Jeff Squyres, le Mon 28 Feb 2011 21:18:52 +0100, a écrit :
> On Feb 28, 2011, at 2:02 PM, Samuel Thibault wrote:
> >> That would seem to imply that I should always hwloc_set_area_membind() if I want it to persist beyond any potential future swapping.
> > I guess that could be right, but it definitely deserves testing before
> > trusting potentially-outdated documentation :)
> Brice - did you see anything about this when reading the kernel code?
> > I don't remember such kind of document details for other OSes, in any case.
> Are you saying that other OS's don't promise anything about whether memory binding / policy is remembered for swapped-out pages?
I've not seen such promises in the documentation, at least (I however
have to say that I hadn't looked for it specifically either).