Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1427818
| From | Mel Gorman <mgorman@techsingularity.net> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy |
| Date | 2016-06-21 16:30 +0200 |
| Message-ID | <rMuQG-6YC-33@gated-at.bofh.it> (permalink) |
| References | <rMuGZ-6Vn-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
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>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 5 ----
mm/internal.h | 1 -
mm/page_alloc.c | 75 +-------------------------------------------------
mm/vmstat.c | 4 +--
4 files changed, 2 insertions(+), 83 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 79fb9f6efc55..2c331f0afd04 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_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_LRU_FILE,
@@ -512,10 +511,6 @@ struct zone {
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
-enum zone_flags {
- ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
-};
-
enum pgdat_flags {
PGDAT_CONGESTED, /* zone has many dirty pages backed by
* a congested BDI
diff --git a/mm/internal.h b/mm/internal.h
index 4abb2336e127..863b12ca7aa2 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -469,7 +469,6 @@ 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 78e5abc41857..1b5080475481 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;
}
@@ -3753,7 +3687,7 @@ __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),
@@ -5954,9 +5888,6 @@ 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;
@@ -6809,10 +6740,6 @@ 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 b58ceb8c872c..ec96d20eeb52 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_zone_anon_lru",
"nr_zone_file_lru",
"nr_mlock",
@@ -1626,10 +1625,9 @@ 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
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 07/27] mm, vmscan: Remove balance gap Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 09/27] mm, vmscan: By default have direct reclaim only shrink once per node Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 06/27] mm, vmscan: Make kswapd reclaim in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 02/27] mm, vmscan: Move lru_lock to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 10/27] mm, vmscan: Remove duplicate logic clearing node congestion and dirty state Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 11/27] mm: vmscan: Do not reclaim from kswapd if there is any eligible zone Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:20 +0200
[PATCH 14/27] mm, workingset: Make working set detection node-aware Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
[PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 17/27] mm: Rename NR_ANON_PAGES to NR_ANON_MAPPED Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:30 +0200
[PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Michal Hocko <mhocko@kernel.org> - 2016-06-22 15:30 +0200
Re: [PATCH 12/27] mm, vmscan: Make shrink_node decisions more node-centric Vlastimil Babka <vbabka@suse.cz> - 2016-06-22 17:50 +0200
[PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 16/27] mm: Move page mapped accounting to the node Andrew Morton <akpm@linux-foundation.org> - 2016-06-22 00:50 +0200
Re: [PATCH 16/27] mm: Move page mapped accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 10:40 +0200
Re: [PATCH 16/27] mm: Move page mapped accounting to the node Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:40 +0200
[PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 13/27] mm, memcg: Move memcg limit enforcement from zones to nodes Michal Hocko <mhocko@kernel.org> - 2016-06-22 15:20 +0200
[PATCH 22/27] mm: Convert zone_reclaim to node_reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
[PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:50 +0200
Re: [PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 16:00 +0200
Re: [PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Vlastimil Babka <vbabka@suse.cz> - 2016-06-23 16:10 +0200
Re: [PATCH 19/27] mm: Move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 18:10 +0200
[PATCH 24/27] mm, page_alloc: Remove fair zone allocation policy Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
[PATCH 18/27] mm: Move most file-based accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:30 +0200
Re: [PATCH 18/27] mm: Move most file-based accounting to the node Michal Hocko <mhocko@kernel.org> - 2016-06-22 17:30 +0200
[PATCH 23/27] mm, vmscan: Add classzone information to tracepoints Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:40 +0200
[PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:40 +0200
Re: [PATCH 20/27] mm, vmscan: Update classzone_idx if buffer_heads_over_limit Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:50 +0200
[PATCH 27/27] mm: vmstat: Account per-zone stalls and pages skipped during reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:40 +0200
[PATCH 26/27] mm: vmstat: Replace __count_zone_vm_events with a zone id equivalent Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:40 +0200
[PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:40 +0200
Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:30 +0200
Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Michal Hocko <mhocko@kernel.org> - 2016-06-22 16:30 +0200
Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 15:00 +0200
Re: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Michal Hocko <mhocko@kernel.org> - 2016-06-23 15:20 +0200
[PATCH 25/27] mm: page_alloc: Cache the last node whose dirty limit is reached Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:50 +0200
[PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Mel Gorman <mgorman@techsingularity.net> - 2016-06-21 16:50 +0200
Re: [PATCH 21/27] mm, vmscan: Only wakeup kswapd once per node for the requested classzone Vlastimil Babka <vbabka@suse.cz> - 2016-06-22 18:10 +0200
Re: [PATCH 03/27] mm, vmscan: Move LRU lists to node Vlastimil Babka <vbabka@suse.cz> - 2016-06-22 15:00 +0200
Re: [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 12:30 +0200
Re: [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Michal Hocko <mhocko@kernel.org> - 2016-06-23 13:30 +0200
Re: [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Mel Gorman <mgorman@techsingularity.net> - 2016-06-23 14:40 +0200
Re: [PATCH 00/27] Move LRU page reclaim from zones to nodes v7 Michal Hocko <mhocko@kernel.org> - 2016-06-23 14:50 +0200
csiph-web