From: Mel Gorman <mgorman@techsingularity.net>
To: Andrew Morton <akpm@linux-foundation.org>, Linux-MM <linux-mm@kvack.org>
Cc: Rik van Riel <riel@surriel.com>, Vlastimil Babka <vbabka@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
Minchan Kim <minchan@kernel.org>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
LKML <linux-kernel@vger.kernel.org>,
Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 16/34] mm, page_alloc: consider dirtyable memory in terms of nodes
Date: Fri, 8 Jul 2016 10:34:52 +0100 [thread overview]
Message-ID: <1467970510-21195-17-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net>
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.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
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 --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 62f477d6cfe8..fae2fe3c6942 100644
--- a/include/linux/mmzone.h
+++ b/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 --git a/include/linux/writeback.h b/include/linux/writeback.h
index 717e6149e753..fc1e16c25a29 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data);
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 --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0ada2b2954b0..f7c0fb993fb9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
*/
/**
- * 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_memory(unsigned long total)
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 *pbackground, unsigned long *pdirty)
}
/**
- * 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(struct zone *zone)
}
/**
- * 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 --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8215c51d5b23..9e113a6ff9a0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2955,31 +2955,24 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
/*
* 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];
@@ -6749,6 +6742,9 @@ static void calculate_totalreserve_pages(void)
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;
@@ -6765,7 +6761,7 @@ static void calculate_totalreserve_pages(void)
if (max > zone->managed_pages)
max = zone->managed_pages;
- zone->totalreserve_pages = max;
+ pgdat->totalreserve_pages += max;
reserve_pages += max;
}
--
2.6.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2016-07-08 9:38 UTC|newest]
Thread overview: 109+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-07-08 9:34 [PATCH 00/34] Move LRU page reclaim from zones to nodes v9 Mel Gorman
2016-07-08 9:34 ` [PATCH 01/34] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman
2016-08-03 19:13 ` Reza Arbab
2016-07-08 9:34 ` [PATCH 02/34] mm, vmscan: move lru_lock to the node Mel Gorman
2016-07-12 11:06 ` Balbir Singh
2016-07-12 11:18 ` Mel Gorman
2016-07-13 5:50 ` Balbir Singh
2016-07-13 8:39 ` Vlastimil Babka
2016-07-08 9:34 ` [PATCH 03/34] mm, vmscan: move LRU lists to node Mel Gorman
2016-08-04 20:59 ` James Hogan
2016-08-05 8:41 ` Mel Gorman
2016-08-05 10:52 ` James Hogan
2016-08-05 11:55 ` Mel Gorman
2016-08-05 12:02 ` James Hogan
2016-07-08 9:34 ` [PATCH 04/34] mm, mmzone: clarify the usage of zone padding Mel Gorman
2016-07-12 13:49 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 05/34] mm, vmscan: begin reclaiming pages on a per-node basis Mel Gorman
2016-07-12 13:54 ` Johannes Weiner
2016-07-14 9:19 ` Vlastimil Babka
2016-07-08 9:34 ` [PATCH 06/34] mm, vmscan: have kswapd only scan based on the highest requested zone Mel Gorman
2016-07-12 14:05 ` Johannes Weiner
2016-07-13 8:37 ` Mel Gorman
2016-07-08 9:34 ` [PATCH 07/34] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman
2016-08-29 9:38 ` Srikar Dronamraju
2016-08-30 12:07 ` Mel Gorman
2016-08-30 14:25 ` Srikar Dronamraju
2016-08-30 15:00 ` Mel Gorman
2016-08-31 6:09 ` Srikar Dronamraju
2016-08-31 8:49 ` Mel Gorman
2016-08-31 11:09 ` Michal Hocko
2016-08-31 12:46 ` Mel Gorman
2016-08-31 17:33 ` Srikar Dronamraju
2016-07-08 9:34 ` [PATCH 08/34] mm, vmscan: remove balance gap Mel Gorman
2016-07-12 14:06 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 09/34] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman
2016-07-08 9:34 ` [PATCH 10/34] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman
2016-07-08 9:34 ` [PATCH 11/34] mm, vmscan: remove duplicate logic clearing node congestion and dirty state Mel Gorman
2016-07-12 14:22 ` Johannes Weiner
2016-07-13 8:40 ` Mel Gorman
2016-07-14 9:45 ` Vlastimil Babka
2016-07-08 9:34 ` [PATCH 12/34] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman
2016-07-12 14:29 ` Johannes Weiner
2016-07-13 8:47 ` Mel Gorman
2016-07-13 12:28 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 13/34] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman
2016-07-12 14:32 ` Johannes Weiner
2016-07-13 8:48 ` Mel Gorman
2016-07-08 9:34 ` [PATCH 14/34] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman
2016-07-12 14:38 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 15/34] mm, workingset: make working set detection node-aware Mel Gorman
2016-07-08 9:34 ` Mel Gorman [this message]
2016-07-08 9:34 ` [PATCH 17/34] mm: move page mapped accounting to the node Mel Gorman
2016-07-12 14:42 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 18/34] mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Mel Gorman
2016-07-12 14:58 ` Johannes Weiner
2016-07-13 8:55 ` Mel Gorman
2016-07-13 13:04 ` Johannes Weiner
2016-07-13 13:37 ` Mel Gorman
2016-07-13 21:13 ` Andrew Morton
2016-07-15 10:46 ` Mel Gorman
2016-07-15 22:35 ` Andrew Morton
2016-07-18 13:34 ` Johannes Weiner
2016-07-14 1:27 ` Minchan Kim
2016-07-08 9:34 ` [PATCH 19/34] mm: move most file-based accounting to the node Mel Gorman
2016-07-12 15:11 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 20/34] mm: move vmscan writes and file write " Mel Gorman
2016-07-12 15:15 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 21/34] mm, vmscan: only wakeup kswapd once per node for the requested classzone Mel Gorman
2016-07-12 17:18 ` Johannes Weiner
2016-07-08 9:34 ` [PATCH 22/34] mm, page_alloc: wake kswapd based on the highest eligible zone Mel Gorman
2016-07-12 17:24 ` Johannes Weiner
2016-07-14 10:05 ` Vlastimil Babka
2016-07-08 9:34 ` [PATCH 23/34] mm: convert zone_reclaim to node_reclaim Mel Gorman
2016-07-12 17:28 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 24/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman
2016-07-12 17:31 ` Johannes Weiner
2016-07-14 10:09 ` Vlastimil Babka
2016-07-08 9:35 ` [PATCH 25/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman
2016-07-12 18:01 ` Johannes Weiner
2016-07-14 12:12 ` Vlastimil Babka
2016-07-08 9:35 ` [PATCH 26/34] mm, vmscan: avoid passing in remaining unnecessarily to prepare_kswapd_sleep Mel Gorman
2016-07-12 18:06 ` Johannes Weiner
2016-07-14 12:48 ` Vlastimil Babka
2016-07-08 9:35 ` [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if reclaiming and buffer_heads_over_limit Mel Gorman
2016-07-12 18:10 ` Johannes Weiner
2016-07-14 12:54 ` Vlastimil Babka
2016-07-08 9:35 ` [PATCH 28/34] mm, vmscan: add classzone information to tracepoints Mel Gorman
2016-07-12 18:13 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 29/34] mm, page_alloc: remove fair zone allocation policy Mel Gorman
2016-07-12 18:18 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 30/34] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman
2016-07-12 18:43 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 31/34] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman
2016-07-12 19:10 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 32/34] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman
2016-07-12 19:06 ` Johannes Weiner
2016-07-08 9:35 ` [PATCH 33/34] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman
2016-07-12 19:18 ` Johannes Weiner
2016-07-14 12:56 ` Vlastimil Babka
2016-07-08 9:35 ` [PATCH 34/34] mm, vmstat: remove zone and node double accounting by approximating retries Mel Gorman
2016-07-14 13:40 ` Vlastimil Babka
2016-07-15 7:48 ` Mel Gorman
2016-07-15 12:20 ` Vlastimil Babka
2016-08-19 13:12 ` [PATCH 00/34] Move LRU page reclaim from zones to nodes v9 Andrea Arcangeli
2016-08-19 13:23 ` Vlastimil Babka
2016-08-19 13:55 ` Andrea Arcangeli
2016-08-19 14:53 ` Mel Gorman
2016-08-19 15:32 ` Andrea Arcangeli
2016-08-19 15:55 ` Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1467970510-21195-17-git-send-email-mgorman@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan@kernel.org \
--cc=riel@surriel.com \
--cc=vbabka@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).