linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim
@ 2016-04-06 11:22 Mel Gorman
  2016-04-06 11:22 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
                   ` (4 more replies)
  0 siblings, 5 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

As reclaim is now per-node based, convert zone_reclaim to be node_reclaim.
It is possible that a node will be reclaimed multiple times if it has
multiple zones but this is unavoidable without caching all nodes traversed
so far.  The documentation and interface to userspace is the same from
a configuration perspective and will will be similar in behaviour unless
the node-local allocation requests were also limited to lower zones.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/mmzone.h   | 18 +++++------
 include/linux/swap.h     |  9 +++---
 include/linux/topology.h |  2 +-
 kernel/sysctl.c          |  4 +--
 mm/huge_memory.c         |  4 +--
 mm/internal.h            |  8 ++---
 mm/page_alloc.c          | 24 ++++++++++-----
 mm/vmscan.c              | 77 ++++++++++++++++++++++++------------------------
 8 files changed, 77 insertions(+), 69 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3668df4a69b9..8c4aa4e98783 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -370,14 +370,6 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_NUMA
-	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
-	 */
-	unsigned long		min_unmapped_pages;
-	unsigned long		min_slab_pages;
-#endif /* CONFIG_NUMA */
-
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
@@ -522,7 +514,6 @@ struct zone {
 } ____cacheline_internodealigned_in_smp;
 
 enum zone_flags {
-	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */
 	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
 };
@@ -538,6 +529,7 @@ enum pgdat_flags {
 	PGDAT_WRITEBACK,		/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
+	PGDAT_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 };
 
 static inline unsigned long zone_end_pfn(const struct zone *zone)
@@ -686,6 +678,14 @@ typedef struct pglist_data {
 	 */
 	unsigned long		totalreserve_pages;
 
+#ifdef CONFIG_NUMA
+	/*
+	 * zone reclaim becomes active if more unmapped pages exist.
+	 */
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
+#endif /* CONFIG_NUMA */
+
 	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
 	spinlock_t		lru_lock;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8d82d1f9d268..76f0ba627ff7 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -333,13 +333,14 @@ extern int remove_mapping(struct address_space *mapping, struct page *page);
 extern unsigned long vm_total_pages;
 
 #ifdef CONFIG_NUMA
-extern int zone_reclaim_mode;
+extern int node_reclaim_mode;
 extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
-extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
 #else
-#define zone_reclaim_mode 0
-static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
+#define node_reclaim_mode 0
+static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
+				unsigned int order)
 {
 	return 0;
 }
diff --git a/include/linux/topology.h b/include/linux/topology.h
index afce69296ac0..cb0775e1ee4b 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -54,7 +54,7 @@ int arch_update_cpu_topology(void);
 /*
  * If the distance between nodes in a system is larger than RECLAIM_DISTANCE
  * (in whatever arch specific measurement units returned by node_distance())
- * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
+ * and node_reclaim_mode is enabled then the VM will only call node_reclaim()
  * on nodes within this distance.
  */
 #define RECLAIM_DISTANCE 30
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 725587f10667..27148ed6bf6a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1476,8 +1476,8 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_NUMA
 	{
 		.procname	= "zone_reclaim_mode",
-		.data		= &zone_reclaim_mode,
-		.maxlen		= sizeof(zone_reclaim_mode),
+		.data		= &node_reclaim_mode,
+		.maxlen		= sizeof(node_reclaim_mode),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 		.extra1		= &zero,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6d73f1a566ae..39ab35a92e53 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2197,10 +2197,10 @@ static bool khugepaged_scan_abort(int nid)
 	int i;
 
 	/*
-	 * If zone_reclaim_mode is disabled, then no extra effort is made to
+	 * If node_reclaim_mode is disabled, then no extra effort is made to
 	 * allocate memory locally.
 	 */
-	if (!zone_reclaim_mode)
+	if (!node_reclaim_mode)
 		return false;
 
 	/* If there is a count for this node already, it must be acceptable */
diff --git a/mm/internal.h b/mm/internal.h
index 1f91ce702cc5..5417545fd86e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -426,10 +426,10 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 }
 #endif /* CONFIG_SPARSEMEM */
 
-#define ZONE_RECLAIM_NOSCAN	-2
-#define ZONE_RECLAIM_FULL	-1
-#define ZONE_RECLAIM_SOME	0
-#define ZONE_RECLAIM_SUCCESS	1
+#define NODE_RECLAIM_NOSCAN	-2
+#define NODE_RECLAIM_FULL	-1
+#define NODE_RECLAIM_SOME	0
+#define NODE_RECLAIM_SUCCESS	1
 
 extern int hwpoison_filter(struct page *p);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e8e518af7a97..46c6a76cacb6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2698,16 +2698,16 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			if (alloc_flags & ALLOC_NO_WATERMARKS)
 				goto try_this_zone;
 
-			if (zone_reclaim_mode == 0 ||
+			if (node_reclaim_mode == 0 ||
 			    !zone_allows_reclaim(ac->preferred_zone, zone))
 				continue;
 
-			ret = zone_reclaim(zone, gfp_mask, order);
+			ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
 			switch (ret) {
-			case ZONE_RECLAIM_NOSCAN:
+			case NODE_RECLAIM_NOSCAN:
 				/* did not scan */
 				continue;
-			case ZONE_RECLAIM_FULL:
+			case NODE_RECLAIM_FULL:
 				/* scanned but unreclaimable */
 				continue;
 			default:
@@ -5519,9 +5519,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
 #ifdef CONFIG_NUMA
 		zone->node = nid;
-		zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
+		pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
 						/ 100;
-		zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
+		pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
 #endif
 		zone->name = zone_names[j];
 		zone->zone_pgdat = pgdat;
@@ -6546,6 +6546,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
 int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int rc;
 
@@ -6553,8 +6554,11 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 	if (rc)
 		return rc;
 
+	for_each_online_pgdat(pgdat)
+		pgdat->min_slab_pages = 0;
+
 	for_each_zone(zone)
-		zone->min_unmapped_pages = (zone->managed_pages *
+		zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
 				sysctl_min_unmapped_ratio) / 100;
 	return 0;
 }
@@ -6562,6 +6566,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
 int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
+	struct pglist_data *pgdat;
 	struct zone *zone;
 	int rc;
 
@@ -6569,8 +6574,11 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
 	if (rc)
 		return rc;
 
+	for_each_online_pgdat(pgdat)
+		pgdat->min_slab_pages = 0;
+
 	for_each_zone(zone)
-		zone->min_slab_pages = (zone->managed_pages *
+		zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
 				sysctl_min_slab_ratio) / 100;
 	return 0;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9a1653fedd88..38325d331aa3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3571,12 +3571,12 @@ module_init(kswapd_init)
 
 #ifdef CONFIG_NUMA
 /*
- * Zone reclaim mode
+ * Node reclaim mode
  *
- * If non-zero call zone_reclaim when the number of free pages falls below
+ * If non-zero call node_reclaim when the number of free pages falls below
  * the watermarks.
  */
-int zone_reclaim_mode __read_mostly;
+int node_reclaim_mode __read_mostly;
 
 #define RECLAIM_OFF 0
 #define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
@@ -3584,14 +3584,14 @@ int zone_reclaim_mode __read_mostly;
 #define RECLAIM_UNMAP (1<<2)	/* Unmap pages during reclaim */
 
 /*
- * Priority for ZONE_RECLAIM. This determines the fraction of pages
+ * Priority for NODE_RECLAIM. This determines the fraction of pages
  * of a node considered for each zone_reclaim. 4 scans 1/16th of
  * a zone.
  */
-#define ZONE_RECLAIM_PRIORITY 4
+#define NODE_RECLAIM_PRIORITY 4
 
 /*
- * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * Percentage of pages in a zone that must be unmapped for node_reclaim to
  * occur.
  */
 int sysctl_min_unmapped_ratio = 1;
@@ -3617,7 +3617,7 @@ static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat)
 }
 
 /* Work out how many page cache pages we can reclaim in this reclaim_mode */
-static unsigned long zone_pagecache_reclaimable(struct zone *zone)
+static unsigned long zone_pagecache_reclaimable(struct pglist_data *pgdat)
 {
 	unsigned long nr_pagecache_reclaimable;
 	unsigned long delta = 0;
@@ -3628,14 +3628,14 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
 	 * pages like swapcache and node_unmapped_file_pages() provides
 	 * a better estimate
 	 */
-	if (zone_reclaim_mode & RECLAIM_UNMAP)
-		nr_pagecache_reclaimable = node_page_state(zone->zone_pgdat, NR_FILE_PAGES);
+	if (node_reclaim_mode & RECLAIM_UNMAP)
+		nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES);
 	else
-		nr_pagecache_reclaimable = node_unmapped_file_pages(zone->zone_pgdat);
+		nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat);
 
 	/* If we can't clean pages, remove dirty pages from consideration */
-	if (!(zone_reclaim_mode & RECLAIM_WRITE))
-		delta += node_page_state(zone->zone_pgdat, NR_FILE_DIRTY);
+	if (!(node_reclaim_mode & RECLAIM_WRITE))
+		delta += node_page_state(pgdat, NR_FILE_DIRTY);
 
 	/* Watch for any possible underflows due to delta */
 	if (unlikely(delta > nr_pagecache_reclaimable))
@@ -3645,23 +3645,24 @@ static unsigned long zone_pagecache_reclaimable(struct zone *zone)
 }
 
 /*
- * Try to free up some pages from this zone through reclaim.
+ * Try to free up some pages from this node through reclaim.
  */
-static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 {
 	/* Minimum pages needed in order to stay on node */
 	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
+	int classzone_idx = gfp_zone(gfp_mask);
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
 		.order = order,
-		.priority = ZONE_RECLAIM_PRIORITY,
-		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
-		.may_unmap = !!(zone_reclaim_mode & RECLAIM_UNMAP),
+		.priority = NODE_RECLAIM_PRIORITY,
+		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
+		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
 		.may_swap = 1,
-		.reclaim_idx = zone_idx(zone),
+		.reclaim_idx = classzone_idx,
 	};
 
 	cond_resched();
@@ -3675,13 +3676,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
+	if (zone_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
 		/*
 		 * Free memory by calling shrink zone with increasing
 		 * priorities until we have enough memory freed.
 		 */
 		do {
-			shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
+			shrink_node(pgdat, &sc, classzone_idx);
 		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
 	}
 
@@ -3691,49 +3692,47 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	return sc.nr_reclaimed >= nr_pages;
 }
 
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 {
-	int node_id;
 	int ret;
 
 	/*
-	 * Zone reclaim reclaims unmapped file backed pages and
+	 * Node reclaim reclaims unmapped file backed pages and
 	 * slab pages if we are over the defined limits.
 	 *
 	 * A small portion of unmapped file backed pages is needed for
 	 * file I/O otherwise pages read by file I/O will be immediately
-	 * thrown out if the zone is overallocated. So we do not reclaim
-	 * if less than a specified percentage of the zone is used by
+	 * thrown out if the node is overallocated. So we do not reclaim
+	 * if less than a specified percentage of the node is used by
 	 * unmapped file backed pages.
 	 */
-	if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
-	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
-		return ZONE_RECLAIM_FULL;
+	if (zone_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
+	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+		return NODE_RECLAIM_FULL;
 
-	if (!pgdat_reclaimable(zone->zone_pgdat))
-		return ZONE_RECLAIM_FULL;
+	if (!pgdat_reclaimable(pgdat))
+		return NODE_RECLAIM_FULL;
 
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
 	if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
-		return ZONE_RECLAIM_NOSCAN;
+		return NODE_RECLAIM_NOSCAN;
 
 	/*
-	 * Only run zone reclaim on the local zone or on zones that do not
+	 * Only run node reclaim on the local node or on nodes that do not
 	 * have associated processors. This will favor the local processor
 	 * over remote processors and spread off node memory allocations
 	 * as wide as possible.
 	 */
-	node_id = zone_to_nid(zone);
-	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
-		return ZONE_RECLAIM_NOSCAN;
+	if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id())
+		return NODE_RECLAIM_NOSCAN;
 
-	if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags))
-		return ZONE_RECLAIM_NOSCAN;
+	if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags))
+		return NODE_RECLAIM_NOSCAN;
 
-	ret = __zone_reclaim(zone, gfp_mask, order);
-	clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
+	ret = __node_reclaim(pgdat, gfp_mask, order);
+	clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
 
 	if (!ret)
 		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints
  2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
@ 2016-04-06 11:22 ` Mel Gorman
  2016-04-06 11:22 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
                   ` (3 subsequent siblings)
  4 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

This is convenient when tracking down why the skip count is high because it'll
show what classzone kswapd woke up at and what zones are being isolated.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/trace/events/vmscan.h | 28 ++++++++++++++++++----------
 mm/vmscan.c                   |  4 ++--
 2 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 897f1aa1ee5f..3d242fb8910a 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -55,21 +55,23 @@ TRACE_EVENT(mm_vmscan_kswapd_sleep,
 
 TRACE_EVENT(mm_vmscan_kswapd_wake,
 
-	TP_PROTO(int nid, int order),
+	TP_PROTO(int nid, int zid, int order),
 
-	TP_ARGS(nid, order),
+	TP_ARGS(nid, zid, order),
 
 	TP_STRUCT__entry(
 		__field(	int,	nid	)
+		__field(	int,	zid	)
 		__field(	int,	order	)
 	),
 
 	TP_fast_assign(
 		__entry->nid	= nid;
+		__entry->zid    = zid;
 		__entry->order	= order;
 	),
 
-	TP_printk("nid=%d order=%d", __entry->nid, __entry->order)
+	TP_printk("nid=%d zid=%d order=%d", __entry->nid, __entry->zid, __entry->order)
 );
 
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
@@ -266,16 +268,18 @@ TRACE_EVENT(mm_shrink_slab_end,
 
 DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
 
 	TP_STRUCT__entry(
+		__field(int, classzone_idx)
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
@@ -285,6 +289,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 	),
 
 	TP_fast_assign(
+		__entry->classzone_idx = classzone_idx;
 		__entry->order = order;
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
@@ -293,8 +298,9 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->file = file;
 	),
 
-	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
+	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
 		__entry->isolate_mode,
+		__entry->classzone_idx,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
@@ -304,27 +310,29 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 38325d331aa3..522378c9849a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1417,7 +1417,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	if (!list_empty(&pages_skipped))
 		list_splice(&pages_skipped, src);
 	*nr_scanned = scan;
-	trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
+	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
 	return nr_taken;
 }
@@ -3405,7 +3405,7 @@ static int kswapd(void *p)
 		 * Try reclaim the requested order but if that fails
 		 * then try sleeping on the basis of the order reclaimed.
 		 */
-		trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
+		trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx, order);
 		if (balance_pgdat(pgdat, order, classzone_idx) < order)
 			goto kswapd_try_sleep;
 
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy
  2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
  2016-04-06 11:22 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
@ 2016-04-06 11:22 ` Mel Gorman
  2016-04-06 11:22 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
                   ` (2 subsequent siblings)
  4 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

The fair zone allocation policy interleaves allocation requests between
zones to avoid an age inversion problem whereby new pages are reclaimed
to balance a zone. Reclaim is now node-based so this should no longer be
an issue and the fair zone allocation policy is not free. This patch
removes it.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/mmzone.h |  2 --
 mm/internal.h          |  1 -
 mm/page_alloc.c        | 76 +-------------------------------------------------
 mm/vmstat.c            |  1 -
 4 files changed, 1 insertion(+), 79 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 8c4aa4e98783..258d4a11b062 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -117,7 +117,6 @@ struct zone_padding {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
-	NR_ALLOC_BATCH,
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
@@ -515,7 +514,6 @@ struct zone {
 
 enum zone_flags {
 	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */
-	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
 };
 
 enum pgdat_flags {
diff --git a/mm/internal.h b/mm/internal.h
index 5417545fd86e..8726c5acddc7 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -460,7 +460,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
 #define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
-#define ALLOC_FAIR		0x100 /* fair zone allocation */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 46c6a76cacb6..54cfe26dcc66 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2399,11 +2399,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 					  get_pcppage_migratetype(page));
 	}
 
-	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
-	if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
-	    !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
-		set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
@@ -2588,40 +2583,18 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
 }
 
 #ifdef CONFIG_NUMA
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
-	return local_zone->node == zone->node;
-}
-
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
 	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
 				RECLAIM_DISTANCE;
 }
 #else	/* CONFIG_NUMA */
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
-	return true;
-}
-
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
 	return true;
 }
 #endif	/* CONFIG_NUMA */
 
-static void reset_alloc_batches(struct zone *preferred_zone)
-{
-	struct zone *zone = preferred_zone->zone_pgdat->node_zones;
-
-	do {
-		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-		clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-	} while (zone++ != preferred_zone);
-}
-
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -2634,11 +2607,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 	struct zoneref *z;
 	struct page *page = NULL;
 	struct zone *zone;
-	int nr_fair_skipped = 0;
-	bool zonelist_rescan;
-
-zonelist_scan:
-	zonelist_rescan = false;
 
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
@@ -2653,20 +2621,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 			!cpuset_zone_allowed(zone, gfp_mask))
 				continue;
 		/*
-		 * Distribute pages in proportion to the individual
-		 * zone size to ensure fair page aging.  The zone a
-		 * page was allocated in should have no effect on the
-		 * time the page has in memory before being reclaimed.
-		 */
-		if (alloc_flags & ALLOC_FAIR) {
-			if (!zone_local(ac->preferred_zone, zone))
-				break;
-			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
-				nr_fair_skipped++;
-				continue;
-			}
-		}
-		/*
 		 * When allocating a page cache page for writing, we
 		 * want to get it from a node that is within its dirty
 		 * limit, such that no single node holds more than its
@@ -2738,27 +2692,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		}
 	}
 
-	/*
-	 * The first pass makes sure allocations are spread fairly within the
-	 * local node.  However, the local node might have free pages left
-	 * after the fairness batches are exhausted, and remote zones haven't
-	 * even been considered yet.  Try once more without fairness, and
-	 * include remote zones now, before entering the slowpath and waking
-	 * kswapd: prefer spilling to a remote zone over swapping locally.
-	 */
-	if (alloc_flags & ALLOC_FAIR) {
-		alloc_flags &= ~ALLOC_FAIR;
-		if (nr_fair_skipped) {
-			zonelist_rescan = true;
-			reset_alloc_batches(ac->preferred_zone);
-		}
-		if (nr_online_nodes > 1)
-			zonelist_rescan = true;
-	}
-
-	if (zonelist_rescan)
-		goto zonelist_scan;
-
 	return NULL;
 }
 
@@ -3312,7 +3245,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
 	unsigned int cpuset_mems_cookie;
-	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
+	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
 	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
 		.high_zoneidx = gfp_zone(gfp_mask),
@@ -5530,9 +5463,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone_seqlock_init(zone);
 		zone_pcp_init(zone);
 
-		/* For bootup, initialized properly in watermark setup */
-		mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
-
 		if (!size)
 			continue;
 
@@ -6377,10 +6307,6 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + tmp;
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
 
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 45ecff0f9f9f..2de1f3790548 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -937,7 +937,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
 const char * const vmstat_text[] = {
 	/* enum zone_stat_item countes */
 	"nr_free_pages",
-	"nr_alloc_batch",
 	"nr_mlock",
 	"nr_slab_reclaimable",
 	"nr_slab_unreclaimable",
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached
  2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
  2016-04-06 11:22 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
  2016-04-06 11:22 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
@ 2016-04-06 11:22 ` Mel Gorman
  2016-04-06 11:22 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
  2016-04-06 11:22 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
  4 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number
of calls to node_dirty_ok().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/page_alloc.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 54cfe26dcc66..a6e6184d3e38 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2607,6 +2607,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 	struct zoneref *z;
 	struct page *page = NULL;
 	struct zone *zone;
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
 
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
@@ -2639,8 +2640,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_ok(zone, order, mark,
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent
  2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
                   ` (2 preceding siblings ...)
  2016-04-06 11:22 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
@ 2016-04-06 11:22 ` Mel Gorman
  2016-04-06 11:22 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
  4 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

This is partially a preparation patch for more vmstat work but it also
has the slight advantage that __count_zid_vm_events is cheaper to
calculate than __count_zone_vm_events().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/vmstat.h | 5 ++---
 mm/page_alloc.c        | 2 +-
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ea00884ac8a0..810914b63564 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -101,9 +101,8 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_vmacache_event(x) do {} while (0)
 #endif
 
-#define __count_zone_vm_events(item, zone, delta) \
-		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
-		zone_idx(zone), delta)
+#define __count_zid_vm_events(item, zid, delta) \
+	__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
 
 /*
  * Zone and node-based page accounting with per cpu differentials.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a6e6184d3e38..ef04dc74e7e9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2399,7 +2399,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 					  get_pcppage_migratetype(page));
 	}
 
-	__count_zone_vm_events(PGALLOC, zone, 1 << order);
+	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
 	local_irq_restore(flags);
 
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim
  2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
                   ` (3 preceding siblings ...)
  2016-04-06 11:22 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
@ 2016-04-06 11:22 ` Mel Gorman
  4 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-06 11:22 UTC (permalink / raw)
  To: Linux-MM; +Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

The vmstat allocstall was fairly useful in the general sense but
node-based LRUs change that. It's important to know if a stall was for an
address-limited allocation request as this will require skipping pages from
other zones. This patch adds pgstall_* counters to replace allocstall. The
sum of the counters will equal the old allocstall so it can be trivially
recalculated. A high number of address-limited allocation requests may
result in a lot of useless LRU scanning for suitable pages.

As address-limited allocations require pages to be skipped, it's important
to know how much useless LRU scanning took place so this patch adds
pgskip* counters. This yields the following model

1. The number of address-space limited stalls can be accounted for (pgstall)
2. The amount of useless work required to reclaim the data is accounted (pgskip)
3. The total number of scans is available from pgscan_kswapd and pgscan_direct
   so from that the ratio of useful to useless scans can be calculated.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/vm_event_item.h |  4 +++-
 mm/vmscan.c                   | 15 +++++++++++++--
 mm/vmstat.c                   |  3 ++-
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8dcb5a813163..0a0503da8c3b 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -23,6 +23,8 @@
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
+		FOR_ALL_ZONES(PGSTALL),
+		FOR_ALL_ZONES(PGSCAN_SKIP),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
@@ -37,7 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		PAGEOUTRUN, PGROTATED,
 		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 522378c9849a..d7d664324442 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1372,6 +1372,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	struct list_head *src = &lruvec->lists[lru];
 	unsigned long nr_taken = 0;
 	unsigned long scan;
+	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	LIST_HEAD(pages_skipped);
 
 	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
@@ -1386,6 +1387,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		if (page_zonenum(page) > sc->reclaim_idx) {
 			list_move(&page->lru, &pages_skipped);
+			nr_skipped[page_zonenum(page)]++;
 			continue;
 		}
 
@@ -1414,8 +1416,17 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	 * scanning would soon rescan the same pages to skip and put the
 	 * system at risk of premature OOM.
 	 */
-	if (!list_empty(&pages_skipped))
+	if (!list_empty(&pages_skipped)) {
+		int zid;
+
 		list_splice(&pages_skipped, src);
+		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+			if (!nr_skipped[zid])
+				continue;
+
+			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
+		}
+	}
 	*nr_scanned = scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
@@ -2686,7 +2697,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
-		count_vm_event(ALLOCSTALL);
+		__count_zid_vm_events(PGSTALL, classzone_idx, 1);
 
 	do {
 		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 2de1f3790548..ee1fb1242c59 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -992,6 +992,8 @@ const char * const vmstat_text[] = {
 	"pswpout",
 
 	TEXTS_FOR_ZONES("pgalloc")
+	TEXTS_FOR_ZONES("pgstall")
+	TEXTS_FOR_ZONES("pgskip")
 
 	"pgfree",
 	"pgactivate",
@@ -1017,7 +1019,6 @@ const char * const vmstat_text[] = {
 	"kswapd_low_wmark_hit_quickly",
 	"kswapd_high_wmark_hit_quickly",
 	"pageoutrun",
-	"allocstall",
 
 	"pgrotated",
 
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached
  2016-06-21 14:15 [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
@ 2016-06-21 14:16 ` Mel Gorman
  0 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-06-21 14:16 UTC (permalink / raw)
  To: Andrew Morton, Linux-MM
  Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number
of calls to node_dirty_ok().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/page_alloc.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1b5080475481..6d0a527cff3d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2853,6 +2853,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2885,8 +2887,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_fast(zone, order, mark,
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* Re: [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached
  2016-06-09 18:04 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
@ 2016-06-17 11:31   ` Vlastimil Babka
  0 siblings, 0 replies; 10+ messages in thread
From: Vlastimil Babka @ 2016-06-17 11:31 UTC (permalink / raw)
  To: Mel Gorman, Andrew Morton, Linux-MM; +Cc: Rik van Riel, Johannes Weiner, LKML

On 06/09/2016 08:04 PM, Mel Gorman wrote:
> If a page is about to be dirtied then the page allocator attempts to limit
> the total number of dirty pages that exists in any given zone. The call
> to node_dirty_ok is expensive so this patch records if the last pgdat
> examined hit the dirty limits. In some cases, this reduces the number
> of calls to node_dirty_ok().
>
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Vlastimil Babka <vbabka@suse.cz>

^ permalink raw reply	[flat|nested] 10+ messages in thread

* [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached
  2016-06-09 18:04 [PATCH 00/27] Move LRU page reclaim from zones to nodes v6 Mel Gorman
@ 2016-06-09 18:04 ` Mel Gorman
  2016-06-17 11:31   ` Vlastimil Babka
  0 siblings, 1 reply; 10+ messages in thread
From: Mel Gorman @ 2016-06-09 18:04 UTC (permalink / raw)
  To: Andrew Morton, Linux-MM
  Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner, LKML, Mel Gorman

If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number
of calls to node_dirty_ok().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/page_alloc.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17fa3f361f01..7c6c18a314a1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2853,6 +2853,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2885,8 +2887,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_fast(zone, order, mark,
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

* [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached
  2016-04-15  9:13 [PATCH 00/27] Move LRU page reclaim from zones to nodes v5 Mel Gorman
@ 2016-04-15  9:13 ` Mel Gorman
  0 siblings, 0 replies; 10+ messages in thread
From: Mel Gorman @ 2016-04-15  9:13 UTC (permalink / raw)
  To: Andrew Morton, Linux-MM
  Cc: Rik van Riel, Vlastimil Babka, Johannes Weiner,
	Jesper Dangaard Brouer, LKML, Mel Gorman

If a page is about to be dirtied then the page allocator attempts to limit
the total number of dirty pages that exists in any given zone. The call
to node_dirty_ok is expensive so this patch records if the last pgdat
examined hit the dirty limits. In some cases, this reduces the number
of calls to node_dirty_ok().

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/page_alloc.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 125f344ff105..d0ca26152716 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2889,6 +2889,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
+	struct pglist_data *last_pgdat_dirty_limit = NULL;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2921,8 +2923,15 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
-			continue;
+		if (ac->spread_dirty_pages) {
+			if (last_pgdat_dirty_limit == zone->zone_pgdat)
+				continue;
+
+			if (!node_dirty_ok(zone->zone_pgdat)) {
+				last_pgdat_dirty_limit = zone->zone_pgdat;
+				continue;
+			}
+		}
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_fast(zone, order, mark,
-- 
2.6.4

^ permalink raw reply related	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2016-06-21 14:45 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-04-06 11:22 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-04-06 11:22 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-04-06 11:22 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-04-06 11:22 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-04-06 11:22 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-04-15  9:13 [PATCH 00/27] Move LRU page reclaim from zones to nodes v5 Mel Gorman
2016-04-15  9:13 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-06-09 18:04 [PATCH 00/27] Move LRU page reclaim from zones to nodes v6 Mel Gorman
2016-06-09 18:04 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-06-17 11:31   ` Vlastimil Babka
2016-06-21 14:15 [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
2016-06-21 14:16 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).