Re: [PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-10 Thread Johannes Weiner
On Wed, Sep 09, 2020 at 09:55:20AM -0700, Roman Gushchin wrote: > On Wed, Sep 09, 2020 at 10:55:34AM -0400, Johannes Weiner wrote: > > On Thu, Sep 03, 2020 at 04:00:55PM -0700, Roman Gushchin wrote: > > > In the memcg case count_shadow_nodes() sums the number of pages in lru > > > lists and the amo

Re: [PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-09 Thread Roman Gushchin
On Wed, Sep 09, 2020 at 10:55:34AM -0400, Johannes Weiner wrote: > On Thu, Sep 03, 2020 at 04:00:55PM -0700, Roman Gushchin wrote: > > In the memcg case count_shadow_nodes() sums the number of pages in lru > > lists and the amount of slab memory (reclaimable and non-reclaimable) > > as a baseline f

Re: [PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-09 Thread Johannes Weiner
On Thu, Sep 03, 2020 at 04:00:55PM -0700, Roman Gushchin wrote: > In the memcg case count_shadow_nodes() sums the number of pages in lru > lists and the amount of slab memory (reclaimable and non-reclaimable) > as a baseline for the allowed number of shadow entries. > > It seems to be a good analo

Re: [PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-03 Thread Roman Gushchin
On Thu, Sep 03, 2020 at 09:10:59PM -0700, Andrew Morton wrote: > On Thu, 3 Sep 2020 16:00:55 -0700 Roman Gushchin wrote: > > > In the memcg case count_shadow_nodes() sums the number of pages in lru > > lists and the amount of slab memory (reclaimable and non-reclaimable) > > as a baseline for the

Re: [PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-03 Thread Andrew Morton
On Thu, 3 Sep 2020 16:00:55 -0700 Roman Gushchin wrote: > In the memcg case count_shadow_nodes() sums the number of pages in lru > lists and the amount of slab memory (reclaimable and non-reclaimable) > as a baseline for the allowed number of shadow entries. > > It seems to be a good analogy for

[PATCH] mm: workingset: ignore slab memory size when calculating shadows pressure

2020-09-03 Thread Roman Gushchin
In the memcg case count_shadow_nodes() sums the number of pages in lru lists and the amount of slab memory (reclaimable and non-reclaimable) as a baseline for the allowed number of shadow entries. It seems to be a good analogy for the !memcg case, where node_present_pages() is used. However, it's