linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@openvz.org>
To: <linux-mm@kvack.org>
Cc: <cgroups@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Greg Thelen <gthelen@google.com>,
	<kamezawa.hiroyu@jp.fujitsu.com>, Michal Hocko <mhocko@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	<linux-fsdevel@vger.kernel.org>,
	Dave Chinner <david@fromorbit.com>,
	Glauber Costa <glommer@openvz.org>,
	Dave Chinner <dchinner@redhat.com>, Mel Gorman <mgorman@suse.de>,
	Rik van Riel <riel@redhat.com>, Hugh Dickins <hughd@google.com>
Subject: [PATCH v6 24/31] list_lru: per-memcg walks
Date: Sun, 12 May 2013 22:13:45 +0400	[thread overview]
Message-ID: <1368382432-25462-25-git-send-email-glommer@openvz.org> (raw)
In-Reply-To: <1368382432-25462-1-git-send-email-glommer@openvz.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@openvz.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/list_lru.h   |  26 ++++++++---
 include/linux/memcontrol.h |   2 +
 lib/list_lru.c             | 110 ++++++++++++++++++++++++++++++++++-----------
 3 files changed, 107 insertions(+), 31 deletions(-)

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index f6756fb..9e6bbb1 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -99,23 +99,37 @@ 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_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count);
+
+unsigned long list_lru_count_nodemask_memcg(struct list_lru *lru,
+			nodemask_t *nodes_to_count, struct mem_cgroup *memcg);
+
+static inline unsigned long
+list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count)
+{
+	return list_lru_count_nodemask_memcg(lru, nodes_to_count, NULL);
+}
 
 static inline unsigned long list_lru_count(struct list_lru *lru)
 {
 	return list_lru_count_nodemask(lru, &lru->active_nodes);
 }
 
-
 typedef enum lru_status
 (*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg);
 
 typedef void (*list_lru_dispose_cb)(struct list_head *dispose_list);
 
-unsigned long
-list_lru_walk_nodemask(struct list_lru *lru, list_lru_walk_cb isolate,
-	   void *cb_arg, unsigned long nr_to_walk, nodemask_t *nodes_to_walk);
+unsigned long list_lru_walk_nodemask_memcg(struct list_lru *lru,
+	list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk,
+	nodemask_t *nodes_to_walk, struct mem_cgroup *memcg);
+
+static inline unsigned long list_lru_walk_nodemask(struct list_lru *lru,
+	list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk,
+	nodemask_t *nodes_to_walk)
+{
+	return list_lru_walk_nodemask_memcg(lru, isolate, cb_arg, nr_to_walk,
+					    &lru->active_nodes, 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 a5753b2..f3a37f5 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -72,6 +72,23 @@ 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,
@@ -131,13 +148,29 @@ list_lru_del(
 EXPORT_SYMBOL_GPL(list_lru_del);
 
 unsigned long
-list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count)
+list_lru_count_nodemask_memcg(
+	struct list_lru *lru,
+	nodemask_t	*nodes_to_count,
+	struct mem_cgroup *memcg)
 {
 	long count = 0;
 	int nid;
+	nodemask_t nodes;
+	int memcg_id = -1;
+
+	if (memcg && memcg_kmem_is_active(memcg))
+		memcg_id = memcg_cache_id(memcg);
+	/*
+	 * Conservative code can call this setting nodes with node_setall.
+	 * This will generate an out of bound access for memcg.
+	 */
+	nodes_and(nodes, *nodes_to_count, node_online_map);
 
-	for_each_node_mask(nid, *nodes_to_count) {
-		struct list_lru_node *nlru = &lru->node[nid];
+	for_each_node_mask(nid, nodes) {
+		struct list_lru_node *nlru;
+		nlru = lru_node_of_index(lru, memcg_id, nid);
+		if (!nlru)
+			continue;
 
 		spin_lock(&nlru->lock);
 		BUG_ON(nlru->nr_items < 0);
@@ -147,17 +180,17 @@ list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count)
 
 	return count;
 }
-EXPORT_SYMBOL_GPL(list_lru_count_nodemask);
+EXPORT_SYMBOL_GPL(list_lru_count_nodemask_memcg);
 
 static unsigned long
 list_lru_walk_node(
 	struct list_lru		*lru,
+	struct list_lru_node	*nlru,
 	int			nid,
 	list_lru_walk_cb	isolate,
 	void			*cb_arg,
 	unsigned long		*nr_to_walk)
 {
-	struct list_lru_node	*nlru = &lru->node[nid];
 	struct list_head *item, *n;
 	unsigned long isolated = 0;
 
@@ -197,25 +230,41 @@ restart:
 }
 
 unsigned long
-list_lru_walk_nodemask(
-	struct list_lru	*lru,
-	list_lru_walk_cb isolate,
-	void		*cb_arg,
-	unsigned long	nr_to_walk,
-	nodemask_t	*nodes_to_walk)
+list_lru_walk_nodemask_memcg(
+	struct list_lru		*lru,
+	list_lru_walk_cb	isolate,
+	void			*cb_arg,
+	unsigned long		nr_to_walk,
+	nodemask_t		*nodes_to_walk,
+	struct mem_cgroup	*memcg)
 {
 	long isolated = 0;
 	int nid;
+	nodemask_t nodes;
+	int memcg_id = -1;
+	struct list_lru_node *nlru;
 
-	for_each_node_mask(nid, *nodes_to_walk) {
-		isolated += list_lru_walk_node(lru, nid, isolate,
+	if (memcg && memcg_kmem_is_active(memcg))
+		memcg_id = memcg_cache_id(memcg);
+	/*
+	 * Conservative code can call this setting nodes with node_setall.
+	 * This will generate an out of bound access for memcg.
+	 */
+	nodes_and(nodes, *nodes_to_walk, node_online_map);
+
+	for_each_node_mask(nid, nodes) {
+		nlru = lru_node_of_index(lru, memcg_id, nid);
+		if (!nlru)
+			continue;
+
+		isolated += list_lru_walk_node(lru, nlru, nid, isolate,
 					       cb_arg, &nr_to_walk);
 		if (nr_to_walk <= 0)
 			break;
 	}
 	return isolated;
 }
-EXPORT_SYMBOL_GPL(list_lru_walk_nodemask);
+EXPORT_SYMBOL_GPL(list_lru_walk_nodemask_memcg);
 
 static unsigned long
 list_lru_dispose_all_node(
@@ -223,23 +272,34 @@ 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:[~2013-05-12 18:14 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-12 18:13 [PATCH v6 00/31] kmemcg shrinkers Glauber Costa
2013-05-12 18:13 ` [PATCH v6 01/31] super: fix calculation of shrinkable objects for small numbers Glauber Costa
2013-05-12 18:13 ` [PATCH v6 02/31] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
2013-05-12 18:13 ` [PATCH v6 03/31] dentry: move to per-sb LRU locks Glauber Costa
2013-05-12 18:13 ` [PATCH v6 04/31] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
2013-05-14  2:02   ` Dave Chinner
2013-05-14  5:46   ` [PATCH v7 " Dave Chinner
2013-05-14  7:10     ` Dave Chinner
2013-05-14 12:43     ` Glauber Costa
     [not found]       ` <51923158.7040002-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2013-05-14 20:32         ` Dave Chinner
2013-05-12 18:13 ` [PATCH v6 05/31] mm: new shrinker API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 06/31] shrinker: convert superblock shrinkers to new API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 07/31] list: add a new LRU list type Glauber Costa
2013-05-13  9:25   ` Mel Gorman
2013-05-12 18:13 ` [PATCH v6 08/31] inode: convert inode lru list to generic lru list code Glauber Costa
2013-05-12 18:13 ` [PATCH v6 09/31] dcache: convert to use new lru list infrastructure Glauber Costa
     [not found]   ` <1368382432-25462-10-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2013-05-14  6:59     ` Dave Chinner
2013-05-14  7:50       ` Glauber Costa
2013-05-14 14:01       ` Glauber Costa
2013-05-12 18:13 ` [PATCH v6 10/31] list_lru: per-node " Glauber Costa
2013-05-12 18:13 ` [PATCH v6 11/31] shrinker: add node awareness Glauber Costa
2013-05-12 18:13 ` [PATCH v6 12/31] fs: convert inode and dentry shrinking to be node aware Glauber Costa
     [not found]   ` <1368382432-25462-13-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2013-05-14  9:52     ` Dave Chinner
2013-05-15 15:27       ` Glauber Costa
2013-05-16  0:02         ` Dave Chinner
2013-05-16  8:03           ` Glauber Costa
2013-05-16 19:14           ` Glauber Costa
2013-05-17  0:51             ` Dave Chinner
2013-05-17  7:29               ` Glauber Costa
     [not found]                 ` <5195DC59.8000205-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2013-05-17 14:49                   ` Glauber Costa
     [not found]                     ` <51964381.8010406-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2013-05-17 22:54                       ` Glauber Costa
2013-05-18  3:39                     ` Dave Chinner
2013-05-18  7:20                       ` Glauber Costa
2013-05-12 18:13 ` [PATCH v6 13/31] xfs: convert buftarg LRU to generic code Glauber Costa
2013-05-12 18:13 ` [PATCH v6 14/31] xfs: convert dquot cache lru to list_lru Glauber Costa
2013-05-12 18:13 ` [PATCH v6 15/31] fs: convert fs shrinkers to new scan/count API Glauber Costa
2013-05-13  6:12   ` Artem Bityutskiy
     [not found]     ` <1368425530.3208.13.camel-Bxnoe/o8FG+Ef9UqXRslZEEOCMrvLtNR@public.gmane.org>
2013-05-13  7:28       ` Glauber Costa
     [not found]         ` <51909610.1010801-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2013-05-13  7:43           ` Artem Bityutskiy
2013-05-13 10:36   ` Jan Kara
2013-05-12 18:13 ` [PATCH v6 16/31] drivers: convert shrinkers to new count/scan API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 17/31] i915: bail out earlier when shrinker cannot acquire mutex Glauber Costa
2013-05-12 18:13 ` [PATCH v6 18/31] shrinker: convert remaining shrinkers to count/scan API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 19/31] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 20/31] shrinker: Kill old ->shrink API Glauber Costa
2013-05-12 18:13 ` [PATCH v6 21/31] vmscan: also shrink slab in memcg pressure Glauber Costa
2013-05-12 18:13 ` [PATCH v6 22/31] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
2013-05-12 18:13 ` [PATCH v6 23/31] lru: add an element to a memcg list Glauber Costa
2013-05-12 18:13 ` Glauber Costa [this message]
2013-05-12 18:13 ` [PATCH v6 25/31] memcg: per-memcg kmem shrinking Glauber Costa
2013-05-12 18:13 ` [PATCH v6 26/31] memcg: scan cache objects hierarchically Glauber Costa
2013-05-12 18:13 ` [PATCH v6 27/31] vmscan: take at least one pass with shrinkers Glauber Costa
2013-05-12 18:13 ` [PATCH v6 28/31] super: targeted memcg reclaim Glauber Costa
2013-05-12 18:13 ` [PATCH v6 29/31] memcg: move initialization to memcg creation Glauber Costa
2013-05-12 18:13 ` [PATCH v6 30/31] vmpressure: in-kernel notifications Glauber Costa
2013-05-12 18:13 ` [PATCH v6 31/31] memcg: reap dead memcgs upon global memory pressure Glauber Costa
2013-05-13  7:14 ` [PATCH v6 00/31] kmemcg shrinkers Dave Chinner
2013-05-13  7:21   ` Dave Chinner
2013-05-13  8:00   ` Glauber Costa
     [not found]     ` <51909D84.7040800-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2013-05-14  1:48       ` Dave Chinner
2013-05-14  5:22         ` Dave Chinner
2013-05-14  5:45           ` Dave Chinner
2013-05-14  7:38           ` 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=1368382432-25462-25-git-send-email-glommer@openvz.org \
    --to=glommer@openvz.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=david@fromorbit.com \
    --cc=dchinner@redhat.com \
    --cc=gthelen@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.cz \
    --cc=riel@redhat.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
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).