[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Sat, 11 Nov 2006 09:08:51 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Lee Schermerhorn <Lee.Schermerhorn@...com>
Cc: clameter@....com, hch@....de, davem@...emloft.net,
linux-kernel@...r.kernel.org, netdev@....sgi.com,
linux-mm@...ck.org
Subject: Re: [PATCH 2/3] add dev_to_node()
On Fri, 10 Nov 2006 13:28:25 -0500
Lee Schermerhorn <Lee.Schermerhorn@...com> wrote:
> On Fri, 2006-11-10 at 10:16 -0800, Christoph Lameter wrote:
> > On Wed, 8 Nov 2006, KAMEZAWA Hiroyuki wrote:
> >
> > > I wonder there are no code for creating NODE_DATA() for device-only-node.
> >
> > On IA64 we remap nodes with no memory / cpus to the nearest node with
> > memory. I think that is sufficient.
>
> I don't think this happens anymore.
In my understanding , from drivers/acpi/numa.c,
a node is created by a pxm found in SRAT table at boot time.
the node-number for the pxm which was not found in SRAT at boot time is "-1".
please check how acpi_map_pxm_to_node() is used.
If pci's node-id is based on pxm, checking return vaule of pxm_to_node()
will be good.
-Kame
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists