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 29/34] mm, page_alloc: remove fair zone allocation policy
Date: Fri, 8 Jul 2016 10:35:05 +0100 [thread overview]
Message-ID: <1467970510-21195-30-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net>
The fair zone allocation policy interleaves allocation requests between
zones to avoid an age inversion problem whereby new pages are reclaimed to
balance a zone. Reclaim is now node-based so this should no longer be an
issue and the fair zone allocation policy is not free. This patch removes
it.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
include/linux/mmzone.h | 5 ----
mm/internal.h | 1 -
mm/page_alloc.c | 75 +-------------------------------------------------
mm/vmstat.c | 4 +--
4 files changed, 2 insertions(+), 83 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e19c081c794e..bd33e6f1bed0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -110,7 +110,6 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_ALLOC_BATCH,
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_LRU_FILE,
@@ -516,10 +515,6 @@ struct zone {
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
-enum zone_flags {
- ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */
-};
-
enum pgdat_flags {
PGDAT_CONGESTED, /* pgdat has many dirty pages backed by
* a congested BDI
diff --git a/mm/internal.h b/mm/internal.h
index 1e21b2d3838d..28932cd6a195 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -467,7 +467,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
-#define ALLOC_FAIR 0x100 /* fair zone allocation */
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index de825b07e233..565f08832853 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2630,7 +2630,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
else
page = list_first_entry(list, struct page, lru);
- __dec_zone_state(zone, NR_ALLOC_BATCH);
list_del(&page->lru);
pcp->count--;
@@ -2656,15 +2655,10 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
spin_unlock(&zone->lock);
if (!page)
goto failed;
- __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
__mod_zone_freepage_state(zone, -(1 << order),
get_pcppage_migratetype(page));
}
- if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
- !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
- set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
@@ -2875,40 +2869,18 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
}
#ifdef CONFIG_NUMA
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
- return local_zone->node == zone->node;
-}
-
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
-static bool zone_local(struct zone *local_zone, struct zone *zone)
-{
- return true;
-}
-
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
}
#endif /* CONFIG_NUMA */
-static void reset_alloc_batches(struct zone *preferred_zone)
-{
- struct zone *zone = preferred_zone->zone_pgdat->node_zones;
-
- do {
- mod_zone_page_state(zone, NR_ALLOC_BATCH,
- high_wmark_pages(zone) - low_wmark_pages(zone) -
- atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
- clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
- } while (zone++ != preferred_zone);
-}
-
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
@@ -2919,10 +2891,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
{
struct zoneref *z = ac->preferred_zoneref;
struct zone *zone;
- bool fair_skipped = false;
- bool apply_fair = (alloc_flags & ALLOC_FAIR);
-
-zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
@@ -2937,23 +2905,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
!__cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
- * Distribute pages in proportion to the individual
- * zone size to ensure fair page aging. The zone a
- * page was allocated in should have no effect on the
- * time the page has in memory before being reclaimed.
- */
- if (apply_fair) {
- if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
- fair_skipped = true;
- continue;
- }
- if (!zone_local(ac->preferred_zoneref->zone, zone)) {
- if (fair_skipped)
- goto reset_fair;
- apply_fair = false;
- }
- }
- /*
* When allocating a page cache page for writing, we
* want to get it from a node that is within its dirty
* limit, such that no single node holds more than its
@@ -3024,23 +2975,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
}
}
- /*
- * The first pass makes sure allocations are spread fairly within the
- * local node. However, the local node might have free pages left
- * after the fairness batches are exhausted, and remote zones haven't
- * even been considered yet. Try once more without fairness, and
- * include remote zones now, before entering the slowpath and waking
- * kswapd: prefer spilling to a remote zone over swapping locally.
- */
- if (fair_skipped) {
-reset_fair:
- apply_fair = false;
- fair_skipped = false;
- reset_alloc_batches(ac->preferred_zoneref->zone);
- z = ac->preferred_zoneref;
- goto zonelist_scan;
- }
-
return NULL;
}
@@ -3789,7 +3723,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
{
struct page *page;
unsigned int cpuset_mems_cookie;
- unsigned int alloc_flags = ALLOC_WMARK_LOW|ALLOC_FAIR;
+ unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
.high_zoneidx = gfp_zone(gfp_mask),
@@ -6001,9 +5935,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone_seqlock_init(zone);
zone_pcp_init(zone);
- /* For bootup, initialized properly in watermark setup */
- mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
-
if (!size)
continue;
@@ -6856,10 +6787,6 @@ static void __setup_per_zone_wmarks(void)
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
- __mod_zone_page_state(zone, NR_ALLOC_BATCH,
- high_wmark_pages(zone) - low_wmark_pages(zone) -
- atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-
spin_unlock_irqrestore(&zone->lock, flags);
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index bc94968400d0..ab7f78995c89 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -921,7 +921,6 @@ int fragmentation_index(struct zone *zone, unsigned int order)
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
- "nr_alloc_batch",
"nr_zone_anon_lru",
"nr_zone_file_lru",
"nr_zone_write_pending",
@@ -1632,10 +1631,9 @@ int vmstat_refresh(struct ctl_table *table, int write,
val = atomic_long_read(&vm_zone_stat[i]);
if (val < 0) {
switch (i) {
- case NR_ALLOC_BATCH:
case NR_PAGES_SCANNED:
/*
- * These are often seen to go negative in
+ * This is often seen to go negative in
* recent kernels, but not to go permanently
* negative. Whilst it would be nicer not to
* have exceptions, rooting them out would be
--
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 9:40 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 ` [PATCH 16/34] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman
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 ` Mel Gorman [this message]
2016-07-12 18:18 ` [PATCH 29/34] mm, page_alloc: remove fair zone allocation policy 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=1467970510-21195-30-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).