Re: Corruption Stats (fwd)

Rogier Wolff (R.E.Wolff@BitWizard.nl)
Thu, 30 Jul 1998 09:39:03 +0200 (MEST)

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