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 07/19] inode: convert inode lru list to generic lru list code.
Date: Wed, 28 Nov 2012 10:14:34 +1100 [thread overview]
Message-ID: <1354058086-27937-8-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>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
fs/inode.c | 173 +++++++++++++++++++++-------------------------------
fs/super.c | 11 ++--
include/linux/fs.h | 6 +-
3 files changed, 75 insertions(+), 115 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 3624ae0..2662305 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -17,6 +17,7 @@
#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
+#include <linux/list_lru.h>
#include "internal.h"
/*
@@ -24,7 +25,7 @@
*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget()
- * inode->i_sb->s_inode_lru_lock protects:
+ * Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
@@ -37,7 +38,7 @@
*
* inode_sb_list_lock
* inode->i_lock
- * inode->i_sb->s_inode_lru_lock
+ * Inode LRU list locks
*
* bdi->wb.list_lock
* inode->i_lock
@@ -399,24 +400,14 @@ EXPORT_SYMBOL(ihold);
static void inode_lru_list_add(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (list_empty(&inode->i_lru)) {
- list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
- inode->i_sb->s_nr_inodes_unused++;
+ if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_inc(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
static void inode_lru_list_del(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_lru_lock);
- if (!list_empty(&inode->i_lru)) {
- list_del_init(&inode->i_lru);
- inode->i_sb->s_nr_inodes_unused--;
+ if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
this_cpu_dec(nr_unused);
- }
- spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/**
@@ -660,24 +651,8 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
return busy;
}
-static int can_unuse(struct inode *inode)
-{
- if (inode->i_state & ~I_REFERENCED)
- return 0;
- if (inode_has_buffers(inode))
- return 0;
- if (atomic_read(&inode->i_count))
- return 0;
- if (inode->i_data.nrpages)
- return 0;
- return 1;
-}
-
/*
- * Walk the superblock inode LRU for freeable inodes and attempt to free them.
- * This is called from the superblock shrinker function with a number of inodes
- * 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().
+ * Isolate the inode from the LRU in preparation for freeing it.
*
* Any inodes which are pinned purely because of attached pagecache have their
* pagecache removed. If the inode has metadata buffers attached to
@@ -691,90 +666,78 @@ static int can_unuse(struct inode *inode)
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
-long prune_icache_sb(struct super_block *sb, long nr_to_scan)
+static int inode_lru_isolate(struct list_head *item, spinlock_t *lru_lock,
+ void *arg)
{
- LIST_HEAD(freeable);
- long nr_scanned;
- long freed = 0;
- unsigned long reap = 0;
+ struct list_head *freeable = arg;
+ struct inode *inode = container_of(item, struct inode, i_lru);
- spin_lock(&sb->s_inode_lru_lock);
- for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
- struct inode *inode;
+ /*
+ * we are inverting the lru lock/inode->i_lock here, so use a trylock.
+ * If we fail to get the lock, just skip it.
+ */
+ if (!spin_trylock(&inode->i_lock))
+ return 2;
- if (list_empty(&sb->s_inode_lru))
- break;
+ /*
+ * Referenced or dirty inodes are still in use. Give them another pass
+ * through the LRU as we canot reclaim them now.
+ */
+ if (atomic_read(&inode->i_count) ||
+ (inode->i_state & ~I_REFERENCED)) {
+ list_del_init(&inode->i_lru);
+ spin_unlock(&inode->i_lock);
+ this_cpu_dec(nr_unused);
+ return 0;
+ }
- inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
+ /* recently referenced inodes get one more pass */
+ if (inode->i_state & I_REFERENCED) {
+ inode->i_state &= ~I_REFERENCED;
+ spin_unlock(&inode->i_lock);
+ return 1;
+ }
- /*
- * we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
- * so use a trylock. If we fail to get the lock, just move the
- * inode to the back of the list so we don't spin on it.
- */
- if (!spin_trylock(&inode->i_lock)) {
- list_move_tail(&inode->i_lru, &sb->s_inode_lru);
- continue;
+ if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(lru_lock);
+ if (remove_inode_buffers(inode)) {
+ unsigned long reap;
+ reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_INODESTEAL, reap);
+ else
+ __count_vm_events(PGINODESTEAL, reap);
+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += reap;
}
+ iput(inode);
+ return 3;
+ }
- /*
- * Referenced or dirty inodes are still in use. Give them
- * another pass through the LRU as we canot reclaim them now.
- */
- if (atomic_read(&inode->i_count) ||
- (inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_lru);
- spin_unlock(&inode->i_lock);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- continue;
- }
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state |= I_FREEING;
+ spin_unlock(&inode->i_lock);
- /* recently referenced inodes get one more pass */
- if (inode->i_state & I_REFERENCED) {
- inode->i_state &= ~I_REFERENCED;
- list_move(&inode->i_lru, &sb->s_inode_lru);
- spin_unlock(&inode->i_lock);
- continue;
- }
- if (inode_has_buffers(inode) || inode->i_data.nrpages) {
- __iget(inode);
- spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_lru_lock);
- if (remove_inode_buffers(inode))
- reap += invalidate_mapping_pages(&inode->i_data,
- 0, -1);
- iput(inode);
- spin_lock(&sb->s_inode_lru_lock);
-
- if (inode != list_entry(sb->s_inode_lru.next,
- struct inode, i_lru))
- continue; /* wrong inode or list_empty */
- /* avoid lock inversions with trylock */
- if (!spin_trylock(&inode->i_lock))
- continue;
- if (!can_unuse(inode)) {
- spin_unlock(&inode->i_lock);
- continue;
- }
- }
- WARN_ON(inode->i_state & I_NEW);
- inode->i_state |= I_FREEING;
- spin_unlock(&inode->i_lock);
+ list_move(&inode->i_lru, freeable);
+ this_cpu_dec(nr_unused);
+ return 0;
+}
- list_move(&inode->i_lru, &freeable);
- sb->s_nr_inodes_unused--;
- this_cpu_dec(nr_unused);
- freed++;
- }
- if (current_is_kswapd())
- __count_vm_events(KSWAPD_INODESTEAL, reap);
- else
- __count_vm_events(PGINODESTEAL, reap);
- spin_unlock(&sb->s_inode_lru_lock);
- if (current->reclaim_state)
- current->reclaim_state->reclaimed_slab += reap;
+/*
+ * Walk the superblock inode LRU for freeable inodes and attempt to free them.
+ * This is called from the superblock shrinker function with a number of inodes
+ * 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)
+{
+ LIST_HEAD(freeable);
+ long freed;
+ freed = list_lru_walk(&sb->s_inode_lru, inode_lru_isolate,
+ &freeable, nr_to_scan);
dispose_list(&freeable);
return freed;
}
diff --git a/fs/super.c b/fs/super.c
index fda6f12..a2f09c8 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -77,12 +77,12 @@ static long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
if (sb->s_op && sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb);
- total_objects = sb->s_nr_dentry_unused +
- sb->s_nr_inodes_unused + fs_objects + 1;
+ inodes = list_lru_count(&sb->s_inode_lru);
+ total_objects = sb->s_nr_dentry_unused + inodes + fs_objects + 1;
/* proportion the scan between the caches */
dentries = (sc->nr_to_scan * sb->s_nr_dentry_unused) / total_objects;
- inodes = (sc->nr_to_scan * sb->s_nr_inodes_unused) / total_objects;
+ inodes = (sc->nr_to_scan * inodes) / total_objects;
/*
* prune the dcache first as the icache is pinned by it, then
@@ -114,7 +114,7 @@ static long super_cache_count(struct shrinker *shrink, struct shrink_control *sc
total_objects = sb->s_op->nr_cached_objects(sb);
total_objects += sb->s_nr_dentry_unused;
- total_objects += sb->s_nr_inodes_unused;
+ total_objects += list_lru_count(&sb->s_inode_lru);
total_objects = (total_objects / 100) * sysctl_vfs_cache_pressure;
drop_super(sb);
@@ -195,8 +195,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_LIST_HEAD(&s->s_inodes);
INIT_LIST_HEAD(&s->s_dentry_lru);
spin_lock_init(&s->s_dentry_lru_lock);
- INIT_LIST_HEAD(&s->s_inode_lru);
- spin_lock_init(&s->s_inode_lru_lock);
+ list_lru_init(&s->s_inode_lru);
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 13833e3..36b7db5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -10,6 +10,7 @@
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
+#include <linux/list_lru.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/init.h>
@@ -1268,10 +1269,7 @@ struct super_block {
struct list_head s_dentry_lru; /* unused dentry lru */
int s_nr_dentry_unused; /* # of dentry on lru */
- /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */
- spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp;
- struct list_head s_inode_lru; /* unused inode lru */
- int s_nr_inodes_unused; /* # of inodes on lru */
+ struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
--
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 23:14 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 ` Dave Chinner [this message]
2012-11-27 23:14 ` [PATCH 08/19] dcache: convert to use new lru list infrastructure Dave Chinner
2012-11-27 23:14 ` [PATCH 09/19] list_lru: per-node " Dave Chinner
2012-12-20 11:21 ` 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=1354058086-27937-8-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).