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 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis
Date: Tue, 21 Jun 2016 15:15:43 +0100	[thread overview]
Message-ID: <1466518566-30034-5-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1466518566-30034-1-git-send-email-mgorman@techsingularity.net>

This patch makes reclaim decisions on a per-node basis. A reclaimer knows
what zone is required by the allocation request and skips pages from
higher zones. In many cases this will be ok because it's a GFP_HIGHMEM
request of some description. On 64-bit, ZONE_DMA32 requests will cause
some problems but 32-bit devices on 64-bit platforms are increasingly
rare. Historically it would have been a major problem on 32-bit with big
Highmem:Lowmem ratios but such configurations are also now rare and even
where they exist, they are not encouraged. If it really becomes a problem,
it'll manifest as very low reclaim efficiencies.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/vmscan.c | 78 +++++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 53 insertions(+), 25 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 39cd6375f54e..7d5bad437809 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -84,6 +84,9 @@ struct scan_control {
 	/* Scan (total_size >> priority) pages at once */
 	int priority;
 
+	/* The highest zone to isolate pages for reclaim from */
+	enum zone_type reclaim_idx;
+
 	unsigned int may_writepage:1;
 
 	/* Can mapped pages be reclaimed? */
@@ -1386,6 +1389,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_taken = 0;
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
 	unsigned long scan, nr_pages;
+	LIST_HEAD(pages_skipped);
 
 	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
 					!list_empty(src); scan++) {
@@ -1396,6 +1400,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 
+		if (page_zonenum(page) > sc->reclaim_idx) {
+			list_move(&page->lru, &pages_skipped);
+			continue;
+		}
+
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
 			nr_pages = hpage_nr_pages(page);
@@ -1414,6 +1423,15 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		}
 	}
 
+	/*
+	 * Splice any skipped pages to the start of the LRU list. Note that
+	 * this disrupts the LRU order when reclaiming for lower zones but
+	 * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX
+	 * scanning would soon rescan the same pages to skip and put the
+	 * system at risk of premature OOM.
+	 */
+	if (!list_empty(&pages_skipped))
+		list_splice(&pages_skipped, src);
 	*nr_scanned = scan;
 	trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
@@ -1583,7 +1601,7 @@ static int current_may_throttle(void)
 }
 
 /*
- * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
+ * shrink_inactive_list() is a helper for shrink_node().  It returns the number
  * of reclaimed pages
  */
 static noinline_for_stack unsigned long
@@ -2395,12 +2413,13 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static bool shrink_zone(struct zone *zone, struct scan_control *sc,
-			bool is_classzone)
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc,
+			enum zone_type classzone_idx)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_reclaimed, nr_scanned;
 	bool reclaimable = false;
+	struct zone *zone = &pgdat->node_zones[classzone_idx];
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2432,7 +2451,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			shrink_zone_memcg(zone, memcg, sc, &lru_pages);
 			zone_lru_pages += lru_pages;
 
-			if (memcg && is_classzone)
+			if (!global_reclaim(sc) && sc->reclaim_idx == classzone_idx)
 				shrink_slab(sc->gfp_mask, zone_to_nid(zone),
 					    memcg, sc->nr_scanned - scanned,
 					    lru_pages);
@@ -2463,7 +2482,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 		 * Shrink the slab caches in the same proportion that
 		 * the eligible LRU pages were scanned.
 		 */
-		if (global_reclaim(sc) && is_classzone)
+		if (global_reclaim(sc) && sc->reclaim_idx == classzone_idx)
 			shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
 				    sc->nr_scanned - nr_scanned,
 				    zone_lru_pages);
@@ -2540,14 +2559,14 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
+static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc,
+		enum zone_type classzone_idx)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
 	gfp_t orig_mask;
-	enum zone_type requested_highidx = gfp_zone(sc->gfp_mask);
 
 	/*
 	 * If the number of buffer_heads in the machine exceeds the maximum
@@ -2560,15 +2579,20 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
-		enum zone_type classzone_idx;
-
 		if (!populated_zone(zone))
 			continue;
 
-		classzone_idx = requested_highidx;
+		/*
+		 * Note that reclaim_idx does not change as it is the highest
+		 * zone reclaimed from which for empty zones is a no-op but
+		 * classzone_idx is used by shrink_node to test if the slabs
+		 * should be shrunk on a given node.
+		 */
 		while (!populated_zone(zone->zone_pgdat->node_zones +
-							classzone_idx))
+							classzone_idx)) {
 			classzone_idx--;
+			continue;
+		}
 
 		/*
 		 * Take care memory controller reclaiming has small influence
@@ -2594,8 +2618,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			 */
 			if (IS_ENABLED(CONFIG_COMPACTION) &&
 			    sc->order > PAGE_ALLOC_COSTLY_ORDER &&
-			    zonelist_zone_idx(z) <= requested_highidx &&
-			    compaction_ready(zone, sc->order, requested_highidx)) {
+			    zonelist_zone_idx(z) <= classzone_idx &&
+			    compaction_ready(zone, sc->order, classzone_idx)) {
 				sc->compaction_ready = true;
 				continue;
 			}
@@ -2615,7 +2639,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			/* need some check for avoid more shrink_zone() */
 		}
 
-		shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+		shrink_node(zone->zone_pgdat, sc, classzone_idx);
 	}
 
 	/*
@@ -2647,6 +2671,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	int initial_priority = sc->priority;
 	unsigned long total_scanned = 0;
 	unsigned long writeback_threshold;
+	enum zone_type classzone_idx = sc->reclaim_idx;
 retry:
 	delayacct_freepages_start();
 
@@ -2657,7 +2682,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
 				sc->priority);
 		sc->nr_scanned = 0;
-		shrink_zones(zonelist, sc);
+		shrink_zones(zonelist, sc, classzone_idx);
 
 		total_scanned += sc->nr_scanned;
 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
@@ -2841,6 +2866,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	struct scan_control sc = {
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+		.reclaim_idx = gfp_zone(gfp_mask),
 		.order = order,
 		.nodemask = nodemask,
 		.priority = DEF_PRIORITY,
@@ -3112,7 +3138,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
 						balance_gap, classzone_idx))
 		return true;
 
-	shrink_zone(zone, sc, zone_idx(zone) == classzone_idx);
+	shrink_node(zone->zone_pgdat, sc, classzone_idx);
 
 	/* TODO: ANOMALY */
 	clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
@@ -3161,6 +3187,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
+		.reclaim_idx = MAX_NR_ZONES - 1,
 		.order = order,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,
@@ -3231,15 +3258,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 			sc.may_writepage = 1;
 
 		/*
-		 * Now scan the zone in the dma->highmem direction, stopping
-		 * at the last zone which needs scanning.
-		 *
-		 * We do this because the page allocator works in the opposite
-		 * direction.  This prevents the page allocator from allocating
-		 * pages behind kswapd's direction of progress, which would
-		 * cause too much scanning of the lower zones.
+		 * Continue scanning in the highmem->dma direction stopping at
+		 * the last zone which needs scanning. This may reclaim lowmem
+		 * pages that are not necessary for zone balancing but it
+		 * preserves LRU ordering. It is assumed that the bulk of
+		 * allocation requests can use arbitrary zones with the
+		 * possible exception of big highmem:lowmem configurations.
 		 */
-		for (i = 0; i <= end_zone; i++) {
+		for (i = end_zone; i >= 0; i--) {
 			struct zone *zone = pgdat->node_zones + i;
 
 			if (!populated_zone(zone))
@@ -3250,6 +3276,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 				continue;
 
 			sc.nr_scanned = 0;
+			sc.reclaim_idx = i;
 
 			nr_soft_scanned = 0;
 			/*
@@ -3698,6 +3725,7 @@ 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_UNMAP),
 		.may_swap = 1,
+		.reclaim_idx = zone_idx(zone),
 	};
 
 	cond_resched();
@@ -3717,7 +3745,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * priorities until we have enough memory freed.
 		 */
 		do {
-			shrink_zone(zone, &sc, true);
+			shrink_node(zone->zone_pgdat, &sc, zone_idx(zone));
 		} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
 	}
 
-- 
2.6.4

  parent reply	other threads:[~2016-06-21 14:17 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
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 01/27] mm, vmstat: Add infrastructure for per-node vmstats Mel Gorman
2016-06-21 14:15 ` [PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman
2016-06-21 14:15 ` [PATCH 03/27] mm, vmscan: Move LRU lists to node Mel Gorman
2016-06-22 12:50   ` Vlastimil Babka
2016-06-21 14:15 ` Mel Gorman [this message]
2016-06-22 14:04   ` [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Vlastimil Babka
2016-06-22 16:00     ` Vlastimil Babka
2016-06-23 11:07       ` Mel Gorman
2016-06-23 11:13         ` Michal Hocko
2016-06-23 10:58     ` Mel Gorman
2016-06-21 14:15 ` [PATCH 05/27] mm, vmscan: Have kswapd only scan based on the highest requested zone Mel Gorman
2016-06-21 14:15 ` [PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman
2016-06-21 14:15 ` [PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman
2016-06-21 14:15 ` [PATCH 08/27] mm, vmscan: Simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-06-22 15:30   ` Vlastimil Babka
2016-06-21 14:15 ` [PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman
2016-06-21 14:15 ` [PATCH 10/27] mm, vmscan: Remove duplicate logic clearing node congestion and dirty state Mel Gorman
2016-06-21 14:15 ` [PATCH 11/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-06-21 14:15 ` [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman
2016-06-22 13:20   ` Michal Hocko
2016-06-22 15:42   ` Vlastimil Babka
2016-06-21 14:15 ` [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman
2016-06-22 13:15   ` Michal Hocko
2016-06-21 14:15 ` [PATCH 14/27] mm, workingset: Make working set detection node-aware 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
2016-06-21 14:15 ` [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman
2016-06-21 22:32   ` Andrew Morton
2016-06-23  8:35     ` Mel Gorman
2016-06-22 14:35   ` Michal Hocko
2016-06-21 14:15 ` [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-06-22 14:28   ` Michal Hocko
2016-06-21 14:15 ` [PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman
2016-06-22 14:38   ` Michal Hocko
2016-06-21 14:15 ` [PATCH 19/27] mm: Move vmscan writes and file write " Mel Gorman
2016-06-22 14:40   ` Michal Hocko
2016-06-23 13:57     ` Mel Gorman
2016-06-23 14:06       ` Vlastimil Babka
2016-06-23 16:03         ` Mel Gorman
2016-06-21 14:15 ` [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman
2016-06-22 14:49   ` Michal Hocko
2016-06-21 14:16 ` [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-06-22 16:08   ` Vlastimil Babka
2016-06-21 14:16 ` [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-06-21 14:16 ` [PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman
2016-06-21 14:16 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-06-21 14:16 ` [PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman
2016-06-21 14:16 ` [PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-06-21 14:16 ` [PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-06-23 10:26 ` [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman
2016-06-23 11:27   ` Michal Hocko
2016-06-23 12:33     ` Mel Gorman
2016-06-23 12:44       ` Michal Hocko
2016-06-23 21:45   ` Andrew Morton
2016-06-24  6:35 ` Balbir Singh
2016-06-24  7:50   ` Mel Gorman
2016-06-27 12:48     ` Balbir Singh
     [not found] <02ed01d1c47a$49fbfbc0$ddf3f340$@alibaba-inc.com>
2016-06-12  7:33 ` [PATCH 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Hillf Danton
2016-06-14 14:47   ` Mel Gorman
  -- strict thread matches above, loose matches on Subject: below --
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 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis Mel Gorman
2016-06-15 12:52   ` Vlastimil Babka
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 04/27] mm, vmscan: Begin reclaiming pages on a per-node basis 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=1466518566-30034-5-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 \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).