Re: [PATCH] mm/page_alloc: cache the result of node_dirty_ok()

[Mel Gorman]

On Sat, Apr 30, 2022 at 10:10:32AM +0900, Wonhyuk Yang wrote:
> To spread dirty page, nodes are checked whether
> it reached the dirty limit using the expensive
> node_dirty_ok(). To reduce the number of calling
> node_dirty_ok(), last node that hit the dirty
> limit is cached.
> 
> Instead of caching the node, caching both node
> and it's result of node_dirty_ok() can reduce
> the number of calling node_dirty_ok() more than
> before.
> 
> Signed-off-by: Wonhyuk Yang <vvghjk1234@xxxxxxxxx>

Acked-by: Mel Gorman <mgorman@xxxxxxx>

I agree with Andrew that last_pgdat_dirty_ok is a better name. The old
name was also bad but seeing as the area is being changed, fixing the
name is harmless.

-- 
Mel Gorman
SUSE Labs