On Fri, Apr 06, 2012 at 10:12:12AM +0900, HATAYAMA Daisuke wrote: [..] > So now we can walk on the memmap array also for free pages like other > kinds of memory. The question I have now is why the current > implementation was chosen. Is there any difference between two ways? I don't know but I am guessing may be going through buddy allocator data structures is faster when there is tons of memory in the system and number of free pages is less. Thanks Vivek
