Re: reiserfs empirical study (very long)
Thorsten Kukuk wrote:
> On Thu, May 31, Steven Hanley wrote:
> > On Wed, May 30, 2001 at 05:39:09PM -0700, Mike Fedyk wrote:
> > > On Wed, May 30, 2001 at 02:09:16PM -0700, Andrew Sharp wrote:
> > > > Cameron Berkenpas wrote:
> > > > >
> > > > > I thought I read somewhere that XFS is working on PPC..
> > > > > I take it that info was incorrect?
> > > >
> > > > I think what you read is that "...they are working on it for PPC."
> > > > Supposedly an endian-fixed version should be available soonish.
> > > >
> > > I would believe that XFS wouldn't have any endian problems; since XFS was
> > > origionally on a big-endian system (mips/irix) before.
> > unfortunately not, they had to add a lot of code and change a fiar bit of
> > stuff to get XFS to work inside linux, all this work and development was done
> > on x86 boxen, as to how far they are towards having this working on linux/ppc
> > now I dont know.
> Since XFS runs stable on UltraSPARC, I see now reason why it should
> not work on Linux/PPC. I don't know if the on-disk-format is compatible
> between big- and little-endian systems, but this is in the moment no
> major problem for me.
I was misquoting someone else when I said it had endian problems.
My bad. I should have said that it has powerpc problems, but don't
take that as gospel, because I'm just parroting someone else. As
for sparc, they say that you can't build a 2.4[.2] kernel on sparc32
right now, so that leaves me out. I even tried SGI's xfs kernel
source (on my sparc32 system), it demands egcs-2.91.66 to build, as
if. I think maybe I'll try it on the ol' powermac ....