On Wed, 23 Jan 2013 14:25:07 +
Mel Gorman wrote:
> On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
> >
> > reset_page_last_nid() is poorly named. page_reset_last_nid() would be
> > better, and consistent.
> >
>
> Look at this closer, are you sure you want? Why is
> Good question.
>
> There are 19 free bits in my configuration but it's related to
> CONFIG_NODES_SHIFT which is 9 for me (512 nodes) and very heavily affected
> by options such as CONFIG_SPARSEMEM_VMEMMAP. Memory hot-remove does not work
> with CONFIG_SPARSEMEM_VMEMMAP and enterprise
On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
>
> reset_page_last_nid() is poorly named. page_reset_last_nid() would be
> better, and consistent.
>
Look at this closer, are you sure you want? Why is page_reset_last_nid()
better or more consistent?
The getter functions for
On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
> On Tue, 22 Jan 2013 17:12:41 +
> Mel Gorman wrote:
>
> > From: Peter Zijlstra
> >
> > page->_last_nid fits into page->flags on 64-bit. The unlikely 32-bit NUMA
> > configuration with NUMA Balancing will still need an extra
On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
On Tue, 22 Jan 2013 17:12:41 +
Mel Gorman mgor...@suse.de wrote:
From: Peter Zijlstra a.p.zijls...@chello.nl
page-_last_nid fits into page-flags on 64-bit. The unlikely 32-bit NUMA
configuration with NUMA Balancing
On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
reset_page_last_nid() is poorly named. page_reset_last_nid() would be
better, and consistent.
Look at this closer, are you sure you want? Why is page_reset_last_nid()
better or more consistent?
The getter functions for
Good question.
There are 19 free bits in my configuration but it's related to
CONFIG_NODES_SHIFT which is 9 for me (512 nodes) and very heavily affected
by options such as CONFIG_SPARSEMEM_VMEMMAP. Memory hot-remove does not work
with CONFIG_SPARSEMEM_VMEMMAP and enterprise distribution
On Wed, 23 Jan 2013 14:25:07 +
Mel Gorman mgor...@suse.de wrote:
On Tue, Jan 22, 2013 at 02:46:59PM -0800, Andrew Morton wrote:
reset_page_last_nid() is poorly named. page_reset_last_nid() would be
better, and consistent.
Look at this closer, are you sure you want? Why is
On Tue, 22 Jan 2013 17:12:41 +
Mel Gorman wrote:
> From: Peter Zijlstra
>
> page->_last_nid fits into page->flags on 64-bit. The unlikely 32-bit NUMA
> configuration with NUMA Balancing will still need an extra page field.
> As Peter notes "Completely dropping 32bit support for
From: Peter Zijlstra
page->_last_nid fits into page->flags on 64-bit. The unlikely 32-bit NUMA
configuration with NUMA Balancing will still need an extra page field.
As Peter notes "Completely dropping 32bit support for CONFIG_NUMA_BALANCING
would simplify things, but it would also remove the
From: Peter Zijlstra a.p.zijls...@chello.nl
page-_last_nid fits into page-flags on 64-bit. The unlikely 32-bit NUMA
configuration with NUMA Balancing will still need an extra page field.
As Peter notes Completely dropping 32bit support for CONFIG_NUMA_BALANCING
would simplify things, but it would
On Tue, 22 Jan 2013 17:12:41 +
Mel Gorman mgor...@suse.de wrote:
From: Peter Zijlstra a.p.zijls...@chello.nl
page-_last_nid fits into page-flags on 64-bit. The unlikely 32-bit NUMA
configuration with NUMA Balancing will still need an extra page field.
As Peter notes Completely dropping
12 matches
Mail list logo