> I must be missing a big point here ... why is it not
> possible to either (a) turn on paging in the kernel
> so that non-contiguous pages can be easily made to look
> contiguous to kernel code, or (b) when you can't find
a) is bad: linux performs so good partly because its own ram is
unswapable.
> 8 contiguous pages, pick the first free page and swap
> the data in the next 7 adjacent pages with other free
b) is impossible: You would have to modify all pointers pointing to
that memory. Or you would have to use MM tricks which are slow - see
a).
> pages in memory. Method (b) could construct any number of
> contiguous free pages atomically with the only penalty
> being some chunky memcpy's ...
Pavel
-- I'm really pavel@atrey.karlin.mff.cuni.cz. Pavel Look at http://atrey.karlin.mff.cuni.cz/~pavel/ ;-).