

Re:immovable object?

[pushing-robot]

Yes, well, giant fighting robots need enterprise-grade hardware too.

Re:immovable object?

[TechForensics]

The smaller diameter / mass will tend to reduce bad effects from conservation of angular momentum.

Re:immovable object?

[Z00L00K]

Even though they are intended to be used in server hardware where they are going to be kept stationary you will also be able to find users that are going to use them in their home computers or in servers that are on the move.

This means that the gyro effects are worth to consider. Also considering my experience from WD disks I'm not sure that I would want to use them for anything reliable.

For a solution where speed is important but the data itself can be re-created or of less critical value they can be OK.

Re:immovable object?

[Anonymous Coward]

What is your experience with WD disks? What kind of disks? What kind of problems?

From my experience in the embedded market, normal off the shelf consumer grade disks do fail more often when not properly secured to the chassis. I really can't imagine someone crazy enough to put it in a notebook. Hint Faster you spin the disk=> more energy used=> shorter battery life. If you do, you can't really blame WD for the failure.

Re:immovable object?

[Phat_Tony]

Does anyone here know what a 2.5" hard disk actually weighs, so we can calculate the angular momentum? For example if we spin it at 20,000 RPM and a bearing seizes, will shattered fragments of disk penetrate the walls of the drive, the case of the computer, and the side of my head?

Re:immovable object?

[audunr]

Once you hit 20K RPM, the platters stay put while the universe is spinning.

Re:immovable object?

[kcbanner]

I've unplugged standard hdd's while their still spinning and you can observe quite readily the gyroscopic effects. You can also observe a grinding sound.

Re:immovable object?

[lsatenstein]

I concur with the gyroscopic effects. In the end, it is not a platter solution, I think that a short term solution is a design of a miniature drum, with multiple movable heads covering short areas of drum surface. SSD is here, and the spinning drive will only become a backing store until pluggable SSD drives appear on the market. I believe that within 5 years, affordable 1 terrabyte SSD drives will be affordable.

Re:immovable object?

[geekgirlandrea]

Well, one would rather expect them to be firmly secured to a server sufficiently heavy to hold them in place.

On the other hand, if they aren't they might do interesting things. Ever try holding even a 5,400 RPM drive in your hand while it's running? I've managed to flip one across the room, courtesy of a loose power cable and forgetting the precession and trying to rotate it too fast.

Don't go into the bathroom!

[Anonymous Coward]

The last person forgot to flush! Now the toilet is full of Ubuntu!

Re:Don't go into the bathroom!

[Anonymous Coward]

I went and some water splashed up onto my debian. Eww! And it looked like somebody was stroking their redhat and gentood all over the seat. Gross!

Solid State

[c0d3r]

I'm wondering why they are still going in this direction, as hard drives are the slowest part of a computer. Why hasn't a solid state / flash ram approach taken over? Is it feasible to have a hybrid solid state/mechanical solution?

Re:Solid State

[jay-be-em]

Economics.

Re:Solid State

[c0d3r]

Apparently http://en.wikipedia.org/wiki/Solid-state_drive answers my questions:

Price - as of mid-2008, flash memory prices are still considerably more costly per gigabyte than are comparable conventional hard drives: around USD 3.50 per GB[10] compared to typically less than USD 0.40 for mechanical drives.[11]

Capacity - although currently far lower than that of conventional hard drives, SSD capacity is predicted to increase rapidly, with experimental drives of up to 1 TB in test.[12][13]

Higher vulnerability to certain types of effects, including abrupt power loss (especially DRAM based SSDs), magnetic fields and electric/static charges, in comparison to normal HDDs (which store the data inside a Faraday cage).

Limited write cycles - flash-memory cells will often wear out after 10,000-100,000 write cycles[citation needed], while high endurance cells may have an endurance of 1-5 million write cycles (many log files, file allocation tables, and other commonly used parts of the file system exceed this over the lifetime of a computer.[14] Special file systems or firmware designs can mitigate this problem by spreading writes over the entire device (so-called wear levelling), rather than rewriting files in place.[15] Today's drives can last up to 20 years with average usage.[dubious - discuss] An example for the lifetime of SSD is explained in detail in this wiki.[dubious - discuss] SSDs based on DRAM, however, do not suffer from this problem.

Slower write speeds - as erase blocks on flash-based SSDs generally are quite large, they are far slower than conventional disks for random writes and therefore vulnerable to write fragmentation,[16] and in some cases for sequential writes.[6] SSDs based on DRAM do not suffer from this problem.
Lower storage density - hard disks can store more data per unit volume than DRAM or flash SSDs, except for very low capacity/small devices.

Higher power consumption at idle or under low workloads laptop battery runtimes decrease when using an SSD over a 7200 RPM 2.5" laptop hard drive,[17] flash drives also take more power per gigabyte.
RAM based SSD require more power than hard disks, both operating and when turned off.[18]

Re:Solid State

[Anonymous Coward]

Reaganomics!

Re:Solid State

[rootofevil]

that bit about power consumption was partially recanted by Toms.

apparently they didnt do their homework well enough.

color me surprised.

not to mention the article basically says that current drives have almost no power saving features and performance was on par to resulting in slightly more consumption, whereas platter drives have had decades to develop power saving features.

i expect this 'result' to be completely wrong in the next couple product cycles. the intel 'mass market' drives already advertise significant power saving potential and are the first consumer component offered.

Re:Solid State

[omfgnosis]

It seems the long-term answer would be DRAM-based, with a battery to help mitigate corruption on power loss. Obviously older DRAM technology hasn't gone down in price/GB, but presumably that's due in part to production going down. I'd love a boot disk using old 100 MHz DRAM chips, if it could be made dependable and as affordable as flash drives.

Re:Solid State

[Anonymatt]

Robonomics!

Re:Solid State

[NerveGas]

Because so far, while some solid-state drives have very low latency, they have not yet been able to match the combination of bandwidth, capacity, and cost of a moving platter.

Re:Solid State

[uglyduckling]

Did you mean something like this?

Re:Solid State

[omfgnosis]

Well, okay but, eventually there needs to be a solution to turning it off without losing storage.

Re:Solid State

[eelke_klein]

Maybe because western digital is a harddrive manufacturer, not a flash memory manufacturer. They do not have the know how to make flash chips they could buy them but it would be hard to compete against the manufacturers that bake their own flash memory.

Re:Solid State

[Enderandrew]

http://en.wikipedia.org/wiki/Memristor

Re:Solid State

[ichigo 2.0]

Higher vulnerability to certain types of effects, including abrupt power loss (especially DRAM based SSDs)

That sounds odd. DRAM based SSDs are certainly vulnerable to that, but I would have thought that flash-based SSDs are almost completely immune to power loss (they need power to operate of course). HDDs, on the other hand are at risk of mechanical damage and/or failure from abrupt power loss.

Re:Solid State

[maynard]

If you want to go RAMDISK, you're better off buying an 8 or 16 DIMM slot motherboard and installing 32GB or 64GB of physical RAM on the host itself. The the main system bus is far faster than pcie. Use LVM to snapshot and then backup your RAMdisks to physical disk at regular intervals. Put /usr, your SQL DBs, and any other dynamic data in RAM and enjoy just silly performance. Works great in combination with Xen.

And don't forget your dual redundant power supplies and a good working UPS.

Re:Solid State

[grumbel]

Give it time, not to long ago flash was quite expensive and also rather slow and small on storage, its only recently that it has come into an area where it is really interesting has a harddrive replacement, it might take some more time till the price is down enough that it is actually interesting for the masses. I don't expect the spinning drives to disappears anytime soon, since they have still quite a leap in terms of storage, but a dual solution with solid state for the OS and a spinning one for the movies and stuff seems to be within reach.

Re:Solid State

[kcbanner]

Idiotics.

Re:Solid State

[hardwarefreak]

I'm wondering why they are still going in this direction, as hard drives are the slowest part of a computer. Why hasn't a solid state / flash ram approach taken over? Is it feasible to have a hybrid solid state/mechanical solution?

Yes. There are already a couple such hybrid products on the market, though I can't recall the manufacturers.

Re:Solid State

[Swiper]

Actually.....the slowest part is the idiot sitting in front of it looking for the Any Key

Is there a point to this?

[Ostsol]

Is there still really a point to huge RPMs? As data density increases, speed should increase naturally. Move over the same distance at the same speed on a drive with twice the density should mean that one has read twice the data in the same amount of time -- therefore reading speed is twice as fast, right? This should even work on low-capacity drives by simply using small, high-data-density disks.

Re:Is there a point to this?

[hedwards]

No, not right, that's assuming that the writes are being done sequentially. Hard disks are random access devices, and while they can definitely do sequential reads and writes, and quite a bit faster, as soon as the files are not next to each other or are fragmented you're going to lose that advantage.

Re:Is there a point to this?

[Jeff DeMaagd]

The higher speed drives aren't so much for their sequential transfer rates by themselves, but their random seek rates. They are trying to get high I/O per second rates (IOPS), which is what a lot of servers need to be at their peak.

Re:Is there a point to this?

[Anonymous Coward]

Ignorance is bliss is it not?

Re:Is there a point to this?

[Anonymous Coward]

No matter how dense the data is, random access speeds are dominated by how long it takes to move the head to the data and how long it takes to wait for the data to rotate under the head. A smaller platter will mean it takes less time to move the head on average, but the only way to get the data under the head faster is to increase rotational speed.

A 7200 rpm drive has an average 8.3ms rotational latency; a 15k rpm drive is 4ms, and a 20k rpm drive is 3ms. In other words, this speed increase could enable the drive to do 10% more random I/Os per second.

dom

Re:Is there a point to this?

[gardyloo]

In other words, this speed increase could enable the drive to do 10% more random I/Os per second.

We at the NSA are interested in things which are more random, and would like to subscribe to your newsletter.

Re:Is there a point to this?

[Detritus]

You can't just wave a magic wand and double the density. Many of these things are interrelated in a complex manner. Increased density requires new head designs, new and improved electronics, new coatings for the platters, etc.

Re:Is there a point to this?

[uncqual]

Two Words - Rotational Latency (For random IO of course)

Re:Is there a point to this?

[Trogre]

Yes. Increasing your bit density to the nth power does nothing for your access times.

Re:Is there a point to this?

[Anonymous Coward]

And those seek times will be absolutely smashed into tiny pieces by the seek times of a solid state drive, which are now in the same broad price bracket as the Raptors for MLC, and will be rapidly approaching it by the end of the year for SLC.

Spend $250 on a new Raptor and get 1.4x the performance from your database server, or spend $250 on a new SSD and get 25x the performance? Oh, that's a tough call. Let me think about it.

I don't think there's any point to these anymore. They're going to be superseded before they come out; they should start focusing on higher-storage solutions that, at the moment, Flash drives can't fulfil.

Re:Is there a point to this?

[Anonymous Coward]

The higher speed drives aren't so much for their sequential transfer rates by themselves, but their random seek rates.

The secret goal is to use the drive as a flywheel, and power a laptop.

Re:Is there a point to this?

[Anonymous Coward]

i'm sad because i don't know if that's true or not

Re:Is there a point to this?

[FromFrom]

Those are the maximum rotational latencies, not average. On average you will wait half a rotation and thus making the average rotational latency of a 15K rpm drive 2 ms.

Re:Is there a point to this?

[MtViewGuy]

I think 20,000 RPM is ridiculous overkill for a desktop computer hard drive, especially with today's Serial ATA-300 interface. Wouldn't it be better with just a modest speed increase (from 7200 to 10,000 RPM) combined with a 32 MB on-drive memory cache and faster head seaks, which makes it much easier to keep down power consumption, heat generation and noise?

Re:Is there a point to this?

[GuidoW]

Theoretically, yes.

But just compare the average seek times of a normal drive from ten years ago with that of a normal disk now. If I recall correctly, ten years ago, average seek times for IDE drives were in the range from 10 to 12 milliseconds or about 5 ms for the expensive SCSI drives, while today it ranges from 8 to 10 ms or around 4 ms for SCSI drives. There is some improvement, sure, but it's nowhere near dramatic as the increases in storage capacity or data throughput.

Re:Is there a point to this?

[Anonymous Coward]

Increasing the linear density increases transfer rate and capacity. Increasing the number of tracks increases the capacity. Increasing the RPMs reduces rotational delay. Increasing the power of the coil reduces seek time.

Re:Is there a point to this?

[MeepMeep]

The problem is that going from 15k drives to 20k drives means going from roughly 150 IOPS to 200 IOPS.

That's it.

SSDs are getting 20,000 IOPS, and some specialized SSD and RAM systems like FusionIO and Violin memory are getting 120,000 to 1,000,000 IOPS (these are not typos)

Sure, SSDs are expensive but spinning disks are beginning to look more and more like an evolutionary dead end, at least for IOPS.

Re:Is there a point to this?

[skelly33]

To your point, something I've long wondered is why there seems to have been little to no interest to date in an array of heads per surface. Sweeping a single head across the entire surface surely takes twice as long as moving two heads half the distance. They could even share the same actuator by covering different, possibly partially overlapping, sections of disk area.

How about a ladder structure with 8 heads that translate 1/8th the platter width instead of the whole thing? How about using opposing sides of the available disk surface instead of just one pie slice in the corner? I'm sure that some relatively minor adjustments could be made mechanically to achieve such a thing and that it would come down to load-splitting electronics which they already have a start on with the ability to split between platters.

It just seems to me that a head aptly placed 180 degrees away is equivalent to 100% RPM increase performance-wise and probably lower power requirement.

Re:Is there a point to this?

[thsths]

> Two Words - Rotational Latency

True, but why don't they use two read heads, one on each side of the drive? That seems a lot easier than going into rocket science material with 25000rpm. After all, at that speed centrifugal forces are over 5 times of the value at 10000 rpm.

Re:Is there a point to this?

[dgatwood]

Good catch. Mod parent up. All of the GP post's numbers are too high by a factor of two.

Re:Is there a point to this?

[Anonymous Coward]

Well, that's what you get using NTFS. If it didn't eventually become slow as fuck you wouldn't be buying a new computer every couple of years.

(I wouldn't be nagging if you had brought the issue using databases as an example but files are supposed to be contiguous.)

Re:Is there a point to this?

[dgatwood]

Well, as I understand it, there is some experimentation with that in the labs, but mostly at a microscopic level with a fixed substrate instead of a spinning disc.

I suspect the main reason not to do that is the complexity of doing thermal calibration for several times as many heads. Add to that the increased risk of head crashes because there are more of them to crash, then add the extra risk of head failure because there are more of them to fail, and you have a recipe for disaster. Oh, and there's also the extra space needed for the extra head arms. Not sure how much of a constraint that is.

That said, rotational latency is just a small part of total HD performance (on average), so a lot of it may be simply a reluctance to add lots of extra hardware to improve things by such a relatively small amount....

Add heads?

[macemoneta]

It seems strange to continuously up the rotation speed, adding noise, vibration, heat and shortening the life of the drive. Why not just add another set of heads on the opposite side of the drive? You get many of the same benefits - increased sustained transfer rate, but also reduce the seek and latency. To maintain the form factor, reduce the size of the platters (use 2.5" drive platters in a 3.5" drive).

Re:Add heads?

[vikstar]

Good idea. I for one would prefer to go solid state.

Re:Add heads?

[BronsCon]

I had this same idea, actually, only I thought to have 4 sets of heads, rather than just two.

I also thought of arranging what would essentially be two 2.5" disks in a 3.5" enclosure. These could either act as a stripe for faster, higher capacity data storage, or as mirrors of each other, providing redundancy at the cost of speed and capacity. If the drives in your RAID stripe are mirroring themselves, you needn't worry about mirroring your RAID stripe, no?

Re:Add heads?

[Gazzonyx]

Well, that would add to the number of components that could fail, and require a high speed bus between the two controllers, as well as a shared cache and all the headaches that would bring with it (think SMP caches being ping-ponged). Then you've got to sync your interface to the system bus as well as the new internal buses. On the other hand, you can just crank the knob up to 11 and go 20K RPMs on known, tried and true, technology.

Re:Add heads?

[ka9dgx]

I'd go even further... use the old 5 1/4 "half height" form factor, stack 8 platters in it, with 4 sets of heads, spin it at 5400 rpm to keep the power requirements down to reasonable.
This would give you 8 platters * 2 sides * 400 Gbit/in^2 * 50 in^2 (estimated working area surface area per platter) ==> 40 Terabytes in a single package, with an average access time on the order of 5 millisecond, and a sustainable transfer rate of at least 300 Megabytes/Second.
Even without the 4 sets of heads, that would still be a 40 Terabyte drive!

As far as RAID goes, it's just one drive, it's all or nothing, so don't think it would count as it's own mirror.

--Mike--

Re:Add heads?

[Detritus]

CDC's hard drive division did this years ago. They were later acquired by Seagate. The drives were too expensive for the improvements in performance and were discontinued. It isn't only a set of heads, it's another positioner assembly and a large amount of duplicated electronics. That's more power, heat, PCB space.

Re:Add heads?

[frieko]

Modern hard drives can only read from one head at a time. The tracks are packed in such that thanks to uneven thermal expansion, only one track will be lined up under a head at any given time. But two sets of heads might work as gp suggested.

Re:Add heads?

[ka9dgx]

Each set of heads would have its own servo, so the small variations in distance due to expansion of the case wouldn't matter. I agree that reading from one head at a time is a limitation that has to be lived with, and always will be.

Re:Add heads?

[YesIAmAScript]

Connor actually did this right around the time 3.5" drives started.

http://en.wikipedia.org/wiki/Conner_Peripherals#Performance_issues_and_the_.22Chinook.22_dual-actuator_drive

It could read from either set of heads, but I believe could only write from one set. Writes can be posted in a write-behind buffer, so this didn't impact performance.

Re:Add heads?

[ndevice]

It's been done before, iirc, but they tend to be more expensive, and the multiple heads run the risk of creating unintended harmonics. Most of the time it would be cheaper and faster to use two drives with one set of heads, than one drive with two sets of heads.

Re:Add heads?

[distantbody]

Even better: how about a strip of heads from a platters center to its perimeter (i.e. radius) --no moving read head! Taking into account that the density of the read heads would be insufficient for the number of tracks, simply stager the heads (my diagram). Surely this is feasible?!

--
C:\WINDOWS\system32\lusrmgr.exe

Re:Add heads?

[FromFrom]

I believe a modern hard disk has many many tracks (10000?). I guess it would be very expensive to make that many heads.

Re:Add heads?

[Shivetya]

Access speed to what your looking for is where many make up for time. The problem with many heads is similar to many drives per controller. You end up over running the controller, bus, etc, with volume.

Our file system (db2) is usually under the load of hundreds of SQL statements being processed at any second, selected columns and linked tables. The data isn't large, just a lot of it from a lot of different files. Plus IBM likes to abuse high speed drives with scatter loaded data... something is always bound to be under a head. It isn't the size of the data that slows us, just the volume of individual bits of it

Re:Add heads?

[ka9dgx]

Even if you could do the electronics to read/write them, the track density of modern drives would mean that any thermal variation would put at least some of the heads out of alignment.

The other problem is that modern drives require a "flying head" arraignment, which wouldn't work because the airflow around the platters would be turbulent and chaotic as all hell, not to mention the power requirements because of all the drag caused by all of those heads that close to the platter at that speed.

Re:Add heads?

[Muad'Dave]

Back in the old days, I remember a 5 MB (yes, megabyte) head-per-track drive. It literally had an arm that went from the center all the way across the platter to the edge, and had a bazillion heads mounted on it. It didn't move; the data came to it - all 5 MB. It used a platter that must've been 14 inches in diameter.

another possible use...

[i_liek_turtles]

Could I possibly use it as a meiter saw?

I always thought...

[distantbody]

...wouldn't it be possible to multiply a hdds thoughput by adding multiple heads per platter? Actually come to think of it are all platters read/write in a RAID0 fashion?

Re:I always thought...

[Detritus]

No. Track densities are far too high for that to work. Each active head needs an independent servo channel and positioner. On a standard drive, only one head is active at a time.

With modern drives, you have to discard the model of the drive as a perfectly rigid and dimensionally stable mechanical device. Keeping a head positioned over a track is like driving a car at very high speed down a road that is constantly and unpredictably curving in one direction or another.

Re:I always thought...

[TapeCutter]

"Keeping a head positioned over a track is like driving a car at very high speed down a road that is constantly and unpredictably curving in one direction or another."

Except the car is a jumbo traveling at cruising speed, 6" above the road.

Western Digital? Oh good!

[ThatsNotFunny]

Now it can lose my data twice as fast the last one I bought.

Re:Western Digital? Oh good!

[Gazzonyx]

Yeah, it's the last time I'm going to buy one of those things... until the next sale... or if I need to pick one up at Wal*Mart at 3AM. I've been saying that for three years now. Somehow my drives die just in time for the newest WD's to be on sale.

Re:Western Digital? Oh good!

[bigstrat2003]

Bad luck? I've never had a problem with WD, I swear by 'em. One of us is having unusual luck, and I'd prefer to think it's you. ;)

Maxtor, on the other hand... I lost count of how damned many Maxtor drives I've seen die. Single most failure-prone drive manufacturer I've come across. Everyone else, I see a dead drive here and there, nothing serious, but Maxtor is obscene.

Re:Western Digital? Oh good!

[Nigel Stepp]

One of us is having unusual luck, and I'd prefer to think it's you. ;)

Sorry, it's you. :) Except for some IBM/Hitachi Travelstor laptop drives, I think every HD I've had that went bad was a WD.

In my experience, Maxtor is better since they were acquired by Seagate.

Re:Western Digital? Oh good!

[Deliveranc3]

WD is pretty good, Seagate has also been kind to me (Kind enough I ran my OS off a Raid0 for 5 years o_0).

But Fujitsu, those drives are CRAP, and they end up in laptops :(

Re:Western Digital? Oh good!

[Gazzonyx]

Actually, I run my Linux desktop on RAID0 Raptors. As far as WD goes, my numbers are skewed from an obscure bug they had in their firmware on their **KS drives. I've got 4 AAKS' in my storage box at home, and 3 RE2 Y(D?)KS' on a rack at work.

I've found that in reality the sheer number of WDs that I've got in boxes at any given moment. Their Raptors are in an entirely different league than their large capacity drives, though. I've got three of those (2 150 GB, and a 75GB) in boxes without a single hitch.

IMHO, WDs drives are just at the right price/performance/failure rate ratio. They're not as solid as Seagate, but they also cost less per GB. Then there's Maxtor. I've seen 2 of those things go under this year. Which is remarkable when you consider that that covers 2/3 that were being used. Avoid Maxtor like the plague. Finally, nothing is holding a candle to my old 5.25" Quantum Bigfoot 20GB drive that's been running for nearly ten years now.

Re:Western Digital? Oh good!

[Anonymous Coward]

Bad luck? I've never had a problem with WD, I swear by 'em. One of us is having unusual luck, and I'd prefer to think it's you. ;)

Maxtor, on the other hand... I lost count of how damned many Maxtor drives I've seen die. Single most failure-prone drive manufacturer I've come across. Everyone else, I see a dead drive here and there, nothing serious, but Maxtor is obscene.

Exactly my experience as well, WD Caviar is the best (Quantum a close second) Maxtor is dead last. I have come across more than one person with this rumour of bad WD hard drives, I have never seen it myself. Perhaps it is a regional shipping issue?

Re:Western Digital? Oh good!

[Dirtside]

See, and I've never had a problem with any Maxtor drive I've owned[1]. It seems that one person's experience is not enough to draw statistical conclusions from.

Or, as someone on Slashdot's sig says: "Data" is not the plural of "anecdote".

[1] Actually I've never had trouble with a substantial portion of any manufacturer's hard drives. I've had IBM, Seagate, WD, and Maxtor drives (and maybe some others), and to the best of my knowledge, none of them ever went bad in less than a year, and I didn't have any manufacturer's drives go back more than once.

Re:Western Digital? Oh good!

[Zemplar]

Bad luck? I've never had a problem with WD, I swear by 'em.

Odd, every WD drive I've ever had I swear at 'em.

Re:Western Digital? Oh good!

[Anonymous Coward]

Agreed: I have Western Digital "Caviars" of 212mb-242mb size here, from around 1991-1993, still "up & running" just fine (when I use them nowadays that is, on an OLD 486 Dx/4 133mhz CPU based rig I keep around that runs Windows NT 3.51 SP#6 plus hotfixes...

(Hardware-wise, that has 32mb Fast Page 30 pin RAM, Diamond SpeedStar64 VLB "windows accelerator" 4mb video, + even a TekRam VLB 16mb RAM bearing Caching Controller - was a "killer machine" for its day))

Those OLD WD's STILL RUNNING? Hey... that speaks worlds of WD disks' reliability in & of itself...

NOW, as to their "RAPTOR" family of disks?? Well, the same!

I.E./E.G>-> I've got every model of those since they came out, from 2003 onwards (36gb sized one I've owned since early 2003), to the later 74gb unit (circa late 2004 iirc), & right up to their "Raptor X" series (150gb size, w/ see thru top window on disk itself, that I purchased & use daily since early 2006)...

Each/All "RAPTORS" here, from every generation of them, has been running perfectly since 2003, 2004, & 2006 respectively here (& living up to their 5 yr. "Enterprise Class" warranty, not that I've ever had to use it that is).

* WD = GOOD STUFF!

APK

I for one...

[saleenS281]

welcome our 20k overlords...

We at Gnome Rotary Disks have a better solution

[iminplaya]

The disk is stationary and we spin the case for better cooling.

Re:We at Gnome Rotary Disks have a better solution

[rubycodez]

and we at Underwear Gnomery Disks have an even far superior solution to that, putting read/write heads at each bit position on the platter. that way, the disk doesn't even have to spin. And then the disk could even be square or shaped like b00b135. Naysayers pointed out we had reinvented 1950s magnetic core storage, but we won't be waylaid on our trek to profit!!

More Parallelism

[Doc Ruby]

the new drives are speculated to be offering lower capacity as a tradeoff for faster seek and write times

How about if they make drives with very thin platters, but stack them up into individually addressable bit slices of the bytes they store? Then the time to read a single bit from the rotating media could read an entire byte, reassembled in the logic.

Or if the platters can't be that thin, how about sacrificing some storage capacity for say 2x2 platters, which could give 4x parallelism.

That parallel access might stave off competition from solid state drives for a couple extra years.

Re:More Parallelism

[TubeSteak]

How about if they make drives with very thin platters,

http://www.theonion.com/content/node/33930

Make the blades so thin they're invisible. Put some on the handle. I don't care if they have to cram the fifth blade in perpendicular to the other four, just do it!

I was going to do a full rewrite of the article, but you can do it yourself by mentally substituting "hard drive" or "platter" for "blade," "razor," or "shave"

Re:More Parallelism

[Anonymous Coward]

Even better!

Store the 1's on one platter. And the 0's on another platter!

And heck. zero is nothing. so don't even store that! Only write the 1's! half the space!

Re:More Parallelism

[ndevice]

As pointed out in a previous comment, it's difficult to precisely address parallel tracks on different platters because of uneven thermal expansion in each of the platters. However, multi-bit perpendicular recording is a similar concept.

Re:More Parallelism

[Anonymous Coward]

Modern drives pack the tracks in so close that only one head can be in alignment at a time. The thermal expansion across the drive's operating range move the tracks relative to each other during operation. The real issue with spinning media now is reducing seek and rotational delay. Adding more spindles (spindle and independent arm) is currently the best way to add IOPS with spinning media.

Re:More Parallelism

[Agripa]

Just to add to this, the track eccentricity is larger then the track spacing and is not consistent between platters so using an embedded servo per head is a necessity. I remember reading about research into using a second stage of servo positioning by mounting a piezoelectric actuator closer to the head but no manufacturer has done this to the best of my knowledge. I would guess that adaptive DSP driven servo positioning algorithms were able to make up for the mechanical limitations of the voice coil and long arm.

Noise?

[RudeIota]

Just imagine how loud something like this will be. The Velociraptor is loud enough, in my opinion. And because of that, these drives will only have a place in environments where speed > noise (perhaps gaming systems).

It would appear to me that mechanical media is on its final throes before SSD totally pounces it. And if the Raptor line is is any indication of price, cost becomes less of an issue against SSDs.

Re:Noise?

[Cochonou]

This will probably come out first as an enterprise drive on a SAS interface, like most of the 15000 RPM disks. Enterprises drives are loud, but you don't really care about this, since they are not supposed to be working in the same room as you are.

Re:Noise?

[Anonymous Coward]

I've never heard of a drive failing because the platter came off, but with a speed of 20k rpm couldn't that cut someone in half if it did?

Kenwood TrueX...?

[RudeIota]

Remember those? It kind of reminds me of the multi-head idea you have. Perhaps one of the differences (I think) is that the actual head assembly moved too, to compensate for the disc itself not being able to rotate faster (discs have the potential to shatter above the usual max speeds on current optical drives). I remember seeing a drive rated at 72X back in early 2000.. maybe even 99.. I don't feel like digging up a link though.

They were fast and quiet, but I don't think they make them anymore. I remember the reviews being favorable too, but they were a bit expensive (not outrageously so, IMO).

Re:Kenwood TrueX...?

[karnal]

From what I remember reading, they actually split the laser into several beams that could be read by a single assembly - that way if you were reading one long continuous file, it could effectively increase your read speed since it was reading 3 or more chunks at once.

Random access wouldn't benefit from this as much; for maximum speed you would need to be reading something that spanned the length of all 3 tracks (or more) at once. Writes would be even more interesting in this scenario.

Re:Kenwood TrueX...?

[KGIII]

When I first read the 20,000 RPM my first thought was that when these disks fail they'll bring new meaning to the phrase "catastrophic failure."

CD-ROM Shattering - MythBusters Wiki: Discovery Channel:
http://mythbusters-wiki.discovery.com/page/CD-ROM+Shattering?t=anon

It isn't the same thing, of course, but I wonder what the required RPM would be to make platters shatter.

Cool means they'll become paperweights faster

[Anonymous Coward]

POS WD's atleast they'll eat themselves up even faster now if they increase the spindle speed.

in 10 years time young programmers will ask ...

[freddy_dreddy]

- why the lowest software for their drives are divided into sectors and tracks
- what a sleep and spin-up delay is
- why these fossils take more than a second to boot
- how to accurately predict when their drive has reached limited write cycles
- how to isolate transistors with bad oxides

my guess: we just added another cache-layer. We'll have super-slow/cheap/mass storage in the form of spinning disks, which are cached by SSD, which are cached on RAM, which are cached on cpu-interconnects where each cpu has L3, L2, L1

And the point would be...?

[RudeIota]

The advantage to having faster RPMs isn't as much throughput as it is seek times. You can RAID 0 all the drives you want together, but you'll never improve the throughput. I'm sure this is in response to SSDs, which really have two huge advantages right now: seek time and reliability. Adding another 10,000 RPMs may help HDDs limp along in the performance arena a little while longer...

So really, RAID 0 helps if your data is read/written to sequentially, but in the real world, your data is all over the place. That's where seek time becomes *really* important and I'd personally take an SSD over a HDDx2 in RAID 0 with twice the sustained throughput.

Re:And the point would be...?

[mrchaotica]

The advantage to having faster RPMs isn't as much throughput as it is seek times.

If you have two sets of heads, on two separate arms, then you halve the seek time on average because each set is only responsible for half the radius of the disk.

Re:And the point would be...?

[Gazzonyx]

I run two Raptors in RAID 0 with short stroked partitions. If you keep your partition slices to the outside of the drive, with variable data partitions (/var, /tmp (if you put that to HD instead of tmpfs), and swap) between static partitions (/usr, /usr/local), you can get much better performance than if you glob the whole thing on LVM. Oh, yeah, and write off the last 15% of the drive, the seek time to it doesn't justify the storage space since it's the slowest part of the drive. Use the kernels I/O elevator to your advantage and lay out your partitions accordingly. If /var is at the middle of the disk, you're, at most, half a disks width from it and will be passing over it to get to other static data.

Re:And the point would be...?

[tepples]

If you have two sets of heads, on two separate arms, then you halve the seek time on average because each set is only responsible for half the radius of the disk.

Or you could just use a pair of 2.5"-class drives, with different apps' data on different drives. But head movement is only one component of seek time; the other is disk rotation, which is the point of The Article.

Statistics?

[RudeIota]

Maybe you'd care to post some statistics which show WD has a higher failure rate than other HDD manufacturers?

It's my experience that they are all equally as awful as each other. :)

The product will be dead on arrival

[bogaboga]

I am afraid the 20,000 rpm drive might be dead on arrival! Isn't the world "going SSD," whose advantages include faster start-up times, low read latency times, "mechanical" reliability and absolute silence while working?

Laptops have SSDs, next will be desktops increasing chances that Western Digital's product will be dead on arrival.

Re:The product will be dead on arrival

[wisty]

SSD has won most of the phone and iPod tier. Ultra-portables will go next. Then laptops, appliance desktops, gamer desktops, then finally business desktops. This might take 5 years. Only then will servers (which is the market for 20k disks) start to go SSD. 5 years is a long time.

Google might find a use for SSD (using caching and stuff), but your average business running an Oracle database to keep track of their business information wants read-write (not read) performance, which is what these things can do.

Re:The product will be dead on arrival

[compro01]

I doubt it. SSDs are coming, but they're still too expensive and don't have the capacity. you can be ones between 2 and 16GB for somewhat cheap, but then look at what kind of capacity that will get you in a mechanical (Since this is a 2.5" drive, you'd be looking at about half the capacity of the current 3.5" velociraptor, so likely ~150GB, possibly more if they crank up the density.) and it's not really a competition outside of the seek times and shock resistance.

Cheapest 64GB SSD (an OCZ one) i could find goes for $285 : $4.45/GB
Current 300GB velociraptor goes for $300 : $1/GB
Projecting 150GB 20k drive going to $400 : $2.67/GB
Projecting at $500 : $3.33/GB
For sane reference, a normal 640GB 7200RPM drive goes for $100 : $0.16/GB

Re:The product will be dead on arrival

[Teriblows]

well the fastest ssd aren't here yet. so this will be an affordable stop gap. people want performance now as well as in the future. its why there are 400+ dollar video cards. sure you could wait a year or two and it will cost half, but lifes short.

Re:The product will be dead on arrival

[bigstrat2003]

When SSDs have large capacities (at least 500 GB) at a comparable price per GB, then I'll consider putting one in my computer. Not before.

Re:The product will be dead on arrival

[Jeff DeMaagd]

SSD is still a bit of a slow transition because the price is high. Excluding select drives that are even more expensive, their alleged performance improvements are dubious.

Notebook computers with SSDs are very few in number. because they are still bloody expensive. With a regular high capacity 250GB+ hard drive costing less than $100, who wants to pay $500 for a 64GB SSD? And those generally aren't even using the fast chips either, they aren't any faster unless you compare them to 1.8" hard drives, going against 2.5" or 3.5" drives, forget it.

The 20k hard drive isn't even intended for desktops, there aren't even 15k desktop drives, they are workstation and server drives.

Re:The product will be dead on arrival

[jez9999]

People say economics are 'stopping' SSDs, but no, not really. Because I'm sure that 10-15 years ago, $4.45/GB would've been a fantastic price-capacity ratio; and they managed to sell hard drives then.

Re:The product will be dead on arrival

[Deliveranc3]

absolute silence while working

I've been thinking about this and I'm not sure it's an advantage, when I'm not doing anything on my computer and I close all the apps I know do periodic access it shouldn't do anything at all.

If my HD makes noise I know I have malware...

I'm not terribly paranoid about it but I like having a physical indicator that my system isn't being monitored or pwned.

Re:The product will be dead on arrival

[swillden]

10 years ago, a 4 GB drive was more capacity than you could figure out how to use. These days, it's barely enough to install the OS.

Re:The product will be dead on arrival

[silas_moeckel]

Funny I see a lot of SSD's getting pushed by the likes of EMC to service Oracle and similar enterprise apps. SSD's have incredible numbers of IOP's and inside SAN enclosures the draw backs of wear can be mitigated though preventive maintenance.

I've got a Velociraptor and it's very quiet

[Joce640k]

Most hardware reviews agree with me - the Velociraptor is one of the quietest drives around.

Maybe you're thinking of the old Raptor drives?

Beowulf

[Anonymous Coward]

Nobody seems to have mentioned a Beowulf cluster of these yet.

Imagine...

Re:linux?

[Anonymous Coward]

quoted for troof

Seagate says....

[Madalienmonk]

OVER 9,000!?!?!?

new math?

[Anonymous Coward]

15,000 rpm drives in an external enclosure which then spins the drive at a further 10,000 rpms, for a total system speed of 25,000 rpms

Um, wouldn't that be 150,000,000 rpm?

Re:new math?

[Anonymous Coward]

Further often means "additional".

Re:new math?

[Anonymous Coward]

No. Running at 10mph on top of a truck going at 30mph means you go at 40mph, not 300... Same with this but angular.

Fame

[Tablizer]

Who will be famous as the first consumer to die in a hard-drive failure?

linear speed

[Anonymous Coward]

A 2.5" platter at 20,000 RPM has a linear speed at its outer edge of 257 km/hr (160 miles/hr). Yeah, that's moving along at a pretty nice clip.

Innovator's Delimma

[MrWa]

WD is dead and they don't know it.

Flash drives are the future and will soon overcome hard drives. This is clearly a classic case of disruptive technology in the disk drive business. Flash can't beat HD's at the current computer buyer's desired capacity-price ratio but the speed and instant access performance is way better. Soon enough flash will reach higher densities and pass HD's in capacity-price. Hard drive's will go the way of the 3.5" floppy.

Re:Innovator's Delimma

[Anonymous Coward]

I'm sure WD is working thier own SSD magic right now.. this would just be something to hold off the HDD hardcores in the meantime, until they can introduce thier own bad A version of a SSD drive.

Re:Innovator's Delimma

[ergean]

Sure... just bring me that flash drive that has 640GB at under 100$... and they would be dead.

Re:Innovator's Delimma

[misaltas]

But I might still can use this 20k drive as a flywheel to store energy and lighten the load on my overheating laptop battery. ;-)

Not the best page on wikipedia...

[Kjella]

Price is about right with USD 3.50/GB

Capacity: Already BitMicro has shown a 1.6TB SSD drive - capacity is only a problem as related to cost.

Limited write cycles: At the rate they're improving, WTF cares? Get one much larger and faster for 1/10th the price in five years. Also this is much less an issue with 32/64/128GB disks than when you try to squeeze it all in on 4GB, a lot being OS files that change a lot. And solved in firmware on all current SSDs.

Slower write speeds: The latest generation beat the crap out of traditional HDDs in application benchmarks - you can create a synthetic test with 100% random write but it's got nothing to do with normal use. "Random" means 4k blocks all over the place, not even BitTorrent writing blocks all over a file is random in that sense.

Higher power consumption: In the link to Tom's Hardware, quote "Since there are test results on the Internet proving that Flash SSDs can improve battery life (and we fully agree that power-optimized Flash SSD products are more efficient than mechanical hard drives)" in short older SSDs used crappy tech.

In short, the one big issue holding SSDs back is price. Well, that and availability as I've been looking for them to show up in webshops here and the short answer is they don't.

Re:Not the best page on wikipedia...

[DMUTPeregrine]

Actually, random data is important. Very, very important. Encrypted data should be indistinguishable from random noise. Anyone using TrueCrypt or similar will see a much larger performance decrease than they would on a normal drive, though the SSD may still be faster. It also won't write to random sectors, the wear-leveling algorithm does that.

And since when is 3.50/GB about right? Thats about 3.5x what it would need to be for me to consider it. Normal HDDs have been under $1/GB for quite some time now. It is dropping quickly though.

Re:Not the best page on wikipedia...

[Kjella]

Actually, random data is important. Very, very important. Encrypted data should be indistinguishable from random noise. Anyone using TrueCrypt or similar will see a much larger performance decrease than they would on a normal drive, though the SSD may still be faster

Disk performance will be exactly the same, they are talking about random vs sequential access on disk not whether the data is random or not. Like, is the data written all in one place or on "random" locations all over the disk. Having a symmetric encryption layer inbetween will not change that.

And since when is 3.50/GB about right?

"Right" as in one of the things the wikipedia page has right. Which is why I said at the bottom that the one thing holding them back is price.

Re:Not the best page on wikipedia...

[dw604]

You can find them on eBay

Re:Not the best page on wikipedia...

[TheLink]

Write speeds aren't that great: http://www.alternativerecursion.info/?p=106

It might be fine for desktop linux.

But for other stuff, I think it needs a fair bit of testing first. For database servers, when say 10 users update a bunch of records, the writes don't usually end up conveniently going to the same area of the drive.

And different databases handle stuff differently - some write directly to the table, some write first to a rollback segment, some write to a write log, and so on.

You really don't want to hit the 4 writes per second scenario. That's abysmal.

It's fine if you are writing 20MB chunks at a time (80MB/sec), but if your write chunks are smaller than say 4MB...

Only 20K?

[mccabem]

Maybe this is a "-1 Redundant", but Formula 1 engine designers have been able to make internal combustion engines that run at around 20K for a while now (granted with a lower MTBF, but considering the environment would a HD last longer? ;-) ) It seems like with the magnitudinal differences in scale/mass going down to a HD mechanism, they/someone should be able to get relatively higher (than F1) speeds at the spindle.

I guess not tho, eh?

-Matt

Re:Only 20K?

[parabolic parasol]

Combustion engine vs electromagnet.

Re:Only 20K?

[dfsmith]

The moment you can show me an F1 engine that runs at 20kRPM for 5 years and costs less than $500 I'll get back to you.

Re:Only 20K?

[mccabem]

Re-read please. (Though you already got the 5 mod points for "Funny" which I guess implies because you didn't read the post you responded to.)

To reiterate, show me a HD that'll last any longer than an F1 engine when mounted in an F1 car during a race. :-)

The F1 engine has to last two whole race weekends (including all testing/qualifying, etc) and the gearbox has to last five race weekends.

I bet a HD on one of these cars - even running as low as 3600rpm (let alone a 20k model) would be toast before the end of practice of race weekend #1.

-Matt

P.S. now *you* get the "-1 Redundant", and I move up to "-1 Off-Topic".

Re:Only 20K?

[mccabem]

I'm not sure I understand. Are you just pointing out the difference, or are you saying that electromagnetic motors are inherently unreliable? (Other?)

My point was that an engine with thousands of explosions happening inside it per second *seems* like it should be less reliable than one based on electromagnetism, but in practice (with all things considered) they seem to me to be more reliable.

Thanks!
-Matt

Missed Point.

[Borg Bucolic]

I think the point was missed. Hard drive data densities and data speed are limited by the thickness of the surface recording media, distance of the head from the platter under operation, head gap, diameter, and encoding. By reducing the platter diameter, you reduce the amount of recording media, less storage. The 'trade up,' if you will, is that you can speed up the platter as the diameter at the outside track is reduced, and have fewer tracks (lower seek times). Hence, faster data, but less storage.

Last week I spied a 4 terrabyte drive in Best Buy. It wasn't THAT expensive. I trying to conceive where I would need storage on that scale.

The problem with solid state drives is the number of data rewrites. Solid state devices do have a limited life that is substantially shorter than hard drives in terms of rewriting files.

The problem with extra platters, and such, is a matter of cost and reliability. The more parts there are the more likely it is to fail. My first hard drive (personally owned) was a 5" half height drive that stored a whopping 11 megs of data. I RLLed that drive up to 18 megs. If they were to duplicate that in today's technology, the same drive would be the size of a stamp and be blazingly fast.

Re:PHELPS WINS!

[Anonymous Coward]

Does he eat them raw or cooked?

Raptor vs SSD

[isthisorigional]

I almost bit the bullet recently to buy one of the new OCZ Core SSD's. If you read any reviews, they're pretty much the first SSD princed anywhere close to what an enthusiast might pay. That's ~$250 for 64GB. They've got a 32 and a 128GB in the lineup as well, but really for an OS+ a few key apps HD, 64GB would be the sweet spot for price/performance.

So, why would you pay $4 per GB for this when you can get a 1TB drive for around $140ish or so? Practically 0 seek time AND ~120MB/sec reads and ~90MB/sec writes. Hence WD upping the RPM's to 20K. SSD's, while pretty much in infancy for the consumer market, are already the fastest thing out there. It won't be long until they catch up on capacity.

Now, the only thing that stopped me from picking one of these bad boys up was checking out their support forums. It looks like these things have some pretty serious problems for at least some chipsets. While I realize that support forums represent the voiced minority, just running through those posts show some major issues at least with certain system combinations. Not to mention, these SSD's are pretty new, yet OCZ just announced a new rev for the lineup, now complete with a USB interface built into the drive to allow for firmware upgrades? I know this is bleeding edge stuff, but wow.

Anyway, I really wanted to upgrade with one of these because the hard drive is the slowest component in the system usually and I didn't see the VelociRaptor as a big enough upgrade for the $$. However, after all these reported problems, I think I'll wait to see how things are in 6 months or so.

Re:Raptor vs SSD

[strelitsa]

Let the early adopters be your unpaid QC department. I really do want to shift to SSD myself for speed reasons, but will wait a couple of years for the tech to sort itself out.

old news

[Anonymous Coward]

This was announced about 2 months ago and many sites wrote about it back then.

Btw. I'm looking forward to this being released and probably buying one to speed up VisualC++ builds. Unfortunately SSD-s perform very poorly with many small files, so that's not an option.

Velocity

[mach1980]

Am I calculating the circumface speed correctly? Got it to approximatley 2350 km/h!

Re:Velocity

[Anonymous Coward]

off by a factor of 10
2.5" drive = about 2" platter dia
2.5" = 63.5mm
63.5mm * 3.14 = ~ 200mm circumference
200mm = 0.2m = 0.0002km
20000 rev/minute * 60 = 1200000 rev/h
0.0002 * 1200000 = 2 * 120 = 240km/h

Re:Velocity

[Thundersnatch]

Am I calculating the circumface speed correctly?

No, you're not.

2.5*Pi in/rev * 20K rev/min * 60 min/hr * (1/12) ft/in * (1/5280) miles/ft = 149 miles/hr = 239 km/h

Still fast enough to injure if the thing shatters, but not supersonic.

Are you serious?

[Anonymous Coward]

You're right, in 5 years there will be no market for the fastest mechanical HD ever made.

I understand SSD will have a greater *portion* of the market, and this might reduce potential sales, but being the best at anything never hurt anyone.

Multi head per platter drives

[tensop]

Do any multiple-head-per-platter drives exist at all? :) I wonder why they've never done it.. .

Docking nightmare?

[argent]

Unless they add a daughterboard adjusting the position of the connectors, isn't this drive going to be a docking nightmare?

Fixed

[eddy]

That's what they do. See picture.

Re:Fixed

[argent]

Three cheers and a tiger!

Much faster is possible, but not worth it.

[Animats]

The next step would probably be hard drives that run in a hard vacuum. Current drives "fly" the head over the surface on an air cushion. A vacuum drive would have to actively measure and servo head height, which is quite feasible. Running in vacuum, drive speeds would no longer be limited by air friction and noise. Ultracentrifuges routinely reach speeds of 100,000 RPM.

But such machinery would require developing a whole new technology, cost far more than a flash drive and wouldn't fit in anything like a PC drive form factor.

Re:Much faster is possible, but not worth it.

[cnettel]

I wonder what level of power saving this would mean with somewhat affordable bearings. That's of course dependent on what level of sophistication would be needed for an active pumping solution to maintain the vacuum. Compared to an ultra-centrifuge, we have the big advantage of much smaller volume, and no foreign matter introduced... ever.

Re:Much faster is possible, but not worth it.

[Animats]

It would be a cute technology to develop. Active pumping shouldn't be necessary; put the drive in a glass case, like a vacuum tube, bring out the connections through the glass using wires with the same coefficient of expansion of the glass, and pump it down once at the factory. Tubes hold vacuum for decades; so should this. The bearings aren't a major problem; active magnetic bearings are no more complex than a motor, and there's been some success with passive magnetic bearings. that work on the same principle as the Levitron.

It's flying the head in vacuum that's the problem. With no air cushion, the whole job has to be done actively. Seagate has a patent (#6,473,259) on one approach to this, so the problem has been addressed.

There's an experimental technology for hard drives which uses an electron beam for reading and writing. That might lead to high-RPM drives.

So there are several potential approaches to ultra high rotation speed disk drives. It's probably a technological dead end, though. You're never going to get more than 10x current rotation speeds, and the cost will go up, which makes this a lose vs. flash and other forms of nonvolatile solid state memory.

Why not work on a 3.5" raid enclosure instead?

[DJRumpy]

I would think they would be better off concentrating on a viable raid solution in a 3.5" enclosure rather than 20K drives. Probably cheaper to manufacture, it doesn't exist now as far as I know, and the performance benefits would be similar to (if not better than) a single 20K drive. This whole 'more rpm' path is like the oil industry. On it's last leg. No matter how efficient they make these engines, it only has a limited life left. I'm thinking if they could miniaturize this tech enough to get a 2 or 3 disk raid into a 3.5 inch enclosure, and drive it through a single sata (or multiple connectors on a single sata enclosure for desktops), they could get decent performance.

Raptors unreliable

[Anonymous Coward]

I don't know about their 20,000rpm offering but all I can say is that I have bought 3 150GB 10,000rpm WD Raptors and all failed within 12 months. Enterprise class my ass.

Re:Raptors unreliable

[Anonymous Coward]

Sounds like they weren't cooled properly.

I have 4 hardrives, and now my computer precesses

[spineboy]

I just balanced my beige box one oneof its corners and now it precesses like a top.

It's a little tough to walk thru a doorway, and then turn a corner, since the computer wants to go at a right angle to the direction I'm turning.

The CIA

[bajatek]

..has shown interest in the research, formatting NTFS causes an explosion similar to a frag grenade.

It'll have a couple of years before that

[Joce640k]

SSDs are still orders of magnitude more expensive.

Reliability

[homerskid]

Does this mean the WD disks will crash even faster? Seriously...they should put some effort into reliability first, maybe then they wouldn't have to be as concerned about losing customers.

Velociraptor link

[ZERO1ZERO]

Was I the only one dissappointed that the velociraptor link didn't point to an xckd comic?

The real future

[caliburngreywolf]

HP has the patent on the memsistor...which is set to revolutionize memory/storage in a big way. Imagine packing a computer away for 2 years, then turning it on, and in half a second, the youtube video you had buffered begins playing. Hard drives will always need to spin up.

A good answer to the question "Add heads?"

[Anonymous Coward]

There is a good answer (as well as a lot of more information and history about hard disks) here:

http://www.storagereview.com/guide2000/ref/hdd/op/actMultiple.html

Rotating Head assembly

[jameskojiro]

Make a carriage that hold the heads and make it rotate the opposite direction, but twice as fast.

That way the whole thing is gyroscopicly stabilized.

See. Size DOESN'T matter.

[redbaritone]

... but shortening it an inch to accommodate cooling? DAMN!