Re: [PATCH v4] page_alloc: allow migration of smaller hugepages during contig_alloc

[Gregory Price]

On Wed, Dec 03, 2025 at 09:14:44PM +0100, David Hildenbrand (Red Hat) wrote:
> On 12/3/25 21:09, Gregory Price wrote:
> > On Wed, Dec 03, 2025 at 08:43:29PM +0100, David Hildenbrand (Red Hat) wrote:
> > > On 12/3/25 19:01, Frank van der Linden wrote:
> > 
> > Worth noting that because this check really only applies to gigantic
> > page *reservation* (not faulting), this isn't necessarily incurred in a
> > time critical path.  So, maybe i'm biased here, the reliability increase
> > feels like a win even if the operation can take a very long time under
> > memory pressure scenarios (which seems like an outliar anyway).
> 
> Not sure I understand correctly. I think the fix from Mel was the right
> thing to do.
> 
> It does not make sense to try migrating a 1GB page when allocating a 1GB
> page. Ever.
> 

Oh yeah I agree, this patch doesn't allow that either.

I was just saying his patch's restriction of omitting all HugeTLB
(including 2MB) was more aggressive than needed.

I.e. allowing movement of 2MB pages to increase reliability is (arguably)
worth the potential long-runtime that doing so may produce (because we no
longer filter out regions with 2MB pages).

tl;dr: just re-iterating the theory of this patch.

~Gregory