Re: [Xen-devel] Memory limit / xen for Conectiva

[Keir Fraser <Keir.Fraser@xxxxxxxxxxxx>]

> > On Fri, Sep 24, 2004 at 06:47:19PM +0100, Ian Pratt wrote:
> > > > (XEN) Initialized 1983MB memory (507888 pages) on a 1983MB machine.
> > > 
> > > Please can you send us the output of a native linux 2.4 or 2.6
> > > kernel booting. Your machine must have a memory hole, and we need
> > > to be smarter about parsing memory tables. You should be able to
> > > get 4GB working, but we have no plans to support PAE36. We're
> > > concentrating on x86_64.
> 
> >  BIOS-e820: 0000000000100000 - 000000007bff0000 (usable)
> >  BIOS-e820: 0000000100000000 - 0000000280000000 (usable)
> 
> Yep, we're probably missing the second of these.  Although its
> perfectly entitled to, its slightly baroque that your BIOS is
> placing the IO hole at just below 2GB rather than 4GB.
> 
> Porting some more Linux table parsing code shouldn't be hard. I
> guess we were going to see a machine like this sooner or later....

Unfortunately this is not the case. You've got a great big memory hole
between 2GB and 4GB. So the remaining 6GB of your memory are all above
the 4GB boundary. That memory is inaccessible when not using PAE-36
mode, which we do not support.

It may be possible to tweak BIOS settings to get more of your memory
into the low 4GB. Probably it is arranged as it is so that large-ish
I/O regions such as the frame buffer can be allocated below the 4GB
boundary without overlapping with any RAM (which would then become
inaccessible). It's worth a look...

 -- Keir


-------------------------------------------------------
This SF.Net email is sponsored by: YOU BE THE JUDGE. Be one of 170
Project Admins to receive an Apple iPod Mini FREE for your judgement on
who ports your project to Linux PPC the best. Sponsored by IBM.
Deadline: Sept. 24. Go here: http://sf.net/ppc_contest.php
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxxx
https://lists.sourceforge.net/lists/listinfo/xen-devel