On 2018-12-04 12:31, David Hildenbrand wrote:
> If I am not wrong, zone_contiguous is a pure mean for performance
improvement, right? So leaving zone_contiguous unset is always save. I
always disliked the whole clear/set_zone_contiguous thingy. I wonder if
we can find a different way to boost performance there (in the general
case). Or is this (zone_contiguous) even worth keeping around at all
for
now? (do we have performance numbers?)
It looks like it was introduced by 7cf91a98e607
("mm/compaction: speed up pageblock_pfn_to_page() when zone is
contiguous").
The improve numbers are in the commit.
So I would say that we need to keep it around.
I'd say let's give it a try and find out if we are missing something.
+1
to simplifying that code.
I will work on a patch removing this and I will integrate it in [1].
Then I will run some tests to see if I can catch something bad.
[1] https://patchwork.kernel.org/cover/10700783/
Thanks for taking a look!
Oscar Salvador
