[PATCH v3 0/5] Sorting out sc.swap_cluster_max and kill hibernation specific reclaim logic

[PATCH v3 0/5] Sorting out sc.swap_cluster_max and kill hibernation specific reclaim logic

[KOSAKI Motohiro]

Currently, shrink_all_memory() and sc.swap_cluster_max have unnecessary
mess. We can cleanup it and kill some useless code.

[PATCH v3 0/5] Sorting out sc.swap_cluster_max and kill hibernation specific reclaim logic

[KOSAKI Motohiro]

Currently, shrink_all_memory() and sc.swap_cluster_max have unnecessary
mess. We can cleanup it and kill some useless code.




--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 1/5] vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim

[KOSAKI Motohiro]

Currently, sc.scap_cluster_max has double meanings.

 1) reclaim batch size as isolate_lru_pages()'s argument
 2) reclaim baling out thresolds

The two meanings pretty unrelated. Thus, Let's separate it.
this patch doesn't change any behavior.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |   25 +++++++++++++++++++------
 1 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f805958..7be2927 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -55,6 +55,9 @@ struct scan_control {
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
 
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -1585,6 +1588,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
 
@@ -1634,8 +1638,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed > swap_cluster_max &&
-			priority < DEF_PRIORITY && !current_is_kswapd())
+		if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
@@ -1733,6 +1736,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+	unsigned long writeback_threshold;
 
 	delayacct_freepages_start();
 
@@ -1768,7 +1772,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
 			ret = sc->nr_reclaimed;
 			goto out;
 		}
@@ -1780,8 +1784,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc->swap_cluster_max +
-					sc->swap_cluster_max / 2) {
+		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+		if (total_scanned > writeback_threshold) {
 			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
 			sc->may_writepage = 1;
 		}
@@ -1827,6 +1831,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
@@ -1885,6 +1890,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_unmap = 1,
 		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
@@ -1932,6 +1938,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		/*
+		 * kswapd doesn't want to be bailed out while reclaim. because
+		 * we want to put equal scanning pressure on each zone.
+		 */
+		.nr_to_reclaim = ULONG_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -2549,7 +2560,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
-					SWAP_CLUSTER_MAX),
+				       SWAP_CLUSTER_MAX),
+		.nr_to_reclaim = max_t(unsigned long, nr_pages,
+				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
 		.order = order,
-- 
1.6.2.5

[PATCH 1/5] vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim

[KOSAKI Motohiro]

Currently, sc.scap_cluster_max has double meanings.

 1) reclaim batch size as isolate_lru_pages()'s argument
 2) reclaim baling out thresolds

The two meanings pretty unrelated. Thus, Let's separate it.
this patch doesn't change any behavior.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |   25 +++++++++++++++++++------
 1 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f805958..7be2927 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -55,6 +55,9 @@ struct scan_control {
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
 
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -1585,6 +1588,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
 
@@ -1634,8 +1638,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed > swap_cluster_max &&
-			priority < DEF_PRIORITY && !current_is_kswapd())
+		if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
@@ -1733,6 +1736,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
+	unsigned long writeback_threshold;
 
 	delayacct_freepages_start();
 
@@ -1768,7 +1772,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
 			ret = sc->nr_reclaimed;
 			goto out;
 		}
@@ -1780,8 +1784,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc->swap_cluster_max +
-					sc->swap_cluster_max / 2) {
+		writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
+		if (total_scanned > writeback_threshold) {
 			wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
 			sc->may_writepage = 1;
 		}
@@ -1827,6 +1831,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
@@ -1885,6 +1890,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_unmap = 1,
 		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
@@ -1932,6 +1938,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.may_unmap = 1,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		/*
+		 * kswapd doesn't want to be bailed out while reclaim. because
+		 * we want to put equal scanning pressure on each zone.
+		 */
+		.nr_to_reclaim = ULONG_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -2549,7 +2560,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
-					SWAP_CLUSTER_MAX),
+				       SWAP_CLUSTER_MAX),
+		.nr_to_reclaim = max_t(unsigned long, nr_pages,
+				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
 		.order = order,
-- 
1.6.2.5



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/5] vmscan: Kill hibernation specific reclaim logic and unify it

[KOSAKI Motohiro]

shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework
memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max
was introduced by commit a06fe4d307 (Speed freeing memory for suspend).

commit a06fe4d307 said

   Without the patch:
   Freed  14600 pages in  1749 jiffies = 32.61 MB/s (Anomolous!)
   Freed  88563 pages in 14719 jiffies = 23.50 MB/s
   Freed 205734 pages in 32389 jiffies = 24.81 MB/s

   With the patch:
   Freed  68252 pages in   496 jiffies = 537.52 MB/s
   Freed 116464 pages in   569 jiffies = 798.54 MB/s
   Freed 209699 pages in   705 jiffies = 1161.89 MB/s

At that time, their patch was pretty worth. However, Modern Hardware
trend and recent VM improvement broke its worth. From several reason,
I think we should remove shrink_all_zones() at all.

detail:

1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle
  at no i/o congestion.
  but current shrink_zone() is sane, not slow.

2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works
  fine on numa system.
  example)
    System has 4GB memory and each node have 2GB. and hibernate need 1GB.

    optimal)
       steal 500MB from each node.
    shrink_all_zones)
       steal 1GB from node-0.

  Oh, Cache balancing logic was broken. ;)
  Unfortunately, Desktop system moved ahead NUMA at nowadays.
  (Side note, if hibernate require 2GB, shrink_all_zones() never success
   on above machine)

3) if the node has several I/O flighting pages, shrink_all_zones() makes
  pretty bad result.

  schenario) hibernate need 1GB

  1) shrink_all_zones() try to reclaim 1GB from Node-0
  2) but it only reclaimed 990MB
  3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1
  4) it reclaimed 990MB

  Oh, well. it reclaimed twice much than required.
  In the other hand, current shrink_zone() has sane baling out logic.
  then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk.

4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only
  shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal.

Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages().
it bring good reviewability and debuggability, and solve above problems.

side note: Reclaim logic unificication makes two good side effect.
 - Fix recursive reclaim bug on shrink_all_memory().
   it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock.
 - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 mm/vmscan.c |  153 ++++++++++-------------------------------------------------
 1 files changed, 26 insertions(+), 127 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7be2927..eebd260 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -58,6 +58,8 @@ struct scan_control {
 	/* How many pages shrink_list() should reclaim */
 	unsigned long nr_to_reclaim;
 
+	unsigned long hibernation_mode;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -1791,7 +1793,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		}
 
 		/* Take a nap, wait for some writeback to complete */
-		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
+		if (!sc->hibernation_mode && sc->nr_scanned &&
+		    priority < DEF_PRIORITY - 2)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
@@ -2266,148 +2269,44 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 
 #ifdef CONFIG_HIBERNATION
 /*
- * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority.
- *
- * For pass > 3 we also try to shrink the LRU lists that contain a few pages
- */
-static void shrink_all_zones(unsigned long nr_pages, int prio,
-				      int pass, struct scan_control *sc)
-{
-	struct zone *zone;
-	unsigned long nr_reclaimed = 0;
-	struct zone_reclaim_stat *reclaim_stat;
-
-	for_each_populated_zone(zone) {
-		enum lru_list l;
-
-		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
-			continue;
-
-		for_each_evictable_lru(l) {
-			enum zone_stat_item ls = NR_LRU_BASE + l;
-			unsigned long lru_pages = zone_page_state(zone, ls);
-
-			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
-						l == LRU_ACTIVE_FILE))
-				continue;
-
-			reclaim_stat = get_reclaim_stat(zone, sc);
-			reclaim_stat->nr_saved_scan[l] +=
-						(lru_pages >> prio) + 1;
-			if (reclaim_stat->nr_saved_scan[l]
-						>= nr_pages || pass > 3) {
-				unsigned long nr_to_scan;
-
-				reclaim_stat->nr_saved_scan[l] = 0;
-				nr_to_scan = min(nr_pages, lru_pages);
-				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
-								sc, prio);
-				if (nr_reclaimed >= nr_pages) {
-					sc->nr_reclaimed += nr_reclaimed;
-					return;
-				}
-			}
-		}
-	}
-	sc->nr_reclaimed += nr_reclaimed;
-}
-
-/*
- * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
  * freed pages.
  *
  * Rather than trying to age LRUs the aim is to preserve the overall
  * LRU order by reclaiming preferentially
  * inactive > active > active referenced > active mapped
  */
-unsigned long shrink_all_memory(unsigned long nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 {
-	unsigned long lru_pages, nr_slab;
-	int pass;
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
-		.gfp_mask = GFP_KERNEL,
-		.may_unmap = 0,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE,
+		.may_swap = 1,
+		.may_unmap = 1,
 		.may_writepage = 1,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = nr_to_reclaim,
+		.hibernation_mode = 1,
+		.swappiness = vm_swappiness,
+		.order = 0,
 		.isolate_pages = isolate_pages_global,
-		.nr_reclaimed = 0,
 	};
+	struct zonelist * zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
+	struct task_struct *p = current;
+	unsigned long nr_reclaimed;
 
-	current->reclaim_state = &reclaim_state;
-
-	lru_pages = global_reclaimable_pages();
-	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
-	/* If slab caches are huge, it's better to hit them first */
-	while (nr_slab >= lru_pages) {
-		reclaim_state.reclaimed_slab = 0;
-		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
-		if (!reclaim_state.reclaimed_slab)
-			break;
-
-		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		if (sc.nr_reclaimed >= nr_pages)
-			goto out;
-
-		nr_slab -= reclaim_state.reclaimed_slab;
-	}
-
-	/*
-	 * We try to shrink LRUs in 5 passes:
-	 * 0 = Reclaim from inactive_list only
-	 * 1 = Reclaim from active list but don't reclaim mapped
-	 * 2 = 2nd pass of type 1
-	 * 3 = Reclaim mapped (normal reclaim)
-	 * 4 = 2nd pass of type 3
-	 */
-	for (pass = 0; pass < 5; pass++) {
-		int prio;
-
-		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2)
-			sc.may_unmap = 1;
-
-		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
-
-			sc.nr_scanned = 0;
-			sc.swap_cluster_max = nr_to_scan;
-			shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-				    global_reclaimable_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(BLK_RW_ASYNC, HZ / 10);
-		}
-	}
-
-	/*
-	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
-	 * something in slab caches
-	 */
-	if (!sc.nr_reclaimed) {
-		do {
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask,
-				    global_reclaimable_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		} while (sc.nr_reclaimed < nr_pages &&
-				reclaim_state.reclaimed_slab > 0);
-	}
+	p->flags |= PF_MEMALLOC;
+	lockdep_set_current_reclaim_state(sc.gfp_mask);
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
 
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
-out:
-	current->reclaim_state = NULL;
+	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+	p->flags &= ~PF_MEMALLOC;
 
-	return sc.nr_reclaimed;
+	return nr_reclaimed;
 }
 #endif /* CONFIG_HIBERNATION */
 
-- 
1.6.2.5

[PATCH 2/5] vmscan: Kill hibernation specific reclaim logic and unify it

[KOSAKI Motohiro]

shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework
memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max
was introduced by commit a06fe4d307 (Speed freeing memory for suspend).

commit a06fe4d307 said

   Without the patch:
   Freed  14600 pages in  1749 jiffies = 32.61 MB/s (Anomolous!)
   Freed  88563 pages in 14719 jiffies = 23.50 MB/s
   Freed 205734 pages in 32389 jiffies = 24.81 MB/s

   With the patch:
   Freed  68252 pages in   496 jiffies = 537.52 MB/s
   Freed 116464 pages in   569 jiffies = 798.54 MB/s
   Freed 209699 pages in   705 jiffies = 1161.89 MB/s

At that time, their patch was pretty worth. However, Modern Hardware
trend and recent VM improvement broke its worth. From several reason,
I think we should remove shrink_all_zones() at all.

detail:

1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle
  at no i/o congestion.
  but current shrink_zone() is sane, not slow.

2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works
  fine on numa system.
  example)
    System has 4GB memory and each node have 2GB. and hibernate need 1GB.

    optimal)
       steal 500MB from each node.
    shrink_all_zones)
       steal 1GB from node-0.

  Oh, Cache balancing logic was broken. ;)
  Unfortunately, Desktop system moved ahead NUMA at nowadays.
  (Side note, if hibernate require 2GB, shrink_all_zones() never success
   on above machine)

3) if the node has several I/O flighting pages, shrink_all_zones() makes
  pretty bad result.

  schenario) hibernate need 1GB

  1) shrink_all_zones() try to reclaim 1GB from Node-0
  2) but it only reclaimed 990MB
  3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1
  4) it reclaimed 990MB

  Oh, well. it reclaimed twice much than required.
  In the other hand, current shrink_zone() has sane baling out logic.
  then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk.

4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only
  shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal.

Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages().
it bring good reviewability and debuggability, and solve above problems.

side note: Reclaim logic unificication makes two good side effect.
 - Fix recursive reclaim bug on shrink_all_memory().
   it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock.
 - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
---
 mm/vmscan.c |  153 ++++++++++-------------------------------------------------
 1 files changed, 26 insertions(+), 127 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7be2927..eebd260 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -58,6 +58,8 @@ struct scan_control {
 	/* How many pages shrink_list() should reclaim */
 	unsigned long nr_to_reclaim;
 
+	unsigned long hibernation_mode;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -1791,7 +1793,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		}
 
 		/* Take a nap, wait for some writeback to complete */
-		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
+		if (!sc->hibernation_mode && sc->nr_scanned &&
+		    priority < DEF_PRIORITY - 2)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
@@ -2266,148 +2269,44 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 
 #ifdef CONFIG_HIBERNATION
 /*
- * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority.
- *
- * For pass > 3 we also try to shrink the LRU lists that contain a few pages
- */
-static void shrink_all_zones(unsigned long nr_pages, int prio,
-				      int pass, struct scan_control *sc)
-{
-	struct zone *zone;
-	unsigned long nr_reclaimed = 0;
-	struct zone_reclaim_stat *reclaim_stat;
-
-	for_each_populated_zone(zone) {
-		enum lru_list l;
-
-		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
-			continue;
-
-		for_each_evictable_lru(l) {
-			enum zone_stat_item ls = NR_LRU_BASE + l;
-			unsigned long lru_pages = zone_page_state(zone, ls);
-
-			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
-						l == LRU_ACTIVE_FILE))
-				continue;
-
-			reclaim_stat = get_reclaim_stat(zone, sc);
-			reclaim_stat->nr_saved_scan[l] +=
-						(lru_pages >> prio) + 1;
-			if (reclaim_stat->nr_saved_scan[l]
-						>= nr_pages || pass > 3) {
-				unsigned long nr_to_scan;
-
-				reclaim_stat->nr_saved_scan[l] = 0;
-				nr_to_scan = min(nr_pages, lru_pages);
-				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
-								sc, prio);
-				if (nr_reclaimed >= nr_pages) {
-					sc->nr_reclaimed += nr_reclaimed;
-					return;
-				}
-			}
-		}
-	}
-	sc->nr_reclaimed += nr_reclaimed;
-}
-
-/*
- * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
  * freed pages.
  *
  * Rather than trying to age LRUs the aim is to preserve the overall
  * LRU order by reclaiming preferentially
  * inactive > active > active referenced > active mapped
  */
-unsigned long shrink_all_memory(unsigned long nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 {
-	unsigned long lru_pages, nr_slab;
-	int pass;
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
-		.gfp_mask = GFP_KERNEL,
-		.may_unmap = 0,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE,
+		.may_swap = 1,
+		.may_unmap = 1,
 		.may_writepage = 1,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = nr_to_reclaim,
+		.hibernation_mode = 1,
+		.swappiness = vm_swappiness,
+		.order = 0,
 		.isolate_pages = isolate_pages_global,
-		.nr_reclaimed = 0,
 	};
+	struct zonelist * zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
+	struct task_struct *p = current;
+	unsigned long nr_reclaimed;
 
-	current->reclaim_state = &reclaim_state;
-
-	lru_pages = global_reclaimable_pages();
-	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
-	/* If slab caches are huge, it's better to hit them first */
-	while (nr_slab >= lru_pages) {
-		reclaim_state.reclaimed_slab = 0;
-		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
-		if (!reclaim_state.reclaimed_slab)
-			break;
-
-		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		if (sc.nr_reclaimed >= nr_pages)
-			goto out;
-
-		nr_slab -= reclaim_state.reclaimed_slab;
-	}
-
-	/*
-	 * We try to shrink LRUs in 5 passes:
-	 * 0 = Reclaim from inactive_list only
-	 * 1 = Reclaim from active list but don't reclaim mapped
-	 * 2 = 2nd pass of type 1
-	 * 3 = Reclaim mapped (normal reclaim)
-	 * 4 = 2nd pass of type 3
-	 */
-	for (pass = 0; pass < 5; pass++) {
-		int prio;
-
-		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2)
-			sc.may_unmap = 1;
-
-		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
-
-			sc.nr_scanned = 0;
-			sc.swap_cluster_max = nr_to_scan;
-			shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-				    global_reclaimable_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-			if (sc.nr_reclaimed >= nr_pages)
-				goto out;
-
-			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(BLK_RW_ASYNC, HZ / 10);
-		}
-	}
-
-	/*
-	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
-	 * something in slab caches
-	 */
-	if (!sc.nr_reclaimed) {
-		do {
-			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask,
-				    global_reclaimable_pages());
-			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
-		} while (sc.nr_reclaimed < nr_pages &&
-				reclaim_state.reclaimed_slab > 0);
-	}
+	p->flags |= PF_MEMALLOC;
+	lockdep_set_current_reclaim_state(sc.gfp_mask);
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
 
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
-out:
-	current->reclaim_state = NULL;
+	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+	p->flags &= ~PF_MEMALLOC;
 
-	return sc.nr_reclaimed;
+	return nr_reclaimed;
 }
 #endif /* CONFIG_HIBERNATION */
 
-- 
1.6.2.5



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 3/5] vmscan: zone_reclaim() don't use insane swap_cluster_max

[KOSAKI Motohiro]

In old days, we didn't have sc.nr_to_reclaim and it brought
sc.swap_cluster_max misuse.

huge sc.swap_cluster_max might makes unnecessary OOM risk and
no performance benefit.

Now, we can stop its insane thing.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eebd260..d0422a8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2458,8 +2458,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.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),
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = max_t(unsigned long, nr_pages,
 				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
-- 
1.6.2.5

[PATCH 3/5] vmscan: zone_reclaim() don't use insane swap_cluster_max

[KOSAKI Motohiro]

In old days, we didn't have sc.nr_to_reclaim and it brought
sc.swap_cluster_max misuse.

huge sc.swap_cluster_max might makes unnecessary OOM risk and
no performance benefit.

Now, we can stop its insane thing.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eebd260..d0422a8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2458,8 +2458,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.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),
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = max_t(unsigned long, nr_pages,
 				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
-- 
1.6.2.5



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 4/5] vmscan: Kill sc.swap_cluster_max

[KOSAKI Motohiro]

Now, All caller of reclaim use swap_cluster_max as SWAP_CLUSTER_MAX.
Then, we can remove it perfectly.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |   26 ++++++--------------------
 1 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d0422a8..d53a934 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -71,12 +71,6 @@ struct scan_control {
 	/* 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
-	 * whole list at once. */
-	int swap_cluster_max;
-
 	int swappiness;
 
 	int all_unreclaimable;
@@ -1127,7 +1121,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_anon;
 		unsigned long nr_file;
 
-		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
+		nr_taken = sc->isolate_pages(SWAP_CLUSTER_MAX,
 			     &page_list, &nr_scan, sc->order, mode,
 				zone, sc->mem_cgroup, 0, file);
 
@@ -1562,15 +1556,14 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
  * until we collected @swap_cluster_max pages to scan.
  */
 static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
-				       unsigned long *nr_saved_scan,
-				       unsigned long swap_cluster_max)
+				       unsigned long *nr_saved_scan)
 {
 	unsigned long nr;
 
 	*nr_saved_scan += nr_to_scan;
 	nr = *nr_saved_scan;
 
-	if (nr >= swap_cluster_max)
+	if (nr >= SWAP_CLUSTER_MAX)
 		*nr_saved_scan = 0;
 	else
 		nr = 0;
@@ -1589,7 +1582,6 @@ static void shrink_zone(int priority, struct zone *zone,
 	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
-	unsigned long swap_cluster_max = sc->swap_cluster_max;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
@@ -1612,8 +1604,7 @@ static void shrink_zone(int priority, struct zone *zone,
 			scan = (scan * percent[file]) / 100;
 		}
 		nr[l] = nr_scan_try_batch(scan,
-					  &reclaim_stat->nr_saved_scan[l],
-					  swap_cluster_max);
+					  &reclaim_stat->nr_saved_scan[l]);
 	}
 
 	trace_printk("sz p=%d %d:%s %lu:%lu [%lu %lu %lu %lu] \n",
@@ -1625,7 +1616,8 @@ static void shrink_zone(int priority, struct zone *zone,
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l], swap_cluster_max);
+				nr_to_scan = min_t(unsigned long,
+						   nr[l], SWAP_CLUSTER_MAX);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
@@ -1833,7 +1825,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
@@ -1858,7 +1849,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem,
@@ -1892,7 +1882,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
@@ -1940,7 +1929,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 1,
 		.may_swap = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		/*
 		 * kswapd doesn't want to be bailed out while reclaim. because
 		 * we want to put equal scanning pressure on each zone.
@@ -2284,7 +2272,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 		.may_swap = 1,
 		.may_unmap = 1,
 		.may_writepage = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = nr_to_reclaim,
 		.hibernation_mode = 1,
 		.swappiness = vm_swappiness,
@@ -2458,7 +2445,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = max_t(unsigned long, nr_pages,
 				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
-- 
1.6.2.5

[PATCH 4/5] vmscan: Kill sc.swap_cluster_max

[KOSAKI Motohiro]

Now, All caller of reclaim use swap_cluster_max as SWAP_CLUSTER_MAX.
Then, we can remove it perfectly.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |   26 ++++++--------------------
 1 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d0422a8..d53a934 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -71,12 +71,6 @@ struct scan_control {
 	/* 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
-	 * whole list at once. */
-	int swap_cluster_max;
-
 	int swappiness;
 
 	int all_unreclaimable;
@@ -1127,7 +1121,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_anon;
 		unsigned long nr_file;
 
-		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
+		nr_taken = sc->isolate_pages(SWAP_CLUSTER_MAX,
 			     &page_list, &nr_scan, sc->order, mode,
 				zone, sc->mem_cgroup, 0, file);
 
@@ -1562,15 +1556,14 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
  * until we collected @swap_cluster_max pages to scan.
  */
 static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
-				       unsigned long *nr_saved_scan,
-				       unsigned long swap_cluster_max)
+				       unsigned long *nr_saved_scan)
 {
 	unsigned long nr;
 
 	*nr_saved_scan += nr_to_scan;
 	nr = *nr_saved_scan;
 
-	if (nr >= swap_cluster_max)
+	if (nr >= SWAP_CLUSTER_MAX)
 		*nr_saved_scan = 0;
 	else
 		nr = 0;
@@ -1589,7 +1582,6 @@ static void shrink_zone(int priority, struct zone *zone,
 	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
-	unsigned long swap_cluster_max = sc->swap_cluster_max;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	int noswap = 0;
@@ -1612,8 +1604,7 @@ static void shrink_zone(int priority, struct zone *zone,
 			scan = (scan * percent[file]) / 100;
 		}
 		nr[l] = nr_scan_try_batch(scan,
-					  &reclaim_stat->nr_saved_scan[l],
-					  swap_cluster_max);
+					  &reclaim_stat->nr_saved_scan[l]);
 	}
 
 	trace_printk("sz p=%d %d:%s %lu:%lu [%lu %lu %lu %lu] \n",
@@ -1625,7 +1616,8 @@ static void shrink_zone(int priority, struct zone *zone,
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l], swap_cluster_max);
+				nr_to_scan = min_t(unsigned long,
+						   nr[l], SWAP_CLUSTER_MAX);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
@@ -1833,7 +1825,6 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
 		.may_swap = 1,
@@ -1858,7 +1849,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem,
@@ -1892,7 +1882,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
@@ -1940,7 +1929,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 1,
 		.may_swap = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		/*
 		 * kswapd doesn't want to be bailed out while reclaim. because
 		 * we want to put equal scanning pressure on each zone.
@@ -2284,7 +2272,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
 		.may_swap = 1,
 		.may_unmap = 1,
 		.may_writepage = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = nr_to_reclaim,
 		.hibernation_mode = 1,
 		.swappiness = vm_swappiness,
@@ -2458,7 +2445,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
 		.may_swap = 1,
-		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.nr_to_reclaim = max_t(unsigned long, nr_pages,
 				       SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
-- 
1.6.2.5



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 5/5][nit fix] vmscan Make consistent of reclaim bale out between do_try_to_free_page and shrink_zone

[KOSAKI Motohiro]

Fix small inconsistent of ">" and ">=".

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d53a934..0d0a948 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1632,7 +1632,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
-- 
1.6.2.5

[PATCH 5/5][nit fix] vmscan Make consistent of reclaim bale out between do_try_to_free_page and shrink_zone

[KOSAKI Motohiro]

Fix small inconsistent of ">" and ">=".

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
---
 mm/vmscan.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d53a934..0d0a948 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1632,7 +1632,7 @@ static void shrink_zone(int priority, struct zone *zone,
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed > nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 
-- 
1.6.2.5



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>