Slashdot Mirror


Seagate Hits 1 Terabit Per Square Inch

MrSeb was one of several readers to submit news that drive manufacturer Seagate has announced (and demoed) the first hard drive to squeeze a terabit into each square inch of platter. "'Initially this will result in 6TB 3.5-inch desktop drives and 2TB 2.5-inch laptop drives, but eventually Seagate is promising up to 60TB and 20TB respectively. To achieve such a huge leap in density, Seagate had to use a technology called heat-assisted magnetic recording (HAMR). Basically, the main issue that governs hard drive density is the size of each magnetic 'bit.' These can only be made so small until the magnetism of nearby bits affects them. With HAMR, 'high density' magnetic compounds that can withstand further miniaturization are used. The only problem is that these materials, such as iron platinum alloy, are more stubborn when it comes to writing data — but if you heat it first, that problem goes away. With HAMR, Seagate has strapped a laser to the hard drive head; when it wants to write data, the laser turns on. Reading data is still done conventionally, without the laser. In theory, HAMR should allow for areal densities up to 10 terabits per square inch (magnetic sites that are just 1nm long!), and thus desktop hard drives in the 60TB range."

49 of 224 comments (clear)

  1. Wondering by hardburlyboogerman · · Score: 4, Insightful

    Can current motherboards handle that?

    --
    Geek Hillbilly
    1. Re:Wondering by xushi · · Score: 2, Insightful

      Also wondering, will this set back SSD by 5 years?

    2. Re:Wondering by fuzzyfuzzyfungus · · Score: 4, Informative

      Depends on your definition of 'current'; but it shouldn't be an issue(density strictly speaking, isn't even meaningfully visible to the motherboard, except in the broad terms that denser=greater capacity from whatever number of platters is viable).

      That said, there are probably still a large number of motherboards that will be questionably bootable from the greater-than-2-terabyte drives that these platters are presumably intended for(some ghastly MBR thing); but anything new enough for 48-bit LBA and a modern OS should, at least, support perfectly normal OS use of the drive once everything is booted.

    3. Re:Wondering by Waffle+Iron · · Score: 4, Funny

      Can current motherboards handle that?

      Do you mean would PC manufacturers would design in arbitrary limits in their hardware and/or BIOS that would create some kind of "barrier", so that disks that are too big won't work with the system?

      That's highly doubtful. Nobody would be that stupid... would they?

    4. Re:Wondering by SuricouRaven · · Score: 2

      LBA-48 should be good up to 128PiB.

    5. Re:Wondering by fuzzyfuzzyfungus · · Score: 5, Informative

      Also wondering, will this set back SSD by 5 years?

      Probably not: This advance(while definitely helpful to the HDD, and no doubt some very impressive engineering work from the R&D team) is a reinforcement of exactly the same virtues that HDDs have historically had and of virtually no value in addressing their historical weaknesses:

      1. Capacity/dollar: Once the production is tooled up, the cost/gigabyte for HDDs can be expected to continue to decline.
      2. Linear read/write speed: Because of their high areal density and fairly swift rotation, HDDs can read or write like a bat out of hell as long as they don't have to do much seeking. Seeky or random I/O tanks them because of the need to physically move the head around and possibly wait the better part of a platter rotation for the spot you want.

      It will continue to be the case that HDDs are cheap for the capacity, and fast as hell for nice, linear, streaming operations; but SSDs can churn out the random I/O without breaking a sweat and are available in physically smaller and more shock-resistant packages(the economical range for HDDs is basically defined in multiples of the volume of a 2.5inch HDD, and don't drop them, SSDs start at BGAs the size of your fingernail and scale in multiples of those until your wallet explodes...

    6. Re:Wondering by fuzzyfuzzyfungus · · Score: 4, Informative

      It's a legacy thing, not an intentional-crippling thing:

      The BIOS' handling of block devices dates back to when booting your OS off a floppy wasn't considered deviant behavior, and a 5MB HDD was some pretty serious gear. The details are kind of messy...

      Most reasonably contemporary stuff should at least do 48-bit LBA; but there are still a lot of systems in the wild that still need MBR, at least on the boot disk(which limits you to 2TB partitions).

    7. Re:Wondering by Waffle+Iron · · Score: 2

      Yeah, they always claim that "this time, we've fixed the barriers for good!". Then a few years later, you learn about some new barrier.

      I had to deal with a subtle version of this just recently when they upped the hardware block size. Lots of fun trying to partition and boot my new disks; LBA didn't save the day there.

      After hitting a dozen or so "barriers" over the decades, I doubt that they're ever going to really succeed in future-proofing systems for storage size.

    8. Re:Wondering by UnknowingFool · · Score: 2

      From a motherboard manufacturer's standpoint, they will future proof but only so far. The main reason is cost and practicality. They could future proof something ten years in advance but what is the likely hood that the equipment isn't obsolete by then. Also future proofing that far means support. They would rather introduce new models every few years and leave out backwards compatibility. Now if you are willing to pay more for a board that is more future proof, you can do so. But most people want cheap. Also most people replace whole computers than upgrade. So you are in the minority.

      --
      Well, there's spam egg sausage and spam, that's not got much spam in it.
    9. Re:Wondering by petermgreen · · Score: 4, Informative

      Computers tend to measure things with fixed size binary numbers since these are by far the most efficient format for them to handle and process. When chosing the size of these numbers there is always a compromise between efficiency and future proofing. Usually the margin left by the designers is enough to last a while.

      However for long lived standards as the years pass that margin is eaten up. Eventually it reaches the point where all the margin is eaten up and things have to be redesigned . The most recent one we hit was that the conventional MBR partition table has a limit of 2^32 sectors (=2TiB assuming standard size sectors). Making things worse is the fact that MS refuses to support the combination of a GPT partition table on the boot drive with conventional BIOS booting so the motherboard may be able to see and access the large drive but it if doesn't support UEFI you can't use the whole drive as a windows boot drive.

      Afaict the next barrier we will hit is the LBA48 limit of 2^48 sectors (=128PiB assuming standard size sectors). So a 60TB drive shouldn't be any more problematic than a 3TB one.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
    10. Re:Wondering by SuricouRaven · · Score: 2

      Pebibytes.Or possibly Pibibytes. Powers of two, not ten.

    11. Re:Wondering by 0123456 · · Score: 3, Insightful

      Don't kid yourself, this is the dying breath of the HDDs.

      How much is a 60TB SSD, and how many times will I be able to write to it before destroying the disk when you're using a process small enough to pack that 60TB into a box the size of an HDD? Each new process shrink seems to be dramatically reducing the write limit for SSDs.

      You go right ahead and wait for 2 fucking hours for your 50 GB Bluray image to be copied/processed on your mechanical toaster; I'm sticking with my 1 minute with complete silence and low power consumption.

      Even my 'Green' HDD manages sustained writes at 80-100MB per second, and why would anyone in their right mind be copying a $10 Bluray onto an SSD that costs more than a dollar per gigabyte?

    12. Re:Wondering by qubezz · · Score: 5, Informative

      As areal density increases on hard drives, so does the transfer rate. The linear density of a track increases, and the amount of data that passes under the head in one rotation of the disc increases. This is how the 5400rpm discs of today have 120MB/s transfer rates compared to the 10MB/s transfer rates of the same rotation speed ten years ago.

      Imagining some system you don't own and benchmarks that exist only in your head is not a practical measure of what consumers will own in the future, and rotational media will continue to occupy the same place it does now for the next several years, as the mainstream consumer PC storage product, and as the main data (blu-ray rip) storage and backup media for enthusiasts with SSD operating system drives.

      My next system will have a killer refresh rate with a P6 chip. Triple the speed of the Pentium. RISC architecture is gonna change everything. That's too much machine for you.

    13. Re:Wondering by Githaron · · Score: 4, Insightful

      ...this is the dying breath of the HDDs.

      With 60 TB drives, assuming they will run around the price of current hard drives, not likely. SSDs and hard drives will just co-exist. SDDs for things that need to be fast (OS, software, etc.) and hard drives for everything else (pictures, videos, documents, etc.).

      60 TB might seem like a lot now but I am sure that humanity will figure out new ways to fill the capacity. We always do.

    14. Re:Wondering by BattleApple · · Score: 2, Informative

      You go right ahead and wait for 2 fucking hours for your 50 GB Bluray image to be copied/processed on your mechanical toaster; I'm sticking with my 1 minute with complete silence and low power consumption.

      Just in case you've been wondering - this is why you are still a virgin.

    15. Re:Wondering by networkBoy · · Score: 2

      Nevermind that some applications will murder an SSD faster than you can say "Fault Tolerant".
      I have a scratch disk on my server, it's the landing zone for most network IO that is disk bound as well as a landing zone for uncompressed video that needs to be batched out for compression and for the resulting compressed file.
      Performance is secondary to cost in my application, so yes, this all hits a single HDD, but I only support about 4 users anyway.
      That drive has been replaced three times now. Each time with a platter drive. I tried an SSD once, it died in a week, platter drives last about 6 months. That's life with gobs of reads and writes.
      I have a very low failure rate on all other drives in the server as they are largely static. Write once read many type operations. Usually, when I upgrade to a larger disk, I take the previous smallest disk and use that as the next scratch disk.
      -nB

      --
      whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
    16. Re:Wondering by networkBoy · · Score: 2

      I collect datasets.
      I have a small selection of movies on the server (mostly so disks don't get scratched with 6 and 8 year old hands).
      I have 12TB with about 5% free, normally I try to run at close to 20% free, but have not been buying disk since the floods. Soon I won't have a choice, so I welcome these 2TB 2.5" platters. I'm out of mechanical space, but if I replace my 3.5" bays with 2.5" I can go from 5 to 12 disks in the same physical space.

      Any way, back to the datasets. I have one that came shipped on 10 DVDs, it is all the data for the US education system crossed as follows:
      zip code of school
      average attendance rate /grade
      average GPA /grade
      average income /grade
      district of school
      ethnicity of school
      ethnicity of zip from census
      income of zip from census
      average teacher income / grade / (zip &&|| district) (not available at a per school granularity because of the low number of teachers/grade in a school could lead to reasonable identification of an individuals income)
      etc.
      etc.
      It is one of my bigger datasets, and I keep it on-line. The SPSS license was *not* cheap, but it made the research for the wife's masters thesis really easy.

      Anyway, long story short I have a multi TB collection of DBs, that I don't want to lose, along with queries.
      All on mirrors, 12TB worth. I'm sure there are /.ers that are movie hounds out there that have vastly more than that.
      -nB
      -nB

      --
      whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
  2. 100% shark jokes by Zouden · · Score: 4, Funny

    "Seagate has strapped a laser to the hard drive head"

    Well, there goes my hopes for an intelligent discussion.

    --
    "A week in the lab saves an hour in the library"
    1. Re:100% shark jokes by Anonymous Coward · · Score: 5, Funny

      Yes, they have strapped a laser to the HAMR head.

    2. Re:100% shark jokes by semi-extrinsic · · Score: 2

      In my understanding, they have basically reinvented the MiniDisc, only at higher storage densities?
      (Disproving your point ;) )

      --
      for i in `facebook friends "=bday" 2>/dev/null | cut -d " " -f 3-`; do facebook wallpost $i "Happy birthday!"; done
    3. Re:100% shark jokes by fuzzyfuzzyfungus · · Score: 4, Informative

      To the best of my understanding, there is one major difference: the magneto-optical drives(minidisc and others) used the laser to do reads as well as to heat sectors to lower their coercivity so that the magnetic head could rewrite them. This HDD-derived technology does magnetic reads; but incorporates a laser for heating during writes, allowing you to use high-coercivity materials(which allow smaller sectors to remain stable over time; but would be prohibitive to rewrite in their normal state).

  3. HAMR Time by Anonymous Coward · · Score: 5, Funny

    STOP! It's HAMR time!

  4. No. by Anonymous Coward · · Score: 3, Insightful

    They are on ultimately diverging paths which may coexist symbiotically forever unless one beats the other out in either cost, reliability, or functionality.

  5. This is bad.... by Anonymous Coward · · Score: 4, Funny

    MPAA says this will cost the entertainment industry billions of dollars every year.

    1. Re:This is bad.... by jd2112 · · Score: 4, Funny

      MPAA says this will cost the entertainment industry billions of dollars every year.

      Trillions of dollars every day! Won't you think of the children of the entertainment company lawyers who may never see thier parent because they are working 24/7 too protect the poor defenseless movie companies and the billions of americans who will loose thier jobs for each of these drives that are sold!

      --
      Any insufficiently advanced magic is indistinguishable from technology.
  6. Some Perspective from their CEO: by fuzzyfuzzyfungus · · Score: 4, Funny

    "Let's face it, we're not changing the world. We're building a product that helps people buy more crap - and watch porn."

    1. Re:Some Perspective from their CEO: by Kjella · · Score: 2

      Ex-CEO. That was Bill Watkins, who was replaced in 2009 by Stephen J. Luczo. And for all the candor of that statement "pirate more crap" would probably be even more honest...

      --
      Live today, because you never know what tomorrow brings
  7. Re:How about reliability? by SuricouRaven · · Score: 4, Insightful

    Once size is sufficient, you can solve reliability through redundency.

  8. Re:How about reliability? by Hatta · · Score: 2

    Not with RAID you can't. If you don't decrease the unrecoverable error rate as you increase the size of the volume, eventually you get to the point where you're almost certain to hit an unrecoverable error while rebuilding your volume. So the real question is, how is the read error rate on these tightly packed data domains?

    --
    Give me Classic Slashdot or give me death!
  9. Power? by Quantus347 · · Score: 4, Interesting

    I wonder what the power consumption increase is if you have to strap a heating laser to the write head. Lately the market seem to reward Technology that trends toward less power usage, not more

    --
    Common Sense isn't as Common as people think...
    1. Re:Power? by fuzzyfuzzyfungus · · Score: 4, Insightful

      The power budget for the laser obviously isn't zero; but if you only want to heat a very small area for a small fraction of a second the total power required to achieve truly alarming "watts/meter^2" is surprisingly small.

      More broadly, Seagate probably knows as well as anybody(although certainly isn't happy about it) that the small-n'-low power market is basically lost for mechanical HDDs. Game over. They'll stick around in cheapie laptops because they are cheap, and in crazed-enthusiast DTR and workstation models because they are huge; but Flash is taking over the good bits.

      In those areas where Serious Storage Capacity still counts, the energy cost of having X platters and 2X heads fighting air resistance as they zip around at high speeds really starts to add up. If you increase the areal density of a platter, you increase the storage capacity of a given number of platters, allowing your customers to either reduce platter counts for a constant workload, or maintain constant platter counts under an increased workload.

  10. Still will go unused by Grizzley9 · · Score: 3, Insightful

    Granted most of *us* can find something to fill it but when Dell and other bulk PC makers start including 1TB or 10TB drives in their basic PC's, most of it will still be unused by the general public. With higher MP cameras I can fill mine up with video and pics and a few converted movies/music. But with streaming options and so much available online or stored online for you, I just don't see the need to keep a ton of torrented movies and other files around taking up space and having to manage.

    The more space we have, it seems the more we keep. I can see a new show as a spinoff of "Hoarders" showing just what all is in your computers HDD.

    1. Re:Still will go unused by Princeofcups · · Score: 3, Insightful

      Granted most of *us* can find something to fill it but when Dell and other bulk PC makers start including 1TB or 10TB drives in their basic PC's, most of it will still be unused by the general public.

      Ridiculous. That same claim has been made over and over for the last 30 years, and proven wrong each time.

      --
      The only thing worse than a Democrat is a Republican.
  11. Too much storage = too much garbage by na1led · · Score: 5, Insightful

    I've noticed that the more storage you have, the more junk you fill it with. At my work, we have SANs with several Terabytes of storage, mostly filled with junk. When you have millions of useless files, it becomes a tedious task to search, and backup data. In the early days, there was a lot more cleanup of stored data, and only important files were kept on disks.

    --
    -- By all means let's be open-minded, but not so open-minded that our brains drop out.
  12. Re:What's an "inch"? by cvtan · · Score: 2

    Let's bring back hogsheads and firkins!

    --
    Sorry, but gray text on gray background is making my eyes bleed.
  13. Re:Downsides? by Anonymous Coward · · Score: 2, Informative

    The media heats and cools in 100-200 picoseconds; the laser turns on and off much faster than that. No addition to latency. Laser lifetime and reliability will be an engineering hurdle, but not a showstopper by the time a production drive is approved for release. The spot size of the laser on the media is much less than 100 x 100 nm (probably less than 50 x 50 nm) so the total heat added to the drive from the laser light itself is quite small. More heat will be added from the electronics, so thermal management of the drive environment my be more critical. However, caveats to all of these statements are that this is an early demo, not a production-ready drive, and in fact is likely not actually a real HDD like you would put in your PC. These demos are done in a lab environment with lab electronics, and lab mechanical systems to stay on-track. Still, this is a very significant step in showing that HAMR is on track for product plans later this decade.

  14. HAMR Head Sharks can hold two frickin lasers! by Dareth · · Score: 4, Funny

    HAMR Head Sharks can hold two frickin lasers! Take that you great white hater!

    --

    I only look human.
    My mother is a halfling and my dad is an ogre, so that makes me an Ogreling
  15. Short-stroking by jones_supa · · Score: 2

    As the density increases, the size of a short-stroked partition will be physically smaller too, making the seek times shorter. :)

  16. Re:What's an "inch"? by fuzzyfuzzyfungus · · Score: 2

    You're absolutely right!!! Why didn't they measure it in meters??? Then I'd have some scale being able to compare it to the length of the path travelled by light in a vacuum in 1/299792458 of a second! I mean, everyone has some idea what that is...

    Don't listen to those pointy-headed physicists and their ivory-tower propaganda! The One True Metre is a piece of Platinum/Iridium bar-stock painstakingly stored by the Bureau International des Poids et Mesures and roughly the same length as 1/10,000,000th of an incorrect estimate of 1/4 of a terrestrial meridian!

  17. Laser Failure Mode by BennyB2k4 · · Score: 2

    The good news is that if the laser fails, the data should still be available to read and copy onto a new hard drive. If the laser was needed for reading as well, I'd be wary of the reliability.

    1. Re:Laser Failure Mode by spire3661 · · Score: 2

      The PS2 says hello.

      --
      Good-bye
  18. Cost? Reliability? Water Resistance? by DarthVain · · Score: 2, Interesting

    As much as I love stories about X company being able to stuff Y capacity into storage device, the last few years have proven instructive.

    1) How about doing it and producing it in such a way so that it is cheaper, not more expensive than last year?
    2) How about making them at least a little bit reliable. I know you just want us to consume more and more of your drives, but lets get back to 5 year warranty's already. This one year BS is BS.
    3) Maybe rather than doing the R&D to find a 60TB HD you do the R&D to find a building lot not on a fscking flood plain?

    Thanks,
          From everyone that bought a HD in the last year or so...

    1. Re:Cost? Reliability? Water Resistance? by AmiMoJo · · Score: 2

      How about some more speed? At a constant 100Mb/sec write speed (impossible on current consumer grade HDDs) it would take about 40 hours to fill a 10TB HDD.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    2. Re:Cost? Reliability? Water Resistance? by rtaylor · · Score: 4, Informative

      Speed on spinning disk is a function of density as much as anything else.

      The tighter you pack the bits, the more bits pass under the head in a given time frame, which makes it faster.

      --
      Rod Taylor
  19. Re:What's an "inch"? by petermgreen · · Score: 2

    but do you ask for a 8.89 or 6.35 cm harddrive?

    Also note that drive bays were named after the size of the disks that went in the drives that went in the bays. Not after the size of the bays themselves.

    --
    note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  20. Re:How about reliability? by TooMuchToDo · · Score: 2

    You spread your data chunks across whole clusters of storage systems (i.e. Nimbus.io, Amazon's S3). The important data you really than need are the SHA hashes of the data.

    Sure, you lose a ton of data on a drive here or there. You immediately invalidate the drive and the data on it, replication has already brought the number of good chunks of data back to the minimum replica requirement (because, you're smart, and you're keeping 3-5 copies of the same data across your storage platform), and you stream new data to the drive.

  21. FSCK and CHKDISK by pysiak · · Score: 2

    What are the time implications of running FSCK or CHKDISK on 20TB NTFS or EXT4 ?

  22. Shift by bill_mcgonigle · · Score: 2

    I do my work from home some days with a VNC connection to work. It runs about 1.2Mbps when I'm busy (6-meg DSL).

    I see almost no reason why a home user should want to have a local hard drive, except perhaps to cache media files until the upload is done (in the background, and seamless working through the cache until the upload is done, of course).

    Give it a couple years and Google will offer free computers with free Internet connections in exchange for usage tracking. 70% of the population will take them up on that deal. Unless Amazon gets there first.

    All that said, there's going to be a huge need for storage on the backend.

    --
    My God, it's Full of Source!
    OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
  23. Hybrid by Bensam123 · · Score: 3, Interesting

    I still think the answer to both the SSD and Mechanical question is hybrid drives. Seagate has tried them in the past, but they definitely aren't as fast as normal SSDs. If they can improve that tech and attach it to something like this, it's literally the best of both world. Honestly it would just be a much improved drive cache, which Seagate and other drive makers could've improved for years... but somehow never did...