The patch titled
Subject: mm, page_alloc: consider dirtyable memory in terms of nodes
has been added to the -mm tree. Its filename is
mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes.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: consider dirtyable memory in terms of nodes
Historically dirty pages were spread among zones but now that LRUs are
per-node it is more appropriate to consider dirty pages in a node.
Link: http://lkml.kernel.org/r/1467970510-21195-17-git-send-email-mgorman@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mmzone.h | 12 ++--
include/linux/writeback.h | 2
mm/page-writeback.c | 91 ++++++++++++++++++++++++------------
mm/page_alloc.c | 26 ++++------
4 files changed, 79 insertions(+), 52 deletions(-)
diff -puN include/linux/mmzone.h~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes include/linux/mmzone.h
--- a/include/linux/mmzone.h~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes
+++ a/include/linux/mmzone.h
@@ -363,12 +363,6 @@ struct zone {
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
- /*
- * This is a per-zone reserve of pages that are not available
- * to userspace allocations.
- */
- unsigned long totalreserve_pages;
-
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -687,6 +681,12 @@ typedef struct pglist_data {
/* Number of pages migrated during the rate limiting time interval */
unsigned long numabalancing_migrate_nr_pages;
#endif
+ /*
+ * This is a per-node reserve of pages that are not available
+ * to userspace allocations.
+ */
+ unsigned long totalreserve_pages;
+
/* Write-intensive fields used by page reclaim */
ZONE_PADDING(_pad1_)
spinlock_t lru_lock;
diff -puN include/linux/writeback.h~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes include/linux/writeback.h
--- a/include/linux/writeback.h~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes
+++ a/include/linux/writeback.h
@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long
static inline void laptop_sync_completion(void) { }
#endif
void throttle_vm_writeout(gfp_t gfp_mask);
-bool zone_dirty_ok(struct zone *zone);
+bool node_dirty_ok(struct pglist_data *pgdat);
int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
#ifdef CONFIG_CGROUP_WRITEBACK
void wb_domain_exit(struct wb_domain *dom);
diff -puN mm/page-writeback.c~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes mm/page-writeback.c
--- a/mm/page-writeback.c~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes
+++ a/mm/page-writeback.c
@@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_
*/
/**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
+ * node_dirtyable_memory - number of dirtyable pages in a node
+ * @pgdat: the node
*
- * Returns the zone's number of pages potentially available for dirty
- * page cache. This is the base value for the per-zone dirty limits.
+ * Returns the node's number of pages potentially available for dirty
+ * page cache. This is the base value for the per-node dirty limits.
*/
-static unsigned long zone_dirtyable_memory(struct zone *zone)
+static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
{
- unsigned long nr_pages;
+ unsigned long nr_pages = 0;
+ int z;
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ nr_pages += zone_page_state(zone, NR_FREE_PAGES);
+ }
- nr_pages = zone_page_state(zone, NR_FREE_PAGES);
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
* clean pages in order to balance the zones.
*/
- nr_pages -= min(nr_pages, zone->totalreserve_pages);
+ nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
- nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE);
- nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE);
+ nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
+ nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
return nr_pages;
}
@@ -299,13 +308,24 @@ static unsigned long highmem_dirtyable_m
int i;
for_each_node_state(node, N_HIGH_MEMORY) {
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zone *z = &NODE_DATA(node)->node_zones[i];
+ for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) {
+ struct zone *z;
+ unsigned long dirtyable;
+
+ if (!is_highmem_idx(i))
+ continue;
+
+ z = &NODE_DATA(node)->node_zones[i];
+ dirtyable = zone_page_state(z, NR_FREE_PAGES) +
+ zone_page_state(z, NR_ZONE_LRU_FILE);
- if (is_highmem(z))
- x += zone_dirtyable_memory(z);
+ /* watch for underflows */
+ dirtyable -= min(dirtyable, high_wmark_pages(z));
+
+ x += dirtyable;
}
}
+
/*
* Unreclaimable memory (kernel memory or anonymous memory
* without swap) can bring down the dirtyable pages below
@@ -445,23 +465,23 @@ void global_dirty_limits(unsigned long *
}
/**
- * zone_dirty_limit - maximum number of dirty pages allowed in a zone
- * @zone: the zone
+ * node_dirty_limit - maximum number of dirty pages allowed in a node
+ * @pgdat: the node
*
- * Returns the maximum number of dirty pages allowed in a zone, based
- * on the zone's dirtyable memory.
+ * Returns the maximum number of dirty pages allowed in a node, based
+ * on the node's dirtyable memory.
*/
-static unsigned long zone_dirty_limit(struct zone *zone)
+static unsigned long node_dirty_limit(struct pglist_data *pgdat)
{
- unsigned long zone_memory = zone_dirtyable_memory(zone);
+ unsigned long node_memory = node_dirtyable_memory(pgdat);
struct task_struct *tsk = current;
unsigned long dirty;
if (vm_dirty_bytes)
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
- zone_memory / global_dirtyable_memory();
+ node_memory / global_dirtyable_memory();
else
- dirty = vm_dirty_ratio * zone_memory / 100;
+ dirty = vm_dirty_ratio * node_memory / 100;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
dirty += dirty / 4;
@@ -470,19 +490,30 @@ static unsigned long zone_dirty_limit(st
}
/**
- * zone_dirty_ok - tells whether a zone is within its dirty limits
- * @zone: the zone to check
+ * node_dirty_ok - tells whether a node is within its dirty limits
+ * @pgdat: the node to check
*
- * Returns %true when the dirty pages in @zone are within the zone's
+ * Returns %true when the dirty pages in @pgdat are within the node's
* dirty limit, %false if the limit is exceeded.
*/
-bool zone_dirty_ok(struct zone *zone)
+bool node_dirty_ok(struct pglist_data *pgdat)
{
- unsigned long limit = zone_dirty_limit(zone);
+ int z;
+ unsigned long limit = node_dirty_limit(pgdat);
+ unsigned long nr_pages = 0;
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ nr_pages += zone_page_state(zone, NR_FILE_DIRTY);
+ nr_pages += zone_page_state(zone, NR_UNSTABLE_NFS);
+ nr_pages += zone_page_state(zone, NR_WRITEBACK);
+ }
- return zone_page_state(zone, NR_FILE_DIRTY) +
- zone_page_state(zone, NR_UNSTABLE_NFS) +
- zone_page_state(zone, NR_WRITEBACK) <= limit;
+ return nr_pages <= limit;
}
int dirty_background_ratio_handler(struct ctl_table *table, int write,
diff -puN mm/page_alloc.c~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes mm/page_alloc.c
--- a/mm/page_alloc.c~mm-page_alloc-consider-dirtyable-memory-in-terms-of-nodes
+++ a/mm/page_alloc.c
@@ -2912,31 +2912,24 @@ zonelist_scan:
}
/*
* When allocating a page cache page for writing, we
- * want to get it from a zone that is within its dirty
- * limit, such that no single zone holds more than its
+ * want to get it from a node that is within its dirty
+ * limit, such that no single node holds more than its
* proportional share of globally allowed dirty pages.
- * The dirty limits take into account the zone's
+ * The dirty limits take into account the node's
* lowmem reserves and high watermark so that kswapd
* should be able to balance it without having to
* write pages from its LRU list.
*
- * This may look like it could increase pressure on
- * lower zones by failing allocations in higher zones
- * before they are full. But the pages that do spill
- * over are limited as the lower zones are protected
- * by this very same mechanism. It should not become
- * a practical burden to them.
- *
* XXX: For now, allow allocations to potentially
- * exceed the per-zone dirty limit in the slowpath
+ * exceed the per-node dirty limit in the slowpath
* (spread_dirty_pages unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
- * zones are together not big enough to reach the
+ * nodes are together not big enough to reach the
* global limit. The proper fix for these situations
- * will require awareness of zones in the
+ * will require awareness of nodes in the
* dirty-throttling and the flusher threads.
*/
- if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
+ if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat))
continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
@@ -6701,6 +6694,9 @@ static void calculate_totalreserve_pages
enum zone_type i, j;
for_each_online_pgdat(pgdat) {
+
+ pgdat->totalreserve_pages = 0;
+
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
long max = 0;
@@ -6717,7 +6713,7 @@ static void calculate_totalreserve_pages
if (max > zone->managed_pages)
max = zone->managed_pages;
- zone->totalreserve_pages = max;
+ pgdat->totalreserve_pages += max;
reserve_pages += max;
}
_
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
