Slashdot Mirror
Next Wave Of Hard Drive Tech: Perpendicular Recording
angrytuna writes "New serial technologies are set to replace standard SCSI and ATA (Advanced Technology Attachment) interfaces over the next two years, even as hard-disk drive manufacturers prepare for an entirely new form of bit storage. Perpendicular recording will replace longitudinal recording in storage devices, placing bits on end instead of lying them parallel on the disc surface, thus dramatically increasing the possible storage density."
that there is such a crackdown on file-sharing. If they take that away from us, then whats the point of having that much space?
I wonder which side of the debate the hard-disk manufacturers are on?
If my drive bit is standing up, it must be hard. Ergo, hard drive.
C|N>K
the hard drive sideways... voila! perpendicular recording ;)
I am less concerned about the amount of stuff I can put on a hard-drive, and more concerned that the next time I boot up my computer, that stuff will still be there, as harddrives get more and more high-tech, the reliability seems to be taking a big nosedive, how will this effect the reliability of future drives?
Why does the article reference interfaces then talk about a new way of storing the bits on the disk survace?
In the days of 250GB hard drives, who cares? All I'm concerned about is the speed of drives. Lets improve that for once...
Does anyone have a link to a description of this that's more detailed than "stacking bits on end"?
Are they using platters with trenches and storing information on the sidewalls?
Are they using some means of reading and writing at many depths within the platter without disturbing other layers?
The article says the technology has been under investigation for 20 years, so presumably there's a forest of technical literature on it.
What is the entirely new form of bit storage?
John Kerry is a Joke!
HDD manufacturers said they expect to start replacing 3.5in. disk drives with smaller 2.5in. devices in enterprise products sometime within the next year.
Why would they want to do this? Has it something to do with vibrations (or even shattering a disk) due to the extreme rpm's that these drives are running?I don't know much about this stuff, so could someone please enlighten me?
The best weapon of a dictatorship is secrecy, but the best weapon of a democracy should be the weapon of openness.
i was thinking of purchasing a 120 gb hdisk, looks like i should wait.
From the article - interface changes indicated in the writeup is going to be implemented very soon (could increase interface bandwidth from 20Mbytes/s to 320Mbytes/s !) while the perpendicular recording is going to take some time to hit the market.
Could someone explain (/point me to a website) as to what this paragraph means ?
"We always have concerns about new connectors and backplane designs but those problems are minimized in a serial environment where the wiring is point-to-point,"
Siggy Say, Siggy Do
This conversation with Jim Gray, head of Microsoft's Bay Area Research Center, has grim, eye-opening comments on the growing gap between storage densities and access speeds/bandwidth. Currently the most effective way to send a multi-terabyte disk array is by UPS -- turns out a UPS truck has a "bandwidth" equivalent to about 7 megabytes/second. And the problem of practical access speeds is only going to get worse. At current and near-future access speeds, searching a 20-terabyte disk might take a year.
More and more cheap RAID solutions for mid->power users?
Check out the DFI LANParty series of MoBos with RAIDx1.5 which allows pseudo RAID 0 and 1 with only two drives. Pretty durn click if you ask me, and not at a ridiculous price point either.
Just a though. (Doesn't actually FIX the problem though)
-- kwashiorkor --
Leaps in Logic
should not be confused with
Jumping to Conclusions.
Storage density is one thing, but storage speed is another. With 200 GB hard drives readily available, and relatively cheap, the main thing I'm itching for is increased access and transfer speeds. Not just the controller speed as most hard drives still only maintain a constant transfer speed of 33Mbps. Theoretically, a denser drive at the same rotational speed will transfer data faster than a less dense drive, but will we see a dramatic improvement in sustained transfer speeds? While this transfer speed is acceptable while watching a DivX movie, it's really a pain while ripping a DivX movie. (A movie that I shot in my backyard, and authored, and own the rights to, and am ripping for the pure exitement as I would never violate a copyright.)
...engineers are working with software developers on a way to dramatically reduce power consumption by maximizing the number of 0-bits in memory.
"We think this could be a major breakthrough for laptop users dissatisfied with battery life," comments one developer who wishes to remain anonymous. "Studies show that modern software uses an increasing number of 1-bits, a side effect of the overcomplexity of today's lax programming standards and abundance of cheap, fast CPUs and RAM."
Sources indicate that in addition, storing fewer 1-bits on the disk may result in portable computers that weigh less, as well.
Don't think of it as a flame---it's more like an argument that does 3d6 fire damage
Of course, both of these are non-magnetic. And holographic memory is still research-only, as far as I know.
I wonder, will magnetic storage (in any number of dimensions) ever get eclipsed by non-magnetic ones like these?
Nothing is so smiple that it can't get screwed up.
So they flip this one on its head (essentially AND no pun intended :)). The disk speed doesn't necessarily matter, but the head speed will need to increase expontentially to account for the loss in RPMs. The head will need to be reinforced to keep from head crashes, which will slow it down further. AND it will require a minimum quality assurance, which hell, it's a corporation. QA isn't going to factor into the first few HD rollouts. If it does I'll be shocked.
Expect seek times to magnify by 10X at least, and far less hours of lifetime. And if you ARE going to be running one of these fresh-off-the-manufacturing-line devices, be sure to have solid DVD-R(W) backups of all your stuff. I'd expect a high-fraction of head crashes in the first few rollouts.
...or
...or
Backing up LEGAL movies and music
Once again, the corporate market.
Also, if they can be produced cheaper, they'll be used in mail order systems. It's not aways about having the space.
Ben
Work Safe Porn
If they stand the 1's up, sure you can fit more because they're skinny. But 0's? They're wide...I don't see a significant amount of savings there...
So, does this mean that instead of looking like this:
0
1
All of my bits will instead look like this?:
_
-
I suppose you can squeeze a lot more of them together that way, but is that really much of an innovation?
Now, if they had figured out a way to fold the suckers, I'd be impressed.
More relevant than this technology that is still many years away, I find much more interesting the part about the desktop industry moving to 2.5" drives. So in the next year or so we'll be able to buy very high density, fast drives that can fit in a pocket and already have serial interfaces! All we need are sata jacks on the front panel and the world moves one giant leap closer to true "plug-n-play" goodness. Mail order sneakernets just got even cheaper!
11.0010010000111111011010101000100010000101101000
Why does the article reference interfaces then talk about a new way of storing the bits on the disk surface?
They are both big changes in the way hard drives work that will lead to improved performance. They also talked about drive sizes changes (3.5in -> 2.5in)
autopr0n is like, down and stuff.
You can get ATA->SATA adaptors. You can also get Seral ATA drives and interface cards today.
autopr0n is like, down and stuff.
Due to the speed of the disk platters, and performance limitations in current magnetic head technology, most drives write their data "end-to-end", like so:
( --> direction of spin --> )
-0--0-00--0-0-0--0-
However, simply by rotating the read-write head by 90 degrees, we can write the data "perpendicularly", like so:
|0||0|00||0|0|0|0|
Obviously the "1" bits stack more efficiently in this orientation. For example:
||||||||
The greatest gains will be seen by data composed mostly of "1" bits, as they take less room to write than the "0" bits (when written "perpendicularly").
Further density improvements are expected with the change to a smaller font size for data storage too...
And to complete the joke see HD-Rosetta
I have seen a few posts from folks not quite understanding how the "bits-on-end" approach works. Some were speculating that it might be holographic, multiple layers, or 3D and such. It is not at all that complicated as they are making it out to be. I heard it best described from Alan Shugart who started the company called Seagate. On an episode from "The Computer Chronicles" back in 1984 he described it as standing the magnetic particles on end to fit more in a given area, which is similar to how a cord of wood could fit into a given smaller area by standing them up on end instead of laying flat. So it really is simpler than you might imagine. Of course the implementation is anything but simple. This is especially evident by the fact that this idea was known as a way to increase storage density back in 1984, when even 200 million bits per square inch was not in a consumer product yet. It was merely in labs with thin film head technology poised to become the next big thing in a short time from that year.g er.php.
By the way, you can see old episodes of "The Computer Chronicles" at the Prelinger Archives collection.
http://www.archive.org/movies/prelin
I believe Slashdot had a story about that a while ago. Good stuff! Great info can be had through those old episodes about computer history.
>>>>>> Chewie, take the professor in the back and plug him into the hyperdrive.
I'm curious to, but i think it's something like this. If I have a log laying on the ground i can rotate it around to put it in it's proper place. But if i stand it on end and rotate it about its axis to get it in its differant positions its not covering nearly as much space. But keaping it standing up is the problem since it naturaly wants to fall over, and you can't attach the base of it to the ground very well if your going to be spinning it all the time.
This is just my thought on what there doing. But how data is actualy stored on a disk is a mystery to me, all i have is guesses. Soon as i think that one little thing not going the right way destroys a file causes me to think it must be weird magic voodoo.
One of the first Sun machines I used was a 3/160 with an external gigabyte disk array. The array was a washing machine size enclosure with a pair of 800 MB SMD disks with 8" platters. In 1994 this was a huge disk, in more ways than one!
Interestingly, my little 486 with its 340 MB drive were far faster than the old Sun, and even competitive with the newer SparcStations. 7200 RPM baraccudas in modified enclosures (extra fans and breathing holes made the difference between life and death) were even faster when they arrived.
After working exclucively with laptops for the past two years, I can see a clear parallel between the old 2.5" -> 2.5" transition and the 8" -> 5.25" -> 3.5" transitions in the past. Sure I keep a pair of 120 GB 3.5" disks in firewire enclosures around, but the 60 GB disk in my powerbook and the 30 GB disk in my Dell i8000 are more than adequate for daily use. My ipod even has 30GB, which is enough for my favorite music, the Warthog Jump video and a few other fun things.
With emphasis on blade and 1-U servers, as well as cardcage oriented telecom gear, I can see a lot of value for 2.5" disks in the telecom and server markets.
RFTA, what am I, your executive administrative assistant? Bah, here bizzotch, from the fine article:
Perpendicular recording will be required at the point when products reach capacities of about 100- to 200Gbits per sq. in., compared to approximately 50Gbits today, industry observers said.
Got that? 2-4x. OK? Happy? Jeez.
everything in moderation
AFAICT, they're not talking about multi-layer recording, they're just standing the existing bits on end so that the same amount of magnetic material uses up less surface real-estate. <deadpan>If they did multi-layer recording, they'd have to slow the drives down so that the surface of the disk wasn't so stretched by centrifugal "force" and the shallower bits didn't sag into the next cylinder. Otherwise they'd have to angle the heads WRT the platter surface, which means they can't fly them close enough to record that deep.</deadpan>
Got time? Spend some of it coding or testing
Interesting? This clueless and sadly-late attepmpt at a FP is misleading everyone that reads it!. And you mods are to blame -- that's right: YOU!
::::::::
::::::::
Grrr, RTFA: there is nothing "3D" about it. It's still a 2-dimensional array of bits on a platter. The density increase comes from standing the little areas of magnetic media on end, instead of laying down. So, a top view of the old scheme would look like:
||||||||
||||||||
The new scheme, from the top:
In this case 2x density, as the lower one has twice as many dots in the same area as the dashes of the upper. (That is, each dot or dash represents the area of the physical medium used to store one bit by changing its magentic orientation). Get it? No 3-d. No holograms. Just 2-4x density increase by changing the orientation of the bits from parallel to perpendicular (relative to the disk platter surface).
everything in moderation
Okay for the last 20 years they've been working on this. WHY are they not looking into solid state storage? There are plenty of companies within 2 years will have drives that will blow away current drives in speed and capacity. One such company is using nanotech to offer 1 terabit per cm2. And it'll run at 10x the speed of current memory.
I cant help to see how this is not wasted time trying to improve the platter drives in favor of pushing out solid state storage faster. The advantages alone overrule more development on platter systems. Imagine instead of 100mbps of bandwidth on the hard drive you would be getting 10gbps of throughtput, no moving parts and much less heat and a longer MTBF time along with size alone this would blow away the server markets..
Who would care about the 16Gig memory limit when you have a solid state hard drive that ran faster than the memory array? Then you can just modify the software to use the Solid State Array (Think I'm going to patent this!hehe) SSA drive as memory and storage thus DB servers would have serious improvements compared to platter systems.
I bought a 120gb drive about a year ago and absolutely love it. Considering you can get a nice 7200 rpm one now for less than $100, what have you got to lose? Especially if that new technology comes out the price the old drives is going to drop to the floor, and I daresay a RAID setup will give more than adequate performance. Heck, I'm copying and editing videos all the time and the issue is mainly with cpu speed rather than hd transfer rates
The sending of this message pretty much inconveniences everyone involved.
What's the potential for damage with these new drives? Don't get me wrong, hard drive space is good, but with more data being packed into smaller and smaller a space, surely any damage at all will cause more information to be lost. Raid is all good, but will these drives be durable or can I forget using my laptop in the car?
SealBeater
-- Its survival of the fittest...and we got the fucking guns!!!
http://www.inphase-tech.com/technology/
Drum storage with a difference. At 10,000 RPM or worse, those suckers would precess like crazy. Perhaps they could use paired contra-rotating shafts, good bearings and hope nobody used them for a mobile app. Or build them into Segways. (-:
Got time? Spend some of it coding or testing
Weren't the 2.88MB floppy discs perpendicular recording also?
I distinctly remember reading that somewhere.
-- The universe began. Life started on a billion worlds...
-- Except on one where stupidity was there first.
See, there's a limit to how many bits you can store on a disk. I see. Because the area of the disk is limited I see. But you don't want a limit, you want more space. I want more space. But you can't have more space, because all of the bits are square they're square. and there's only so many square inches of surface. Only so much. Yes. Look at this disk. Radius 3.25" 3.25 It's a circle. It's round. Pie-R-square Pie-R-square So the area's limited. I see.
And the bits, they're almost square, because that's the way the manufacturers' engineers like them. They like squares? Yes. I see. Well, really they're not square, they're almost square. And how's that? Well, they're square sections of a round arc. Not square? But almost square. Almost square. I see.
So what do we do? I don't know. Well, we get a better packing fraction. Better packing fraction? Yes. That's the key. A better packing fraction. I see. And your data is round. Data is round Because the magnetic field is round. I see. And a square doesn't approximate a circle very well, does it? No. What does it better? A circle? Well, yes, but you can't do it with a circle, because circles bump each other. They bump each other? Yes, and they leave empty space between them. And we want a better packing fraction? Yes. So what do we take a cue from? I don't know. I know you don't know, but I'll tell you. We take a cue from the bee. The bee? The honeybee. He uses hexagons. Aaah. Hexagons. Yes, hexagons. They're all the future. The future? The future. The future. Yes, the future. Hexagons. Yes. That's where the money is. You're a nut.
Correct Horse Battery Staple: 72 bits of entropy. Enter "Correct H" into google. When it generates the phrase, that's
My rule of thumb for getting a new hard drive is: If you're "starting to run low" but still have 25% or more of your drive space left, wait. If you can wait even just 3 months, you'll save money and/or get more space.
I usually wait until I've actually run out. Then I delete all the useless crap I've collected, leaving me about 10-20% of the drive. At this point, I start shopping around, and try to overbuy so as to not have to purchase another drive too soon.
7.2 megabytes/picture? Not to troll, but isn't that a bit excessive? Why such resolution and/or bitdepth?
To make laws that man cannot, and will not obey, serves to bring all law into contempt.
--E.C. Stanton
Heh, holographic memory eh? naw, this is the real deal: quantum-phase memory! Unlimited storage in just... one electron! :D
If you have no idea what the difference between Longitudinal Recording and Perpendicular Recording might be, and the phrase "stands the bits on end" meant absolutely nothing to you because its an utterly ridiculous way to explain it, here's the lodown. Longitudinal recording is what we use today in everything from cassette tape to hard disks. It works by magnetising tiny sections of the recording medium. You can imagine the magnetised sections as tiny bar magnets laid end-to-end. The read head detects transitions in the direction of the magnetic field.
.
<- -> <-- -> <- -->
In the above diagram we're looking down at one track on the surface of a platter. Perpendicular recording works differently. The "magnets" or bits are arranged so that the field they emit is perpendicular to the medium, like this:
x . x . x . x
In the above diagram we're looking down at one track on the surface of a platter 'x' represents a field pointing away from us, '.' is one pointing towards us. This is what it looks like in cross-section (looking in from the edge of the platter):
^ | ^ | ^ | ^ | ^
| v | v | v | v |
In perpendicular recording the read head detects the actual direction of the fields emitted by these bits/magnets, rather than transitions in the field. Perpendicular recording is advantageous because it allows one to use a much smaller surface area on the medium for one bit. Imagine if you laid a line of bricks end-to-end on the ground, you could make the line shorter but taller if you stood each brick on end (so they're laid flat-to-flat), but you've not had to make the bricks any smaller in order to acheive this change in the length of your line.
Most of the above is hopefully right. Anyway it's a better explanation than that site gave.
dont mean to be rude here, but your an idiot. what part about utilizing the depth of the plater to improve storage density instead of just the surface does not = 3d?
we have xyz - x=radius,y=circumfrence,z=plater depth
thats 3D
Both schemes store the bit to some depth physically. You can't have an infinitely thin bit. Both schemes also still use a 2-D grid of bits. (Well, polar grid, since it's a spinning disc.)
A truly 3-D organization of bits within a single platter face would be something like those multi-layer DVDs, where within the same grid position you can access multiple bits by changing some aspect of the reading mechanism. (In the case of the DVDs, it's achieved by focusing the lense differently so only the desired layer is in-focus.)
--JoeProgram Intellivision!
Sorry, but your wrong. It's only 3D storage when you start stacking bits directly on top of each other on a 2D plane. So it's still 2D, just more effecient.
Life is not for the lazy.
Don't make fun of my floppy. I know it's small, but I use it alot. :(
Life is not for the lazy.
ASCII art is great for porn but for technical stuff I prefer real images. This image cleared things up for me.
I can definitely see how they'd have reliability problems. The drive rotation speed would be a real issue. It's like standing up on a merry-go-round. The bits are all standing there, but then you spin up the drive and they all start jostling each other and the ones on the edges fall off, while the ones in the middle just fall over on each other. The only bits you can really count on being close to correct are the ones in the middle of the drive. Is this is why we keep getting smaller and smaller diameter drives, to prevent the bits at the edges from flying off?
"It's real and we can touch it, so least we know where we stand." - Jack Burton
Does this increase relability at all and will we get back our 3 yeah warrenties?
Rus
Cheap UK and US VPS
And we had xyz and 3D before, in that sense. Seems you read netiher the article nor the post you're trying to defend. The relative dimensions per bit are changing (this time z is getting bigger and x and y are getting 2-4x smaller, as opposed to usual incremental drive density changes where z is constant and x and y shrink a bit.) But, in all cases, all 3 dimensions were (unavoidably) used before and now. It is not, as the OP claimed, a move from 2D to 3D storage any way you want to look at it.
Moreover, the original post led people to believe that data were being stored in 3D, i.e., layering of data on ther platter, offering n times density where n is the number of layers possible. See the posts below for evidence of this confusion. The reality, of course, is nothing of the sort. Please RTFA and STFU.
everything in moderation
What a poorly researched article. It is way below EEtimes quality and should have never been published as it is.
1. "As opposed to longitudinal recording, where the bits are impressed in a parallel format along the surface of a disc, perpendicular recording stands the bits on end, enabling more data storage per square inch."
What does it stand the bits at the end? I have never seend a standing bit. Especially on the end of it. Now c'mon, it could have been described a little more "technically". This is not USA Today.
And "impressed in parellel format" is such a crap of a phrase. It is not impressed, nothing touches, no impression, it is MAGNETIC, god damn!
2. "Apple Computer Inc.'s new G5 computers are all SATA-based while Intel systems will by the end of this year be based on the new interface."
Now this is utter turd. Before even G5 was announced, and probably before Jobs had the brainfart to invent them, some of the high-end PC motherboard manufacturers were already churning out SATA equipped motherboards. It was in the Intel development road map for several years now. I remember reading about it on Tom's 2 years ago.
Mr. Bolaji Ojo (EBN), please do your homework. Do not just blair (as in Jayson) out an article. You do wipe your ass after takin a sh*t, don't you? I am just asking that you would apply the same attitude toward writing articles. Thank you for your future cooperation.
Code poet, espresso fiend, starter upper.
I only play with teh audio component, but that can get real huge real fast. Suppose you are doing professional multitrack. You will be wanting to store your files in 24-bit and your minimum smaple rate will be 44.1khz, and may be over 3x that. Now some programs can use lossless compression that gets about a 50% cut, but you don't want to use anything lossy until you've mastered and have a final file. So you need between 3.8MB (44.1khz/24bit compressed, best case) and 32.9MB (192khz/24bit uncompressed, worst case) per MINUTE per TRACK. Now even if you ahve a simple recording, such as small jazz combo with 1 lead track, 1 bass track, 2 piano tracks and 3 drum tracks you are still talking a minimum data rate of 26MB/minute, which is 1.2GB for a 45 minute recording assuming no retakes. Now suppose you wanted to record a whole symphone with a 50 mike setup, and you wanted to do it in 192khz. You want 60 minutes of music and take each song a minimum of 2 times. That's 192GB of data, and you still need space to process that to a final form.
Now, this is just all audio data, and audio plaes in comparsion to video when it comes to size. Perhaps you'd like a full QUXGA-W (3840x2400, sufficient for threatre quality movies) stream. How much do you imagine that takes, even witha semi-lossy compression like the DV standard? How much do you think it takes if you need it uncompressed (791MB/second, which is why video isn't often worked on uncompressed)? There are applications, even today, for that kind of storage.
And then, of course, there is the future. I don't know about you, but I'd some day like to have high resolutions 3d movies on my computer. While I'm sure these will be well compressed, I still imagine they'll need high data rates. For that, you need big storage.
"Never underestimate the bandwidth of a station wagon full of tapes hurtling down the highway."
-- Andrew S. Tanenbaum
sure, you save space by stacking bits on top of each other -- but the way i figure, you lose stability because they're that much more likely to topple over, leaving your poor bits scattered all over the place.
- rabs
Think of matchsticks flat on the floor and standing up. The ones standing up will be further apart, or you could pack more in the same floor area and have them the same distance apart.
The difficulty is, matchsticks have an easily distinguishable top and bottom end, but magnet ends are only distinguishable by the direction of flux. The bottom ends are buried in the media, so there are challenges in writing and reading the data because only one end of the magnet is accessible. Does this help?
Panurge has posted for the last time. Thanks for the positive moderations.
Most Web links seem rather heavy on the physics side, but this was good for me:
DSI Media & Materials research group article on perpendicular recording.Anssi Porttikivi / app@iki.fi
... will it go into a domino-like cascade?
Perhaps they could design the bits so they're like weebles... they wobble, but they never fall down!
8==8 Bones 8==8
Reminds me a lot of cheap, flat-screen televisions to hang on your wall that have been prophesized as being only being five years away for at least the last two decades. Even now the ones we have are certainly not cheap yet.
Please wake me when both arrive, and quit bothering me until then.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Never underestimate the bandwidth of a station wagon full of quarter-inch tapes. Or a US postal truck leaving NetFlix's warehouse.
Well, in my experience, engineers only like to brag about a new technique if it gives a 10x improvement. (Or more.) If you read the article, you would have noticed some numbers:
:)
:)
The "brick wall" in magnetic recording is called the superparamagnetic effect. This is the point at which the recorded data starts to get lost in the thermal noise of the media. (As you approach the superparamagnetic, it becomes statistically likely for recorded bits to sporadically flip states resulting in data corruption.)
For longitudinal recording technology, it is estimated that superparamagnetic will start to become a problem around 100Gbits/square inch recording density. (Current hard drive technology is around 50Gbits/square inch - so they are getting close to the wall.)
Perpendicular recording technology is estimate to scale up to around 1Tbit/square inch.
Now, what did I say about engineers liking to brag about 10x improvements? Well, 1Tbit is about 10x improvement over 100Gbit. How about that!
What this means to you: if current hard drives store about 120GB using a recording density of about 50Gbit/square inch, then we can expect perpendicular recording to eventually deliver drives that store about 2.4TB extrapolating up to a 1Tbit/square inch. Even if this technology only works half as good, at least we will eventually have hard drives that store 1TB!
On top of that, the article say they are moving away from 3.5" drives toward 2.5" even for "enterprise" applications. Now, if we get 1TB drives in 2.5" form factor that's going to result in some killer MP3^^err...uncompressed 24bit, 192kHz iPods
I was quite surprised to see this article, because I thought of it a couple of years ago, and to be honest, I assumed they already did it! It seemed so logical to me that I thought someone was bound to have thought of it already, and that all drives were like that. Maybe I should have patented it :)
From what I have seen, the problem has been intercepting enough magnetic flux to recover enough signal to get a decent signal-to-noise ratio. If you have "access" to both sides of the magnetized domain, its much simpler to design your read/write head to detect/magnetize signal differentially from one side of the head to the other. Differential signals are much easier to recover the signal from than single-ended signals, as by its very nature, differential signals give you a reference to compare your signal against. That is you only worry about is A greater than B or is A less than B, you really don't care if both A and B are riding on a substantial amount of common-mode noise. There is a very common electronic circuit, known as the "differential amplifier" which is used for this sort of thing. It doesn't much care if the voltage levels of A and B have a lot of common "noise" on them, it only pays attention to the signal on A referenced to signal B.
So, as the two ends of your "pickup coil" in the read head passes over the magnetic domain areas "A" and "B" on the disk simultaneously, you get a clean signal.
Now the problem if the magnetic domains are vertical - you only have access to the surface. You can't really expect to get to the other magnetic pole to reference your read signal to. So its single ended. Now, you have the problem of trying to identify what is signal and what to reject as noise. You have nothing to compare your recovered signal to.
When trying to read a vertically-recorded magnetic domain, you no longer have the luxury of referencing it to the opposite pole of the magnetic domain of that particular bit. You can't get to it. Its against the physical disk platter. You can't get the other head pole in there to "look" at it.
I hope you get modded back off the noise floor - I would have tried, but that meant I would not be able to post... and hence unable to answer what I considered to be a perfectly legit question.
"Prove all things; hold fast that which is good." [KJV: I Thessalonians 5:21]
"Nanotube based RAM, under development by Nantero, promises to deliver densities of over 1 terabit per cm^2, is non-volatile and faster than current DRAM. The Economist has a nice story. Forget about just kicking DRAM's and FLASH's butt, is this finally the end of magnetic storage as well?"
If they can get this down in price then I guess 20 years of trying to get this new perpendicular recording was just a waste. I'm not going to hold my breath but frankly I think it's high time to get into solid state storage and eliminate once and for all the wrost speed bottleneck on the pc.
PlaY tried it. Remember them? They had a really neat technology - not bigger than CD but much, much smaller. It was self contained so you could toss a dozen in your pocket like coins. It was actually this close to being a killer technology, then they got too close to the RIAA and DRM'd themselves out of existence.
Hard drives are decent enough backup. They're now cheap enough to justify keeping a second drive just to duplicate everything on the first. But copying even 80Gb of data still takes damn forever, especially if the drives are in different boxes (I mean, if you're going to make a backup, you do want that backup protected in case of a power suply glitch... right?)
But a pocket full of sealed discs is a lot more convenient and error resistant than a case of CDs. Then again, the next generation commodity RAM is supposed to be magnetic, so maybe we'll finally get that convenient, portable storage in the form of actual solid state "coins!"
Vertical disk writing goes from
:
-------
to
|||||||
which is really (you must isolate + from -)
+--++-+-+--+-+
(H string of -+ and +- bits)
to
+-+++--
-+---++
(V string )
which is a 2x increase.
am I right ?
Although the solution proposed in the article would increase storage capacity by, say, a factor 2 or 4, it still is a temporary solution that does not solve the fundamental problem at hand.
The fundamental problem is the superparamagnetic limit: if you make a magnetic domain (a bit) smaller than a certain size, it becomes thermodynamically unstable. In English, this means that very small bits loose their value after a while. It also means that for the time being, we'll have to use tricks to pack the bits closer together while keeping them large enough to be stable.
It should be noted that perpendicular recording is not the only effort to achieve higher recording densities in the looming shadow of the superparamagnetic limit. Indeed, harddrive manufacturers have seen this problem coming for a number of years now, and have had meeting to discuss possible solutions.
On a brighter note, there seems to be progress in circumventing the superparamagnetic limit: very recent research show promising results for the future.
Support a Europe-related section on Slashdot!
I guess you don't like that...
Hmmm... Pie...
I thought legitimate content was a myth.
The snow doesn't give a soft white damn whom it touches. -- ee cummings
Perpendicular recording will replace longitudinal recording in storage devices, placing bits on end instead of lying them parallel on the disc surface
Okay, yes, I've read the description of how "placing bits on end" works, and it even makes some sense.
This immediately makes me think of dominoes. But I still can't get the image out of my head of some computer entity trying to set up these "bits on end" like dominoes on a hard drive like some French guy on the old TV show That's Incredible! filling a gymnasium floor with 30,000 dominoes to break the world record
"Suddenly, Pierre makes one small mistake and his work for the last week all goes tumbling away"
Gives a new image to a hard drive crash as well.
BTW, no I do not know how many dominoes it actually was, and generally do not care, and I do not know that the guy was French or named Pierre. But devoting you life to breaking the dominoes world record does seem like the kind of thing that only a French guy named Pierre would do. Summary-If you are offended by me not knowing the details of obscure info such as who holds the record for dominoes instead be offended by my stereotyping of dominoes type people and the French.
---"What did I say that sounded like 'Tell me about your day?'"---
placing bits on end instead of lying them parallel on the disc surface
This one threw me off. Is the use of "lie" instead of "lay" due to low literacy, or does it mean that the data will be inverted - "lies", so to speak? The article doesn't mention encoding.
If I can't download anymore mp3s why do I need more storage?
"It's so convenient to have a system where everyone is a criminal" - A. Hitler
They keep talking about how the new serial interfaces are going to bring huge performance increases. To this I have to say BS!!
Ok.. So ATA is going to go from 100MB/s shared by two devices (PATA) to 150MB/s for a single device (SATA) and SCSI is going from 320MB/s for up to 15 devices to 300MB/s for a single device. Big whoop! I wan't to see a device that will actually make these improvements really noticable. Hard drives don't come anywhere close to that kind of throughput.
Until some major changes come to the HDD world, we'll only see minor increases in performance when dealing with storage devices. The main thing I'm looking forward to with SATA is that there won't be any more problems with having two devices trying to use the same channel at the same time (like trying to burn a CD from a CD or HDD on the same channel) since it isn't shared anymore.
End of line..
I always wondered why drives use discrete heads moved around on an arm.
If a "stationary bridge" was positioned radially over the platter, and a large number of discrete r/w unitswere placed on the underside of the bridge (1 per physical track) any sector could be read by electrically selecting the appropriate r/w unit and waiting until the data spun under it.
Seek time becomes purely a funtion of the RPM of the platter. Moving parts are reduced. Speed could even be further improved by arranging blocks of data to be stored as a single or small gorup of bits on each track, in the same radial location, and reading the entire block in parrallel.
I suppose that in order for this to be feasible, the r/w bridge would need to be fabricated by etching silicon.
Historical Note: This "new" recording technique is the same one that failed to take hold in 2.88M EHD floppy disks about 15 years ago. Back then the new recording material was barium ferrite, whose magnetic domains arrange themselves vertically with respect to the substrate.
Compared to ordinary floppy disks with horizontal magnetic domains, this technology had the potential of increasing data densities by as much as 2-3 orders of magnitude. Unfortunately, the new disks were expensive and not compatible with the huge installed base of 1.44M drives. EHD drives required BIOS changes that weren't possible in those non-FlashBIOS days. Even if those problems could have been solved, IOMEGA's Zip drives were offering far more bang for the buck.
Of course, none of this would matter for hard drives.
I won't be satisfied until they stop wasting space on drive platters and start recording on the outer edge of the disc!
And, of course, it'll only take about a week to format the thing, and just forget about backups...
Wait for it
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
Your comment has too few characters per line (currently 1.7).
The Perpindecular Port!
"Reality is that which, when you stop believing in it, it doesn't go away." - Philip K. Dick
I would hate to see their libraries.
I am the Alpha and the Omega-3
Oh, so they are going to use the old sony 2.88 MB floppy tech. For this. Wasn't perp. recording patented or something which killed it so long ago? Props to those of you lucky enough to find a 2.88M floppy drive.
If you look at a 1 or a 0 from the side, they're pretty big. But if you look at a 1 or a 0 from the top, they're a lot smaller! I guess a 1 will look like a dot, and a 0 will look like a line. That must be pretty easy to do, right? Pure genius!
The rotational speed of the drive is directly related to the access time. If the data you want is on the other side of the platter, you must wait for it to rotate 180 degrees before you can start reading, regardless of whether the disc is 1/2" in diameter or 2" diameter, whether there are 1GB per square inch or 10GB per square inch.
When the head gets lined up with the track and ready to read, the data it's waiting for can be anywhere between 0 degrees and 360 degrees away. If you average out all those possibilities, you can expect the data to be about 180 degrees away.
Now, a 15000 rpm drive rotates 180 degrees 30000 times per minute. Conversely, it takes 2ms to rotate 180 degrees. If you consider that a typical 15k rpm drive has an average seek time of 3.3ms and we know that 2ms are spent waiting for the disk to spin, than 1.3ms must be spent moving the head. This proves to me that rotational speed is more important to access time than data density.
I'm no hard drive engineer, but I would bet that an increase in density would mean a decrease for rotational speed since a read head probably has a limited bandwidth. (This is probably why the faster-spinning drives typically hold less data.) If you halve the time moving the head while doubling the time waiting for spinning data, you will see an overall increase in seek time.
My conclusion is that greater density and less rpms would hurt access time which is the most important performance factor. However, like the "MHz myth", I'm sure marketing will focus on bandwidth benchmarks for performance instead of real-life application performance.
So what is the difference between disinterested and uninterested? :-p
No, seriously, Webster was no help whatsoever.
So, a top view of the old scheme would look like:
::::::::
::::::::
..1....0....1....1....0..
||||||||
||||||||
The new scheme, from the top:
In this case 2x density, as the lower one has twice as many dots in the same area as the dashes of the upper.
I don't think that's quite right.
Unless I missed a transition from longitudinal to transverse recording, the old scheme produced a track like this (viewed either from the top or side:)
N---SS---NN--------SS---N
The vertical scheme lays the magnets INTO the medium rather than ALONG the track. Viewed from the side:
NSNNS
|||||
SNSSN
10110
Or, viewed from the top:
NSNNS
The problem with longitudinal recording is that, as you make the bits shorter, the magnetic fields of adjacent opposite-sense bits become more effective at trying to flip the singleton to go along with them. (Magnetic domains are more self-reenforcing, and thus stable, when they're long and thin, subject to flipping from thermal agitation at progressively lower temperatures as they become more short and fat.)
Make the bit too short and the neighbors "squeeze it out":
N--SSNN--S -> N--------S
1.1.0.1.1. -> 1.1.1.1.1.
But with vertical recording the adjacent, opposite-sense neighbors tend to STABILIZE the bit, and the smaller it gets, the more stable it gets. (And you're guaranteed a limit on the number of long runs of same-sense by the coding scheme, which has to flip now and then to keep the read electronics in sync.)
So you can shrink it WAY down - both along the track and across it - to the limit of the head technology to produce the original magnitizing field or the inherent domain size of the magnetic medium.
You can get FAR more than a factor of two in EACH direction - and multiply the two improvements to get the increase in bits per unit area.
(They've been talking about this for years. How come it's just hitting the field now? Did they go to transverse magnetization in the meantime? That would have similar advantages of smaller-is-more-stable. But the track would be far wider than with vertical, as would the gap, so you'd still save a bunch in one of the dimensions by standing the magnets on their head and packing them in tightly, like a bundle of sticks, rather than laying them on their sides.)
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
Suppose you have 10^11 brain cells (common estimate). There are (10^11-1)*(10^11-2)/2 = 5*10^21 possible links between different neurons. A link is either there, or not there. Therefore, a link could correspond to a bit, therefore the capacity would be about 5 billion terabits. How many possible brain configurations are there? Well, there's 5 billion trillion bits, therefore there are 2^(5 billion trillion) possible brains -- a number somewhere near 2*10^1505149978.
But of course, that estimate is just as bogus as the 1Tbit estimate, since nobody really knows how the brain stores data. But it's fun to calculate huge numbers :-)
I keep seeing people say that today's hard drives are pleanty big enough. You will fill up any drive you're given.
I had a 3.2 gb drive. It was pleanty. Then i installed some apps and it filled up so i upgraded to a 13.6 gb hdd. It was huge. I couldn't imagine ever filling it up. Then p2p came out. It filled up so i bought a 40 gb drive. Well, i knew i couldn't ever fill this up. Then p2p became good. I just got a 200 gb hdd. As i sit here configuring mythtv i know i'll need another hard drive at some point even if this one is only 25% full and i have another 56.8 gigs of empty, older hdds.
Firewire isn't popular outside consumer gear (and not really that much even there) in part because those who understand it don't trust it, and those who don't understand it don't see a need for it.
Until this nonsense with hardware makers locking up specs on commodity chips because they fear regulatory reprisals, I (and, I suspect most) will happily embrace incremental upgrades to legacy standards that don't provide yet more opportunities for the parasites in the valley to dictate how we may use our own machines.
Yeah. Or PowerQuest Drive Image. Both work fine for me.
The higher the technology, the sharper that two-edged sword.
It's not just speed that makes it important to shrink the drive technology. Just like it's cheaper to produce 3.5" drives than 5.25" drives, it's cheaper to produce 2.5" than 3.5" (assuming the same volume). Less raw materials, less machining, cheaper shipping, storage, etc. Eventually the added expense of manufacturing on the smaller scale get's reduced to the point where it makes sense. It is inevitible that we will end up with 2.5" harddrives in desktops and servers. Smaller devices are often easier to make more reliable and durable (drop a matchbox car and a real car from 6 feet up onto it's roof and see which one is cheaper to repair)
Storage system scalability is another reason to reduce the form factor of the drives. You can fit a lot more 2.5" drives in 1U than 3.5".
set softtabstop=4 shiftwidth=4 expandtab nocp worlddomination
For over 25 years we have wanted to evolve into
something better. This technology can only offer
a small degree of storage capacity increase and
we are still faced with the same para magnetic
obsolescence.
Take a pencil and fit 20 pencils vertical to the
one horizaontal.
Well there is only one problem with vertical and
that is the data bits like the maxed horizontal
data bits are hard to tell apart, margin code.
Its unfortunate but the magnetic road map is
going to collapse whether it goes horizontal
or vertical in the next few years.
I have seen transparent magnetic concepts on
Scientific America and Physics Org for writing
data, but I have yet to see one concept on how
to read data on future magnetics.
We need to look at optical nanotechnology like
the Japanese, Taiwanese, Chinese, Koreans, and
Europeans before its too late like Read Rite.
i love it, when people make fools of themselves... :)
the computer is online
i am not at it
what a waste of ressources
how do you define data in a human brain?
i could imagine, that -converted to digital data- just reading this stupid comment, produced 1Tbit of data...
think about the whole sensoric data from your eyes, the deep database access produced by your interpretation of individual patterns (read: letters) and following the endless ramifications, spreading through completely unrelated structures, changing your overall state of mind (read: anger rising)... you can't fill that in 1 TBit of data...
no, sir.
the computer is online
i am not at it
what a waste of ressources
Personally, I've used the Promise FastTrak line of cards for a few years now and have never had a problem with them. The cards are pretty cheap (under US$100), have good drivers, and perform very well (12Mb/sec on an ATA/100 mirror). Much better then software RAID solutions that I've tried in the past.
Wolde you bothe eate your cake, and have your cake?
Also there are multiple levels of quality, the higher levels of quality are almost lossless and file sizes are much smaller.
Hmmm... Pie...
HMMM I wonder if Morse could be used to store messages and use peanut sized segments of storage space. Would be neat if a teX like interpretor program could be developed to save files as 1s and zeros directly then use an interpretor to read and display the output. Problem is this new horse code could turn ham radio users into hackers. A new separator charater would need to be defined but the system would be fun if you could enter messages without a keyboard using simple usb mouse like based morse code key with a thumb switch activated separator. So you could have a little Morse with your mouse! What would be really great is if this idea could be then legally used on the shortwave ham band, with some software to do text messaging on cheap home computers. Someone is bound to have thought of this but, real time text messaging in Morse on the ham band sounds like fun. -.-., --.- etc? The spin off might be even smaller sized text files. Making huge harddrives good for things like uncompressed wave files. Then hard storage mediums like compact flash would be adequate for holding enormous amounts of simple text in new horse code files.
OH THE SHAME I fell off the wagon and use sigs again!
Believe me, they don't "get-it"... They operate on a completely different rationale as the western world. Basically, the reason many Japanese use the technically best technologies is because the majority of the population go buy all the new gadgets when the come out, no matter if they can use them or not. That is why it is not uncommon that the Japanese public will usually have multiple console game systems in each home. Anyhow..
Well, I'm a heavy MiniDisc user myself, but partially because I was seriously into recording and editing, and it was when consumer CD-Burners were just comming into existance. These days, I'm rather anxious to drop the format to tell you the truth. The incorporated copy protection means I can only make one digital copy of my Discs, then I'm out of luck, unless I want to start breaking the law...
Using computers for audio more and more means MiniDisc is at a disadvantage to every other audio technology, since I have to record in real-time. I know that NetMDs are out there, but I don't use Windows in the first place, so I'm out of luck, and even if I did, the inability to edit the music once recorded to MD from computer would be a dig disadvantage, as would the inability to copy the file off to any other computer. Certainly,I like the caddy, and how inexpensive the media is (compared to CompactFlash) but the restrictions on use are making me cringe. I'll buy the first Vorbis MiniCD-player made (and use MiniCD-Rs). Even the battery life isn't worth the restrictions.
I think it will happen. Once people see that slightly more expensive cartridge media can hold many times the data as the slightly less expensive bare discs, the tide will turn. Unfortunately, I don't see it happening until the capacities are different.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant