Re: [PATCH v2] gfp.h: GFP_THISNODE can go to other nodes if some are unpopulated

[Christoph Lameter <clameter@sgi.com>]

On Mon, 11 Jun 2007, Nishanth Aravamudan wrote:

> > +	do {
> > +		next = next_node(nid, policy->v.nodes);
> > +		if (next >= MAX_NUMNODES)
> > +			next = first_node(policy->v.nodes);
> > +	} while (!NODE_DATA(node)->present_pages);
> 
> If something like Lee/Anton's patch were to go in (which, as Lee pointed
> out, I refreshed as Patch 1/3 in the series I posted a few days ago),
> this would be
> 
> 	while(!node_populated(nid))

Right. That would be much better.

> Presuming I understand everything correctly. Not sure which would be
> preferred, or if perhaps node_populated, rather than using a nodemask
> should just use NODE_DATA(nid)->present_pages?

I think the node_populate is better. Simple bitmap lookup.


--
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>