This is a note to let you know that I've just added the patch titled
mm: move zone->pages_scanned into a vmstat counter
to the 3.14-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
and it can be found in the queue-3.14 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 0d5d823ab4e608ec7b52ac4410de4cb74bbe0edd Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@xxxxxxx>
Date: Wed, 6 Aug 2014 16:07:16 -0700
Subject: mm: move zone->pages_scanned into a vmstat counter
From: Mel Gorman <mgorman@xxxxxxx>
commit 0d5d823ab4e608ec7b52ac4410de4cb74bbe0edd upstream.
zone->pages_scanned is a write-intensive cache line during page reclaim
and it's also updated during page free. Move the counter into vmstat to
take advantage of the per-cpu updates and do not update it in the free
paths unless necessary.
On a small UMA machine running tiobench the difference is marginal. On
a 4-node machine the overhead is more noticable. Note that automatic
NUMA balancing was disabled for this test as otherwise the system CPU
overhead is unpredictable.
3.16.0-rc3 3.16.0-rc3 3.16.0-rc3
vanillarearrange-v5 vmstat-v5
User 746.94 759.78 774.56
System 65336.22 58350.98 32847.27
Elapsed 27553.52 27282.02 27415.04
Note that the overhead reduction will vary depending on where exactly
pages are allocated and freed.
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 2 +-
mm/page_alloc.c | 12 +++++++++---
mm/vmscan.c | 7 ++++---
mm/vmstat.c | 3 ++-
4 files changed, 16 insertions(+), 8 deletions(-)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -143,6 +143,7 @@ enum zone_stat_item {
NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */
NR_DIRTIED, /* page dirtyings since bootup */
NR_WRITTEN, /* page writings since bootup */
+ NR_PAGES_SCANNED, /* pages scanned since last reclaim */
#ifdef CONFIG_NUMA
NUMA_HIT, /* allocated in intended node */
NUMA_MISS, /* allocated in non intended node */
@@ -478,7 +479,6 @@ struct zone {
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
- unsigned long pages_scanned; /* since last reclaim */
struct lruvec lruvec;
/*
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -678,9 +678,12 @@ static void free_pcppages_bulk(struct zo
int migratetype = 0;
int batch_free = 0;
int to_free = count;
+ unsigned long nr_scanned;
spin_lock(&zone->lock);
- zone->pages_scanned = 0;
+ nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+ if (nr_scanned)
+ __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
while (to_free) {
struct page *page;
@@ -729,8 +732,11 @@ static void free_one_page(struct zone *z
unsigned int order,
int migratetype)
{
+ unsigned long nr_scanned;
spin_lock(&zone->lock);
- zone->pages_scanned = 0;
+ nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+ if (nr_scanned)
+ __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
__free_one_page(page, pfn, zone, order, migratetype);
if (unlikely(!is_migrate_isolate(migratetype)))
@@ -3251,7 +3257,7 @@ void show_free_areas(unsigned int filter
K(zone_page_state(zone, NR_BOUNCE)),
K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
- zone->pages_scanned,
+ K(zone_page_state(zone, NR_PAGES_SCANNED)),
(!zone_reclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pa
bool zone_reclaimable(struct zone *zone)
{
- return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+ return zone_page_state(zone, NR_PAGES_SCANNED) <
+ zone_reclaimable_pages(zone) * 6;
}
static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -1470,7 +1471,7 @@ shrink_inactive_list(unsigned long nr_to
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
if (global_reclaim(sc)) {
- zone->pages_scanned += nr_scanned;
+ __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
if (current_is_kswapd())
__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
else
@@ -1659,7 +1660,7 @@ static void shrink_active_list(unsigned
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, isolate_mode, lru);
if (global_reclaim(sc))
- zone->pages_scanned += nr_scanned;
+ __mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
reclaim_stat->recent_scanned[file] += nr_taken;
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -761,6 +761,7 @@ const char * const vmstat_text[] = {
"nr_shmem",
"nr_dirtied",
"nr_written",
+ "nr_pages_scanned",
#ifdef CONFIG_NUMA
"numa_hit",
@@ -1055,7 +1056,7 @@ static void zoneinfo_show_print(struct s
min_wmark_pages(zone),
low_wmark_pages(zone),
high_wmark_pages(zone),
- zone->pages_scanned,
+ zone_page_state(zone, NR_PAGES_SCANNED),
zone->spanned_pages,
zone->present_pages,
zone->managed_pages);
Patches currently in stable-queue which might be from mgorman@xxxxxxx are
queue-3.14/mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
queue-3.14/mm-vmscan-only-update-per-cpu-thresholds-for-online-cpu.patch
queue-3.14/mm-page_alloc-use-jump-labels-to-avoid-checking-number_of_cpusets.patch
queue-3.14/mm-page_alloc-do-not-treat-a-zone-that-cannot-be-used-for-dirty-pages-as-full.patch
queue-3.14/mm-non-atomically-mark-page-accessed-during-page-cache-allocation-where-possible.patch
queue-3.14/mm-page_alloc-convert-hot-cold-parameter-and-immediate-callers-to-bool.patch
queue-3.14/memcg-vmscan-fix-forced-scan-of-anonymous-pages.patch
queue-3.14/mm-thp-only-collapse-hugepages-to-nodes-with-affinity-for-zone_reclaim_mode.patch
queue-3.14/mm-page_alloc-only-check-the-zone-id-check-if-pages-are-buddies.patch
queue-3.14/mm-page_alloc-only-check-the-alloc-flags-and-gfp_mask-for-dirty-once.patch
queue-3.14/mm-page_alloc-do-not-update-zlc-unless-the-zlc-is-active.patch
queue-3.14/mm-swap.c-clean-up-lru_cache_add-functions.patch
queue-3.14/mm-page_alloc-take-the-alloc_no_watermark-check-out-of-the-fast-path.patch
queue-3.14/fs-buffer-do-not-use-unnecessary-atomic-operations-when-discarding-buffers.patch
queue-3.14/mm-do-not-use-atomic-operations-when-releasing-pages.patch
queue-3.14/mm-page_alloc-reduce-number-of-times-page_to_pfn-is-called.patch
queue-3.14/mm-page_alloc-use-unsigned-int-for-order-in-more-places.patch
queue-3.14/mm-avoid-unnecessary-atomic-operations-during-end_page_writeback.patch
queue-3.14/vmalloc-use-rcu-list-iterator-to-reduce-vmap_area_lock-contention.patch
queue-3.14/mm-page_alloc-abort-fair-zone-allocation-policy-when-remotes-nodes-are-encountered.patch
queue-3.14/mm-page_alloc-reduce-cost-of-the-fair-zone-allocation-policy.patch
queue-3.14/mm-shmem-avoid-atomic-operation-during-shmem_getpage_gfp.patch
queue-3.14/mm-pagemap-avoid-unnecessary-overhead-when-tracepoints-are-deactivated.patch
queue-3.14/shmem-fix-init_page_accessed-use-to-stop-pagelru-bug.patch
queue-3.14/mm-memory.c-use-entry-access_once-pte-in-handle_pte_fault.patch
queue-3.14/mm-make-copy_pte_range-static-again.patch
queue-3.14/mm-rearrange-zone-fields-into-read-only-page-alloc-statistics-and-page-reclaim-lines.patch
queue-3.14/mm-do-not-use-unnecessary-atomic-operations-when-adding-pages-to-the-lru.patch
queue-3.14/include-linux-jump_label.h-expose-the-reference-count.patch
queue-3.14/mm-page_alloc-calculate-classzone_idx-once-from-the.patch
queue-3.14/mm-page_alloc-lookup-pageblock-migratetype-with-irqs-enabled-during-free.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html