The patch titled
Subject: mm, page_alloc: avoid looking up the first zone in a zonelist twice
has been added to the -mm tree. Its filename is
mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice.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: avoid looking up the first zone in a zonelist twice
The allocator fast path looks up the first usable zone in a zonelist and
then get_page_from_freelist does the same job in the zonelist iterator.
This patch preserves the necessary information.
4.6.0-rc2 4.6.0-rc2
fastmark-v1r20 initonce-v1r20
Min alloc-odr0-1 364.00 ( 0.00%) 359.00 ( 1.37%)
Min alloc-odr0-2 262.00 ( 0.00%) 260.00 ( 0.76%)
Min alloc-odr0-4 214.00 ( 0.00%) 214.00 ( 0.00%)
Min alloc-odr0-8 186.00 ( 0.00%) 186.00 ( 0.00%)
Min alloc-odr0-16 173.00 ( 0.00%) 173.00 ( 0.00%)
Min alloc-odr0-32 165.00 ( 0.00%) 165.00 ( 0.00%)
Min alloc-odr0-64 161.00 ( 0.00%) 162.00 ( -0.62%)
Min alloc-odr0-128 159.00 ( 0.00%) 161.00 ( -1.26%)
Min alloc-odr0-256 168.00 ( 0.00%) 170.00 ( -1.19%)
Min alloc-odr0-512 180.00 ( 0.00%) 181.00 ( -0.56%)
Min alloc-odr0-1024 190.00 ( 0.00%) 190.00 ( 0.00%)
Min alloc-odr0-2048 196.00 ( 0.00%) 196.00 ( 0.00%)
Min alloc-odr0-4096 202.00 ( 0.00%) 202.00 ( 0.00%)
Min alloc-odr0-8192 206.00 ( 0.00%) 205.00 ( 0.49%)
Min alloc-odr0-16384 206.00 ( 0.00%) 205.00 ( 0.49%)
The benefit is negligible and the results are within the noise but each
cycle counts.
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/buffer.c | 10 +++++-----
include/linux/mmzone.h | 18 +++++++++++-------
mm/internal.h | 2 +-
mm/mempolicy.c | 19 ++++++++++---------
mm/page_alloc.c | 32 +++++++++++++++-----------------
5 files changed, 42 insertions(+), 39 deletions(-)
diff -puN fs/buffer.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice fs/buffer.c
--- a/fs/buffer.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice
+++ a/fs/buffer.c
@@ -255,17 +255,17 @@ out:
*/
static void free_more_memory(void)
{
- struct zone *zone;
+ struct zoneref *z;
int nid;
wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM);
yield();
for_each_online_node(nid) {
- (void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
- gfp_zone(GFP_NOFS), NULL,
- &zone);
- if (zone)
+
+ z = first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
+ gfp_zone(GFP_NOFS), NULL);
+ if (z->zone)
try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
GFP_NOFS, NULL);
}
diff -puN include/linux/mmzone.h~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice
+++ a/include/linux/mmzone.h
@@ -962,13 +962,10 @@ static __always_inline struct zoneref *n
*/
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
enum zone_type highest_zoneidx,
- nodemask_t *nodes,
- struct zone **zone)
+ nodemask_t *nodes)
{
- struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs,
+ return next_zones_zonelist(zonelist->_zonerefs,
highest_zoneidx, nodes);
- *zone = zonelist_zone(z);
- return z;
}
/**
@@ -983,10 +980,17 @@ static inline struct zoneref *first_zone
* within a given nodemask
*/
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
- for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \
+ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \
zone; \
z = next_zones_zonelist(++z, highidx, nodemask), \
- zone = zonelist_zone(z)) \
+ zone = zonelist_zone(z))
+
+#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+ for (zone = z->zone; \
+ zone; \
+ z = next_zones_zonelist(++z, highidx, nodemask), \
+ zone = zonelist_zone(z))
+
/**
* for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
diff -puN mm/internal.h~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice mm/internal.h
--- a/mm/internal.h~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice
+++ a/mm/internal.h
@@ -102,7 +102,7 @@ extern pmd_t *mm_find_pmd(struct mm_stru
struct alloc_context {
struct zonelist *zonelist;
nodemask_t *nodemask;
- struct zone *preferred_zone;
+ struct zoneref *preferred_zoneref;
int classzone_idx;
int migratetype;
enum zone_type high_zoneidx;
diff -puN mm/mempolicy.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice mm/mempolicy.c
--- a/mm/mempolicy.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice
+++ a/mm/mempolicy.c
@@ -1739,18 +1739,18 @@ unsigned int mempolicy_slab_node(void)
return interleave_nodes(policy);
case MPOL_BIND: {
+ struct zoneref *z;
+
/*
* Follow bind policy behavior and start allocation at the
* first node.
*/
struct zonelist *zonelist;
- struct zone *zone;
enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
zonelist = &NODE_DATA(node)->node_zonelists[0];
- (void)first_zones_zonelist(zonelist, highest_zoneidx,
- &policy->v.nodes,
- &zone);
- return zone ? zone->node : node;
+ z = first_zones_zonelist(zonelist, highest_zoneidx,
+ &policy->v.nodes);
+ return z->zone ? z->zone->node : node;
}
default:
@@ -2266,7 +2266,7 @@ static void sp_free(struct sp_node *n)
int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
{
struct mempolicy *pol;
- struct zone *zone;
+ struct zoneref *z;
int curnid = page_to_nid(page);
unsigned long pgoff;
int thiscpu = raw_smp_processor_id();
@@ -2298,6 +2298,7 @@ int mpol_misplaced(struct page *page, st
break;
case MPOL_BIND:
+
/*
* allows binding to multiple nodes.
* use current page if in policy nodemask,
@@ -2306,11 +2307,11 @@ int mpol_misplaced(struct page *page, st
*/
if (node_isset(curnid, pol->v.nodes))
goto out;
- (void)first_zones_zonelist(
+ z = first_zones_zonelist(
node_zonelist(numa_node_id(), GFP_HIGHUSER),
gfp_zone(GFP_HIGHUSER),
- &pol->v.nodes, &zone);
- polnid = zone->node;
+ &pol->v.nodes);
+ polnid = z->zone->node;
break;
default:
diff -puN mm/page_alloc.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice
+++ a/mm/page_alloc.c
@@ -2730,7 +2730,7 @@ static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
{
- struct zoneref *z;
+ struct zoneref *z = ac->preferred_zoneref;
struct zone *zone;
bool fair_skipped = false;
bool apply_fair = (alloc_flags & ALLOC_FAIR);
@@ -2740,7 +2740,7 @@ zonelist_scan:
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
*/
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
+ for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
ac->nodemask) {
struct page *page;
unsigned long mark;
@@ -2760,7 +2760,7 @@ zonelist_scan:
fair_skipped = true;
continue;
}
- if (!zone_local(ac->preferred_zone, zone)) {
+ if (!zone_local(ac->preferred_zoneref->zone, zone)) {
if (fair_skipped)
goto reset_fair;
apply_fair = false;
@@ -2806,7 +2806,7 @@ zonelist_scan:
goto try_this_zone;
if (zone_reclaim_mode == 0 ||
- !zone_allows_reclaim(ac->preferred_zone, zone))
+ !zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
continue;
ret = zone_reclaim(zone, gfp_mask, order);
@@ -2828,7 +2828,7 @@ zonelist_scan:
}
try_this_zone:
- page = buffered_rmqueue(ac->preferred_zone, zone, order,
+ page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order,
gfp_mask, alloc_flags, ac->migratetype);
if (page) {
if (prep_new_page(page, order, gfp_mask, alloc_flags))
@@ -2857,7 +2857,7 @@ try_this_zone:
reset_fair:
apply_fair = false;
fair_skipped = false;
- reset_alloc_batches(ac->preferred_zone);
+ reset_alloc_batches(ac->preferred_zoneref->zone);
goto zonelist_scan;
}
@@ -3140,7 +3140,7 @@ static void wake_all_kswapds(unsigned in
for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
ac->high_zoneidx, ac->nodemask)
- wakeup_kswapd(zone, order, zone_idx(ac->preferred_zone));
+ wakeup_kswapd(zone, order, zonelist_zone_idx(ac->preferred_zoneref));
}
static inline unsigned int
@@ -3360,7 +3360,7 @@ retry:
if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) ||
((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) {
/* Wait for some write requests to complete then retry */
- wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50);
+ wait_iff_congested(ac->preferred_zoneref->zone, BLK_RW_ASYNC, HZ/50);
goto retry;
}
@@ -3398,7 +3398,6 @@ struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, nodemask_t *nodemask)
{
- struct zoneref *preferred_zoneref;
struct page *page = NULL;
unsigned int cpuset_mems_cookie;
unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
@@ -3434,9 +3433,9 @@ retry_cpuset:
ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
/* The preferred zone is used for statistics later */
- preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
- ac.nodemask, &ac.preferred_zone);
- ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);
+ ac.preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
+ ac.nodemask);
+ ac.classzone_idx = zonelist_zone_idx(ac.preferred_zoneref);
/* First allocation attempt */
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
@@ -4497,13 +4496,12 @@ static void build_zonelists(pg_data_t *p
*/
int local_memory_node(int node)
{
- struct zone *zone;
+ struct zoneref *z;
- (void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
+ z = first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
gfp_zone(GFP_KERNEL),
- NULL,
- &zone);
- return zone->node;
+ NULL);
+ return z->zone->node;
}
#endif
_
Patches currently in -mm which might be from mgorman@xxxxxxxxxxxxxxxxxxx are
mm-page_alloc-only-check-pagecompound-for-high-order-pages.patch
mm-page_alloc-use-new-pageanonhead-helper-in-the-free-page-fast-path.patch
mm-page_alloc-reduce-branches-in-zone_statistics.patch
mm-page_alloc-inline-zone_statistics.patch
mm-page_alloc-inline-the-fast-path-of-the-zonelist-iterator.patch
mm-page_alloc-use-__dec_zone_state-for-order-0-page-allocation.patch
mm-page_alloc-avoid-unnecessary-zone-lookups-during-pageblock-operations.patch
mm-page_alloc-convert-alloc_flags-to-unsigned.patch
mm-page_alloc-convert-nr_fair_skipped-to-bool.patch
mm-page_alloc-remove-unnecessary-local-variable-in-get_page_from_freelist.patch
mm-page_alloc-remove-unnecessary-initialisation-in-get_page_from_freelist.patch
mm-page_alloc-remove-redundant-check-for-empty-zonelist.patch
mm-page_alloc-simplify-last-cpupid-reset.patch
mm-page_alloc-move-might_sleep_if-check-to-the-allocator-slowpath.patch
mm-page_alloc-move-__gfp_hardwall-modifications-out-of-the-fastpath.patch
mm-page_alloc-check-once-if-a-zone-has-isolated-pageblocks.patch
mm-page_alloc-shorten-the-page-allocator-fast-path.patch
mm-page_alloc-reduce-cost-of-fair-zone-allocation-policy-retry.patch
mm-page_alloc-shortcut-watermark-checks-for-order-0-pages.patch
mm-page_alloc-avoid-looking-up-the-first-zone-in-a-zonelist-twice.patch
mm-page_alloc-remove-field-from-alloc_context.patch
mm-page_alloc-check-multiple-page-fields-with-a-single-branch.patch
mm-page_alloc-remove-unnecessary-variable-from-free_pcppages_bulk.patch
mm-page_alloc-inline-pageblock-lookup-in-page-free-fast-paths.patch
mm-page_alloc-defer-debugging-checks-of-freed-pages-until-a-pcp-drain.patch
mm-page_alloc-defer-debugging-checks-of-pages-allocated-from-the-pcp.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
