> >How do the kernel alloc/free functions defend against memory fragmentation?
> 
> Um, good question.  And one that I don't really know the answer to.
> 
> The amount of memory being allocated really isn't that much (since
> pointers to the ifnet structure are being passed around, not a copy
> of it itself).  So even if there is fragmentation, I don't think there
> will be much.
> 
> Does that answer your question?

Only if you're right :)  I was really just trying to generate a little
interest in seeing if we could prove that fragmentation of the kernel
heap is bounded for any given kernel config. It would be a nice warm fuzzy.

Todd Whitesel
toddpw @ best.com