From: Dave Chinner <david@fromorbit.com>
To: glommer@parallels.com
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-mm@kvack.org, xfs@oss.sgi.com
Subject: [PATCH 09/19] list_lru: per-node list infrastructure
Date: Wed, 28 Nov 2012 10:14:36 +1100 [thread overview]
Message-ID: <1354058086-27937-10-git-send-email-david@fromorbit.com> (raw)
In-Reply-To: <1354058086-27937-1-git-send-email-david@fromorbit.com>
From: Dave Chinner <dchinner@redhat.com>
Now that we have an LRU list API, we can start to enhance the
implementation. This splits the single LRU list into per-node lists
and locks to enhance scalability. Items are placed on lists
according to the node the memory belongs to. To make scanning the
lists efficient, also track whether the per-node lists have entries
in them in a active nodemask.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
include/linux/list_lru.h | 14 ++--
lib/list_lru.c | 160 +++++++++++++++++++++++++++++++++++-----------
2 files changed, 129 insertions(+), 45 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 3423949..b0e3ba2 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -8,21 +8,23 @@
#define _LRU_LIST_H 0
#include <linux/list.h>
+#include <linux/nodemask.h>
-struct list_lru {
+struct list_lru_node {
spinlock_t lock;
struct list_head list;
long nr_items;
+} ____cacheline_aligned_in_smp;
+
+struct list_lru {
+ struct list_lru_node node[MAX_NUMNODES];
+ nodemask_t active_nodes;
};
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);
-
-static inline long list_lru_count(struct list_lru *lru)
-{
- return lru->nr_items;
-}
+long list_lru_count(struct list_lru *lru);
typedef int (*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock,
void *cb_arg);
diff --git a/lib/list_lru.c b/lib/list_lru.c
index 475d0e9..881e342 100644
--- a/lib/list_lru.c
+++ b/lib/list_lru.c
@@ -6,6 +6,7 @@
*/
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/mm.h>
#include <linux/list_lru.h>
int
@@ -13,14 +14,19 @@ list_lru_add(
struct list_lru *lru,
struct list_head *item)
{
- spin_lock(&lru->lock);
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ BUG_ON(nlru->nr_items < 0);
if (list_empty(item)) {
- list_add_tail(item, &lru->list);
- lru->nr_items++;
- spin_unlock(&lru->lock);
+ list_add_tail(item, &nlru->list);
+ if (nlru->nr_items++ == 0)
+ node_set(nid, lru->active_nodes);
+ spin_unlock(&nlru->lock);
return 1;
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_add);
@@ -30,43 +36,72 @@ list_lru_del(
struct list_lru *lru,
struct list_head *item)
{
- spin_lock(&lru->lock);
+ int nid = page_to_nid(virt_to_page(item));
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
if (!list_empty(item)) {
list_del_init(item);
- lru->nr_items--;
- spin_unlock(&lru->lock);
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ BUG_ON(nlru->nr_items < 0);
+ spin_unlock(&nlru->lock);
return 1;
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_del);
long
-list_lru_walk(
- struct list_lru *lru,
- list_lru_walk_cb isolate,
- void *cb_arg,
- long nr_to_walk)
+list_lru_count(
+ struct list_lru *lru)
{
+ long count = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes) {
+ struct list_lru_node *nlru = &lru->node[nid];
+
+ spin_lock(&nlru->lock);
+ BUG_ON(nlru->nr_items < 0);
+ count += nlru->nr_items;
+ spin_unlock(&nlru->lock);
+ }
+
+ return count;
+}
+EXPORT_SYMBOL_GPL(list_lru_count);
+
+static long
+list_lru_walk_node(
+ struct list_lru *lru,
+ int nid,
+ list_lru_walk_cb isolate,
+ void *cb_arg,
+ long *nr_to_walk)
+{
+ struct list_lru_node *nlru = &lru->node[nid];
struct list_head *item, *n;
- long removed = 0;
+ long isolated = 0;
restart:
- spin_lock(&lru->lock);
- list_for_each_safe(item, n, &lru->list) {
+ spin_lock(&nlru->lock);
+ list_for_each_safe(item, n, &nlru->list) {
int ret;
- if (nr_to_walk-- < 0)
+ if ((*nr_to_walk)-- < 0)
break;
- ret = isolate(item, &lru->lock, cb_arg);
+ ret = isolate(item, &nlru->lock, cb_arg);
switch (ret) {
case 0: /* item removed from list */
- lru->nr_items--;
- removed++;
+ if (--nlru->nr_items == 0)
+ node_clear(nid, lru->active_nodes);
+ BUG_ON(nlru->nr_items < 0);
+ isolated++;
break;
case 1: /* item referenced, give another pass */
- list_move_tail(item, &lru->list);
+ list_move_tail(item, &nlru->list);
break;
case 2: /* item cannot be locked, skip */
break;
@@ -76,42 +111,89 @@ restart:
BUG();
}
}
- spin_unlock(&lru->lock);
- return removed;
+ spin_unlock(&nlru->lock);
+ return isolated;
+}
+
+long
+list_lru_walk(
+ struct list_lru *lru,
+ list_lru_walk_cb isolate,
+ void *cb_arg,
+ long nr_to_walk)
+{
+ long isolated = 0;
+ int nid;
+
+ for_each_node_mask(nid, lru->active_nodes) {
+ isolated += list_lru_walk_node(lru, nid, isolate,
+ cb_arg, &nr_to_walk);
+ if (nr_to_walk <= 0)
+ break;
+ }
+ return isolated;
}
EXPORT_SYMBOL_GPL(list_lru_walk);
long
-list_lru_dispose_all(
- struct list_lru *lru,
- list_lru_dispose_cb dispose)
+list_lru_dispose_all_node(
+ struct list_lru *lru,
+ int nid,
+ list_lru_dispose_cb dispose)
{
- long disposed = 0;
+ struct list_lru_node *nlru = &lru->node[nid];
LIST_HEAD(dispose_list);
+ long disposed = 0;
- spin_lock(&lru->lock);
- while (!list_empty(&lru->list)) {
- list_splice_init(&lru->list, &dispose_list);
- disposed += lru->nr_items;
- lru->nr_items = 0;
- spin_unlock(&lru->lock);
+ 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);
- spin_lock(&lru->lock);
+ spin_lock(&nlru->lock);
}
- spin_unlock(&lru->lock);
+ spin_unlock(&nlru->lock);
return disposed;
}
+long
+list_lru_dispose_all(
+ struct list_lru *lru,
+ list_lru_dispose_cb dispose)
+{
+ long disposed;
+ long total = 0;
+ int nid;
+
+ do {
+ disposed = 0;
+ for_each_node_mask(nid, lru->active_nodes) {
+ disposed += list_lru_dispose_all_node(lru, nid,
+ dispose);
+ }
+ total += disposed;
+ } while (disposed != 0);
+
+ return total;
+}
+
int
list_lru_init(
struct list_lru *lru)
{
- spin_lock_init(&lru->lock);
- INIT_LIST_HEAD(&lru->list);
- lru->nr_items = 0;
+ int i;
+ nodes_clear(lru->active_nodes);
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ spin_lock_init(&lru->node[i].lock);
+ INIT_LIST_HEAD(&lru->node[i].list);
+ lru->node[i].nr_items = 0;
+ }
return 0;
}
EXPORT_SYMBOL_GPL(list_lru_init);
--
1.7.10
--
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:[~2012-11-27 23:15 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-27 23:14 [RFC, PATCH 00/19] Numa aware LRU lists and shrinkers Dave Chinner
2012-11-27 23:14 ` [PATCH 01/19] dcache: convert dentry_stat.nr_unused to per-cpu counters Dave Chinner
2012-11-27 23:14 ` [PATCH 02/19] dentry: move to per-sb LRU locks Dave Chinner
2012-11-27 23:14 ` [PATCH 03/19] dcache: remove dentries from LRU before putting on dispose list Dave Chinner
2012-11-27 23:14 ` [PATCH 04/19] mm: new shrinker API Dave Chinner
2012-11-27 23:14 ` [PATCH 05/19] shrinker: convert superblock shrinkers to new API Dave Chinner
2012-12-20 11:06 ` Glauber Costa
2012-12-21 1:46 ` Dave Chinner
2012-12-21 10:17 ` Glauber Costa
2012-11-27 23:14 ` [PATCH 06/19] list: add a new LRU list type Dave Chinner
2012-11-28 16:10 ` Christoph Hellwig
2012-11-27 23:14 ` [PATCH 07/19] inode: convert inode lru list to generic lru list code Dave Chinner
2012-11-27 23:14 ` [PATCH 08/19] dcache: convert to use new lru list infrastructure Dave Chinner
2012-11-27 23:14 ` Dave Chinner [this message]
2012-12-20 11:21 ` [PATCH 09/19] list_lru: per-node " Glauber Costa
2012-12-21 1:54 ` Dave Chinner
2013-01-16 19:21 ` Glauber Costa
2013-01-16 22:55 ` Dave Chinner
2013-01-17 0:35 ` Glauber Costa
2013-01-17 4:22 ` Dave Chinner
2013-01-17 18:21 ` Glauber Costa
2013-01-18 0:10 ` Dave Chinner
2013-01-18 0:14 ` Glauber Costa
2013-01-18 8:11 ` Dave Chinner
2013-01-18 19:10 ` Glauber Costa
2013-01-19 0:10 ` Dave Chinner
2013-01-19 0:13 ` Glauber Costa
2013-01-18 0:51 ` Glauber Costa
2013-01-18 8:08 ` Dave Chinner
2013-01-18 19:01 ` Glauber Costa
2012-11-27 23:14 ` [PATCH 10/19] shrinker: add node awareness Dave Chinner
2012-11-27 23:14 ` [PATCH 11/19] fs: convert inode and dentry shrinking to be node aware Dave Chinner
2012-11-27 23:14 ` [PATCH 12/19] xfs: convert buftarg LRU to generic code Dave Chinner
2012-11-27 23:14 ` [PATCH 13/19] xfs: Node aware direct inode reclaim Dave Chinner
2012-11-27 23:14 ` [PATCH 14/19] xfs: use generic AG walk for background " Dave Chinner
2012-11-27 23:14 ` [PATCH 15/19] xfs: convert dquot cache lru to list_lru Dave Chinner
2012-11-28 16:17 ` Christoph Hellwig
2012-11-27 23:14 ` [PATCH 16/19] fs: convert fs shrinkers to new scan/count API Dave Chinner
2012-11-27 23:14 ` [PATCH 17/19] drivers: convert shrinkers to new count/scan API Dave Chinner
2012-11-28 1:13 ` Chris Wilson
2012-11-28 3:17 ` Dave Chinner
2012-11-28 8:21 ` Glauber Costa
2012-11-28 21:28 ` Dave Chinner
2012-11-29 10:29 ` Glauber Costa
2012-11-29 22:02 ` Dave Chinner
2013-06-07 13:37 ` Konrad Rzeszutek Wilk
2012-11-27 23:14 ` [PATCH 18/19] shrinker: convert remaining shrinkers to " Dave Chinner
2012-11-27 23:14 ` [PATCH 19/19] shrinker: Kill old ->shrink API Dave Chinner
2012-11-29 19:02 ` [RFC, PATCH 00/19] Numa aware LRU lists and shrinkers Andi Kleen
2012-11-29 22:09 ` Dave Chinner
2012-12-20 11:45 ` Glauber Costa
2012-12-21 2:50 ` Dave Chinner
2012-12-21 10:41 ` Glauber Costa
2013-01-21 16:08 ` Glauber Costa
2013-01-21 23:21 ` Dave Chinner
2013-01-23 14:36 ` Glauber Costa
2013-01-23 23:46 ` Dave Chinner
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=1354058086-27937-10-git-send-email-david@fromorbit.com \
--to=david@fromorbit.com \
--cc=glommer@parallels.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=xfs@oss.sgi.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).