[PATCH] vmscan: memcg needs may_swap (Re: [patch] vmscan: renamesc.may_swap to may_unmap)

[Daisuke Nishimura]

Added
 Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
 Cc: Balbir Singh <balbir@xxxxxxxxxx>

I'm sorry for replying to a very old mail.

> @@ -1713,7 +1713,7 @@ unsigned long try_to_free_mem_cgroup_pag
>  {
>  	struct scan_control sc = {
>  		.may_writepage = !laptop_mode,
> -		.may_swap = 1,
> +		.may_unmap = 1,
>  		.swap_cluster_max = SWAP_CLUSTER_MAX,
>  		.swappiness = swappiness,
>  		.order = 0,
> @@ -1723,7 +1723,7 @@ unsigned long try_to_free_mem_cgroup_pag
>  	struct zonelist *zonelist;
>  
>  	if (noswap)
> -		sc.may_swap = 0;
> +		sc.may_unmap = 0;
>  
>  	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
>  			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
IIUC, memcg had used may_swap as a flag for "we need to use swap?" as the name indicate.

Because, when mem+swap hits the limit, trying to swapout pages is meaningless
as it doesn't change mem+swap usage.

What do you think of this patch?
===
From: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>

vmscan-rename-scmay_swap-to-may_unmap.patch removed may_swap flag,
but memcg had used it as a flag for "we need to use swap?", as the
name indicate.

And in current implementation, memcg cannot reclaim mapped file caches
when mem+swap hits the limit.

re-introduce may_swap flag and handle it at shrink_page_list.

This patch doesn't influence any scan_control users other than memcg.

Signed-off-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
---
 mm/vmscan.c |   15 ++++++++++++++-
 1 files changed, 14 insertions(+), 1 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c815653..86118d9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -64,6 +64,9 @@ struct scan_control {
 	/* Can mapped pages be reclaimed? */
 	int may_unmap;
 
+	/* Can pages be swapped as part of reclaim? */
+	int may_swap;
+
 	/* This context's SWAP_CLUSTER_MAX. If freeing memory for
 	 * suspend, we effectively ignore SWAP_CLUSTER_MAX.
 	 * In this context, it doesn't matter that we scan the
@@ -616,6 +619,11 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (!sc->may_unmap && page_mapped(page))
 			goto keep_locked;
 
+		if (!sc->may_swap && PageSwapBacked(page)
+			/* SwapCache uses 'swap' already */
+			&& !PageSwapCache(page))
+			goto keep_locked;
+
 		/* Double the slab pressure for mapped and swapcache pages */
 		if (page_mapped(page) || PageSwapCache(page))
 			sc->nr_scanned++;
@@ -1696,6 +1704,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
+		.may_swap = 1,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -1715,6 +1724,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
+		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
@@ -1724,7 +1734,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 	struct zonelist *zonelist;
 
 	if (noswap)
-		sc.may_unmap = 0;
+		sc.may_swap = 0;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -1764,6 +1774,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 1,
+		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
@@ -2110,6 +2121,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 0,
+		.may_swap = 1,
 		.may_writepage = 1,
 		.isolate_pages = isolate_pages_global,
 	};
@@ -2292,6 +2304,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/