Re: [patch] generic nonlinear mappings, 2.5.44-mm2-D0

[Ingo Molnar]

On Wed, 23 Oct 2002, Andrea Arcangeli wrote:

> it's not another vma tree, furthmore another vma tree indexed by the
> hole size wouldn't be able to defragment and it would find the best fit
> not the first fit on the left.

what i was talking about was a hole-tree indexed by the hole start
address, not a vma tree indexed by the hole size. (the later is pretty
pointless.) And even this solution still has to search the tree linearly
for a matching hole.

	Ingo