Re: Re: Re: [PATCH] mm: memcg: Use larger chunks for proactive reclaim

[T.J. Mercier]

On Fri, Feb 2, 2024 at 11:46 AM Michal Koutný <mkoutny@xxxxxxxx> wrote:
>
> On Fri, Feb 02, 2024 at 10:22:34AM -0800, "T.J. Mercier" <tjmercier@xxxxxxxxxx> wrote:
> > So all of these should be more or less equivalent:
> > delta <= SWAP_CLUSTER_MAX ? delta : (delta + 3*SWAP_CLUSTER_MAX) / 4
> > max((nr_to_reclaim - nr_reclaimed) / 4, (nr_to_reclaim - nr_reclaimed) % 4)
> > (nr_to_reclaim - nr_reclaimed) / 4 + 4
> > (nr_to_reclaim - nr_reclaimed) / 4
> >
> > I was just trying to avoid putting in a 0 for the request size with the mod.
>
> The third variant would be simpler then. Modulo looks weird.
>
> Oh, and I just realized that try_to_free_mem_cgroup_pages() does
> max(nr_pages, SWAP_CLUSTER_MAX). Then I'd vote for the fourth variant +
> possible comment about harmless 0.
> (I'm sorry if this was discussed before.)
>
> Michal

Ok great, let's do that. Thanks for your input.