linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@techsingularity.net>
To: Andrew Morton <akpm@linux-foundation.org>, Linux-MM <linux-mm@kvack.org>
Cc: Rik van Riel <riel@surriel.com>, Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes
Date: Thu,  9 Jun 2016 19:04:31 +0100	[thread overview]
Message-ID: <1465495483-11855-16-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1465495483-11855-1-git-send-email-mgorman@techsingularity.net>

Historically dirty pages were spread among zones but now that LRUs are
per-node it is more appropriate to consider dirty pages in a node.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/mmzone.h    | 12 +++---
 include/linux/writeback.h |  2 +-
 mm/page-writeback.c       | 94 ++++++++++++++++++++++++-----------------------
 mm/page_alloc.c           | 26 ++++++-------
 4 files changed, 67 insertions(+), 67 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 19a7adf0a734..5de2fc2dd0e6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -358,12 +358,6 @@ struct zone {
 	struct pglist_data	*zone_pgdat;
 	struct per_cpu_pageset __percpu *pageset;
 
-	/*
-	 * This is a per-zone reserve of pages that are not available
-	 * to userspace allocations.
-	 */
-	unsigned long		totalreserve_pages;
-
 #ifndef CONFIG_SPARSEMEM
 	/*
 	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -682,6 +676,12 @@ typedef struct pglist_data {
 	/* Number of pages migrated during the rate limiting time interval */
 	unsigned long numabalancing_migrate_nr_pages;
 #endif
+	/*
+	 * This is a per-node reserve of pages that are not available
+	 * to userspace allocations.
+	 */
+	unsigned long		totalreserve_pages;
+
 	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
 	spinlock_t		lru_lock;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index d0b5ca5d4e08..44b4422ae57f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data);
 static inline void laptop_sync_completion(void) { }
 #endif
 void throttle_vm_writeout(gfp_t gfp_mask);
-bool zone_dirty_ok(struct zone *zone);
+bool node_dirty_ok(struct pglist_data *pgdat);
 int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
 #ifdef CONFIG_CGROUP_WRITEBACK
 void wb_domain_exit(struct wb_domain *dom);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3ddfa0b48436..4db3be44bb1d 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
  */
 
 /**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
+ * node_dirtyable_memory - number of dirtyable pages in a node
+ * @pgdat: the node
  *
- * Returns the zone's number of pages potentially available for dirty
- * page cache.  This is the base value for the per-zone dirty limits.
+ * Returns the node's number of pages potentially available for dirty
+ * page cache.  This is the base value for the per-node dirty limits.
  */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
+static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
 {
-	unsigned long nr_pages;
+	unsigned long nr_pages = 0;
+	int z;
+
+	for (z = 0; z < MAX_NR_ZONES; z++) {
+		struct zone *zone = pgdat->node_zones + z;
+
+		if (!populated_zone(zone))
+			continue;
+
+		nr_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
 
-	nr_pages = zone_page_state(zone, NR_FREE_PAGES);
 	/*
 	 * Pages reserved for the kernel should not be considered
 	 * dirtyable, to prevent a situation where reclaim has to
 	 * clean pages in order to balance the zones.
 	 */
-	nr_pages -= min(nr_pages, zone->totalreserve_pages);
+	nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
 
-	nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
-	nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
+	nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
+	nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
 
 	return nr_pages;
 }
@@ -294,29 +303,13 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
 static unsigned long highmem_dirtyable_memory(unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
-	int node;
 	unsigned long x = 0;
-	int i;
-
-	for_each_node_state(node, N_HIGH_MEMORY) {
-		for (i = 0; i < MAX_NR_ZONES; i++) {
-			struct zone *z = &NODE_DATA(node)->node_zones[i];
 
-			if (is_highmem(z))
-				x += zone_dirtyable_memory(z);
-		}
-	}
 	/*
-	 * Unreclaimable memory (kernel memory or anonymous memory
-	 * without swap) can bring down the dirtyable pages below
-	 * the zone's dirty balance reserve and the above calculation
-	 * will underflow.  However we still want to add in nodes
-	 * which are below threshold (negative values) to get a more
-	 * accurate calculation but make sure that the total never
-	 * underflows.
+	 * LRU lists are per-node so there is no fast and accurate means of
+	 * calculating dirtyable memory in the highmem zone.
 	 */
-	if ((long)x < 0)
-		x = 0;
+	x = totalhigh_pages;
 
 	/*
 	 * Make sure that the number of highmem pages is never larger
@@ -442,23 +435,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 }
 
 /**
- * zone_dirty_limit - maximum number of dirty pages allowed in a zone
- * @zone: the zone
+ * node_dirty_limit - maximum number of dirty pages allowed in a node
+ * @pgdat: the node
  *
- * Returns the maximum number of dirty pages allowed in a zone, based
- * on the zone's dirtyable memory.
+ * Returns the maximum number of dirty pages allowed in a node, based
+ * on the node's dirtyable memory.
  */
-static unsigned long zone_dirty_limit(struct zone *zone)
+static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 {
-	unsigned long zone_memory = zone_dirtyable_memory(zone);
+	unsigned long node_memory = node_dirtyable_memory(pgdat);
 	struct task_struct *tsk = current;
 	unsigned long dirty;
 
 	if (vm_dirty_bytes)
 		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
-			zone_memory / global_dirtyable_memory();
+			node_memory / global_dirtyable_memory();
 	else
-		dirty = vm_dirty_ratio * zone_memory / 100;
+		dirty = vm_dirty_ratio * node_memory / 100;
 
 	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
 		dirty += dirty / 4;
@@ -467,19 +460,30 @@ static unsigned long zone_dirty_limit(struct zone *zone)
 }
 
 /**
- * zone_dirty_ok - tells whether a zone is within its dirty limits
- * @zone: the zone to check
+ * node_dirty_ok - tells whether a node is within its dirty limits
+ * @pgdat: the node to check
  *
- * Returns %true when the dirty pages in @zone are within the zone's
+ * Returns %true when the dirty pages in @pgdat are within the node's
  * dirty limit, %false if the limit is exceeded.
  */
-bool zone_dirty_ok(struct zone *zone)
+bool node_dirty_ok(struct pglist_data *pgdat)
 {
-	unsigned long limit = zone_dirty_limit(zone);
+	int z;
+	unsigned long limit = node_dirty_limit(pgdat);
+	unsigned long nr_pages = 0;
+
+	for (z = 0; z < MAX_NR_ZONES; z++) {
+		struct zone *zone = pgdat->node_zones + z;
+
+		if (!populated_zone(zone))
+			continue;
+
+		nr_pages += zone_page_state(zone, NR_FILE_DIRTY);
+		nr_pages += zone_page_state(zone, NR_UNSTABLE_NFS);
+		nr_pages += zone_page_state(zone, NR_WRITEBACK);
+	}
 
-	return zone_page_state(zone, NR_FILE_DIRTY) +
-	       zone_page_state(zone, NR_UNSTABLE_NFS) +
-	       zone_page_state(zone, NR_WRITEBACK) <= limit;
+	return nr_pages <= limit;
 }
 
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fc5bad895732..37e7b909ba48 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2917,31 +2917,24 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		}
 		/*
 		 * When allocating a page cache page for writing, we
-		 * want to get it from a zone that is within its dirty
-		 * limit, such that no single zone holds more than its
+		 * want to get it from a node that is within its dirty
+		 * limit, such that no single node holds more than its
 		 * proportional share of globally allowed dirty pages.
-		 * The dirty limits take into account the zone's
+		 * The dirty limits take into account the node's
 		 * lowmem reserves and high watermark so that kswapd
 		 * should be able to balance it without having to
 		 * write pages from its LRU list.
 		 *
-		 * This may look like it could increase pressure on
-		 * lower zones by failing allocations in higher zones
-		 * before they are full.  But the pages that do spill
-		 * over are limited as the lower zones are protected
-		 * by this very same mechanism.  It should not become
-		 * a practical burden to them.
-		 *
 		 * XXX: For now, allow allocations to potentially
-		 * exceed the per-zone dirty limit in the slowpath
+		 * exceed the per-node dirty limit in the slowpath
 		 * (spread_dirty_pages unset) before going into reclaim,
 		 * which is important when on a NUMA setup the allowed
-		 * zones are together not big enough to reach the
+		 * nodes are together not big enough to reach the
 		 * global limit.  The proper fix for these situations
-		 * will require awareness of zones in the
+		 * will require awareness of nodes in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
+		if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
 			continue;
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
@@ -6701,6 +6694,9 @@ static void calculate_totalreserve_pages(void)
 	enum zone_type i, j;
 
 	for_each_online_pgdat(pgdat) {
+
+		pgdat->totalreserve_pages = 0;
+
 		for (i = 0; i < MAX_NR_ZONES; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 			long max = 0;
@@ -6717,7 +6713,7 @@ static void calculate_totalreserve_pages(void)
 			if (max > zone->managed_pages)
 				max = zone->managed_pages;
 
-			zone->totalreserve_pages = max;
+			pgdat->totalreserve_pages += max;
 
 			reserve_pages += max;
 		}
-- 
2.6.4

  parent reply	other threads:[~2016-06-09 18:07 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
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 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman
2016-06-10 13:31   ` Vlastimil Babka
2016-06-10 13:47     ` Mel Gorman
2016-06-13 17:26   ` Christoph Lameter
2016-06-14 14:25     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman
2016-06-10 16:39   ` Vlastimil Babka
2016-06-10 17:48     ` Peter Zijlstra
2016-06-14 14:41     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 03/27] mm, vmscan: Move LRU lists to node Mel Gorman
2016-06-10 18:00   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman
2016-06-15 12:52   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 05/27] mm, vmscan: Have kswapd only scan based on the highest requested zone Mel Gorman
2016-06-15 13:13   ` Vlastimil Babka
2016-06-16  7:44     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman
2016-06-15 14:23   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman
2016-06-15 14:28   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-06-15 15:18   ` Vlastimil Babka
2016-06-16  8:30     ` Mel Gorman
2016-06-16  9:16       ` Mel Gorman
2016-06-09 18:04 ` [PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman
2016-06-16  8:59   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 10/27] mm, vmscan: Clear congestion, dirty and need for compaction on a per-node basis Mel Gorman
2016-06-16  9:29   ` Vlastimil Babka
2016-06-16 10:29     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 11/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-06-16 10:08   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman
2016-06-16 13:35   ` Vlastimil Babka
2016-06-16 14:47     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman
2016-06-16 15:06   ` Vlastimil Babka
2016-06-16 15:53     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 14/27] mm, workingset: Make working set detection node-aware Mel Gorman
2016-06-16 15:13   ` Vlastimil Babka
2016-06-16 15:56     ` Mel Gorman
2016-06-09 18:04 ` Mel Gorman [this message]
2016-06-16 15:45   ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Vlastimil Babka
2016-06-09 18:04 ` [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman
2016-06-16 15:52   ` Vlastimil Babka
2016-06-16 16:04     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-06-17  8:28   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman
2016-06-17  8:35   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 19/27] mm: Move vmscan writes and file write " Mel Gorman
2016-06-17  8:51   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman
2016-06-17  8:53   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-06-17 10:46   ` Vlastimil Babka
2016-06-17 12:03     ` Mel Gorman
2016-06-09 18:04 ` [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-06-17 10:55   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-06-17 10:57   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-06-17 11:27   ` Vlastimil Babka
2016-06-17 12:07     ` 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
2016-06-09 18:04 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-06-17 11:36   ` Vlastimil Babka
2016-06-09 18:04 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-06-17 12:39   ` Vlastimil Babka
  -- strict thread matches above, loose matches on Subject: below --
2016-06-21 14:15 [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
2016-06-21 14:15 ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-06-22 14:15   ` Michal Hocko
2016-06-22 14:27     ` Michal Hocko
2016-06-23 12:53       ` Mel Gorman
2016-06-23 13:13         ` Michal Hocko
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 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-04-06 11:19 [RFC PATCH 00/27] Move LRU page reclaim from zones to nodes v3 Mel Gorman
2016-04-06 11:20 ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1465495483-11855-16-git-send-email-mgorman@techsingularity.net \
    --to=mgorman@techsingularity.net \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=riel@surriel.com \
    --cc=vbabka@suse.cz \
    --subject='Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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).