From: Glauber Costa <glommer@parallels.com>
To: linux-mm@kvack.org
Cc: linux-fsdevel@vger.kernel.org,
containers@lists.linux-foundation.org,
Michal Hocko <mhocko@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
kamezawa.hiroyu@jp.fujitsu.com,
Andrew Morton <akpm@linux-foundation.org>,
Dave Shrinnker <david@fromorbit.com>,
Greg Thelen <gthelen@google.com>,
hughd@google.com, yinghan@google.com,
Dave Chinner <dchinner@redhat.com>
Subject: [PATCH v2 13/28] fs: convert inode and dentry shrinking to be node aware
Date: Fri, 29 Mar 2013 13:13:55 +0400 [thread overview]
Message-ID: <1364548450-28254-14-git-send-email-glommer@parallels.com> (raw)
In-Reply-To: <1364548450-28254-1-git-send-email-glommer@parallels.com>
From: Dave Chinner <dchinner@redhat.com>
Now that the shrinker is passing a nodemask in the scan control
structure, we can pass this to the the generic LRU list code to
isolate reclaim to the lists on matching nodes.
This requires a small amount of refactoring of the LRU list API,
which might be best split out into a separate patch.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/dcache.c | 7 ++++---
fs/inode.c | 7 ++++---
fs/internal.h | 6 ++++--
fs/super.c | 22 +++++++++++++---------
fs/xfs/xfs_super.c | 6 ++++--
include/linux/fs.h | 4 ++--
include/linux/list_lru.h | 19 ++++++++++++++++---
lib/list_lru.c | 18 ++++++++++--------
8 files changed, 57 insertions(+), 32 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index b59d341..79f6820 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -881,13 +881,14 @@ static int dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock,
* This function may fail to free any resources if all the dentries are in
* use.
*/
-long prune_dcache_sb(struct super_block *sb, long nr_to_scan)
+long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_walk)
{
LIST_HEAD(dispose);
long freed;
- freed = list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate,
- &dispose, nr_to_scan);
+ freed = list_lru_walk_nodemask(&sb->s_dentry_lru, dentry_lru_isolate,
+ &dispose, nr_to_scan, nodes_to_walk);
shrink_dentry_list(&dispose);
return freed;
}
diff --git a/fs/inode.c b/fs/inode.c
index 18505c5..1332eef 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -745,13 +745,14 @@ static int inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock,
* to trim from the LRU. Inodes to be freed are moved to a temporary list and
* then are freed outside inode_lock by dispose_list().
*/
-long prune_icache_sb(struct super_block *sb, long nr_to_scan)
+long prune_icache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_walk)
{
LIST_HEAD(freeable);
long freed;
- freed = list_lru_walk(&sb->s_inode_lru, inode_lru_isolate,
- &freeable, nr_to_scan);
+ freed = list_lru_walk_nodemask(&sb->s_inode_lru, inode_lru_isolate,
+ &freeable, nr_to_scan, nodes_to_walk);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/internal.h b/fs/internal.h
index 5099f87..ed6944e 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,7 +110,8 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
-extern long prune_icache_sb(struct super_block *sb, long nr_to_scan);
+extern long prune_icache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_scan);
extern void inode_add_lru(struct inode *inode);
/*
@@ -126,4 +127,5 @@ extern int invalidate_inodes(struct super_block *, bool);
* dcache.c
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
-extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan);
+extern long prune_dcache_sb(struct super_block *sb, long nr_to_scan,
+ nodemask_t *nodes_to_scan);
diff --git a/fs/super.c b/fs/super.c
index 66f5cde..5c7b879 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -75,10 +75,10 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
return -1;
if (sb->s_op && sb->s_op->nr_cached_objects)
- fs_objects = sb->s_op->nr_cached_objects(sb);
+ fs_objects = sb->s_op->nr_cached_objects(sb, &sc->nodes_to_scan);
- inodes = list_lru_count(&sb->s_inode_lru);
- dentries = list_lru_count(&sb->s_dentry_lru);
+ inodes = list_lru_count_nodemask(&sb->s_inode_lru, &sc->nodes_to_scan);
+ dentries = list_lru_count_nodemask(&sb->s_dentry_lru, &sc->nodes_to_scan);
total_objects = dentries + inodes + fs_objects + 1;
/* proportion the scan between the caches */
@@ -89,13 +89,14 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
- freed = prune_dcache_sb(sb, dentries);
- freed += prune_icache_sb(sb, inodes);
+ freed = prune_dcache_sb(sb, dentries, &sc->nodes_to_scan);
+ freed += prune_icache_sb(sb, inodes, &sc->nodes_to_scan);
if (fs_objects) {
fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
total_objects);
- freed += sb->s_op->free_cached_objects(sb, fs_objects);
+ freed += sb->s_op->free_cached_objects(sb, fs_objects,
+ &sc->nodes_to_scan);
}
drop_super(sb);
@@ -113,10 +114,13 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
return -1;
if (sb->s_op && sb->s_op->nr_cached_objects)
- total_objects = sb->s_op->nr_cached_objects(sb);
+ total_objects = sb->s_op->nr_cached_objects(sb,
+ &sc->nodes_to_scan);
- total_objects += list_lru_count(&sb->s_dentry_lru);
- total_objects += list_lru_count(&sb->s_inode_lru);
+ total_objects += list_lru_count_nodemask(&sb->s_dentry_lru,
+ &sc->nodes_to_scan);
+ total_objects += list_lru_count_nodemask(&sb->s_inode_lru,
+ &sc->nodes_to_scan);
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 1ff991b..7fa6021 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1525,7 +1525,8 @@ xfs_fs_mount(
static long
xfs_fs_nr_cached_objects(
- struct super_block *sb)
+ struct super_block *sb,
+ nodemask_t *nodes_to_count)
{
return xfs_reclaim_inodes_count(XFS_M(sb));
}
@@ -1533,7 +1534,8 @@ xfs_fs_nr_cached_objects(
static long
xfs_fs_free_cached_objects(
struct super_block *sb,
- long nr_to_scan)
+ long nr_to_scan,
+ nodemask_t *nodes_to_scan)
{
return xfs_reclaim_inodes_nr(XFS_M(sb), nr_to_scan);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8b25de0..306c83e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1607,8 +1607,8 @@ struct super_operations {
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
- long (*nr_cached_objects)(struct super_block *);
- long (*free_cached_objects)(struct super_block *, long);
+ long (*nr_cached_objects)(struct super_block *, nodemask_t *);
+ long (*free_cached_objects)(struct super_block *, long, nodemask_t *);
};
/*
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b0e3ba25..02796da 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -24,14 +24,27 @@ struct list_lru {
int list_lru_init(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);
-long list_lru_count(struct list_lru *lru);
+long list_lru_count_nodemask(struct list_lru *lru, nodemask_t *nodes_to_count);
+
+static inline long list_lru_count(struct list_lru *lru)
+{
+ return list_lru_count_nodemask(lru, &lru->active_nodes);
+}
+
typedef int (*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);
-long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
- void *cb_arg, long nr_to_walk);
+long list_lru_walk_nodemask(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, long nr_to_walk, nodemask_t *nodes_to_walk);
+
+static inline long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
+ void *cb_arg, long nr_to_walk)
+{
+ return list_lru_walk_nodemask(lru, isolate, cb_arg, nr_to_walk,
+ &lru->active_nodes);
+}
long list_lru_dispose_all(struct list_lru *lru, list_lru_dispose_cb dispose);
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 881e342..0f08ed6 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -54,13 +54,14 @@ list_lru_del(
EXPORT_SYMBOL_GPL(list_lru_del);
long
-list_lru_count(
- struct list_lru *lru)
+list_lru_count_nodemask(
+ struct list_lru *lru,
+ nodemask_t *nodes_to_count)
{
long count = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_mask(nid, *nodes_to_count) {
struct list_lru_node *nlru = &lru->node[nid];
spin_lock(&nlru->lock);
@@ -71,7 +72,7 @@ list_lru_count(
return count;
}
-EXPORT_SYMBOL_GPL(list_lru_count);
+EXPORT_SYMBOL_GPL(list_lru_count_nodemask);
static long
list_lru_walk_node(
@@ -116,16 +117,17 @@ restart:
}
long
-list_lru_walk(
+list_lru_walk_nodemask(
struct list_lru *lru,
list_lru_walk_cb isolate,
void *cb_arg,
- long nr_to_walk)
+ long nr_to_walk,
+ nodemask_t *nodes_to_walk)
{
long isolated = 0;
int nid;
- for_each_node_mask(nid, lru->active_nodes) {
+ for_each_node_mask(nid, *nodes_to_walk) {
isolated += list_lru_walk_node(lru, nid, isolate,
cb_arg, &nr_to_walk);
if (nr_to_walk <= 0)
@@ -133,7 +135,7 @@ list_lru_walk(
}
return isolated;
}
-EXPORT_SYMBOL_GPL(list_lru_walk);
+EXPORT_SYMBOL_GPL(list_lru_walk_nodemask);
long
list_lru_dispose_all_node(
--
1.8.1.4
--
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:[~2013-03-29 9:14 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-29 9:13 [PATCH v2 00/28] memcg-aware slab shrinking Glauber Costa
2013-03-29 9:13 ` [PATCH v2 01/28] super: fix calculation of shrinkable objects for small numbers Glauber Costa
2013-04-01 7:16 ` Kamezawa Hiroyuki
2013-03-29 9:13 ` [PATCH v2 02/28] vmscan: take at least one pass with shrinkers Glauber Costa
2013-04-01 7:26 ` Kamezawa Hiroyuki
2013-04-01 8:10 ` Glauber Costa
2013-04-10 5:09 ` Ric Mason
2013-04-10 7:32 ` Glauber Costa
2013-04-10 9:19 ` Dave Chinner
2013-04-08 8:42 ` Joonsoo Kim
2013-04-08 8:47 ` Glauber Costa
2013-04-08 9:01 ` Joonsoo Kim
2013-04-08 9:05 ` Glauber Costa
2013-04-09 0:55 ` Joonsoo Kim
2013-04-09 1:29 ` Dave Chinner
2013-04-09 2:05 ` Joonsoo Kim
2013-04-09 7:43 ` Glauber Costa
2013-04-09 9:08 ` Joonsoo Kim
2013-04-09 12:30 ` Dave Chinner
2013-04-10 2:51 ` Joonsoo Kim
2013-04-10 7:30 ` Glauber Costa
2013-04-10 8:19 ` Joonsoo Kim
2013-04-10 8:46 ` Wanpeng Li
2013-04-10 8:46 ` Wanpeng Li
2013-04-10 10:07 ` Dave Chinner
2013-04-10 14:03 ` JoonSoo Kim
2013-04-11 0:41 ` Dave Chinner
2013-04-11 7:27 ` Wanpeng Li
2013-04-11 7:27 ` Wanpeng Li
2013-04-11 7:27 ` Wanpeng Li
2013-04-11 9:25 ` Dave Chinner
[not found] ` <20130410025115.GA5872-Hm3cg6mZ9cc@public.gmane.org>
2013-04-10 8:46 ` Wanpeng Li
2013-03-29 9:13 ` [PATCH v2 03/28] dcache: convert dentry_stat.nr_unused to per-cpu counters Glauber Costa
2013-04-05 1:09 ` Greg Thelen
2013-04-05 1:15 ` Dave Chinner
2013-04-08 9:14 ` Glauber Costa
2013-04-08 13:18 ` Glauber Costa
2013-04-08 23:26 ` Dave Chinner
2013-04-09 8:02 ` Glauber Costa
2013-04-09 12:47 ` Dave Chinner
2013-03-29 9:13 ` [PATCH v2 04/28] dentry: move to per-sb LRU locks Glauber Costa
2013-03-29 9:13 ` [PATCH v2 05/28] dcache: remove dentries from LRU before putting on dispose list Glauber Costa
2013-04-03 6:51 ` Sha Zhengju
2013-04-03 8:55 ` Glauber Costa
2013-04-04 6:19 ` Dave Chinner
2013-04-04 6:56 ` Glauber Costa
2013-03-29 9:13 ` [PATCH v2 06/28] mm: new shrinker API Glauber Costa
2013-04-05 1:09 ` Greg Thelen
2013-03-29 9:13 ` [PATCH v2 07/28] shrinker: convert superblock shrinkers to new API Glauber Costa
2013-03-29 9:13 ` [PATCH v2 08/28] list: add a new LRU list type Glauber Costa
2013-04-04 21:53 ` Greg Thelen
2013-04-05 1:20 ` Dave Chinner
2013-04-05 8:01 ` Glauber Costa
2013-04-06 0:04 ` Dave Chinner
2013-03-29 9:13 ` [PATCH v2 09/28] inode: convert inode lru list to generic lru list code Glauber Costa
2013-03-29 9:13 ` [PATCH v2 10/28] dcache: convert to use new lru list infrastructure Glauber Costa
2013-04-08 13:14 ` Glauber Costa
2013-04-08 23:28 ` Dave Chinner
2013-03-29 9:13 ` [PATCH v2 11/28] list_lru: per-node " Glauber Costa
2013-03-29 9:13 ` [PATCH v2 12/28] shrinker: add node awareness Glauber Costa
2013-03-29 9:13 ` Glauber Costa [this message]
2013-03-29 9:13 ` [PATCH v2 14/28] xfs: convert buftarg LRU to generic code Glauber Costa
2013-03-29 9:13 ` [PATCH v2 15/28] xfs: convert dquot cache lru to list_lru Glauber Costa
2013-03-29 9:13 ` [PATCH v2 16/28] fs: convert fs shrinkers to new scan/count API Glauber Costa
2013-03-29 9:13 ` [PATCH v2 17/28] drivers: convert shrinkers to new count/scan API Glauber Costa
2013-03-29 9:14 ` [PATCH v2 18/28] shrinker: convert remaining shrinkers to " Glauber Costa
2013-03-29 9:14 ` [PATCH v2 19/28] hugepage: convert huge zero page shrinker to new shrinker API Glauber Costa
2013-03-29 9:14 ` [PATCH v2 20/28] shrinker: Kill old ->shrink API Glauber Costa
2013-03-29 9:14 ` [PATCH v2 21/28] vmscan: also shrink slab in memcg pressure Glauber Costa
2013-04-01 7:46 ` Kamezawa Hiroyuki
2013-04-01 8:51 ` Glauber Costa
2013-04-03 10:11 ` Sha Zhengju
2013-04-03 10:43 ` Glauber Costa
2013-04-04 9:35 ` Sha Zhengju
2013-04-05 8:25 ` Glauber Costa
2013-03-29 9:14 ` [PATCH v2 22/28] memcg,list_lru: duplicate LRUs upon kmemcg creation Glauber Costa
2013-04-01 8:05 ` Kamezawa Hiroyuki
2013-04-01 8:22 ` Glauber Costa
2013-03-29 9:14 ` [PATCH v2 23/28] lru: add an element to a memcg list Glauber Costa
2013-04-01 8:18 ` Kamezawa Hiroyuki
2013-04-01 8:29 ` Glauber Costa
2013-03-29 9:14 ` [PATCH v2 24/28] list_lru: also include memcg lists in counts and scans Glauber Costa
2013-03-29 9:14 ` [PATCH v2 25/28] list_lru: per-memcg walks Glauber Costa
2013-03-29 9:14 ` [PATCH v2 26/28] memcg: per-memcg kmem shrinking Glauber Costa
2013-04-01 8:31 ` Kamezawa Hiroyuki
2013-04-01 8:48 ` Glauber Costa
2013-04-01 9:01 ` Kamezawa Hiroyuki
2013-04-01 9:14 ` Glauber Costa
2013-04-01 9:35 ` Kamezawa Hiroyuki
2013-03-29 9:14 ` [PATCH v2 27/28] list_lru: reclaim proportionaly between memcgs and nodes Glauber Costa
2013-03-29 9:14 ` [PATCH v2 28/28] super: targeted memcg reclaim Glauber Costa
2013-04-01 12:38 ` [PATCH v2 00/28] memcg-aware slab shrinking Serge Hallyn
2013-04-01 12:45 ` Glauber Costa
2013-04-01 14:12 ` Serge Hallyn
2013-04-08 8:11 ` Glauber Costa
2013-04-02 4:58 ` Dave Chinner
2013-04-02 7:55 ` 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=1364548450-28254-14-git-send-email-glommer@parallels.com \
--to=glommer@parallels.com \
--cc=akpm@linux-foundation.org \
--cc=containers@lists.linux-foundation.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=mhocko@suse.cz \
--cc=yinghan@google.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