On Fri, 14 Dec 2018, Mel Gorman wrote:

> > In other words, I think there is a lot of potential stranding that occurs 
> > for both scanners that could otherwise result in completely free 
> > pageblocks.  If there a single movable page present near the end of the 
> > zone in an otherwise fully free pageblock, surely we can do better than 
> > the current implementation that would never consider this very easy to 
> > compact memory.
> > 
> 
> While it's somewhat premature, I posted a series before I had a full set
> of results because it uses free lists to reduce searches and reduces
> inference between multiple scanners. Preliminary results indicated it
> boosted allocation success rates by 20%ish, reduced migration scanning
> by 99% and free scanning by 27%.
> 

Always good to have code to look at, I'll take a closer look.  I've 
unfortunately been distracted with other kernel issues lately :/