[RFC PATCH] No Reclaim LRU Infrastructure enhancement for memcgroup

[KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>]

[-- Attachment #1: Type: text/plain, Size: 871 bytes --]

Hi

> In my understanding, 2 checks we have to do.
> 
> 1. When memcg finds PG_noreclaim page in its LRU, move it to noreclaim list of
>    memcg.
> 2. When PG_noreclaim page is moved back to generic LRU, memcg should move
>    it on its list. (we have to add a hook somewhere.)
> 
> But this may break current 'loose' synchronization between global LRU and
> memcg's LRU. When PG_noreclaim page is put back into active/inactive LRU ?
> 
> concerns are
> A. how to implement '2'

I tried to implement it today.
this patch is made against "[PATCH -mm 13/16] No Reclaim LRU Infrastructure"


> B. race condtions.

don't worry :)
it isn't big problem.

global lru is reclaimbale and memcg lru is noreclaimable
	-> we can repair at move lru of shrink_[in]active_page().

global lru is noreclaimbale and memcg lru is reclaimable
	-> we can repair mem_cgroup_isolate_pages()



[-- Attachment #2: rvr-13.2-kosaki-memcg-noreclaim.patch --]
[-- Type: application/octet-stream, Size: 7316 bytes --]

When memco lru moved, mem_cgroup_move_lists() is called.
thus, I add noreclaim lru logic at that point.


Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

---
 include/linux/memcontrol.h |    2 -
 mm/memcontrol.c            |   73 +++++++++++++++++++++++++++------------------
 mm/swap.c                  |    2 -
 mm/vmscan.c                |   10 ++++--
 4 files changed, 54 insertions(+), 33 deletions(-)

Index: b/mm/memcontrol.c
===================================================================
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -161,9 +161,10 @@ struct page_cgroup {
 	int ref_cnt;			/* cached, mapped, migrating */
 	int flags;
 };
-#define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
-#define PAGE_CGROUP_FLAG_FILE	(0x4)	/* page is file system backed */
+#define PAGE_CGROUP_FLAG_CACHE	   (0x1)	/* charged as cache */
+#define PAGE_CGROUP_FLAG_ACTIVE    (0x2)	/* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE	   (0x4)	/* page is file system backed */
+#define PAGE_CGROUP_FLAG_NORECLAIM (0x8)	/* page is noreclaimable page */
 
 static int page_cgroup_nid(struct page_cgroup *pc)
 {
@@ -283,10 +284,14 @@ static void __mem_cgroup_remove_list(str
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_NORECLAIM)
+		lru = LRU_NORECLAIM;
+	else {
+		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+			lru += LRU_ACTIVE;
+		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+			lru += LRU_FILE;
+	}
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -299,10 +304,14 @@ static void __mem_cgroup_add_list(struct
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_NORECLAIM)
+		lru = LRU_NORECLAIM;
+	else {
+		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+			lru += LRU_ACTIVE;
+		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+			lru += LRU_FILE;
+	}
 
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_add(&pc->lru, &mz->lists[lru]);
@@ -310,21 +319,31 @@ static void __mem_cgroup_add_list(struct
 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
 {
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
-	int lru = LRU_FILE * !!file + !!from;
+	int active    = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int file      = pc->flags & PAGE_CGROUP_FLAG_FILE;
+	int noreclaim = pc->flags & PAGE_CGROUP_FLAG_NORECLAIM;
+	enum lru_list from = noreclaim ? LRU_NORECLAIM :
+				(LRU_FILE * !!file + !!active);
 
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	if (lru == from)
+		return;
 
-	if (active)
-		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
-	else
+	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+
+	if (is_noreclaim_lru(lru)) {
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags |= PAGE_CGROUP_FLAG_NORECLAIM;
+	} else {
+		if (is_active_lru(lru))
+			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+		else
+			pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags &= ~PAGE_CGROUP_FLAG_NORECLAIM;
+	}
 
-	lru = LRU_FILE * !!file + !!active;
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_move(&pc->lru, &mz->lists[lru]);
 }
@@ -342,7 +361,7 @@ int task_in_mem_cgroup(struct task_struc
 /*
  * This routine assumes that the appropriate zone's lru lock is already held
  */
-void mem_cgroup_move_lists(struct page *page, bool active)
+void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup_per_zone *mz;
@@ -362,7 +381,7 @@ void mem_cgroup_move_lists(struct page *
 	if (pc) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, active);
+		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
 	unlock_page_cgroup(page);
@@ -460,12 +479,10 @@ unsigned long mem_cgroup_isolate_pages(u
 		/*
 		 * TODO: play better with lumpy reclaim, grabbing anything.
 		 */
-		if (PageActive(page) && !active) {
-			__mem_cgroup_move_lists(pc, true);
-			continue;
-		}
-		if (!PageActive(page) && active) {
-			__mem_cgroup_move_lists(pc, false);
+		if (PageNoreclaim(page) ||
+		    (PageActive(page) && !active) ||
+		    (!PageActive(page) && active)) {
+			__mem_cgroup_move_lists(pc, page_lru(page));
 			continue;
 		}
 
Index: b/mm/swap.c
===================================================================
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -189,7 +189,7 @@ void activate_page(struct page *page)
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
-		mem_cgroup_move_lists(page, true);
+		mem_cgroup_move_lists(page, lru);
 
 		if (file) {
 			zone->recent_scanned_file++;
Index: b/mm/vmscan.c
===================================================================
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -475,13 +475,16 @@ int putback_lru_page(struct page *page)
 		 * non-reclaimable page on [in]active list.
 		 * We know how to handle that.
 		 */
-		lru_cache_add_lru(page, lru + page_file_cache(page));
+		lru += page_file_cache(page);
+		lru_cache_add_lru(page, lru);
+		mem_cgroup_move_lists(page, lru);
 	} else {
 		/*
 		 * Put non-reclaimable pages directly on zone's noreclaim
 		 * list.
 		 */
 		add_page_to_noreclaim_list(page);
+		mem_cgroup_move_lists(page, LRU_NORECLAIM);
 	}
 
 	put_page(page);		/* drop ref from isolate */
@@ -1065,6 +1068,7 @@ static unsigned long shrink_inactive_lis
 			}
 			SetPageLRU(page);
 			add_page_to_lru_list(zone, page, lru);
+			mem_cgroup_move_lists(page, lru);
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
 				__pagevec_release(&pvec);
@@ -1202,7 +1206,7 @@ static void shrink_active_list(unsigned 
 		ClearPageActive(page);
 
 		list_move(&page->lru, &zone->list[lru]);
-		mem_cgroup_move_lists(page, false);
+		mem_cgroup_move_lists(page, lru);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_INACTIVE_ANON + lru,
@@ -1234,7 +1238,7 @@ static void shrink_active_list(unsigned 
 		VM_BUG_ON(!PageActive(page));
 
 		list_move(&page->lru, &zone->list[lru]);
-		mem_cgroup_move_lists(page, true);
+		mem_cgroup_move_lists(page, lru);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_INACTIVE_ANON + lru,
Index: b/include/linux/memcontrol.h
===================================================================
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -35,7 +35,7 @@ extern int mem_cgroup_charge(struct page
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
 extern void mem_cgroup_uncharge_page(struct page *page);
-extern void mem_cgroup_move_lists(struct page *page, bool active);
+extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,

[-- Attachment #3: rvr-13.3-kosaki-memcg-stat.patch --]
[-- Type: application/octet-stream, Size: 1165 bytes --]

add noreclaim field to /dev/cgroup/[group]/memory.stat.


Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

---
 mm/memcontrol.c |    6 ++++++
 1 file changed, 6 insertions(+)

Index: b/mm/memcontrol.c
===================================================================
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -903,6 +903,7 @@ static int mem_control_stat_show(struct 
 	{
 		unsigned long active_anon, inactive_anon;
 		unsigned long active_file, inactive_file;
+		unsigned long noreclaim;
 
 		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
 						LRU_INACTIVE_ANON);
@@ -912,10 +913,15 @@ static int mem_control_stat_show(struct 
 						LRU_INACTIVE_FILE);
 		active_file = mem_cgroup_get_all_zonestat(mem_cont,
 						LRU_ACTIVE_FILE);
+		noreclaim = mem_cgroup_get_all_zonestat(mem_cont,
+							LRU_NORECLAIM);
+
 		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
 		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
 		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
 		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
+		cb->fill(cb, "noreclaim", noreclaim * PAGE_SIZE);
+
 	}
 	return 0;
 }