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>,
	Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
Subject: [PATCH v9 11/35] list_lru: per-node list infrastructure
Date: Thu, 30 May 2013 14:35:57 +0400	[thread overview]
Message-ID: <1369910181-20026-12-git-send-email-glommer@openvz.org> (raw)
In-Reply-To: <1369910181-20026-1-git-send-email-glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>

From: Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>

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.

Note:
We use a fixed-size array for the node LRU, this struct can be very big
if MAX_NUMNODES is big. If this becomes a problem this is fixable by
turning this into a pointer and dynamically allocating this to
nr_node_ids. This quantity is firwmare-provided, and still would provide
room for all nodes at the cost of a pointer lookup and an extra
allocation. Because that allocation will most likely come from a
different slab cache than the main structure holding this structure, we
may very well fail.

[ glommer: fixed warnings, added note about node lru ]
Signed-off-by: Dave Chinner <dchinner-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Signed-off-by: Glauber Costa <glommer-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
Reviewed-by: Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Acked-by: Mel Gorman <mgorman-l3A5Bk7waGM@public.gmane.org>
---
 include/linux/list_lru.h |  24 +++++--
 lib/list_lru.c           | 161 +++++++++++++++++++++++++++++++++++------------
 2 files changed, 139 insertions(+), 46 deletions(-)

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 4f82a57..668f1f1 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -8,6 +8,7 @@
 #define _LRU_LIST_H
 
 #include <linux/list.h>
+#include <linux/nodemask.h>
 
 enum lru_status {
 	LRU_REMOVED,		/* item removed from list */
@@ -17,20 +18,31 @@ enum lru_status {
 				   internally, but has to return locked. */
 };
 
-struct list_lru {
+struct list_lru_node {
 	spinlock_t		lock;
 	struct list_head	list;
 	long			nr_items;
+} ____cacheline_aligned_in_smp;
+
+struct list_lru {
+	/*
+	 * Because we use a fixed-size array, this struct can be very big if
+	 * MAX_NUMNODES is big. If this becomes a problem this is fixable by
+	 * turning this into a pointer and dynamically allocating this to
+	 * nr_node_ids. This quantity is firwmare-provided, and still would
+	 * provide room for all nodes at the cost of a pointer lookup and an
+	 * extra allocation. Because that allocation will most likely come from
+	 * a different slab cache than the main structure holding this
+	 * structure, we may very well fail.
+	 */
+	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 unsigned long list_lru_count(struct list_lru *lru)
-{
-	return lru->nr_items;
-}
+unsigned long list_lru_count(struct list_lru *lru);
 
 typedef enum lru_status
 (*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 3127edd..7611df7 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);
@@ -30,41 +36,69 @@ 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);
 
 unsigned long
-list_lru_walk(
-	struct list_lru *lru,
-	list_lru_walk_cb isolate,
-	void		*cb_arg,
-	unsigned 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 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)
+{
+	struct list_lru_node	*nlru = &lru->node[nid];
 	struct list_head *item, *n;
-	unsigned long removed = 0;
+	unsigned long isolated = 0;
 
-	spin_lock(&lru->lock);
-	list_for_each_safe(item, n, &lru->list) {
+	spin_lock(&nlru->lock);
+	list_for_each_safe(item, n, &nlru->list) {
 		enum lru_status ret;
 		bool first_pass = true;
 restart:
-		ret = isolate(item, &lru->lock, cb_arg);
+		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
 		case LRU_REMOVED:
-			lru->nr_items--;
-			removed++;
+			if (--nlru->nr_items == 0)
+				node_clear(nid, lru->active_nodes);
+			BUG_ON(nlru->nr_items < 0);
+			isolated++;
 			break;
 		case LRU_ROTATE:
-			list_move_tail(item, &lru->list);
+			list_move_tail(item, &nlru->list);
 			break;
 		case LRU_SKIP:
 			break;
@@ -77,46 +111,93 @@ restart:
 			BUG();
 		}
 
-		if (nr_to_walk-- == 0)
+		if ((*nr_to_walk)-- == 0)
 			break;
 
 	}
-	spin_unlock(&lru->lock);
-	return removed;
+	spin_unlock(&nlru->lock);
+	return isolated;
 }
-EXPORT_SYMBOL_GPL(list_lru_walk);
 
 unsigned long
-list_lru_dispose_all(
-	struct list_lru *lru,
-	list_lru_dispose_cb dispose)
+list_lru_walk(
+	struct list_lru	*lru,
+	list_lru_walk_cb isolate,
+	void		*cb_arg,
+	unsigned long	nr_to_walk)
 {
-	unsigned long disposed = 0;
+	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);
+
+static unsigned long
+list_lru_dispose_all_node(
+	struct list_lru		*lru,
+	int			nid,
+	list_lru_dispose_cb	dispose)
+{
+	struct list_lru_node	*nlru = &lru->node[nid];
 	LIST_HEAD(dispose_list);
+	unsigned 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;
 }
 
+unsigned long
+list_lru_dispose_all(
+	struct list_lru		*lru,
+	list_lru_dispose_cb	dispose)
+{
+	unsigned long disposed;
+	unsigned 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);
-- 
1.8.1.4

  parent reply	other threads:[~2013-05-30 10:35 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
     [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   ` Glauber Costa [this message]
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   ` [PATCH v9 28/35] list_lru: per-memcg walks Glauber Costa
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 20/35] drivers: convert shrinkers to new count/scan API 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=1369910181-20026-12-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 \
    /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).