Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Data Storage Hardware Technology

Consortium Roadmap Shows 100TB Hard Drives Possible By 2025 215

Posted by samzenpus from the in-the-future dept.
Lucas123 writes An industry consortium made up by leading hard disk drive manufacturers shows they expect the areal density of platters to reach 10 terabits per square inch by 2025, which is more than 10 times what it is today. At that density, hard disk drives could conceivably hold up to 100TB of data. Key to achieving greater bit density is Heat-Assisted Magnetic Recording (HAMR) and Bit Patterned Media Recording (BPMR). While both HAMR and BPMR will increase density, the combination of both technologies in 2021 will drive it to the 10Tbpsi level, according to the Advanced Storage Technology Consortium (ASTC).
This discussion has been archived. No new comments can be posted.

Consortium Roadmap Shows 100TB Hard Drives Possible By 2025 More

Consortium Roadmap Shows 100TB Hard Drives Possible By 2025

Comments Filter:

  • But what about (Score:2, Informative)

    by Anonymous Coward

    http://hardware.slashdot.org/story/14/11/25/2027220/how-intel-and-micron-may-finally-kill-the-hard-disk-drive

  • How about transfer rate and reliability? (Score:5, Interesting)

    by mlts ( 1038732 ) on Wednesday November 26, 2014 @10:22PM (#48471837)

    MTBF and transfer rate numbers are boring... but those can be just as important, if not more, than the drive's capacity.

    With high capacity tier 3 drives, one reason that RAID 6 (or a RAID 50 setup with tiers/groups of disks) is used is because it can take days to rebuild a blown drive. If drives continue to have larger capacities, but I/O stays the same, then we will need to add more parity drives to RAID arrays to support multiple drive failures and still keep the data accessible, better algorithms that run in the background to detect (and fix) bit rot, and bigger/smarter caches.

    Maybe this is just me, but I'd rather see drives with double the MTBF than double the capacity. I can always add more drives and arrays. A failed disk will cost time no matter what, even if it is just walking to the server room, pulling it out and replacing it with a spare. For non-enterprise customers, a failed drive can be catastrophic since not many users have RAID arrays for protection.

    • There was an article recently (can't remember where) that made the case that with slowing density increase the lifetime of HDDs has to increase because you're not going to replace them after two or three years anyway because the next generation is so much better. Much better MTBF is clearly possible - just look at HGST versus the rest in the Backblaze reports.

      Yup, in large arrays the trend is to go beyond RAID6 - see e.g. NetApp's DDP. Too bad there's so little technical info available about it.

      • Re: (Score:2)

        by fnj ( 64210 )

        1) If one is not using ZFS with RAID-Z2 (double parity) or RAID-Z3 (triple parity), one is an idiot. I think we're in basic agreement, but I'm just emphasizing that no crude RAID technology can compare with ZFS.

        2) You do understand that MTBF has nothing to do with design lifetime. Right?

        • Fuck that shit. RAID 0 with daily backups for home use, RAID 10 with daily backups for any servers. If you're paranoid add a hot spare.
          Oh, and SSDs only, even for servers. If you need more space, put on your big boy pants and fork over the cash.

      • There was an article recently (can't remember where) that made the case that with slowing density increase the lifetime of HDDs has to decrease because you're not going to replace them after two or three years anyway because the next generation is so much better.

        Fixed that for you. Why would hard drives be exempt from the forced obsolescence business model?

    • Transfer rate is proportional to areal density. If the areal density increases 10x, then for each rotation of the platter 10x as many bits pass under the read/write heads, and (sequential) transfer rate increases by 10x as well.

      The problem for HDDs is and always has been random seek times - the time it takes to move the read/write heads to a new location and wait for the proper part of the platter to spin underneath. Look at this 7200 RPM HDD reivew from 2003 [google.com]. The sequential read/write speeds (45/27 MB

      • Re: (Score:3)

        by fnj ( 64210 )

        As long as only a single head is active at a time, reading a single track at a time, transfer rate is proportional to LINEAR density, not AREAL density.

        • As long as only a single head is active at a time, reading a single track at a time, transfer rate is proportional to LINEAR density, not AREAL density.

          We used to have drives that read/wrote multiple heads at a time. But the drives are too dense for that. I think the last ones that did it had glass platters to reduce expansion. Now we'd need a separate arm for each platter. Some drives have two sets of arms, but that's still only two read/write tasks simultaneously.

      • That doesn't work linearly. It's the square root of 10: 3.16

        Ten times the density means 3.16 times the amount of tracks beside each other and 3.16 times the amount of bits per track.
        If the head still reads only one track that means the amount of bits it can read in a given time is 3.16 times as high.
        Not 10.

    • Sadly, the trend with SSDs is the same: higher density without any regards to MTBF.

    • I'm not sure hard drives will still be used in the same way. It's increasingly looking like SSDs will take over for a lot of things, and hard drives will take the role that once was filled by tape: Backups, archival and the lowest rank of tiered storage. In which case you won't be using RAID or even a conventional filesystem, but some form of object storage.

    • Re: (Score:2, Funny)

      by Anonymous Coward

      Regarding MTBF, did you overlook the new recording technology? They are using a HAMR. The platter will consistently break on first write.

    • ...I'd rather see drives with double the MTBF than double the capacity.

      That's not the way the market sees it. Increased reliability can only hurt sales. Our economy system requires perpetual growth, or it will collapse. Planned obsolescence is a very old method of keeping the growth alive. There is no reason that a computer and all its components can't last 20-25 years like our old TVs and refrigerators did.

  • I remember 1GB drive going for ~$100 in 1998. 1TB drives have been under $100 for a few years. We will probably see 1PB drives by 2025

    • I remember when I upgraded from my Armstrad cpc 6128 to a 386sx machine which was my first box with a HDD. I choose the large one then with 40MB. Somewhen at the last third of the eighties. Those things were expensive then and I could have got a used car for the price of it

  • 2 types of drives for the foreseeable future.... SSD main drive for the OS and programs, HDD for storing pron. Better get used to it.

    Here is my desktop setup:
    - One fast SSD main drive
    - One 3 TB HDD for video/picture/mp3/document storage
    - Second 3TB HDD, gets synched to the first HDD nightly as a backup

    SSD gets a manual disk image stored on the first HDD once in a while.

    I feel pretty good with this setup, as I'm protected from any single drive failure. Also I have some accidental deletion/corruption protecti

    • Every personal laptop/desktop/server box has a SSD which holds the machine base (boot, swap, root, home dirs, etc). For laptops and workstations, the SSD also holds nominal data and there is no HDD at all. On the servers, the SSD is beefier and also caches the HDD.

      Bulk data is stored on a large 2TB HDD on the server and exported via NFS and samba. There's another 2TB spare on the server.

      There is a backup machine on the LAN in another part of the house with a 2TB HDD and there is an off-site backup machi

  • Limitless? (Score:3)

    by hcs_$reboot ( 1536101 ) on Thursday November 27, 2014 @12:37AM (#48472325)
    In a few more years, everybody will have enough data space in a laptop to store the whole humanity data (as long as it's not recursive). The Internet in a cache...

  • heat and patterned-media (Score:3)

    by markhahn ( 122033 ) on Thursday November 27, 2014 @12:47AM (#48472359)

    interesting that these density improvements could both be applied to tape as well.

    yeah, "tape yuck", but it makes a certain amount of sense for cool data. which we have lots of, always increasing. tape seeks are a minute or so, and if density is competitive, tape has a good chance to beat disks on price. certainly on power. the real problem is that the tape industry seems to be sort of demographically challenged...

  • So what happened to shingled, is it dead?

  • trillions of bits, why one head per platter? (Score:5, Interesting)

    by raymorris ( 2726007 ) on Thursday November 27, 2014 @01:13AM (#48472441) Journal

    Somewhat off topic, but while we're talking about drives:

    We put millions of transistors on a chip. Millions of photodetectors (pixels) in your phone's camera, a million pixels on it's display. Yet our hard drives have ONE sensor that swings back and forth on a mechanical arm?!?! Why the heck isn't the read/write head a strip, with a few thousand "pixels", so it can read any sector as the platter spins beneath it, without swinging the heads back and forth? That would eliminate seek time.

      If needed, you could move the strip back and forth a thousandth of an inch to align a head with one of it's four tracks. That'd be a lot quicker that moving the head a full inch as they do now.

    So presumably there is some good reason that can't be done. Still, an additional arm exactly like the existing one, but on the opposite side of the platter, would cut rotational latency in half and increase throughout up to 100%. Seems like an easy win.

    • Re: (Score:3, Insightful)

      by Anonymous Coward

      Before hard disk drives, they had magnetic drums. It was a large drum that spun at a constant speed and had a separate head per track. You could read from any track, but only once the data you wanted to read rotated to be under the head for that track. Once upon a time computers used drums for main memory and core for cache.

      Your idea for an arm with a head for every track is essentially a more modern drum. That and the two-armed HD are both ideas that are likely more expensive to be worth it. The head mecha

      • Most disk have multiple platters, so already have multiple heads simultaneously reading multiple tracks. Replicating the actuator (motor+magnet + electronics) would be the expensive bit.

    • an additional arm exactly like the existing one, but on the opposite side of the platter, would cut rotational latency in half and increase throughout up to 100%. Seems like an easy win.

      Drives like this exist, I don't know if any are being sold at the moment but they've certainly been made. I believe the strategy has been used both for dual-attach and for increasing throughput. Some drives also used to read/write multiple tracks (that is, on multiple platters) at a time, but (as has been covered elsewhere in this thread) it got to be too complicated to keep everything aligned as the temperatures and rotational velocities increased.

      • Re: (Score:2)

        by tlhIngan ( 30335 )

        Drives like this exist, I don't know if any are being sold at the moment but they've certainly been made. I believe the strategy has been used both for dual-attach and for increasing throughput. Some drives also used to read/write multiple tracks (that is, on multiple platters) at a time, but (as has been covered elsewhere in this thread) it got to be too complicated to keep everything aligned as the temperatures and rotational velocities increased.

        Alignment isn't an issue - there's no alignment on a modern

        • Alignment isn't an issue - there's no alignment on a modern drive. Instead, at the factory, they write a set of servo tracks all over the platters which do the aligning for you - basically the head seeks to approximately the right position and starts reading, and the servo track tells it where it actually is, so feedback gets the head to the right track.

          Sigh. Alignment is an issue, because each platter has its own alignment. That means that when you're reading/writing one platter, you're not aligned for the other platters. That's why you can't have multiple heads on one armature (which has multiple arms, all fixed together) and read/write multiple platters at once.

          the bigger reason why two actuators didn't work is far simpler - think multiprocess programming. Both actuators could read or write data to the platters (of which there was one set) and if you screwed up the order of the accesses, you could easily write the wrong thing

          You're being ridiculous. That's true no matter how many actuators you have — if you screw up, you write the wrong thing. Even if you only have one actuator, if you write the data to the wro

        • This cache and especially native command queuing (ncq), the drive ALREADY has to pay attention to the sequence in which operations are carried out. A read requested first, then a write, might already be done in reverse order, requiring a check that the sector read isn't the same one written.

          I don't see any reason reading and writing two sectors at a time makes any fundamental difference.

  • Cheap $300 laptops these days slap in a 500GB HDD to satisfy the requirement of a hard drive. A basic 500GB disk is what they can source cheaply and easily from the market. However, I suspect that they could ship a smaller capacity disk as well, if that allows the manufacturer to shave off some of the laptop's price. What follows is, that I also suspect that when making a 128 GB SSD becomes cheaper to manufacture than a mechanical HDD, many low-end laptops will move to the SSD format.

    • Happens sort of in announced $200 laptops. You get 32GB eMMC soldered on the motherboard and can't add or change anything - beware of what you ask for lol.

  • ...especially when the *AA congloms get their way as they usually do in forcing ISPs to block certain content.

    "But it's to protect the children!" Bullshit, try shutting down the child traffickers accounts on facebook and ban advertising for foster carers for financial incentives - in fact, ban financial incentives for looking after other peoples' kids and instead try helping the families instead of making shit up about them. The best place for a child is with the family he was born into, NO EXCEPTIONS. If h

    • Re: (Score:2)

      by Kjella ( 173770 )

      "But it's to protect the children!" Bullshit, try shutting down the child traffickers accounts on facebook and ban advertising for foster carers for financial incentives - in fact, ban financial incentives for looking after other peoples' kids and instead try helping the families instead of making shit up about them. The best place for a child is with the family he was born into, NO EXCEPTIONS. If his entire family is dead, THEN you can talk about adoption, otherwise it's not adoption, it's trafficking.

      No exceptions? Have you any idea how bad violence, sexual abuse, neglect and so on can get? In the worst cases, children die. Foster parents are paid because they tend to get deeply traumatized kids with behavioral problems who need lots of care and therapy. The alternative is often institutions because leaving them with the parents was not an option. You rarely if ever get paid for adopting healthy, normal children because there's many childless couples that'll do that job for free.

    • The best place for a child is with the family he was born into, NO EXCEPTIONS. [...] musicians don't make anything on CD sales (the last person who did died of a drug overdose, his name was Michael Jackson

      And his father beat the living shit out of him. And look at how well he turned out! Boy, I'm sure he's happy today!

      • Re: (Score:2)

        by ihtoit ( 3393327 )

        I'm pretty sure he's dead.

        • I'm pretty sure he's dead.

          So you can agree that being raised by his own parents didn't work out so well, right? He destroyed his face out of low self-esteem in spite of being one of the best-loved entertainers in history, and died of a prescription drug overdose. Now, can you prove that being raised by someone else wouldn't have been better for him?

          • Re: (Score:2)

            by ihtoit ( 3393327 )

            no I don't agree on that at all. Being brought up by someone else: can you prove it could? I can provide ample anecdotal evidence that being brought up by anyone other than natural parents breeds psychopaths (R V Stafford 2010 where a 24yo out of the care system and just out of prison on parole for arson reckless immediately attempted to murder three entire families, including his own, by petrol bombing their homes in the middle of the night: R V Bacon (1994?) 18yo just aged out of the care system jailed fo

            • I can provide ample anecdotal evidence that being brought up by anyone other than natural parents breeds psychopaths

              Oh, so nothing substantive then. Just as I believed.

              Oh, by the way, MJ didn't kill himself, his doctor killed him

              Yes, that's quite common.

              • Re: (Score:2)

                by ihtoit ( 3393327 )

                I gave you two very substantive examples out of many. BAILII is bursting with them.

                • I gave you two very substantive examples

                  There is no such thing, only substantive evidence, which test your examples fail. You've utterly failed to show anything whatsoever.

  • Who would need that ? (Score:4, Insightful)

    by bobjr94 ( 1120555 ) on Thursday November 27, 2014 @04:23AM (#48472959) Homepage
    The average new computer being sold today sits on a desk in an office or is a facebook machine at home. It will have in it 500GB to 1TB of storage on average ? Then whats the actual usage, 20% or less ? I have people asking me all the time, my computer is slow do I have too many pictures on it ? I look at their drive, 482GB capacity, 404GB free.

    Sure there are some users who have hundreds of movies stored on their computer and businesses and datacenters who would love a drive like that but by number of computers, thats a small percentage. A majority of computers would do much better with just a SSD 1/4 the size of the HDD they currently have. A faster system overall, bootup times cut by 60%, 20-30 minutes more battery life in laptops....

  • We'll all be able to store all our "home movies" and photos on one drive!

  • To increase tenfold in 11 years, the Kryder rate https://en.wikipedia.org/wiki/... [wikipedia.org] would have to jump from 15%/year to 23%/year. While this is not fundamentally impossible, in an era of diminishing revenue for magnetic storage I can't see it happening.

Slashdot Top Deals

Every nonzero finite dimensional inner product space has an orthonormal basis. It makes sense, when you don't think about it.

Close