Slashdot Mirror

← Back to Stories (view on slashdot.org)

No Cheap Replacement For Hard Disks Before 2020

Posted by timothy on from the we'll-see-in-10-years-about-that dept.

siddesu writes with disappointing news to anyone who'd like to see solid-state storage dominate in the near-term future. "A new study of storage technology by the former CTO of Seagate predicts that hard disks will remain the cheapest storage technology in the next decade and probably beyond."

24 of 346 comments (clear)

  1. Huh? by chuckymonkey · · Score: 4, Interesting

    So these people can predict the future now?! Really, you never know what is going to happen for sure. Look at current HDD tech, IBM made the GMR breakthrough and BAM! Huge storage capacity in drives. What makes people think that there cannot be another such discovery with solid state or some other yet unknown tech?

    --
    "Some books contain the machinery required to create and sustain universes."-Tycho
    1. Re:Huh? by im_thatoneguy · · Score: 4, Insightful

      Probably because manufacturing techniques often take at least 10 years to become mainstream. Even if someone invents something faster, smaller and more reliable than magnetic storage... you still have to conceive of a way to produce it in mass quantities to drive the price below that of established spinning disks.

    2. Re:Huh? by TheRaven64 · · Score: 4, Informative

      Well, the breakthrough is PCRAM, which is almost as fast as DRAM but non-volatile and rewritable per byte, unlike Flash, which needs (relatively large) cells to be deleted. Samsung are already producing 64MB PCRAM modules, but you can expect the capacities to increase quickly.

      --
      I am TheRaven on Soylent News
    3. Re:Huh? by timeOday · · Score: 5, Insightful

      you still have to conceive of a way to produce it in mass quantities to drive the price below that of established spinning disks.

      Nope! Roast beef costs more than bologna, yet people chose to buy it every day. SSD drives don't need to be cheaper because they are better - silent, far less prone to shock damage, and ohhh so much faster. Morever, HDD's, though cheaper per megabyte for huge-sized drives, will be more expensive for the smaller sizes people actually need. You can get a memory stick for, what, $10? HDD's never touch that because of their complexity. Well before 2020 a 250 GB SSD will be $20, and will have ample capacity for most users, and will be cheaper than any HDD. Granted, a 50 TB HDD will still be cheaper than a 50 TB SDD, but most people won't care. About that time, HDDs will become specialty products, further crippling any remaining cost advantage.

    4. Re:Huh? by Kjella · · Score: 4, Informative

      Good thing we haven't been working with solid state storage in digital cameras for 10+ years then. Or the RAID controller technology which could make them kick-ass fast. Sorry, but SSDs aren't revolutionary in that sense, they're taking two rather mainstream technologies combined with the same process improvement you see in CPU/GPU/RAM and coming to whoop ass in all performance oriented markets. I have an SSD as my primary disk and I'd say it's the biggest revolution since dual cores. Almost no matter what I do, the machine remains very responsive under heavy IO load completely unlike hard disks.

      --
      Live today, because you never know what tomorrow brings
    5. Re:Huh? by 0123456 · · Score: 4, Insightful

      Well before 2020 a 250 GB SSD will be $20, and will have ample capacity for most users, and will be cheaper than any HDD.

      Rather like the average user will ever need more than 640k of RAM.

      By 2020, 250GB will be as much of a joke for the average user as a 250MB drive would be today; 250GB will probably be just about big enough to hold one super-extra-high-definition video file.

    6. Re:Huh? by tepples · · Score: 4, Insightful

      250GB will be as much of a joke for the average user as a 250MB drive would be today

      Nintendo DSi has the equivalent of a 256 MB microSD soldered onto the motherboard. It's enough to hold a few apps from the DSi Shop. If it were a joke, why would Nintendo have used it?

      250GB will probably be just about big enough to hold one super-extra-high-definition video file.

      For one thing, the eye has a resolution limit, so why would people need more than, say, 2560x1440 (quad 720p) in home electronics? For another, are you talking about the consumer's use (which would be streaming rather than storage if the movie industry has its way) or the movie producer's use?

    7. Re:Huh? by epine · · Score: 5, Insightful

      At the rate we're going, by 2020 Windows will probably need 500GB for a base install

      Only if you install the Federation Font Pack and the holographic tridi layout engine. And that's supposing the SETI program makes an immediate break-through, like tomorrow, and Perl 7 ships on time.

      We've already passed the visual resolution where porn becomes gynaecology. Even lust has resolution limits.

      Or maybe Google decides it saves bandwidth to send out the entire public Internet encoded as a single quantum particle, but for some reason people don't disable their Mozilla page cache.

      Extrapolation is a valid exercise, but works better accompanied by graphs and data points rather than historical fat jokes. The last time Windows hung over its pants like a muffin top, I had a 6GB hard drive. Seagate hasn't sold anything smaller than a military surplus tent awning for years now. Hard to believe, times change.

    8. Re:Huh? by Forge · · Score: 4, Interesting

      There is another factor.

      Flash is faster and more energy efficient than spinning disks. This creates a demand for flash which reduces the incentive of manufacturers to drop the price per GB.

      Also try to understand the gap we are dealing with.
      Flash is around $1.87 per GB while Hard drives are closer to 7c per GB.

      That's 26 times the price. Sure SSDs are getting cheaper every day but so are hard drives. I am sure they will get so close that the price gap becomes less important than all the other features which separate them. Some time after that, SSDs may even become cheaper, or both SSDs and hard drives will be supplanted by some other technology. It just won't happen right away.

      Is one more decade too pessimistic an estimate? Only time will tell. What I do know is that where SSD's advantages are more important the change has already started. You can buy a portable computer with only SSD storage today.

      --
      --= Isn't it surprising how badly I spell ?
    9. Re:Huh? by Eil · · Score: 5, Insightful

      So these people can predict the future now?! Really, you never know what is going to happen for sure.

      If you want to see what's going to happen in regard to mechanical vs solid state hard disks, you don't need a crystal ball. Just look at the transition from CRT to LCD displays. It wasn't so long ago (seems like only a few years) that LCD monitors were horribly expensive and that fact (combined with their other drawbacks) made them an unattractive option for most people. I can recall many, many people right here on Slashdot saying that they would never give up their enormous, power-hungry, failure-prone CRT displays. Now, you can't even buy a CRT computer monitor because LCD quality caught up and surpassed CRTs for most purposes while price plummeted. The same will happen with mechanical disks and SSDs. Maybe it'll happen faster, maybe slower, but it will happen.

      Keep in mind also which company this "prediction" is coming from: Seagate lived a long and prosperous career engineering and manufacturing mechanical hard disks. They are a huge company whose entire operation is based around the concept of shipping hunks of metal with rotating platters inside. Since an SSD is just a bunch of memory chips duct-taped together, the memory companies (Transcend, Crucial, Corsair, Samsung, etc) were the first ones with SSDs on the market. The SSD thing likely hit Seagate by surprise and they can see that their run won't last long. It's not too late for them to start transitioning to manufacturing memory chips, but doing so would be brutal for many reasons. To start with, their decades of mechanical drive development experience, manufacturing facilities, engineers, trade secrets, R&D, etc are mostly about to be worthless. If they start selling this stuff off now while it's still fairly valuable, shareholders are going to do a huge "WTF?" and walk off. Second, the memory companies have a few years head start. Even if Seagate could enter the market and compete with them, the company would be leaving their position as a market leader to be a market newcomer, taking cues from everyone else. (Cue the sound of their last few shareholders stomping out.)

      Basically, unless Seagate can buy up a few of the leading memory companies making SSDs right now, they're screwed. Until (or unless) that happens, all they can do right now is appease their shareholders and put their executives up on stage to have them parrot the lie that their business is going to be viable for a good long time yet. Oh, and frivolously sue all the SSD manufacturers on broad patent infringement grounds.

    10. Re:Huh? by commodore64_love · · Score: 4, Interesting

      No. There is English. And then in 1066 the damn French invaded the island and polluted the language with their messed-up words. True English died with Beowulf.

      What exists today in both Britannia and America is a mongrel mess of Germanic and Latinate words. No wonder the spelling and rules make no sense. Damn French.

      (I'm chust joking. Put down the guillotine Mr. Frenchman.)

      --
      "I disapprove of what you say, but I will defend to the death your right to say it." - historian Evelyn Beatrice Hall
    11. Re:Huh? by Bob_Who · · Score: 4, Funny

      Saying Are and Is are both correct.

      Saying Are and Is are both correct, is correct.

      Both are, is correct. Are is both are saying is.

  2. So that means that by 2015... by John+Hasler · · Score: 5, Insightful

    ...10 TB drives will be $10? More likely, 100TB drives will be $100 but you won't be able to get anything smaller. And they'll still crap out after a couple of years.

    --
    Warning: this article may contain humor, sarcasm, parody, and perhaps even irony. Read at your own risk.
    1. Re:So that means that by 2015... by dgatwood · · Score: 5, Insightful

      Pretty much. And the Seagate folks are forgetting the fixed costs in their estimates. There are a lot of fixed costs that go into manufacturing hard drives. That's the reason prices on HDs aren't dropping. Instead, capacity is increasing, giving the perception that storage is getting cheap. It isn't, though, unless you really expect to use all of that 1 TB capacity. The average computer user uses maybe 1-200 gigs. For them, the effective price of HD storage hasn't changed significantly in about five years.

      The price of SSDs is going down because most of their cost can still be reduced by economies of scale. At some point---probably within a couple of years---the price of a SSD will drop to the point where you can get a 256 GB drive for $100. At that point, it doesn't matter how big the hard drive vendors make their drive capacity; they're through. Most people will buy the much more reliable SSDs over the larger HDs once the price is about the same. At that point, the tables will turn, HD manufacturing will be relegated to power users, and hard drive prices will skyrocket. I'd give them five years. At most.

      Their statement reads like a press release by a company that sees the writing on the wall and is trying to keep stock prices propped up as long as they can. Just saying.

      --

      Check out my sci-fi/humor trilogy at PatriotsBooks.

    2. Re:So that means that by 2015... by nine-times · · Score: 4, Insightful

      At some point---probably within a couple of years---the price of a SSD will drop to the point where you can get a 256 GB drive for $100. At that point, it doesn't matter how big the hard drive vendors make their drive capacity; they're through.

      Agreed. It doesn't really matter if the price per TB for magnetic hard drives is much lower than for flash. The question will be, can I get enough storage in my computer without breaking the bank?

      Of course it depends on what amount is "enough". Honestly, on my laptop, I'm only using 25 GB. It's not that I'm trying to keep my storage requirements down. I have 160GB to work with, I just don't store anything except my OS, a few applications, and some documents. My desktop is in about the same state, except add about 20 GB of music. I think the next time I buy a new drive (which may still be a couple years off) it will be SSD.

      On the other hand, I would probably still want something very high capacity for archiving/backup, and hard drives might still be suitable there. Also, it's possible that I could be prodded into collecting movies and TV shows at 1080p like I have MP3s right now, in which cases I might want several hundred gigabytes of video storage. That might be another suitable use for hard drives. So maybe you'll see more of a tiered approach, with smaller/faster SSDs used internally to store the OS and apps, and then bigger external HD for video, backup, and archives.

    3. Re:So that means that by 2015... by Hortensia+Patel · · Score: 4, Insightful

      But.. why would you do this? DVD's successor is *already* mainstream, and the successor's successor is already being hinted at.

      Why do people rip their CD collections? Because they've got them, and they don't have any burning desire to buy them all over again, and dealing with huge numbers of physical discs is a royal PITA.

      DVD for me hits a "good enough" spot: cheap, reasonable quality, ineffectual DRM. Blu-Ray is higher quality, sure, but I gather the DRM is really obnoxious, and even if it weren't the filesizes are so ludicrous as to rule out all the possibilities that make digital formats a good thing. iTunes downloads and the like are OK for rentals, and I've used them for that, but I actually like owning movies, and that doesn't seem to be an option in the current marketplace. ("DRM that hasn't screwed you yet" is not "ownership".)

    4. Re:So that means that by 2015... by Anonymous Coward · · Score: 5, Funny

      It's getting better, but I'll wait a few more product generations before using them in SQL servers. With HDD crashes, at least the data can be professionally recovered to some degree. But what about SSDs? If the controller dies and/or a PSU fries every chip, I'm afraid all the data would be lost forever!

      The backup strategy that you are using on your database server is to have your data professionally recovered after a disk crash?

    5. Re:So that means that by 2015... by dgatwood · · Score: 4, Insightful

      1) HDDs don't have excessive wear and tear from use. We don't know how long high end SSDs will last - but HDDs can go years of heavy read/write use.

      You're joking, right? One of the most common causes of hard drive failures is damage to the heads from the head ramp. That's mechanical damage every time the heads get parked. And in laptops, the rate of damage is even worse because when they get bumped around, the head arm slams itself against the ramp to protect the platters. And the second most common cause is data corruption of the control track, without which the hard drive becomes a brick; there's a theory from one data recovery company that fluid bearings cause vibration that leads to this corruption. And that's not even counting the fact that you have a head arm moving back and forth, bearings spinning, etc. There's plenty of mechanical wear and tear going on, and some of it can be quite catastrophic.

      SSDs have none of those mechanical failure modes. And even the risk of solder ball failure (a common cause of hard drive controller board failure) should be significantly lower because solid state drives generally don't dissipate as much heat as spinning drives. Thus, the failure of a SSD is likely to be fairly predictable in write count to the point that you could set your watch by it, and the exceptions are likely to be much fewer than with hard drives.

      To put this in perspective, ask yourself this: when is the last time you had RAM suddenly go bad? In my life, I can only think of one single time when I've seen RAM that worked from the factory stop working, and I'm not 100% sure even of that one. Hard drives? I lost four last year alone. So it's not a question of whether SSDs will be more reliable on average, but how many orders of magnitude more reliable they will be. My money is on either 2 or 3.

      2) As prices of SSDs drop, companies will flock to the new market, shovelling out short lived crap. (Same thing happened to HDDs)

      Maybe so, but this is what reviews are for. :-)

      2) HDDs will have superior capacity for a very long time. It will be hard to match that for the "best value" drives priced at around $100, or even the cheapest ones priced at ~$50.

      Again, though, if 95% of customers don't need that capacity, there's no reason for them to buy a less reliable technology. And there's little question, given the failure rates on hard drives, that even the most poorly built junk SSDs are going to be more reliable on average, assuming you ignore all drives that are DOA....

      3) HDDs can ramp up the cache to have very awesome performance.

      I'd settle for a tenth of hard drive performance to have avoided my four hard drive failures last year. It was a brutal year. As soon as I can move entirely to SSDs, I'm switching and never looking back.

      Now picture a modern 3.5" drive with dual or quad heads from WD. Add in 4GB of cache, and make it 10000 RPM. Stick it in a DVD drive bay and include battery backup. The cost would literally be hundreds of dollars, but you'd have something like 8TB of space capable of almost maxing out SATA3. (500MB/sec for short bursts under 3 minutes long isn't unrealistic)

      And the average computer user would use... pretty much the 4 GB of cache, and wouldn't ever read or write a single byte to the physical platter except for data reliability reasons.... Saying that hard drive vendors could increase space by fourfold doesn't matter. They could increase it a hundredfold and it wouldn't matter if 95% of the customers don't care. It's like the problem with selling software upgrades. If customers don't see enough value in upgrading, they won't.

      --

      Check out my sci-fi/humor trilogy at PatriotsBooks.

  3. Define 'cheapest' by TheRaven64 · · Score: 5, Insightful

    If you mean 'lowest cost per GB' then you're probably right. If you mean 'lowest cost per IOPS' then you're already wrong. And if we're talking 'lowest cost for something of adequate capacity and a low power consumption for a laptop' then you're also probably wrong too. When flash drives drop below about $1/GB (and it's already close) there will be little advantage in mechanical disks for most users. It doesn't matter if the disk is bigger if you're only using 10% of the capacity, and it's slower than the alternative and uses more power.

    --
    I am TheRaven on Soylent News
  4. Prediction eh by xtal · · Score: 4, Insightful

    The fact a major, respected, industry leader has predicted an upstart new technology will not surpass the incumbent technology is an indication it is almost certainly false.

    --
    ..don't panic
  5. Very old article by iYk6 · · Score: 4, Insightful

    today, a typical 500 GB hard drive costs about $100

    This article must be several years old. In present day, a 1TB hard drive costs about $80.

    October 23rd, 2009 By Lisa Zyga

    Doh!

  6. Re:Fragmentation by Darkness404 · · Score: 4, Informative

    "more predictable lifespan"? I take it someone hasn't had a drive head crash... SSDs have wear-leveling and usually on sectors that go bad it is still readable, you just can't write to it. HDDs are more prone to cataclysmic failure compared to SSDs, a SSD usually won't break unless you manage to physically break the circuit board, compared to the fragile platters of the HDD, etc. SSDs fail nicely, HDDs do not.

    --
    Taxation is legalized theft, no more, no less.
  7. Re:Fragmentation by BikeHelmet · · Score: 4, Interesting

    You're correct, but I have two nitpicks.

    First, don't confuse NAND used in SD cards and stuff with the same NAND used in SSDs. They're quite different qualities.

    I've had SD cards drop 1/8th their capacity after days of heavy use. SSDs, however, have higher quality NAND and wear-levelling controllers. For Linux, they have better filesystems, too.

    Second, up until the newest generation, most SSDs were susceptible to debilitating speed loss after some usage. To be safe, you had to half the benchmarked results. With TRIM and smarter controllers, this is mostly solved, but very heavy usage for extended periods will still result in speed loss. Remember, on an HDD deleting is basically a free operation, but on an SSD it has to physically erase. This would be most noticeable for say... a security camera box recording a dozen or more streams 24/7.

  8. 40 years of work isn't really a breakthrough... by dlenmn · · Score: 4, Informative

    I wouldn't exactly call PCRAM a breakthrough -- people have been working on it since the 1960s. There are a host of new non-volatile memory technologies that claim to be read for prime time Real Soon Now. Just look at the list of upcoming non-volatile memory technologies in the right column at the wikipedia article. You can't go out and buy most of them yet, but any of them could be winners (besides PCRAM, MRAM is available from Everspin/freescale -- you can buy some on DigiKey if you want).

    I wouldn't hold my breath for any of these to replace hard drives, they've been a long time in coming and they're still not really here yet. Hopefully by 2020.