linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
To: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: <linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Mel Gorman <mgorman-l3A5Bk7waGM@public.gmane.org>,
	Dave Chinner <david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org>,
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	<cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>,
	Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>,
	Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
	hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
	Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
	Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>,
	Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Subject: [PATCH v9 28/35] list_lru: per-memcg walks
Date: Thu, 30 May 2013 14:36:14 +0400	[thread overview]
Message-ID: <1369910181-20026-29-git-send-email-glommer@openvz.org> (raw)
In-Reply-To: <1369910181-20026-1-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>

This patch extend the list_lru interfaces to allow for a memcg
parameter. Because most of its users won't need it, instead of
modifying the function signatures we create a new set of _memcg()
functions and write the old API ontop of that.

Signed-off-by: Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
Cc: Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Mel Gorman <mgorman-l3A5Bk7waGM@public.gmane.org>
Cc: Rik van Riel <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
Cc: Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>
c: Hugh Dickins <hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
Cc: Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
---
 include/linux/list_lru.h   | 26 ++++++++++++---
 include/linux/memcontrol.h |  2 ++
 lib/list_lru.c             | 82 ++++++++++++++++++++++++++++++++++++----------
 3 files changed, 88 insertions(+), 22 deletions(-)

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 3b8c301..dcb67dc 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -100,7 +100,15 @@ static inline int list_lru_init_memcg(struct list_lru *lru)
 int list_lru_add(struct list_lru *lru, struct list_head *item);
 int list_lru_del(struct list_lru *lru, struct list_head *item);
 
-unsigned long list_lru_count_node(struct list_lru *lru, int nid);
+unsigned long list_lru_count_node_memcg(struct list_lru *lru, int nid,
+					struct mem_cgroup *memcg);
+
+static inline unsigned long
+list_lru_count_node(struct list_lru *lru, int nid)
+{
+	return list_lru_count_node_memcg(lru, nid, NULL);
+}
+
 static inline unsigned long list_lru_count(struct list_lru *lru)
 {
 	long count = 0;
@@ -118,9 +126,19 @@ typedef enum lru_status
 typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
 
 
-unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
-				 list_lru_walk_cb isolate, void *cb_arg,
-				 unsigned long *nr_to_walk);
+unsigned long
+list_lru_walk_node_memcg(struct list_lru *lru, int nid,
+			 list_lru_walk_cb isolate, void *cb_arg,
+			 unsigned long *nr_to_walk, struct mem_cgroup *memcg);
+
+static inline unsigned long
+list_lru_walk_node(struct list_lru *lru, int nid,
+		 list_lru_walk_cb isolate, void *cb_arg,
+		 unsigned long *nr_to_walk)
+{
+	return list_lru_walk_node_memcg(lru, nid, isolate, cb_arg,
+					nr_to_walk, NULL);
+}
 
 static inline unsigned long
 list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 50f199f..3eeece8 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -593,6 +593,8 @@ static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
 
+#define memcg_limited_groups_array_size 0
+
 static inline bool memcg_kmem_enabled(void)
 {
 	return false;
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 128af5e..316c95a 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -80,6 +80,23 @@ memcg_kmem_lru_of_page(struct list_lru *lru, struct page *page)
 	return lru_node_of_index(lru, memcg_id, nid);
 }
 
+/*
+ * This helper will loop through all node-data in the LRU, either global or
+ * per-memcg.  If memcg is either not present or not used,
+ * memcg_limited_groups_array_size will be 0. _idx starts at -1, and it will
+ * still be allowed to execute once.
+ *
+ * We convention that for _idx = -1, the global node info should be used.
+ * After that, we will go through each of the memcgs, starting at 0.
+ *
+ * We don't need any kind of locking for the loop because
+ * memcg_limited_groups_array_size can only grow, gaining new fields at the
+ * end. The old ones are just copied, and any interesting manipulation happen
+ * in the node list itself, and we already lock the list.
+ */
+#define for_each_memcg_lru_index(_idx)	\
+	for ((_idx) = -1; ((_idx) < memcg_limited_groups_array_size); (_idx)++)
+
 int
 list_lru_add(
 	struct list_lru	*lru,
@@ -139,10 +156,19 @@ list_lru_del(
 EXPORT_SYMBOL_GPL(list_lru_del);
 
 unsigned long
-list_lru_count_node(struct list_lru *lru, int nid)
+list_lru_count_node_memcg(struct list_lru *lru, int nid,
+			  struct mem_cgroup *memcg)
 {
 	long count = 0;
-	struct list_lru_node *nlru = &lru->node[nid];
+	int memcg_id = -1;
+	struct list_lru_node *nlru;
+
+	if (memcg && memcg_kmem_is_active(memcg))
+		memcg_id = memcg_cache_id(memcg);
+
+	nlru = lru_node_of_index(lru, memcg_id, nid);
+	if (!nlru)
+		return 0;
 
 	spin_lock(&nlru->lock);
 	BUG_ON(nlru->nr_items < 0);
@@ -151,19 +177,28 @@ list_lru_count_node(struct list_lru *lru, int nid)
 
 	return count;
 }
-EXPORT_SYMBOL_GPL(list_lru_count_node);
+EXPORT_SYMBOL_GPL(list_lru_count_node_memcg);
 
 unsigned long
-list_lru_walk_node(
+list_lru_walk_node_memcg(
 	struct list_lru		*lru,
 	int			nid,
 	list_lru_walk_cb	isolate,
 	void			*cb_arg,
-	unsigned long		*nr_to_walk)
+	unsigned long		*nr_to_walk,
+	struct mem_cgroup	*memcg)
 {
-	struct list_lru_node	*nlru = &lru->node[nid];
 	struct list_head *item, *n;
 	unsigned long isolated = 0;
+	struct list_lru_node *nlru;
+	int memcg_id = -1;
+
+	if (memcg && memcg_kmem_is_active(memcg))
+		memcg_id = memcg_cache_id(memcg);
+
+	nlru = lru_node_of_index(lru, memcg_id, nid);
+	if (!nlru)
+		return 0;
 
 	spin_lock(&nlru->lock);
 	list_for_each_safe(item, n, &nlru->list) {
@@ -200,7 +235,7 @@ restart:
 	spin_unlock(&nlru->lock);
 	return isolated;
 }
-EXPORT_SYMBOL_GPL(list_lru_walk_node);
+EXPORT_SYMBOL_GPL(list_lru_walk_node_memcg);
 
 static unsigned long
 list_lru_dispose_all_node(
@@ -208,23 +243,34 @@ list_lru_dispose_all_node(
 	int			nid,
 	list_lru_dispose_cb	dispose)
 {
-	struct list_lru_node	*nlru = &lru->node[nid];
+	struct list_lru_node *nlru;
 	LIST_HEAD(dispose_list);
 	unsigned long disposed = 0;
+	int idx;
 
-	spin_lock(&nlru->lock);
-	while (!list_empty(&nlru->list)) {
-		list_splice_init(&nlru->list, &dispose_list);
-		disposed += nlru->nr_items;
-		nlru->nr_items = 0;
-		node_clear(nid, lru->active_nodes);
-		spin_unlock(&nlru->lock);
-
-		dispose(&dispose_list);
+	for_each_memcg_lru_index(idx) {
+		nlru = lru_node_of_index(lru, idx, nid);
+		if (!nlru)
+			continue;
 
 		spin_lock(&nlru->lock);
+		while (!list_empty(&nlru->list)) {
+			list_splice_init(&nlru->list, &dispose_list);
+
+			if (atomic_long_sub_and_test(nlru->nr_items,
+							&lru->node_totals[nid]))
+				node_clear(nid, lru->active_nodes);
+			disposed += nlru->nr_items;
+			nlru->nr_items = 0;
+			spin_unlock(&nlru->lock);
+
+			dispose(&dispose_list);
+
+			spin_lock(&nlru->lock);
+		}
+		spin_unlock(&nlru->lock);
 	}
-	spin_unlock(&nlru->lock);
+
 	return disposed;
 }
 
-- 
1.8.1.4

  parent reply	other threads:[~2013-05-30 10:36 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-30 10:35 [PATCH v9 00/35] kmemcg shrinkers Glauber Costa
2013-05-30 10:35 ` [PATCH v9 02/35] super: fix calculation of shrinkable objects for small numbers Glauber Costa
2013-05-30 10:36 ` [PATCH v9 20/35] drivers: convert shrinkers to new count/scan API Glauber Costa
     [not found] ` <1369910181-20026-1-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2013-05-30 10:35   ` [PATCH v9 01/35] fs: bump inode and dentry counters to long Glauber Costa
2013-05-30 10:35   ` [PATCH v9 03/35] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
2013-05-30 10:35   ` [PATCH v9 04/35] dentry: move to per-sb LRU locks Glauber Costa
2013-05-30 10:35   ` [PATCH v9 05/35] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
2013-05-30 10:35   ` [PATCH v9 06/35] mm: new shrinker API Glauber Costa
2013-05-30 10:35   ` [PATCH v9 07/35] shrinker: convert superblock shrinkers to new API Glauber Costa
2013-05-30 10:35   ` [PATCH v9 08/35] list: add a new LRU list type Glauber Costa
2013-05-30 10:35   ` [PATCH v9 09/35] inode: convert inode lru list to generic lru list code Glauber Costa
2013-05-30 10:35   ` [PATCH v9 10/35] dcache: convert to use new lru list infrastructure Glauber Costa
2013-05-30 10:35   ` [PATCH v9 11/35] list_lru: per-node " Glauber Costa
2013-05-30 10:35   ` [PATCH v9 12/35] shrinker: add node awareness Glauber Costa
2013-05-30 10:35   ` [PATCH v9 13/35] vmscan: per-node deferred work Glauber Costa
2013-05-30 10:36   ` [PATCH v9 14/35] list_lru: per-node API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 15/35] fs: convert inode and dentry shrinking to be node aware Glauber Costa
2013-05-30 10:36   ` [PATCH v9 16/35] xfs: convert buftarg LRU to generic code Glauber Costa
2013-05-30 10:36   ` [PATCH v9 17/35] xfs: rework buffer dispose list tracking Glauber Costa
2013-05-30 10:36   ` [PATCH v9 18/35] xfs: convert dquot cache lru to list_lru Glauber Costa
2013-05-30 10:36   ` [PATCH v9 19/35] fs: convert fs shrinkers to new scan/count API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 21/35] i915: bail out earlier when shrinker cannot acquire mutex Glauber Costa
2013-05-30 10:36   ` [PATCH v9 22/35] shrinker: convert remaining shrinkers to count/scan API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 23/35] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 24/35] shrinker: Kill old ->shrink API Glauber Costa
2013-05-30 10:36   ` [PATCH v9 25/35] vmscan: also shrink slab in memcg pressure Glauber Costa
2013-05-30 10:36   ` [PATCH v9 26/35] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
2013-05-30 10:36   ` [PATCH v9 27/35] lru: add an element to a memcg list Glauber Costa
2013-05-30 10:36   ` Glauber Costa [this message]
2013-05-30 10:36   ` [PATCH v9 29/35] memcg: per-memcg kmem shrinking Glauber Costa
2013-05-30 10:36   ` [PATCH v9 30/35] memcg: scan cache objects hierarchically Glauber Costa
2013-05-30 10:36   ` [PATCH v9 32/35] super: targeted memcg reclaim Glauber Costa
2013-05-30 10:36   ` [PATCH v9 33/35] memcg: move initialization to memcg creation Glauber Costa
2013-05-30 10:36   ` [PATCH v9 34/35] vmpressure: in-kernel notifications Glauber Costa
2013-05-30 10:36   ` [PATCH v9 35/35] memcg: reap dead memcgs upon global memory pressure Glauber Costa
2013-05-30 10:36 ` [PATCH v9 31/35] vmscan: take at least one pass with shrinkers Glauber Costa

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=1369910181-20026-29-git-send-email-glommer@openvz.org \
    --to=glommer-gefaqzzx7r8dnm+yrofe0a@public.gmane.org \
    --cc=akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org \
    --cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=david-FqsqvQoI3Ljby3iVrkZq2A@public.gmane.org \
    --cc=dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org \
    --cc=hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
    --cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
    --cc=mgorman-l3A5Bk7waGM@public.gmane.org \
    --cc=mhocko-AlSwsSmVLrQ@public.gmane.org \
    --cc=riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    /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).