Re: [RFC 10/13] Memoryless nodes: Fix GFP_THISNODE behavior

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

On 14.06.2007 [09:07:04 -0700], Nishanth Aravamudan wrote:
> On 14.06.2007 [00:50:36 -0700], clameter@sgi.com wrote:
> > GFP_THISNODE checks that the zone selected is within the pgdat (node) of the
> > first zone of a nodelist. That only works if the node has memory. A
> > memoryless node will have its first node on another pgdat (node).
> > 
> > GFP_THISNODE currently will return simply memory on the first pgdat.
> > Thus it is returning memory on other nodes. GFP_THISNODE should fail
> > if there is no local memory on a node.
> > 
> > 
> > Add a new set of zonelists for each node that only contain the nodes
> > that belong to the zones itself so that no fallback is possible.
> 
> Should be
> 
> Add a new set of zonelists for each node that only contain the zones
> that belong to the node itself so that no fallback is possible?
> 
> This is the last patch in the stack I should based my patches on,
> correct (I believe 11-13 were mis-sends)?
> 
> Will test everything and send out Acks later today, hopefully.

Tested on a 4-node ppc64 w/ 2 memoryless nodes and a 4-node x86_64 w/
no memoryless nodes, with my patches applied on top (will send out the
latest versions again).

All get

Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>

Thanks for doing this work, Christoph!

-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>