Subject: + mm-page_alloc-fair-zone-allocator-policy-v2-fix.patch added to -mm tree
To: hannes@xxxxxxxxxxx,aarcange@xxxxxxxxxx,mgorman@xxxxxxx,paul.bollee@xxxxxxxxx,riel@xxxxxxxxxx,zcalusic@xxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Mon, 12 Aug 2013 14:25:55 -0700
The patch titled
Subject: mm: page_alloc: use vmstats for fair zone allocation batching
has been added to the -mm tree. Its filename is
mm-page_alloc-fair-zone-allocator-policy-v2-fix.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-fair-zone-allocator-policy-v2-fix.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-fair-zone-allocator-policy-v2-fix.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: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm: page_alloc: use vmstats for fair zone allocation batching
Avoid dirtying the same cache line with every single page allocation by
making the fair per-zone allocation batch a vmstat item, which will turn
it into batched percpu counters on SMP.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Zlatko Calusic <zcalusic@xxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Paul Bolle <paul.bollee@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 2 +-
mm/page_alloc.c | 21 ++++++++++++---------
mm/vmstat.c | 1 +
3 files changed, 14 insertions(+), 10 deletions(-)
diff -puN include/linux/mmzone.h~mm-page_alloc-fair-zone-allocator-policy-v2-fix include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-page_alloc-fair-zone-allocator-policy-v2-fix
+++ a/include/linux/mmzone.h
@@ -105,6 +105,7 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
+ NR_ALLOC_BATCH,
NR_LRU_BASE,
NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
NR_ACTIVE_ANON, /* " " " " " */
@@ -352,7 +353,6 @@ struct zone {
* free areas of different sizes
*/
spinlock_t lock;
- int alloc_batch;
int all_unreclaimable; /* All pages pinned */
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
diff -puN mm/page_alloc.c~mm-page_alloc-fair-zone-allocator-policy-v2-fix mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-fair-zone-allocator-policy-v2-fix
+++ a/mm/page_alloc.c
@@ -1551,6 +1551,7 @@ again:
get_pageblock_migratetype(page));
}
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
@@ -1924,7 +1925,7 @@ zonelist_scan:
* fairness round-robin cycle of this zonelist.
*/
if (alloc_flags & ALLOC_WMARK_LOW) {
- if (zone->alloc_batch <= 0)
+ if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
continue;
if (zone_reclaim_mode &&
!zone_local(preferred_zone, zone))
@@ -2036,8 +2037,7 @@ this_zone_full:
goto zonelist_scan;
}
- if (page) {
- zone->alloc_batch -= 1U << order;
+ if (page)
/*
* page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
* necessary to allocate the page. The expectation is
@@ -2046,7 +2046,6 @@ this_zone_full:
* for !PFMEMALLOC purposes.
*/
page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
- }
return page;
}
@@ -2397,8 +2396,10 @@ static void prepare_slowpath(gfp_t gfp_m
*/
if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
continue;
- zone->alloc_batch = high_wmark_pages(zone) -
- low_wmark_pages(zone);
+ mod_zone_page_state(zone, NR_ALLOC_BATCH,
+ high_wmark_pages(zone) -
+ low_wmark_pages(zone) -
+ zone_page_state(zone, NR_ALLOC_BATCH));
}
}
@@ -4798,7 +4799,7 @@ static void __paginginit free_area_init_
zone->zone_pgdat = pgdat;
/* For bootup, initialized properly in watermark setup */
- zone->alloc_batch = zone->managed_pages;
+ mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
zone_pcp_init(zone);
lruvec_init(&zone->lruvec);
@@ -5571,8 +5572,10 @@ static void __setup_per_zone_wmarks(void
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
- zone->alloc_batch = high_wmark_pages(zone) -
- low_wmark_pages(zone);
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH,
+ high_wmark_pages(zone) -
+ low_wmark_pages(zone) -
+ zone_page_state(zone, NR_ALLOC_BATCH));
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
diff -puN mm/vmstat.c~mm-page_alloc-fair-zone-allocator-policy-v2-fix mm/vmstat.c
--- a/mm/vmstat.c~mm-page_alloc-fair-zone-allocator-policy-v2-fix
+++ a/mm/vmstat.c
@@ -703,6 +703,7 @@ static void walk_zones_in_node(struct se
const char * const vmstat_text[] = {
/* Zoned VM counters */
"nr_free_pages",
+ "nr_alloc_batch",
"nr_inactive_anon",
"nr_active_anon",
"nr_inactive_file",
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
linux-next.patch
memcg-dont-initialize-kmem-cache-destroying-work-for-root-caches.patch
mm-kill-one-if-loop-in-__free_pages_bootmem.patch
mm-vmscan-fix-numa-reclaim-balance-problem-in-kswapd.patch
mm-page_alloc-rearrange-watermark-checking-in-get_page_from_freelist.patch
mm-page_alloc-fair-zone-allocator-policy.patch
mm-page_alloc-fair-zone-allocator-policy-v2.patch
mm-page_alloc-fair-zone-allocator-policy-v2-fix.patch
mm-revert-page-writebackc-subtract-min_free_kbytes-from-dirtyable-memory.patch
memcg-remove-redundant-code-in-mem_cgroup_force_empty_write.patch
memcg-vmscan-integrate-soft-reclaim-tighter-with-zone-shrinking-code.patch
memcg-get-rid-of-soft-limit-tree-infrastructure.patch
vmscan-memcg-do-softlimit-reclaim-also-for-targeted-reclaim.patch
memcg-enhance-memcg-iterator-to-support-predicates.patch
memcg-track-children-in-soft-limit-excess-to-improve-soft-limit.patch
memcg-vmscan-do-not-attempt-soft-limit-reclaim-if-it-would-not-scan-anything.patch
memcg-track-all-children-over-limit-in-the-root.patch
memcg-vmscan-do-not-fall-into-reclaim-all-pass-too-quickly.patch
arch-mm-remove-obsolete-init-oom-protection.patch
arch-mm-do-not-invoke-oom-killer-on-kernel-fault-oom.patch
arch-mm-pass-userspace-fault-flag-to-generic-fault-handler.patch
x86-finish-user-fault-error-path-with-fatal-signal.patch
mm-memcg-enable-memcg-oom-killer-only-for-user-faults.patch
mm-memcg-rework-and-document-oom-waiting-and-wakeup.patch
mm-memcg-do-not-trap-chargers-with-full-callstack-on-oom.patch
mm-page_alloc-add-unlikely-macro-to-help-compiler-optimization.patch
mm-move-pgtable-related-functions-to-right-place.patch
swap-clean-up-ifdef-in-page_mapping.patch
mm-vmalloc-remove-useless-variable-in-vmap_block.patch
mm-vmalloc-use-well-defined-find_last_bit-func.patch
swap-add-a-simple-detector-for-inappropriate-swapin-readahead-fix.patch
debugging-keep-track-of-page-owners-fix-2-fix-fix-fix.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
