Re: [PATCH 1/5] v2 Split the memory_block structure

[Dave Hansen <dave@linux.vnet.ibm.com>]

On Fri, 2010-07-16 at 13:23 -0500, Nathan Fontenot wrote:
> > If the memory_block's state was inferred to be the same as each
> > memory_block_section, couldn't we just keep a start and end phys_index
> > in the memory_block, and get away from having memory_block_sections at
> > all?
> 
> Oooohhh... I like.  Looking at the code it appears this is possible.  I'll
> try this out and include it in the next version of the patch.
> 
> Do you think we need to add an additional file to each memory block directory
> to indicate the number of memory sections in the memory block that are actually
> present? 

I think it's easiest to just say that each 'memory_block' can only hold
contiguous 'memory_block_sections', and we give either the start/end or
start/length pairs.  It gets a lot more complicated if we have to deal
with lots of holes.

I can just see the hardware designers reading this thread, with their
Dr. Evil laughs trying to come up with a reason to give us a couple of
terabytes of RAM with only every-other 16MB area populated. :)  

-- Dave