Re: RAID-6 support in kernel?

[Kasper Dupont <kasperd@daimi.au.dk>]

Roy Sigurd Karlsbakk wrote:
> 
> > > RAID-6 layout: http://www.acnc.com/04_01_06.html
> >
> > If it is supposed to survive two arbitrary disk failures something is
> > wrong with that figure. They store 12 logical sectors in 20 physical
> > sectors across 4 drives. With two lost disks there are 10 physical
> > sectors left from which we want to reconstruct 12 logical sectors.
> > That is impossible.
> 
> Might be the diagram is wrong.

Could be the case, so until I find another description I will
still not know how RAID-6 works.

> 
> > OTOH it is possible to construct a system with optimal capacity and
> > ability to survive any chosen number of disk failures. This can be
> > done using either a Reed-Soloman code or Lagrange interpolation of
> > polynomials over a finite field.
> >
> > However I guess those techniques would be inefficient in software.
> 
> Yeah? That's what the hardware RAID vendors all say, and I yet haven't
> seen one single test where Linux Software RAID can't beat hardware RAID.

Well, I'm not a hardware vendor. I just happen to have tried
doing it in software, and I wasn't able to do it efficiently.

> That is also after some testing I did on a high-end intel server at
> Compaq's lab in Oslo. How can RAID-6 be so much different?

I guess RAID-6 can be done efficiently in software. It is the
other encodings I'm worried about.

-- 
Kasper Dupont -- der bruger for meget tid på usenet.
For sending spam use mailto:razor-report@daimi.au.dk