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 24/27] mm, page_alloc: Remove fair zone allocation policy
Date: Thu,  9 Jun 2016 19:04:40 +0100	[thread overview]
Message-ID: <1465495483-11855-25-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1465495483-11855-1-git-send-email-mgorman@techsingularity.net>

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        | 75 +-------------------------------------------------
 mm/vmstat.c            |  4 +--
 4 files changed, 2 insertions(+), 80 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d826d203185e..347a13a62d55 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -110,7 +110,6 @@ 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,
@@ -511,7 +510,6 @@ 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 5231344a9e52..51505914d7c9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -468,7 +468,6 @@ 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 a249128999a8..17fa3f361f01 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2592,7 +2592,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 			else
 				page = list_first_entry(list, struct page, lru);
 
-			__dec_zone_state(zone, NR_ALLOC_BATCH);
 			list_del(&page->lru);
 			pcp->count--;
 
@@ -2618,15 +2617,10 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 		spin_unlock(&zone->lock);
 		if (!page)
 			goto failed;
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 		__mod_zone_freepage_state(zone, -(1 << order),
 					  get_pcppage_migratetype(page));
 	}
 
-	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);
@@ -2837,40 +2831,18 @@ 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.
@@ -2881,10 +2853,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 {
 	struct zoneref *z = ac->preferred_zoneref;
 	struct zone *zone;
-	bool fair_skipped = false;
-	bool apply_fair = (alloc_flags & ALLOC_FAIR);
-
-zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2899,23 +2867,6 @@ 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 (apply_fair) {
-			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
-				fair_skipped = true;
-				continue;
-			}
-			if (!zone_local(ac->preferred_zoneref->zone, zone)) {
-				if (fair_skipped)
-					goto reset_fair;
-				apply_fair = false;
-			}
-		}
-		/*
 		 * 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
@@ -2986,23 +2937,6 @@ 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 (fair_skipped) {
-reset_fair:
-		apply_fair = false;
-		fair_skipped = false;
-		reset_alloc_batches(ac->preferred_zoneref->zone);
-		z = ac->preferred_zoneref;
-		goto zonelist_scan;
-	}
-
 	return NULL;
 }
 
@@ -3758,7 +3692,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
-	unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
+	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
 		.high_zoneidx = gfp_zone(gfp_mask),
@@ -5959,9 +5893,6 @@ 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;
 
@@ -6814,10 +6745,6 @@ 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 26e9873be7a2..dd60fa3ca66b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -920,7 +920,6 @@ 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",
@@ -1624,10 +1623,9 @@ int vmstat_refresh(struct ctl_table *table, int write,
 		val = atomic_long_read(&vm_zone_stat[i]);
 		if (val < 0) {
 			switch (i) {
-			case NR_ALLOC_BATCH:
 			case NR_PAGES_SCANNED:
 				/*
-				 * These are often seen to go negative in
+				 * This is often seen to go negative in
 				 * recent kernels, but not to go permanently
 				 * negative.  Whilst it would be nicer not to
 				 * have exceptions, rooting them out would be
-- 
2.6.4

  parent reply	other threads:[~2016-06-09 18:19 UTC|newest]

Thread overview: 73+ 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 ` [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman
2016-06-16 15:45   ` 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 ` Mel Gorman [this message]
2016-06-17 11:27   ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy 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 14:16 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy 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 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman
2016-04-06 11:22 [PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman
2016-04-06 11:22 ` [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy 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=1465495483-11855-25-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 24/27] mm, page_alloc: Remove fair zone allocation policy' \
    /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).