Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Johannes Weiner <hannes@cmpxchg.org>
To: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@suse.com>,
	Vladimir Davydov <vdavydov.dev@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Rik van Riel <riel@redhat.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH 2/6] mm: vmstat: move slab statistics from zone to node counters
Date: Tue, 30 May 2017 14:17:20 -0400
Message-ID: <20170530181724.27197-3-hannes@cmpxchg.org> (raw)
In-Reply-To: <20170530181724.27197-1-hannes@cmpxchg.org>

To re-implement slab cache vs. page cache balancing, we'll need the
slab counters at the lruvec level, which, ever since lru reclaim was
moved from the zone to the node, is the intersection of the node, not
the zone, and the memcg.

We could retain the per-zone counters for when the page allocator
dumps its memory information on failures, and have counters on both
levels - which on all but NUMA node 0 is usually redundant. But let's
keep it simple for now and just move them. If anybody complains we can
restore the per-zone counters.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 drivers/base/node.c    | 10 +++++-----
 include/linux/mmzone.h |  4 ++--
 mm/page_alloc.c        |  4 ----
 mm/slab.c              |  8 ++++----
 mm/slub.c              |  4 ++--
 mm/vmscan.c            |  2 +-
 mm/vmstat.c            |  4 ++--
 7 files changed, 16 insertions(+), 20 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 5548f9686016..e57e06e6df4c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -129,11 +129,11 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
 		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
-				sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) +
+			      node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
@@ -141,7 +141,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
 				       HPAGE_PMD_NR));
 #else
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)));
 #endif
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ebaccd4e7d8c..eacadee83964 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -125,8 +125,6 @@ enum zone_stat_item {
 	NR_ZONE_UNEVICTABLE,
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
@@ -152,6 +150,8 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_SLAB_RECLAIMABLE,
+	NR_SLAB_UNRECLAIMABLE,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_REFAULT,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f9e450c6b6e4..5f89cfaddc4b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4601,8 +4601,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" slab_reclaimable:%lukB"
-			" slab_unreclaimable:%lukB"
 			" kernel_stack:%lukB"
 			" pagetables:%lukB"
 			" bounce:%lukB"
@@ -4624,8 +4622,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone->present_pages),
 			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
-			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
-			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
 			zone_page_state(zone, NR_KERNEL_STACK_KB),
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
diff --git a/mm/slab.c b/mm/slab.c
index 2a31ee3c5814..b55853399559 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1425,10 +1425,10 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		add_zone_page_state(page_zone(page),
+		add_node_page_state(page_pgdat(page),
 			NR_SLAB_RECLAIMABLE, nr_pages);
 	else
-		add_zone_page_state(page_zone(page),
+		add_node_page_state(page_pgdat(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 
 	__SetPageSlab(page);
@@ -1459,10 +1459,10 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 	kmemcheck_free_shadow(page, order);
 
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		sub_zone_page_state(page_zone(page),
+		sub_node_page_state(page_pgdat(page),
 				NR_SLAB_RECLAIMABLE, nr_freed);
 	else
-		sub_zone_page_state(page_zone(page),
+		sub_node_page_state(page_pgdat(page),
 				NR_SLAB_UNRECLAIMABLE, nr_freed);
 
 	BUG_ON(!PageSlab(page));
diff --git a/mm/slub.c b/mm/slub.c
index 57e5156f02be..673e72698d9b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1615,7 +1615,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		return NULL;
 
-	mod_zone_page_state(page_zone(page),
+	mod_node_page_state(page_pgdat(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		1 << oo_order(oo));
@@ -1655,7 +1655,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	kmemcheck_free_shadow(page, compound_order(page));
 
-	mod_zone_page_state(page_zone(page),
+	mod_node_page_state(page_pgdat(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		-pages);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c5f9d1673392..5d187ee618c0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3815,7 +3815,7 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	 * unmapped file backed pages.
 	 */
 	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
-	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+	    node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
 		return NODE_RECLAIM_FULL;
 
 	/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 76f73670200a..a64f1c764f17 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -928,8 +928,6 @@ const char * const vmstat_text[] = {
 	"nr_zone_unevictable",
 	"nr_zone_write_pending",
 	"nr_mlock",
-	"nr_slab_reclaimable",
-	"nr_slab_unreclaimable",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
 	"nr_bounce",
@@ -952,6 +950,8 @@ const char * const vmstat_text[] = {
 	"nr_inactive_file",
 	"nr_active_file",
 	"nr_unevictable",
+	"nr_slab_reclaimable",
+	"nr_slab_unreclaimable",
 	"nr_isolated_anon",
 	"nr_isolated_file",
 	"workingset_refault",
-- 
2.12.2

--
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>

  parent reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-30 18:17 [PATCH 0/6] mm: per-lruvec slab stats Johannes Weiner
2017-05-30 18:17 ` [PATCH 1/6] mm: vmscan: delete unused pgdat_reclaimable_pages() Johannes Weiner
2017-05-30 21:50   ` Andrew Morton
2017-05-30 22:02     ` Johannes Weiner
2017-05-30 18:17 ` Johannes Weiner [this message]
2017-05-31  9:12   ` [PATCH 2/6] mm: vmstat: move slab statistics from zone to node counters Heiko Carstens
2017-05-31 11:39     ` Heiko Carstens
2017-05-31 17:11       ` Yury Norov
2017-06-01 10:07         ` Michael Ellerman
2017-06-05 18:35           ` Johannes Weiner
2017-06-05 21:38             ` Andrew Morton
2017-06-07 16:20               ` Johannes Weiner
2017-06-06  4:31             ` Michael Ellerman
2017-06-06 11:15               ` Michael Ellerman
2017-06-06 14:33                 ` Johannes Weiner
2017-05-30 18:17 ` [PATCH 3/6] mm: memcontrol: use the node-native slab memory counters Johannes Weiner
2017-06-03 17:39   ` Vladimir Davydov
2017-05-30 18:17 ` [PATCH 4/6] mm: memcontrol: use generic mod_memcg_page_state for kmem pages Johannes Weiner
2017-06-03 17:40   ` Vladimir Davydov
2017-05-30 18:17 ` [PATCH 5/6] mm: memcontrol: per-lruvec stats infrastructure Johannes Weiner
2017-05-31 17:14   ` Johannes Weiner
2017-05-31 18:18     ` Andrew Morton
2017-05-31 19:02       ` Tony Lindgren
2017-05-31 22:03         ` Stephen Rothwell
2017-06-01  1:44       ` Johannes Weiner
2017-06-03 17:50   ` Vladimir Davydov
2017-06-05 17:53     ` Johannes Weiner
2017-05-30 18:17 ` [PATCH 6/6] mm: memcontrol: account slab stats per lruvec Johannes Weiner
2017-06-03 17:54   ` Vladimir Davydov
2017-06-05 16:52   ` [6/6] " Guenter Roeck
2017-06-05 17:52     ` Johannes Weiner

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=20170530181724.27197-3-hannes@cmpxchg.org \
    --to=hannes@cmpxchg.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=josef@toxicpanda.com \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=riel@redhat.com \
    --cc=vdavydov.dev@gmail.com \
    /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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git