On Mon, 27 Nov 2006, Mel Gorman wrote:
> Later, MOVABLE might be a constraint. For example, hotpluggable nodes may only
> allow MOVABLE allocations to be allocated.
Also, (a much more immediate need since we have memory hotplug already) if
a zone has hotpluggable memory then MOVABLE/unmovable
On Sun, 26 Nov 2006, Hugh Dickins wrote:
On Sat, 25 Nov 2006, Linus Torvalds wrote:
On Fri, 24 Nov 2006, Hugh Dickins wrote:
You need to add in something like the patch below (mutatis mutandis
for whichever approach you end up taking): tmpfs uses highmem pages
for its swap vector blocks,
On Sun, 26 Nov 2006, Hugh Dickins wrote:
On Sat, 25 Nov 2006, Linus Torvalds wrote:
On Fri, 24 Nov 2006, Hugh Dickins wrote:
You need to add in something like the patch below (mutatis mutandis
for whichever approach you end up taking): tmpfs uses highmem pages
for its swap vector blocks,
On Mon, 27 Nov 2006, Mel Gorman wrote:
Later, MOVABLE might be a constraint. For example, hotpluggable nodes may only
allow MOVABLE allocations to be allocated.
Also, (a much more immediate need since we have memory hotplug already) if
a zone has hotpluggable memory then MOVABLE/unmovable
On Sat, 25 Nov 2006, Linus Torvalds wrote:
> On Fri, 24 Nov 2006, Hugh Dickins wrote:
> >
> > You need to add in something like the patch below (mutatis mutandis
> > for whichever approach you end up taking): tmpfs uses highmem pages
> > for its swap vector blocks, noting where on swap the data
On Sat, 25 Nov 2006, Linus Torvalds wrote:
On Fri, 24 Nov 2006, Hugh Dickins wrote:
You need to add in something like the patch below (mutatis mutandis
for whichever approach you end up taking): tmpfs uses highmem pages
for its swap vector blocks, noting where on swap the data pages are,
6 matches
Mail list logo