The patch titled
Subject: mm: move zone->pages_scanned into a vmstat counter
has been added to the -mm tree. Its filename is
mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-move-zone-pages_scanned-into-a-vmstat-counter.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@xxxxxxx>
Subject: mm: move zone->pages_scanned into a vmstat counter
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>
---
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(-)
diff -puN include/linux/mmzone.h~mm-move-zone-pages_scanned-into-a-vmstat-counter include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-move-zone-pages_scanned-into-a-vmstat-counter
+++ a/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 */
@@ -480,7 +481,6 @@ struct zone {
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
- unsigned long pages_scanned; /* since last reclaim */
struct lruvec lruvec;
/* Evictions & activations on the inactive file list */
diff -puN mm/page_alloc.c~mm-move-zone-pages_scanned-into-a-vmstat-counter mm/page_alloc.c
--- a/mm/page_alloc.c~mm-move-zone-pages_scanned-into-a-vmstat-counter
+++ a/mm/page_alloc.c
@@ -680,9 +680,12 @@ 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;
@@ -731,8 +734,11 @@ 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)))
@@ -3248,7 +3254,7 @@ 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[]:");
diff -puN mm/vmscan.c~mm-move-zone-pages_scanned-into-a-vmstat-counter mm/vmscan.c
--- a/mm/vmscan.c~mm-move-zone-pages_scanned-into-a-vmstat-counter
+++ a/mm/vmscan.c
@@ -173,7 +173,8 @@ 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)
@@ -1508,7 +1509,7 @@ 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
@@ -1700,7 +1701,7 @@ 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;
diff -puN mm/vmstat.c~mm-move-zone-pages_scanned-into-a-vmstat-counter mm/vmstat.c
--- a/mm/vmstat.c~mm-move-zone-pages_scanned-into-a-vmstat-counter
+++ a/mm/vmstat.c
@@ -763,6 +763,7 @@ const char * const vmstat_text[] = {
"nr_shmem",
"nr_dirtied",
"nr_written",
+ "nr_pages_scanned",
#ifdef CONFIG_NUMA
"numa_hit",
@@ -1067,7 +1068,7 @@ 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 -mm which might be from mgorman@xxxxxxx are
mm-page_alloc-add-__meminit-to-alloc_pages_exact_nid.patch
mm-thp-move-invariant-bug-check-out-of-loop-in-__split_huge_page_map.patch
mm-thp-replace-smp_mb-after-atomic_add-by-smp_mb__after_atomic.patch
mem-hotplug-improve-zone_movable_is_highmem-logic.patch
mm-vmscan-remove-remains-of-kswapd-managed-zone-all_unreclaimable.patch
mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch
mm-vmscan-remove-all_unreclaimable.patch
mm-vmscan-move-swappiness-out-of-scan_control.patch
tracing-tell-mm_migrate_pages-event-about-numa_misplaced.patch
mm-export-nr_shmem-via-sysinfo2-si_meminfo-interfaces.patch
mm-replace-init_page_accessed-by-__setpagereferenced.patch
mm-update-the-description-for-vm_total_pages.patch
mm-pagemap-avoid-unnecessary-overhead-when-tracepoints-are-deactivated.patch
mm-rearrange-zone-fields-into-read-only-page-alloc-statistics-and-page-reclaim-lines.patch
mm-move-zone-pages_scanned-into-a-vmstat-counter.patch
mm-vmscan-only-update-per-cpu-thresholds-for-online-cpu.patch
mm-page_alloc-abort-fair-zone-allocation-policy-when-remotes-nodes-are-encountered.patch
mm-page_alloc-reduce-cost-of-the-fair-zone-allocation-policy.patch
mm-introduce-do_shared_fault-and-drop-do_fault-fix-fix.patch
mm-compactionc-isolate_freepages_block-small-tuneup.patch
mm-zbud-zbud_alloc-minor-param-change.patch
mm-zbud-change-zbud_alloc-size-type-to-size_t.patch
mm-zpool-implement-common-zpool-api-to-zbud-zsmalloc.patch
mm-zpool-zbud-zsmalloc-implement-zpool.patch
mm-zpool-update-zswap-to-use-zpool.patch
mm-zpool-prevent-zbud-zsmalloc-from-unloading-when-used.patch
do_shared_fault-check-that-mmap_sem-is-held.patch
linux-next.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
