The patch titled
Subject: mm, page_alloc: remove fair zone allocation policy
has been added to the -mm tree. Its filename is
mm-page_alloc-remove-fair-zone-allocation-policy.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-remove-fair-zone-allocation-policy.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-remove-fair-zone-allocation-policy.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Subject: mm, page_alloc: remove fair zone allocation policy
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.
Link: http://lkml.kernel.org/r/1467970510-21195-30-git-send-email-mgorman@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
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 -puN include/linux/mmzone.h~mm-page_alloc-remove-fair-zone-allocation-policy include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-page_alloc-remove-fair-zone-allocation-policy
+++ a/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,
@@ -516,10 +515,6 @@ 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, /* pgdat has many dirty pages backed by
* a congested BDI
diff -puN mm/internal.h~mm-page_alloc-remove-fair-zone-allocation-policy mm/internal.h
--- a/mm/internal.h~mm-page_alloc-remove-fair-zone-allocation-policy
+++ a/mm/internal.h
@@ -467,7 +467,6 @@ unsigned long reclaim_clean_pages_from_l
#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 -puN mm/page_alloc.c~mm-page_alloc-remove-fair-zone-allocation-policy mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-remove-fair-zone-allocation-policy
+++ a/mm/page_alloc.c
@@ -2587,7 +2587,6 @@ struct page *buffered_rmqueue(struct zon
else
page = list_first_entry(list, struct page, lru);
- __dec_zone_state(zone, NR_ALLOC_BATCH);
list_del(&page->lru);
pcp->count--;
@@ -2613,15 +2612,10 @@ struct page *buffered_rmqueue(struct zon
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);
@@ -2832,40 +2826,18 @@ bool zone_watermark_ok_safe(struct zone
}
#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.
@@ -2876,10 +2848,6 @@ get_page_from_freelist(gfp_t gfp_mask, u
{
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.
@@ -2894,23 +2862,6 @@ zonelist_scan:
!__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
@@ -2981,23 +2932,6 @@ try_this_zone:
}
}
- /*
- * 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;
}
@@ -3746,7 +3680,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u
{
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),
@@ -5958,9 +5892,6 @@ static void __paginginit free_area_init_
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;
@@ -6808,10 +6739,6 @@ 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 -puN mm/vmstat.c~mm-page_alloc-remove-fair-zone-allocation-policy mm/vmstat.c
--- a/mm/vmstat.c~mm-page_alloc-remove-fair-zone-allocation-policy
+++ a/mm/vmstat.c
@@ -921,7 +921,6 @@ int fragmentation_index(struct zone *zon
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_zone_write_pending",
@@ -1632,10 +1631,9 @@ int vmstat_refresh(struct ctl_table *tab
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
_
Patches currently in -mm which might be from mgorman@xxxxxxxxxxxxxxxxxxx are
mm-meminit-always-return-a-valid-node-from-early_pfn_to_nid.patch
mm-meminit-ensure-node-is-online-before-checking-whether-pages-are-uninitialised.patch
mm-meminit-remove-early_page_nid_uninitialised.patch
mm-vmstat-add-infrastructure-for-per-node-vmstats.patch
mm-vmscan-move-lru_lock-to-the-node.patch
mm-vmscan-move-lru-lists-to-node.patch
mm-mmzone-clarify-the-usage-of-zone-padding.patch
mm-vmscan-begin-reclaiming-pages-on-a-per-node-basis.patch
mm-vmscan-have-kswapd-only-scan-based-on-the-highest-requested-zone.patch
mm-vmscan-make-kswapd-reclaim-in-terms-of-nodes.patch
mm-vmscan-remove-balance-gap.patch
mm-vmscan-simplify-the-logic-deciding-whether-kswapd-sleeps.patch
mm-vmscan-by-default-have-direct-reclaim-only-shrink-once-per-node.patch
mm-vmscan-remove-duplicate-logic-clearing-node-congestion-and-dirty-state.patch
mm-vmscan-do-not-reclaim-from-kswapd-if-there-is-any-eligible-zone.patch
mm-vmscan-make-shrink_node-decisions-more-node-centric.patch
mm-memcg-move-memcg-limit-enforcement-from-zones-to-nodes.patch
mm-workingset-make-working-set-detection-node-aware.patch
mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes.patch
mm-move-page-mapped-accounting-to-the-node.patch
mm-rename-nr_anon_pages-to-nr_anon_mapped.patch
mm-move-most-file-based-accounting-to-the-node.patch
mm-move-vmscan-writes-and-file-write-accounting-to-the-node.patch
mm-vmscan-only-wakeup-kswapd-once-per-node-for-the-requested-classzone.patch
mm-page_alloc-wake-kswapd-based-on-the-highest-eligible-zone.patch
mm-convert-zone_reclaim-to-node_reclaim.patch
mm-vmscan-avoid-passing-in-classzone_idx-unnecessarily-to-shrink_node.patch
mm-vmscan-avoid-passing-in-classzone_idx-unnecessarily-to-compaction_ready.patch
mm-vmscan-avoid-passing-in-remaining-unnecessarily-to-prepare_kswapd_sleep.patch
mm-vmscan-have-kswapd-reclaim-from-all-zones-if-reclaiming-and-buffer_heads_over_limit.patch
mm-vmscan-add-classzone-information-to-tracepoints.patch
mm-page_alloc-remove-fair-zone-allocation-policy.patch
mm-page_alloc-cache-the-last-node-whose-dirty-limit-is-reached.patch
mm-vmstat-replace-__count_zone_vm_events-with-a-zone-id-equivalent.patch
mm-vmstat-account-per-zone-stalls-and-pages-skipped-during-reclaim.patch
mm-vmstat-print-node-based-stats-in-zoneinfo-file.patch
mm-vmstat-remove-zone-and-node-double-accounting-by-approximating-retries.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
