Re: [PATCH] populated_map: fix !NUMA case, remove comment

[Nishanth Aravamudan <nacc@us.ibm.com>]

On 13.06.2007 [16:26:15 -0700], Christoph Lameter wrote:
> On Wed, 13 Jun 2007, Nishanth Aravamudan wrote:
> 
> > Well...maybe we can do better by just adding another GFP flag?
> > 
> > GFP_ONLYTHISNODE?
> > 
> > THISNODE has the current semantics, that the "closest" node is
> > preferred, which may be local, and it will succeed if memory exists
> > somewhere for the allocation you want (I think).
> 
> No we want one GFP_THISNODE working in a consistent way.

Ok, I've started auditing things. I have a final exam tomorrow, however,
so probably won't make much progress before then.

I did notice that ia64/mm/discontig.c actually already tries to deal
with memoryless nodes, but all static to that file. See
memory_less_mask. Probably can be replaced via an inverted
node_memory_map.

Are you sure just the VM needs to be audited? I'm going to try the other
way around and look at GFP_THISNODE callers and go up from there.

Will let you know what I find.

Thanks,
Nish

-- 
Nishanth Aravamudan <nacc@us.ibm.com>
IBM Linux Technology Center

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>