Re: [PATCH] mm/vmscan: clear hopeless kswapd when global direct reclaim makes progress

[Andrew Morton]

On Thu, 9 Jul 2026 21:04:20 -0700 Altan Hacigumus <ahacigu.linux@xxxxxxxxx> wrote:

> > Does this change have any user-visible effect?  If so, please describe
> > in elaborate detail.
> >
> 
> Yes, the effect is visible on systems where a db workload mlocks 80%+
> of memory and the remaining memory is under continuous pressure:
> allocations stall long enough that ordinary tasks (e.g. ssh) become
> slow or unresponsive.
> 
> > If not then that's OK - we make such changes all the time, but they're
> > less fun.
> >
> This was introduced by commit dc9fe9b7056a; for long before it, any
> reclaim progress revived kswapd. Now only a balanced node clears the
> hopeless state, which is too restrictive for global direct reclaim.

Great, thanks.  Please get this info into the changelog and maintain it!

I'll park the patch for a week or so, give reviewers time to catch up.