On Sat, 2022-04-09 at 17:34 +0800, Miaohe Lin wrote:
> Since commit 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from
> shrink_zone()"), slab reclaim and lru page reclaim are done together
> in the shrink_node. So we should take min_slab_pages into account
> when try to call shrink_node.
>
Looks reasonable to me, copying Johannes.
Hi, Christoph,
Should we check min_unmapped_pages and min_slab_pages in shrink_node()
to avoid reclaim LRU when necessary and vice versa? This may be done
via another 2 scan_control flags.
Best Regards,
Huang, Ying
> Signed-off-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
> ---
> mm/vmscan.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 53f1d0755b34..ba83d8f3e53e 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -4714,7 +4714,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
> noreclaim_flag = memalloc_noreclaim_save();
> set_task_reclaim_state(p, &sc.reclaim_state);
>
>
>
>
> - if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
> + if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages ||
> + node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) {
> /*
> * Free memory by calling shrink node with increasing
> * priorities until we have enough memory freed.
