Slashdot Mirror


New Technique Promises Much Faster Hard Drive Write Speeds

MrSeb writes "Hold onto your hats: Scientists at the University of York, England have completely rewritten the rules of magnetic storage (abstract; full paper paywalled). Instead of switching a magnetic region using a magnetic field (like a hard drive head), the researchers have managed to switch a ferrimagnetic nanoisland using a 60-femtosecond laser. Storing magnetic data using lasers is up to 1,000 times faster than writing to a conventional hard drive (we're talking about gigabytes or terabytes per second) — and the ferrimagnetic nanoislands that store the data are capable of storage densities that are some 15 times greater than existing hard drive platters. Unfortunately the York scientists only detailed writing data with lasers; there's no word on how to read it."

148 comments

  1. write only media FTW! by Anonymous Coward · · Score: 5, Funny

    Who needs to read data back anyway?

    1. Re:write only media FTW! by NoNonAlphaCharsHere · · Score: 4, Funny

      But that means we have to use Perl!

    2. Re:write only media FTW! by Robert+Zenz · · Score: 4, Funny

      Absolutely true! I store all customer user-accounts in /dev/null to save diskspace (the compression of that device is awesome!)...so far nobody complained.

    3. Re:write only media FTW! by datapharmer · · Score: 1

      psshhht if you don't need to read it back my /dev/null tech can beat the pants off your laser nanoisland tech any day.

      --
      Get a web developer
    4. Re:write only media FTW! by Anonymous Coward · · Score: 0

      That was invented back in the 1970s...

    5. Re:write only media FTW! by The+MAZZTer · · Score: 5, Funny

      Let me guess... you set up customer complaints to get filed in /dev/null too?

    6. Re:write only media FTW! by idontusenumbers · · Score: 1

      Just leave it to future generations to solve the problem of reading archived data. It's like climate change.

    7. Re:write only media FTW! by rrohbeck · · Score: 1

      In large disk subsystems used for archival, the assumption is generally that >90% of the data is never read back. That's why they're heavily write-optimized.
      Now if we could determine which data isn't needed any more, we could store it on /dev/null.

    8. Re:write only media FTW! by greenreaper · · Score: 4, Funny

      No, but you have to login to file a complaint.

    9. Re:write only media FTW! by Anonymous Coward · · Score: 1

      This sounds like Write-Only-Memory or "WOM", which was developed by Signetics back in the early 70's. Datasheet is here: http://www.national.com/rap/files/datasheet.pdf.

      How is this new technology?

    10. Re:write only media FTW! by hawguy · · Score: 1

      In large disk subsystems used for archival, the assumption is generally that >90% of the data is never read back. That's why they're heavily write-optimized.
      Now if we could determine which data isn't needed any more, we could store it on /dev/null.

      I once worked at a place that had a hierarchical storage system that did pretty much just that -- little used data was migrated off of expensive disks to tape. However, due to a a flaw in the tape drive or the tapes themselves, over time the data became unreadable, leaving much of the data that was migrated off of disk unreadable. Most of it was recovered from backups (which fortunately used a completely different tape system).

      Do companies still use HSM that moves data to tape or is everyone using cheap SATA disks for "cheap" storage now?

    11. Re:write only media FTW! by rrohbeck · · Score: 1

      Both. I used to do tape but I'm involved with disk based backup now, with SSDs, 15k SAS drives and 7200rpm SATA. But disk based backup systems get full so you still have to offload old data to tape, hopefully to never touch it again. That means tape better be reliable, it's the last resort. Customer escalations because they can't read their data are no fun. The good thing is that low end tape libraries are dying out - the $5k ones that were bought by customers with clueless IT organizations. Companies that buy $200k+ tape libraries usually know what they're doing.

  2. So how do they know if they actually wrote it by Anonymous Coward · · Score: 2, Interesting

    If they can't read it, how do they know if they actually wrote it? Or maybe reading it is 10,000 times slower than current read technology.

    1. Re:So how do they know if they actually wrote it by TheRaven64 · · Score: 5, Informative

      It's stored in the same way as a normal hard disk - in ferromagnetic domains on a platter. You can still read it back using the same techniques as current drives (i.e. put a coil over it and see which way the induced current flows), but you then have a drive that you can write to orders of magnitude than you can read from it. I can think of a few places where this might be useful. The most obvious is the underlying storage for something like ZFS. For reliability, you want to flush everything to the backing store as quickly as possible, and with copy-on-write and snapshotting you may never erase it, but most of your reads are satisfied from flash or DRAM caches. A drive using this technology would let you dump data there as quickly as you wanted and would let you read it back for data recovery if you needed to, while in normal operation you wouldn't care about the read speed because reading from the disk is comparatively rare. It would also be useful for a number of scientific applications. I did some work a few years ago with someone building a solar observatory. A single one of their cameras generated 10GB/s of data, and they had 8 cameras in a typical setup. They run these for the entire time that the sun is visible. A single drive that can handle a sustained write speed of 1GB/s would be very useful for them (although they'd fill up several per hour...).

      For consumer devices, random read speed is still the most important factor, and mechanical drives suck at that.

      --
      I am TheRaven on Soylent News
    2. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      "but you then have a drive that you can write to orders of magnitude than you can read from it"

      Nice problem to have.

    3. Re:So how do they know if they actually wrote it by Stonent1 · · Score: 3, Insightful

      I would think that you would still have to read the location of the cluster before writing to it. Sure you can flip magnetic particles N > S or S > N at bazillions per second speed but if you don't know what you're flipping that's not good.

    4. Re:So how do they know if they actually wrote it by Twinbee · · Score: 1

      Which makes me often wonder how people get the motivation to research this kind of stuff. I mean, yes puzzles are often fun in and of themself, but if it were me personally, I'd feel kinda soul-crushed to finalize this tech only to see SSDs and technologies like racetrack memory win in the end. Also, they're presumably being *paid* to research this as well.

      It's not too abstruse to see that solid-state devices are the natural way forward.

      --
      Why OpalCalc is the best Windows calc
    5. Re:So how do they know if they actually wrote it by IWannaBeAnAC · · Score: 1

      Harddrives haven't used coils for a long time. Nowdays they use the GMR effect http://en.wikipedia.org/wiki/Giant_magnetoresistance and in principle the CMR effect could give another few orders of magnitude more sensitivity. That only solves the size problem, it doesn't do much for the speed problem.

    6. Re:So how do they know if they actually wrote it by causeur · · Score: 1

      Sounds like a good fit for updating a warehouse database. Our loads are supposed to occur at night but with increased volumes they often spill over well into daytime.

    7. Re:So how do they know if they actually wrote it by the_B0fh · · Score: 3, Insightful

      Why? If they can write TB/s and store data at 15X of current capacity, and SSDs can't, why move to SSDs?

      The read problem is easily resolved by having multiple read heads that can read independently.

    8. Re:So how do they know if they actually wrote it by sheepe2004 · · Score: 5, Informative

      Nope, that was a few years ago. Now they use TMR http://en.wikipedia.org/wiki/Tunnel_magnetoresistance#Applications .

      --
      http://compsoc.man.ac.uk/~shep/
    9. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      "A single one of their cameras generated 10GB/s of data, and they had 8 cameras in a typical setup. They run these for the entire time that the sun is visible. A single drive that can handle a sustained write speed of 1GB/s would be very useful for them (although they'd fill up several per hour...). "

      10GB/s is 36 Terabytes per hour. That's a 3TB disk every 5 minutes... That must be some specialized hardware to multiplex 10GB/s stream to multiple storage devices. A regular PC couldn't handle that, even with the best RAID controller you can find. You're lucky to find a system that can sustain 10GB/s writing to and 10GB/s reading from (non-cache) memory for buffering...

      If that's a high-framerate camera, at, say 100fps, then that's still 100MB per frame. I haven't heard of a 100Mpixel ccd yet, nor a 66Mpixel (if its 12 bits per pixel)...

      Unless a 'camera' for that system actually consists of multiple CCD's with independent output streams, I think some of your numbers might be off by perhaps an order of magnitude or more. Otherwise, it sounds like a system where you could save some serious dough with a lossless codec...

    10. Re:So how do they know if they actually wrote it by sosume · · Score: 1

      I don't think that when storing such absurd amounts of data as high speed, you're interested in possible fragmentation.

    11. Re:So how do they know if they actually wrote it by sheepe2004 · · Score: 2

      Because the actual research that has been done is fundamental physics. For better or worse news articles always talk up the applications rather than the science.

      --
      http://compsoc.man.ac.uk/~shep/
    12. Re:So how do they know if they actually wrote it by jellomizer · · Score: 1

      Well I could see it useful in more then just a few places. The basic rule of Computer Science is the 80/20 rule. 80% of the Use is on 20% of the data. For the most part we Store far more then we read back. Sounds wasteful? Well it is in a way however not collecting the data will mean 20% of the time you may need to access the other 80% of the data. So it may still be needed, and the 20% of popular data can change over time.

      --
      If something is so important that you feel the need to post it on the internet... It probably isn't that important.
    13. Re:So how do they know if they actually wrote it by LordLimecat · · Score: 1

      Why? If they can write TB/s

      Except that youre still limited by rotational latency and whatnot. Was the magnetic write head ever the main bottleneck?

    14. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      "put a coil over it and see which way the induced current flows"

      LOL, that hasn't been done for decades....

    15. Re:So how do they know if they actually wrote it by Adriax · · Score: 1

      I don't care which way becomes the "best" choice as long as both styles interface through a standardized connector.
      Both sides of chip vs platter will always have their own strengths and weaknesses, I like choice.

      It's very easy to see this becoming the highest cost and highest performance drive of the near future that server admins and performance enthusiasts go to. While the SSD takes over as the PC and small device storage of choice.

      --
      I don't suffer from insanity, I enjoy every minute of it!
    16. Re:So how do they know if they actually wrote it by tibit · · Score: 4, Interesting

      It's time to dust off the old concept of hard sectored discs ;) Realistically, of course, it's a bit more complex than that.

      First of all, modern hard drives have a servo track that's used to maintain radial position of the head servo. Instead of each hard drive having a very accurate (and expensive) radial and axial head position sensor, you pay for it once, install it in the factory, use it to accurately guide a hard drive to write the servo track. Its cost is amortized over thousands of drives made. This is probably the reason for a covered up radial slot in many hard drive enclosures: I guess it's used for the sensor to couple with the head system while the drive writes the servo track. Or perhaps the servo platter is prewritten outside the disc? Someone familiar with how it's made please chip in!

      The servo track can be also used to provide angular position feedback. A rough estimate of angular position of the spindle is available first from the Hall sensors in the spindle motor. A somewhat more accurate estimate can be had from back-EMF from the spindle motor windings. This still is methinks a couple orders of magnitude away from what's needed to pack sectors tightly on the drive -- thus the feedback can come from the servo track. Not having to read the data tracks helps with packing the sectors: there's no read-write switchover overhead (if it were significant -- perhaps it isn't nowadays). The servo head is always reading, and the data heads can be kept in write/erase standby. It'd be nondestructive, but read amplifiers are disconnected to prevent saturating them -- amplifier overload recovery is slow. Heck, if you want an amp that recovers from overloads quickly, you have to split it into more stages, and you need fast clamps between each stage. There are other similar approaches to this problem, too, and perhaps modern read amps are designed to deal with overloads gracefully -- I never tested a recent one. Stuff from a decade ago was painfully slow on overloads (tried to reuse a head amp from a hard drive for a non-drive-related project).

      Alas, this ultra-fast-writing drive would unfortunately need very accurate position sensors -- both angular and radial. It's an engineering issue to make those affordable, as is the design of the optochip with femtosecond laser and its driver and serializer. The latter would probably take a couple serial lanes and multiplex them -- I presume it's not all that easy to push 10gbit/s data between external chips and the laser driver/laser combo. I think that to make it all practical you need an on-chip serializer, write precompensation, driver, and the diode. Perhaps the diode would be "tacked on" later to a substrate that has everything else. I only imagine that bond wire parasitics, even over a couple mm, become kinda important when the laser waveform has a 100GHz bandwidth...

      --
      A successful API design takes a mixture of software design and pedagogy.
    17. Re:So how do they know if they actually wrote it by rrohbeck · · Score: 1

      You don't know if you actually wrote successfully on today's disk drives either.

    18. Re:So how do they know if they actually wrote it by awfar · · Score: 1

      As I understand, if you can accurately write such a smaller magnetic domain with a laser vs. the relatively large area under a write head, you obviously increase the data density. And since higher and more focused energy to flip the domains can now be applied, lessening the problem of flipping their neighbors, this probably means smaller particle and higher coercivity media can be used or developed. This also implies that the tracks get smaller and reduces or eliminates guard areas and tracks. All of which increases the data density. And as a bonus the data rate on read back would also be much faster, even without increasing rotational speed, since the data density has been increased.

    19. Re:So how do they know if they actually wrote it by mike260 · · Score: 2

      Was the magnetic write head ever the main bottleneck?

      Maybe not the 'main' bottleneck, but it depends on the application, no? Seems to me there are at least a few firehose situations where you can never have enough write bandwidth (say, uncompressed video-capture).

      Maybe normal workloads on normal filesystems wouldn't see much improvement, but I bet you could find ways to capitalise on the extra bandwidth and space. Log-structured filesystems spring to mind for one.

    20. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      Yes, because there's only 1 head per platter, they should have long ago made multiple rails over each side with a slide/shifting multi head setup.

    21. Re:So how do they know if they actually wrote it by ninjackn · · Score: 1

      Except multiple read heads does not solve the slow hard drive read speed and is not easy. You're still limited by rotational latency and especially by how fast the actuator can move the head. That read head is physically limited. If you make it go any faster the acceleration force will break it, if you make the support arm bigger and sturdier you have the same problem. It's mass went up and now it's harder to accelerate it. Use a better material? I don't know of any better material and the ones that you can think of are probably magnitudes more expensive.

      Even if you're okay with not improving the read head and slap 3 more read heads to a platter that's only a 4x performance gain. Now how much more complex is the system? How much more expensive is the system? At that point it's just cheaper to have 4 separate hard drives... which is what we do. The multiple head with independent read is already solved and implemented by RAID.

      --
      [FUCK BETA 2.6.2014]
    22. Re:So how do they know if they actually wrote it by Burning1 · · Score: 1

      Maybe not the 'main' bottleneck, but it depends on the application, no? Seems to me there are at least a few firehose situations where you can never have enough write bandwidth (say, uncompressed video-capture).

      Centralized backup, especially of large data-stores. You have to write massive amounts of data on a regular basis, but rarely read the data, and when you do you usually only need a small subset of what's been written. I could imagine it being useful for certain kinds of RAID configurations and network filers as well.

    23. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      >The read problem is easily resolved by having multiple read heads that can read independently.

      The pain is reduced somewhat by multiple read heads but still doesn't touch decent modern SSDs in read performance.

    24. Re:So how do they know if they actually wrote it by Anonymous Coward · · Score: 0

      Yes and no - it is stored the same way, but if the density is 15x higher then wouldn't a considerable increase in the reading technology also be required to make use of that density? Same technology? Yes. But same degree of development of that tech? Not so much...

  3. At last! by undulato · · Score: 5, Funny

    A future-proof storage medium.

    1. Re:At last! by Anonymous Coward · · Score: 0

      Are they really future-proof if they've still got rapidly moving parts, or will they just wear out and break as usual?

  4. omg by Anonymous Coward · · Score: 4, Funny

    frickin hard drives with laser beams!

    1. Re:omg by Anonymous Coward · · Score: 0

      ...attached to their heads.

    2. Re:omg by Ihmhi · · Score: 5, Funny

      1) Western Digital licenses this technology.

      2) WD releases a new model, the WD Shark. A "Now with LASERs!" starburst graphic adorns the front of the box.

      3) Profit!

    3. Re:omg by poetmatt · · Score: 1

      You mean like, I don't know.....cd roms as hard drives? or DVD's? or Laserdisc?

    4. Re:omg by Brad1138 · · Score: 1

      inside.. joke... overload.....

      --
      If you could reason with religious people, there would be no religious people
    5. Re:omg by pscottdv · · Score: 1

      No, the data is not stored in a magnetic domain on an optical disk.

      --

      this signature has been removed due to a DMCA takedown notice

    6. Re:omg by the_B0fh · · Score: 1

      why go so far? magneto opticals work too

    7. Re:omg by jones_supa · · Score: 2

      Sharks could also swim their way out of flooded manufacturing plants.

    8. Re:omg by Ihmhi · · Score: 1

      They could make a thumb drive using a miniature hard drive and call it the Sharktooth.

      ...okay WD, cut me a check already, would you?

    9. Re:omg by treeves · · Score: 1

      2a) And a warning sticker on the back that says "Do not look into hard drive with remaining eye."

      --
      ...the future crusty old bastards are already drinking the Kool-Aid.
    10. Re:omg by Anonymous Coward · · Score: 0

      You missed:

      3) ???

      4) Profit!

  5. Memory Hole by mdsolar · · Score: 1

    Just got wider.

    1. Re:Memory Hole by GodfatherofSoul · · Score: 3, Funny

      Goatse Drive technology?

      --
      I swear to God...I swear to God! That is NOT how you treat your human!
  6. Write speeds, I guess they should read ... by Anonymous Coward · · Score: 0

    I would certainly guess that the technology would allow for reading, if not at top speed, but at least significantly faster read times than the current technology. If it can write, stands to reason that the laser can read... do we not already have reading lasers in use in various technologies?

    1. Re:Write speeds, I guess they should read ... by SJHillman · · Score: 1

      Lasers are currently used in reading optical media like CDs and DVDs... this is magnetic media

    2. Re:Write speeds, I guess they should read ... by DigiShaman · · Score: 1

      But how would you write the data with lasers? Current optical drives use a mechanical tracking system. Perhaps some form of piezoelectric oscillating mirror would be preferred?

      --
      Life is not for the lazy.
    3. Re:Write speeds, I guess they should read ... by SJHillman · · Score: 1

      In the case of magnetic media, lasers write by literally burning sections of the disc and read by reading the reflections from burnt/unburnt sections to get bits (commercially pressed discs have bumps instead of burned sections, but are read in much the same manner). From what I recall, CD burners are separate lasers for burning and reading. Optical media just happens to use lasers for both reading and writing, but they're two different lasers (assuming I remember correctly).

      I'm guessing here, but I'm assuming for magnetic media, the energy from the laser targets the magnetic bit and causes it to flip in a similar manner to how CDs are burnt, but because its magnetic, lasers can't also be used to read it so you'd need a traditional magnetic head.

  7. i can beat that by Anonymous Coward · · Score: 0

    At one time I had designed a backup storage system that could handle backing up PBs of data in only a few seconds -- and it's capacity was endless, and it was free for anyone to use.

    Restore? You want to restore? Let me introduce you to my price list. :-)

  8. Yay! if they figure out 2 read da stuff, we'r gold by youn · · Score: 0

    writing the cute useless powerpoint presentations that waste so much everyone's time will be done 1000 times faster, so will downloading swimsuit pictures (minus the swimsuit for some :) )

    awesome, we're gonna be able to waste time so much faster haha

    --
    Never antropomorphize computers, they do not like that :p
  9. Implied Read? by Anonymous Coward · · Score: 1

    How can scientists know the write was successful without being able to read back as well...surely there is an in implied read in the mix, otherwise the discovery isn't worth the paper it is written on!

    1. Re:Implied Read? by wagnerrp · · Score: 1

      They can read the content in their laboratory test samples. They just don't know how to read the content when its spun up to several thousand RPM.

  10. Who cares about reading? by rjejr · · Score: 5, Insightful

    Considering how often I back stuff up, but how rarely I ever use those backups, I'll gladly take 1,000 times faster backups even if it means slower read speeds than we have now. Really, I'ld take that trade-off in a heartbeat.

    1. Re:Who cares about reading? by Anonymous Coward · · Score: 3, Insightful

      You can only write as fast as data can be read so your backups will not be 1,000 times faster.

    2. Re:Who cares about reading? by Anonymous Coward · · Score: 0

      Really? Backups are no use unless you test, i.e., read-verify, them (once in a while)!

    3. Re:Who cares about reading? by CAIMLAS · · Score: 1

      You say that until you've got to be at the office until 3am waiting for a backup to restore for DR.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
  11. Promises, Promises by na1led · · Score: 2

    If I remember correctly, several years ago they said a 500 Terabyte Drive would be comming out soon, never happend.

    --
    -- By all means let's be open-minded, but not so open-minded that our brains drop out.
    1. Re:Promises, Promises by Anonymous Coward · · Score: 1

      Yet.

      If capacity doubles every 2 years, 500TB should be available in (math.log(500./3)/math.log(2)) 7.3808217839409318 years.

  12. Oh hey! This looks fascinating! by DC2088 · · Score: 1

    I think I'll - $32?! Jeezus, if I was still a student I'd be set..

    1. Re:Oh hey! This looks fascinating! by Anonymous Coward · · Score: 0, Offtopic

      There's something inherently wrong about this statement:

      Personal Customers
      Nature Communications is not available through a personal subscription. Personal customers can purchase individual articles (that are not already open access) on an article by article basis.

  13. Now... by larys · · Score: 1

    we just need fiber optic internet connections to become standard enough so we can put all that fast reading and writing to use! ;)

    1. Re:Now... by Yvan256 · · Score: 1

      My current ISP still thinks I'm using MFM drives.

    2. Re:Now... by kanweg · · Score: 1

      That's because of the type of pictures you download?

      Bert

    3. Re:Now... by Yvan256 · · Score: 1

      Not, it's because it's a 5 megabits per second cable modem.

      You can drop your nerd card in the little box on the way out.

    4. Re:Now... by Dishevel · · Score: 1

      I love ASCII art pr0n!

      --
      Why is it so hard to only have politicians for a few years, then have them go away?
    5. Re:Now... by larys · · Score: 2

      Yeah, sure...it's all fun and good until word wrap is set but the window of Notepad isn't stretched to the right width and all of a sudden some otherwise beautiful woman is wearing her own breast as a hat...

    6. Re:Now... by Anonymous Coward · · Score: 0

      Nah,that's just old-lady porn.

  14. To read it, you say? by Anonymous Coward · · Score: 0

    Would one of those Blu-Ray reader lenses work? Or does it need to be smaller than that?

    1. Re:To read it, you say? by linuxgeek64 · · Score: 2

      Blu-Ray is an optical medium. Hard drives are magnetic. The use of lasers in writing is unusual. They use the lasers to flip magnetic bits. The lasers can't simply be shined onto a bit and then have light deflected in one of two directions depending on the data stored.

    2. Re:To read it, you say? by Anonymous Coward · · Score: 0

      And a miniature magnetometer wouldn't work either?

    3. Re:To read it, you say? by wagnerrp · · Score: 1

      The difficulty is getting one sensitive enough to handle bits a tiny fraction the size current hard drives use, and sufficiently high speed to do it on a platter spinning at several thousand RPM.

  15. No Encryption required! by bobbied · · Score: 1

    No way to read these things? Wow, Who needs encryption now... (Ok.. Ok.. Just write your data to /dev/null...)

    --
    "File to fit, pound to insert, paint to match" - Aircraft Maintenance 101
  16. hmmm by Anonymous Coward · · Score: 0

    How do they know that they wrote it if they can't read it?

  17. Good news everyone! by Yvan256 · · Score: 3, Insightful

    If they can read it at least as fast as today's technologies, the power required to read/write data is roughly the same as today's drives and the manufacturing cost is also about the same, this is good news for everyone:

    1. On the consumer side, cheaper drives per terabyte meaning cheaper home media servers
    2. On the commercial side, a lot less energy required, i.e. no need for ultra-fast 15k RPM drives in servers, need up to 15 times fewer drives in server farms. This is BIG.

    There is only one problem.

    1. Re:Good news everyone! by LWATCDR · · Score: 1

      "2. On the commercial side, a lot less energy required, i.e. no need for ultra-fast 15k RPM drives in servers, need up to 15 times fewer drives in server farms. This is BIG."
      Probably not. Spindles == speed and redundancy. If you are looking at a data warehousing situation then maybe but if you are dealing with a lot of transactions you will still want as many spindles as you can afford.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    2. Re:Good news everyone! by HockeyPuck · · Score: 2

      We have 15k RPM drives because we need to move the sector to which we want to read/write at quicker to the actuator head. The slowest point isn't the transfer of data from head to platter, but a) moving the actuator arm and b) waiting for the correct sector to come around.

      I'm not sure how much performance benefit using lasers could help since access time (moving the mechanical arm) is still on the order of ms.

    3. Re:Good news everyone! by wagnerrp · · Score: 1

      Exactly. 15k RPM drives tended to be small diameter for structural reasons and to allow a shorter arm stroke. As a consequence, their linear velocity, and thus sequential throughput, was not all that much better than for 3.5" 7.2k RPM drives. The only reason to pay for their extremely high cost per GB was for low latency operations. For low latency operations, you're so much better off just buying SSDs. That's a disadvantage that rotating storage will simply never overcome. This technology will only see usage in bulk archival storage.

  18. um... by Killerfishmonkey · · Score: 0

    If they can't read it.. how do they know they have written data?..

  19. Re:Yay! if they figure out 2 read da stuff, we'r g by linuxgeek64 · · Score: 1

    Those two activities are generally not limited by disk access speed.

  20. Pay wall by Skapare · · Score: 1

    If it's paywalled, it didn't happen!

    --
    now we need to go OSS in diesel cars
  21. Amphibious storage by Hognoxious · · Score: 1

    As an added bonus the factory can continue to operate even if it's flooded [//to do: insert conspiracy theory here] as the lasers can then be attached to sharks.

    --
    Confucius say, "Find worm in apple - bad. Find half a worm - worse."
  22. This sounds like Perl by fredan · · Score: 1

    Write Once Read None.

    1. Re:This sounds like Perl by MrMacman2u · · Score: 1

      You mean like old 3.5" floppy disks!

      --
      This signature is lame.
  23. Finally! by overshoot · · Score: 1
    --
    Lacking <sarcasm> tags, /. substitutes moderation as "Troll."
  24. Mindisc by Danoz · · Score: 0

    Isn't this similar to/an extension of how minidisc worked? So couldn't the reading be done in a similar matter then?

  25. Congratulations! by Megane · · Score: 1

    They've just re-invented the Magneto-optical drive!

    --
    #naabhaprzrag, #sverubfr-000, #agi-fcbafberq, negvpyr[pynff*=' negvpyr-ary-'] { qvfcynl: abar !vzcbegnag; }
    1. Re:Congratulations! by Walking+The+Walk · · Score: 2

      For writing, magneto-optical drives only used the laser to heat up a bit to a point where it could be flipped. The actual magnetic drive head flipped the heated bit, not the laser. This post says they can now use the laser to flip a bit, and that's a big difference.

      --
      A recursive sig
      Can impart wisdom and truth
      Call proc signature()
  26. Re:Yay! if they figure out 2 read da stuff, we'r g by noh8rz2 · · Score: 1

    You have no idea how much pron that guy downloads. Although viewing it would still be limited by read speeds.

  27. Write without reading? by Synon · · Score: 3, Interesting

    "Unfortunately the York scientists only detailed writing data with lasers; there's no word on how to read it." A bit of a paradox don't you think? How did they know it was written without being able to read it?

    1. Re:Write without reading? by robot256 · · Score: 2

      Probably they used a scanning-tunneling electron microscope or similar to do the read. Those obviously don't scale down easily, hence there is no practical way to read the data yet.

    2. Re:Write without reading? by Anonymous Coward · · Score: 0

      It's just the famous write only memory!

  28. No way to read it? by idbeholda · · Score: 1

    Pfffffft. You silly scientists... it's lasers all the way down!

  29. Should read it faster than writing... by Anonymous Coward · · Score: 0

    Using polarized reflection - the reading beam is unpolarized, a reflected polarized light would be rotated under the influence of the magnetic recording, thus allowing high speed read read.

    Might still require a much higher speed rotation though.

    1. Re:Should read it faster than writing... by jmak · · Score: 1

      Indeed, if the disk could be also read the same way like MO disks, it would be promising: http://en.wikipedia.org/wiki/Magneto-optic_Kerr_effect

  30. No man... by coinreturn · · Score: 1

    No man is a nano-island!

    1. Re:No man... by LeadSongDog · · Score: 1

      Coming soon to a newsfeed near you: "A nano-island is one one-billionth of an island."

      --
      Oh, I'm sorry sir, I thought you were referring to me, Mr. Wensleydale.
  31. Re:finally! by Anonymous Coward · · Score: 0
    Do0d!!1!

    A harddrive with frikkin LASERS attached to its HEAD!!

  32. WORN by Anonymous Coward · · Score: 0

    Next to WORM we now also have WORN (Write Once Read Never) memory. Progress!

  33. My head is spinning by causeur · · Score: 1

    or the platter is spinning 1000 times faster to achieve this throughput?

  34. That is highly secure by Anonymous Coward · · Score: 0

    Don''t have to worry about anyone reading your data.

  35. Readback can be easier by goombah99 · · Score: 5, Interesting

    This solves a major problem with mag recording. Readback head have always been way smaller than write head. You can read back with just a tiny permalloy head but to write you need large currents and loops of wire. So miniaturization has been limited by the write head size not the read head. This solves the write-head size problem but may have created a new read head problem. But that's very promising.

    --
    Some drink at the fountain of knowledge. Others just gargle.
  36. Cryogenic data storage by goombah99 · · Score: 3, Funny

    This is the data equivalent of freezing Walt Disney and assuming that someday we'll figure out how to thaw and revive him. Write now, read someday.

    --
    Some drink at the fountain of knowledge. Others just gargle.
    1. Re:Cryogenic data storage by jd2112 · · Score: 3, Funny

      His first words after being thawed out would be "is 'Stramboat Mickey' still under copyright?"

      --
      Any insufficiently advanced magic is indistinguishable from technology.
    2. Re:Cryogenic data storage by ProbablyJoe · · Score: 4, Insightful

      And the answer will almost certainly be yes.

    3. Re:Cryogenic data storage by Anonymous Coward · · Score: 1

      And the answer will almost certainly be yes.

      I always figured that the way to thaw and revice Walt Disney would be to let the Mickey copyright expire.

    4. Re:Cryogenic data storage by BigSes · · Score: 5, Funny

      Walt: "Are all the Jews gone?" Scientist: "No." Walt: "Put me back in."

    5. Re:Cryogenic data storage by GameboyRMH · · Score: 1

      Oh jeez why don't I get mod points anymore? XD

      --
      "When information is power, privacy is freedom" - Jah-Wren Ryel
    6. Re:Cryogenic data storage by treeves · · Score: 1

      No, the answer would be "No" because the question should have been about "Steamboat Willie".

      --
      ...the future crusty old bastards are already drinking the Kool-Aid.
    7. Re:Cryogenic data storage by Flyerman · · Score: 1

      It's a Family Guy quote, calm down.

    8. Re:Cryogenic data storage by Anonymous Coward · · Score: 0

      that's hardly an assumption. it's almost a certainty. akin to assuming our sun will exist 20 years from now

    9. Re:Cryogenic data storage by darkonc · · Score: 1

      So, WORSE storage? (Write Once Read Someday - Experimental)

      --
      Sometimes boldness is in fashion. Sometimes only the brave will be bold.
    10. Re:Cryogenic data storage by Robert+Zenz · · Score: 1

      *lol* :D

  37. 60fs pulse, but what is the rep rate by Lluc · · Score: 1

    Newport has an ultrafast 400 fs laser with a claimed high repetition rate (http://www.newport.com/Spirit#tab_Specifications), but the rep rate is only 1 MHz. Who cares if you set a bit in 60 fs but then your laser can only write 1Mb/sec to disk. What's that, the speed of a Zip Disk?

    1. Re:60fs pulse, but what is the rep rate by Anonymous Coward · · Score: 0

      Fiber laser oscillators can be (easily) put in a hard drive-sized box with few hundred femtosecond pulses and 50-100 MHz repetition rates. Much less compact VECSEL lasers can have similar pulses with 10 Ghz repetition rates (both of these are areas of active research and are not consumer level.) At this point, though, you're throwing around gobs of average power, and I doubt people want a class 4 laser in their computer.

  38. Write performance still improved by Anonymous Coward · · Score: 0

    Unfortunately the York scientists only detailed writing data with lasers; there's no word on how to read it.

    Well, that's not necessarily a problem. You could easily have a drive where the write is done by a laser while reading still uses the conventional magnetic head.

    A lot of applications such as databases are still bound by the speed they write to the drive (where the write cache is fairly small so when doing a large write it slows to a crawl after the initial Mb has been written), while reading is already much faster because the OS can use any spare RAM as a cache which can be several Gb. This increases the write speed to the platter by an order of magnitude which could have a huge impact on those write times.

    (As an alumini of the University of York I find this rather exciting news).

  39. No you can't by cnaumann · · Score: 2

    This uses ferrimagnetic domains, not ferromagnetic domains. There is no external magnetic field, and you can't use a coil to read them.

  40. Hmm by eternaldoctorwho · · Score: 1

    only detailed writing data with lasers; there's no word on how to read it.

    Sounds like Windows' strategy: Crap the write to wherever on disk, and don't care about performance in reading it back. Why bother when read-time performance, when the user can defrag every day?

  41. RDX devices by sandytaru · · Score: 1

    Backup "tapes" currently grind along at 10,000 RPM or so, depending on the device. Their primary purpose is to write data; you hope you never have to read from it. The thought of writing backups at 150K RPM - finishing what is currently a three hour backup in about fifteen minutes - that would be spectacular. Sure, the data restore would still take 3+ hours - but again, you cross your fingers and hope you never have to do that restore anyway.

    --
    Occasionally living proof of the Ballmer peak.
  42. Write only? by Anonymous Coward · · Score: 0

    Hey, we have had files that were read-only for a very long time! Now we'll have files that are write-only. Brilliant!

    1. Re:Write only? by GameboyRMH · · Score: 1

      Been done before. Chmod 222.

      --
      "When information is power, privacy is freedom" - Jah-Wren Ryel
  43. This is an old invention by cvtan · · Score: 1

    They have re-invented the write-only memory or WOM! Back in grad school some friends and I developed a spec sheet for the wood-insulated gate write-only memory or WIGWOM. Another billion dollar idea that went nowhere.

    --
    Sorry, but gray text on gray background is making my eyes bleed.
  44. Comment removed by account_deleted · · Score: 2

    Comment removed based on user account deletion

  45. Write Speed Limit by Anonymous Coward · · Score: 0

    Maybe someone could explain this, but it appears that this method will always flip the bit from its current position. This would imply you need to know the current state of a bit in order to know if you needed to flip it, so wouldn't you have to read each bit before you could write any data with this method?

  46. WORM vs WORN by Anonymous Coward · · Score: 0

    WORM - Write Once Read Many
    WORN - Write Once Read Never

  47. Write only... by Anonymous Coward · · Score: 0

    I've been using write-only media for years - it's the stuff between my ears! FWIW, back in the 1970's, Signetics posted a full page ad in (I think) EDN magazine for a write-only memory chip (complete with schematic) for the April 1 issue... I still have a scanned copy of it in my archives for posterity sake. Absolute a brilliant hoot!

  48. How do they know it worked? by Z_A_Commando · · Score: 1

    If they can't read it, how can they know that the lasers wrote successfully? Or does that mean they read it using conventional means?

  49. Why not just ditch magnetic HDDs altogether? by Anonymous Coward · · Score: 0

    SSDs, anyone?

  50. could radar be used for reads? by Anonymous Coward · · Score: 0

    I could be off-base, but could radar be effective to read info at that scale?

  51. Discovered ! by neo12 · · Score: 1

    Is dd if=file of=/dev/null they talking about?

  52. This just in! by RandomAvatar · · Score: 1

    possible terabyte-per-second writing to cd! fastest writing ever! You will be amazed at the speed! More storage capacity! and more!

    fine-print note: the content copied onto cd may not be able to be read.

  53. Convar reads data from hard drives using lasers by Beliskner · · Score: 1

    The German company Convar reads data from damaged hard drives using blue lasers. They're currently recovering data from the World Trade Centre hard disks using this blue laser method.

    --
    A caveman dreams of being us, the incalculable power and riches. We dream of being Q, then what?
    1. Re:Convar reads data from hard drives using lasers by RalphTheWonderLlama · · Score: 1

      Something tells me the blue laser method wouldn't help much for the disk in the third image on page 1 of their PDF.

      --
      simple, fast homepage with your links: http://www.ngumbi.com/
  54. Cool, write only media. by Anonymous Coward · · Score: 0

    Cool, write only media.

  55. there's no word on how to read it by Anonymous Coward · · Score: 0

    > there's no word on how to read it

    With the remaining eye.

  56. Liquid Paper by retroworks · · Score: 0

    I told my wife we might need it someday!

    --
    Gently reply
  57. Well obviously.... by Groo+Wanderer · · Score: 1

    "Unfortunately the York scientists only detailed writing data with lasers; there's no word on how to read it."

    Use lasers. Duh. :)

                      -Charlie

  58. Hot damn! by autophile · · Score: 1

    OK, my visual cortex is officially due for repair. I read the headline as "New Technique Promises Much Faster Hot Damn Write Speeds"

    --
    Towards the Singularity.