Alan Cox wrote:
>
> > Alas, yes. If there is a power of two rule, it should surely be documented in
> > the code. The existing code in page.h encourages people to make improper
> > changes. The only other value I know of that works correctly is 0x80000000.
>
> Yep - and that documentation is indeed a real bug.
Using 0x80000000 is probably better anyway, no? Just how many megs less
than 2GB does that give us - something like (2048-30) total? Possibly
better than using 0x70000000, since the way I figure it, that robs us of
256 megs of process address space. If you want a single process to use
as much RAM as possible (like nearly 2GB, and this isn't a silly case in
numerical codes) then it seems like you're actually better off
sacrificing the 30megs (or 50 or whatever) and using 0x8...
Neil
ps: who volunteers to remove the man-trap in page.h?
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
