Forgot your password?
typodupeerror
Data Storage

HDD Manufacturers Moving To 4096-Byte Sectors 442

Posted by CmdrTaco
from the zomg-the-world-will-collapse dept.
Luminous Coward writes "As previously discussed on Slashdot, according to AnandTech and The Tech Report, hard disk drive manufacturers are now ready to bump the size of the disk sector from 512 to 4096 bytes, in order to minimize storage lost to ECC and sync. This may not be a smooth transition, because some OSes do not align partitions on 4K boundaries."
This discussion has been archived. No new comments can be posted.

HDD Manufacturers Moving To 4096-Byte Sectors

Comments Filter:
  • by gbjbaanb (229885) on Monday December 28, 2009 @11:39AM (#30571538)

    whoooooo. WinXP is end-of-life? You'd best tell that to all the millions of users (including big businesses) out there.

    What that's you say? Upgrade to Windows 7 and use its perfectly infallible XP mode?

    Ah, I understand now. Hi Bill, how's Steve getting on, still a bit sweaty and concerned he's not selling enough?

  • by Himring (646324) on Monday December 28, 2009 @12:01PM (#30571818) Homepage Journal
    This may not be a smooth transition, because some OSes do not align partitions on 4K boundaries.

    "One life ends; another begins"
  • by lorenlal (164133) on Monday December 28, 2009 @12:09PM (#30571928)

    Eventually, you have to put a line in the sand. If you push off the deadline, manufacturers will still take their time, and they'll be in the same place 9 years and 11 months from now.

    Example: IPv6.

  • by alen (225700) on Monday December 28, 2009 @12:12PM (#30571960)

    MS has a clear support policy. Maybe you like Apple's 3 year support policy better than Microsoft's 10 year 7/3 policy?

  • by drinkypoo (153816) <martin.espinoza@gmail.com> on Monday December 28, 2009 @12:30PM (#30572150) Homepage Journal

    Except that pretty much every OS in use now has IPv6 support.

    Except that name resolution is broken for IPv6 on Windows XP, which is the operating system not supporting 4k sectors that people are complaining about... so IPv6 was a super shitty example for you to try to defend.

  • Re:disable ECC? (Score:5, Insightful)

    by Waffle Iron (339739) on Monday December 28, 2009 @12:31PM (#30572162)

    It doesn't seem like a great idea to me. There are a lot of different ECC algorithms and implementations. It seems to me that it would be better to let the hard drive manufacturer select one that closely matches the expected signal and noise characteristics of a particular disk drive rather than some generic algorithm in the filesystem.

  • by LOLLinux (1682094) on Monday December 28, 2009 @12:31PM (#30572164)

    Or the Linux policy of barely a year.

  • Re:disable ECC? (Score:3, Insightful)

    by Izmunuti (461052) on Monday December 28, 2009 @12:52PM (#30572468)

    Ugh. Sounds like a bad idea. Hard drive channels are noisy. How will ZFS fare if lots and lots of sectors read from every drive have at least a couple of bits in error? With no ECC in the drive, errors would be common.

  • Re:disable ECC? (Score:2, Insightful)

    by Anonymous Coward on Monday December 28, 2009 @12:59PM (#30572588)

    One of the reasons there is so much BS and hype surrounding ZFS...

    Drives already do and have for years done error correction and most revector badblocks dynamically and the OS never even knows. It's part of how drives are so reliable as it is. Pushing that logic up in to the filesystem just introduces more complexity to the filesystem and reduces overall reliability.

    Talk to any drive engineer, what they want the most is for filesystem engineers to stop trying to outsmart the drive guys. THere is not a guaranteed relationship between a sector and it's location on the disk, the drive and the firmware it has will try to figure that out the best way it can.

    What they really should spend their time on is filesystems and their relationship with cache will have to change in the next decade, solid state medias don't need caching the same way disks do, I fully expect disks to start coming as hybrid devices with solid state storage and disk based storage as a singular device. There are some relatively complex problems to solve to provide media awareness to all the storage algorithms.

  • by Sir_Lewk (967686) <sirlewkNO@SPAMgmail.com> on Monday December 28, 2009 @01:03PM (#30572648)

    That's ok, the linux policy of free upgrades more than makes up for that for me.

    But hey, you're a known troll, logic doesn't have much to do with this does it?

  • Re:disable ECC? (Score:1, Insightful)

    by Anonymous Coward on Monday December 28, 2009 @01:05PM (#30572674)

    An ECC should be implemented as close to where the problem occurs as possible. For a hard drive, this means on sectors, not (abstract) blocks. Otherwise you'll see the OS rewriting clean sectors that are parts of unclean blocks (if the block size is greater than the sector size), and gain nothing if the block size is smaller than the sector size.

  • Re:disable ECC? (Score:3, Insightful)

    by drinkypoo (153816) <martin.espinoza@gmail.com> on Monday December 28, 2009 @01:06PM (#30572700) Homepage Journal

    If you were going to eliminate ECC in one place or another, it wouldn't be on the drive. The drives have to operate in the real world of analog states, while the filesystem works in the virtual world of "whatever the disk actually feeds me". Disks have to have correctable ECC just to reliably give you accurate data from magnetic media at these densities. It would make more sense to upgrade the on-disk ECC and give the filesystem better access to the disk's ECC.

  • by pclminion (145572) on Monday December 28, 2009 @01:31PM (#30573052)
    ECC means "error correcting code." It isn't just a way of detecting errors, it's a way of operating even in the face of them. As such, the length of the ECC chunk is proportional to the sector payload size. So going to a larger sector does not reduce ECC overhead, unless you switch to a more efficient ECC code (and you can do that without changing sector size). The other stuff, like sync, is fixed size and your argument does apply to that. The real reason for using a 4-kilobyte sector is because it exactly matches the size of a VM page on most consumer architectures, therefore guaranteeing at a hardware level that a single page worth of information cannot be fragmented.
  • by Anonymous Coward on Monday December 28, 2009 @01:40PM (#30573202)

    This brings back memories of the HPFS disasters in Asia where they used 4k disks back in the day... and HPFS was set to use 512 sector sizes.....

    Surprising nothing changes that much.

  • by kbielefe (606566) <karl.bielefeldt+ ... m ['il.' in gap]> on Monday December 28, 2009 @01:49PM (#30573312)

    Sidestepping your ignorance or deliberate deception on periods of typical Linux support contracts, it still amazes me that comments touting Microsoft support periods continue to appear on articles like this. Who cares if support goes out 10 years if you can't buy a new hard drive that will work with the OS? It's articles and comments like this that give me difficulty discerning what exactly Microsoft "support" entails. A warm fuzzy number you can call where they say you have to upgrade to Windows 7 for that hardware to work?

  • by Leebert (1694) * on Monday December 28, 2009 @01:52PM (#30573364)

    That's ok, the linux policy of free upgrades more than makes up for that for me.

    You know, in a production computing environment, the cost of the software is pretty darn close to the least significant part of the costs of an upgrade, right?

  • Re:Factors of 10 (Score:3, Insightful)

    by m1xram (1595991) on Monday December 28, 2009 @02:01PM (#30573446)

    That's Grey Code. 000, 001, 011, 010, 110, 111 and the joke should read...

    There are only 11 types of old timer geeks... :-)

  • by Idiot with a gun (1081749) on Monday December 28, 2009 @02:32PM (#30573844)
    I've never understood this long living love for XP. The longer I work with it (I'm a support tech), the more I hate it. It genuinely has the feeling of an OS that was organically grown, without any fore planning. Wireless control often ends up in the hands of a user-space program instead of in the OS (wtf?), and updates are done through a god awful activex webpage. Blech. The long term (and even short term) stability of XP these days is poor at best, and I have no clue why everyone claims to love it.

    On the other hand, most people I've met who make fun of Vista, never used it. My dad was slamming it earlier "Did you ever use it?" "... No". The vast majority of complaints about it stemmed from 2 problems:
    • The so called "power users" always complain about any change, regardless of whether or not it's good.
    • Underpowered machines were marked as "Vista Capable" when they were not.

    And to honest, 7 is quite good. This is coming from a die hard Linux user (who actually liked Gentoo).

  • Re:Factors of 10 (Score:1, Insightful)

    by Anonymous Coward on Monday December 28, 2009 @05:37PM (#30576032)

    in that case, there would be no hardware "byte" since "byte" depends on
    the character set. byte size may even be variable, as in utf-8.

  • by butlerm (3112) on Monday December 28, 2009 @07:29PM (#30577074)

    This would require a firmware change, and for SATA drives, it is just not going to happen. High end SCSI drives maybe.

  • by butlerm (3112) on Monday December 28, 2009 @07:38PM (#30577152)

    Making the drive handle things at the file level is the equivalent of turning it into a NAS device where the system software would generally be inaccessible, unmodifiable, and un-upgradeable, unfortunately. It would still be an interesting engineering challenge, of course.

  • Re:Factors of 10 (Score:3, Insightful)

    by afidel (530433) on Monday December 28, 2009 @09:24PM (#30577952)
    Dude, MS's KB for kilo-byte predates the silly KiB definition by about two decades (KiB was only adopted as a standard in 2000 and proposed in 1998, MS DOS traces to M-DOS in 1979). Oh and as to performance, almost nothing writes in 512byte chunks, 4KB chunks are about the smallest defaults for current platforms and 8KB is becoming more common.
  • Re:Factors of 10 (Score:4, Insightful)

    by drsmithy (35869) <drsmithy@gmailFREEBSD.com minus bsd> on Monday December 28, 2009 @09:42PM (#30578086)

    It's also worth noting that this is Microsoft's fault. Other OS's are doing it properly. Microsoft only does it properly when it benefits them. HDD manufacturers have faced numerous lawsuits simply because Microsoft is using the wrong prefix, so people feel cheated out of space.

    I hate to rain on your anti-Microsoft parade, but back when hard disk manufactures realised they could make their hard disks look bigger than they really were, capacities were still being measured in 10s of MB, and *all* OSes were using power-of-two prefixes.

    The rest of your rant is about as accurate.

Money will say more in one moment than the most eloquent lover can in years.

Working...