lkml.org 
[lkml]   [1998]   [Jul]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    SubjectRe: Corruption Stats (fwd)
    Date
    From
    Linus Torvalds wrote:
    >
    >
    > On Thu, 30 Jul 1998, Stefan Traby wrote:
    > >
    > > BTW: A drive following the SCSI-specs may cause disk-corruption
    > > under Linux (WCE=1). Data may still be in write-cache after
    > > shutdown and power-off. (I miss "synchronize cache").
    > > This is for shure a theoretical problem, but a practical bug.
    > > Or did I miss something ?
    >
    > No, you didn't miss anything.
    >
    > The thing has been discussed occasionally (very occasionally), and I don't
    > know what the proper response is. According to some people the better
    > drives make sure that they have enough rotational energy that they can
    > make sure they get their data written out even after powerdown, but
    > personally that sounds like science fiction to me (oh, I wouldn't be
    > surprised if there are some drives that do it, but I'd be surprised if
    > it's universal).

    It is VERY hard to use the rotational energy to write more than just
    one block. You would have the disk already spinning down, and you
    might still have to do a few seeks, and you still have to write a
    properly synchronized track.

    This "feature" was specified on a DEC 1.6G SCSI disk that we bought
    back in about '90. It said:
    The disk has enough power to finish writing a sector should the
    power go down.

    Thus any sector it would start writing, it would finish, even if the
    power goes down.

    But that was just ONE sector.

    Roger.

    --
    Actor asks a collegue: "To what do you owe your success in acting?"
    Answer: "Honesty. Once you've learned how to fake that, you've got it made."
    -------- Custom Linux device drivers for sale! Call for a quote. ----------
    Email: R.E.Wolff@BitWizard.nl || Tel: +31-15-2137555 || FAX: +31-15-2138217

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.rutgers.edu
    Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html

    \
     
     \ /
      Last update: 2005-03-22 13:43    [W:0.025 / U:30.528 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site