[ale] "per-process virtual address space" limit only for x86 architecture?

Jerry Yu jjj863 at gmail.com
Tue Jul 29 00:12:09 EDT 2008


thanks, Michael.
The boxens have 32G RAM each,  thus should be all within reach on RHEL
5.1/x86_64.

2008/7/28 Michael B. Trausch <mike at trausch.us>

> On Mon, 2008-07-28 at 15:46 -0600, JK wrote:
> > Do the 64-bit archs support bigger pages than 4MiB?  Even on x86-32
> > with PAE, a fully-decked-out (64G) server was using a huge chunk of
> > kernelspace just for pagetables and the physical page bookkeeping.
> > I'd expect that would definitely have to change when squaring the
> > address space.
>
> On the IA-32, there are 4 KiB and 4 MiB page sizes [1]; on the x86-64,
> in Long Mode, you can have page size that are 4 KiB, 2 MiB, or 1 GiB
> [2].  Not sure why 4 MiB seems to be missing from the x86-64
> architecture, but it is supported in Legacy Mode and probably
> Compatibility Mode, I should hope, or 32-bit software that uses a 4 MiB
> page size wouldn't run.  :)
>
>        --- Mike
>
> [1] http://www.cse.unsw.edu.au/~cs9244/06/seminars/06-nfd.pdf<http://www.cse.unsw.edu.au/%7Ecs9244/06/seminars/06-nfd.pdf>
> [2] http://en.wikipedia.org/wiki/X86-64#Virtual_address_space_details
>
> --
> My sigfile ran away and is on hiatus.
>
> _______________________________________________
> Ale mailing list
> Ale at ale.org
> http://mail.ale.org/mailman/listinfo/ale
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.ale.org/pipermail/ale/attachments/20080729/8b2d3bf9/attachment.html 


More information about the Ale mailing list