Date: Fri, 29 Oct 1999 12:05:55 +0200 (CEST) From: Lars Gerhard Kuehl <kuehl@lgk.de> To: Mike Smith <mike@smith.net.au> Cc: hackers@FreeBSD.ORG, Chuck Youse <cyouse@paradox.nexuslabs.com> Subject: Re: Limitations in FreeBSD Message-ID: <XFMail.991029120555.kuehl@lgk.de> In-Reply-To: <199910290502.WAA03970@dingo.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 29-Oct-99 Mike Smith wrote:
>> > That's correct; it's why the ia32 architecture has a '32' in its name.
>>
>> I don't believe that's true. I don't have any hard evidence within easy
>> reach, but with the introduction of the Pentium, the address space was
>> increased. A user process, of course, can only have 4G of addressible
>> space (32-bit addresses) but the OS can map pages of the 4G space into a
>> larger area.
The Pentium and successors can address more than 4G
_physical_ memory, 32 or 64GB, I need to look into
the manual. But that feature needs to be explicitely
enabled.
>>
>> Something to do with 4MB pages instead of 4K pages.
>>
>> Again, I could be wrong on this one.
With extended physical addressing enabled the bigger
page size is 2MB instead of 4 MB.
> Think about it for a second. How big is a pointer?
The Intel architecture still supports segmented memory,
so the effective maximum pointer size is 48 bit.
Lars
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.991029120555.kuehl>