Re: Linux and sparse memory (was Re: Breaking the 64MB barrier)

H. Peter Anvin (hpa@transmeta.com)
20 Oct 1998 04:29:54 GMT

Followup to: <v03130306b251280497cf@[130.161.115.44]>
By author: "J.D. Bakker" <bakker@thorgal.et.tudelft.nl>
In newsgroup: linux.dev.kernel
>
> At 8:13 AM +0200 19-10-1998, david parsons wrote:
> > A brute-force memory scan might be useful, but it could get unhappily
> > bitten by memory holes, and until Linux supports sparse memory, it's
> > somewhat pointless to look above a memory hole.
>
> Is it true that the kernel has problems on machines/architectures where
> main memory isn't contiguous ? That would be quite a downer for my plans to
> build a Linux-running StrongARM board, as the DRAM banks on a SA-1100 have
> pretty large holes in between (in physical address space).
>

No; main memory is noncontiguous on the i386 for example (there is a
big memory hole between 640K and 1024K) and the kernel handles it just
fine. It makes it harder to make the boot phase work properly, but it
isn't something inherently hard.

> Jan-Derk Bakker.
> [Coming to a theatre near you: inexpensive SA-1100 boards. If I get Linux
> to run on them, that is]
>

Cool :)

-hpa

-- 
    PGP: 2047/2A960705 BA 03 D3 2C 14 A8 A8 BD  1E DF FE 69 EE 35 BD 74
    See http://www.zytor.com/~hpa/ for web page and full PGP public key
        I am Bahá'í -- ask me about it or see http://www.bahai.org/
   "To love another person is to see the face of God." -- Les Misérables


-
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.tux.org/lkml/