From: Dave Chinner <david@fromorbit.com>
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 05/19] fs: inode split IO and LRU lists
Date: Sat, 16 Oct 2010 19:13:59 +1100 [thread overview]
Message-ID: <1287216853-17634-6-git-send-email-david@fromorbit.com> (raw)
In-Reply-To: <1287216853-17634-1-git-send-email-david@fromorbit.com>
From: Nick Piggin <npiggin@suse.de>
The use of the same inode list structure (inode->i_list) for two
different list constructs with different lifecycles and purposes
makes it impossible to separate the locking of the different
operations. Therefore, to enable the separation of the locking of
the writeback and reclaim lists, split the inode->i_list into two
separate lists dedicated to their specific tracking functions.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/block_dev.c | 4 ++--
fs/fs-writeback.c | 27 ++++++++++++++-------------
fs/inode.c | 40 ++++++++++++++++++++++------------------
fs/nilfs2/mdt.c | 3 ++-
include/linux/fs.h | 3 ++-
include/linux/writeback.h | 1 -
mm/backing-dev.c | 6 +++---
7 files changed, 45 insertions(+), 39 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 501eab5..63b1c4c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -58,8 +58,8 @@ static void bdev_inode_switch_bdi(struct inode *inode,
{
spin_lock(&inode_lock);
inode->i_data.backing_dev_info = dst;
- if (inode->i_state & I_DIRTY)
- list_move(&inode->i_list, &dst->wb.b_dirty);
+ if (!list_empty(&inode->i_wb_list))
+ list_move(&inode->i_wb_list, &dst->wb.b_dirty);
spin_unlock(&inode_lock);
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 33e9857..92d73b6 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -172,11 +172,11 @@ static void redirty_tail(struct inode *inode)
if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
- tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+ tail = list_entry(wb->b_dirty.next, struct inode, i_wb_list);
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &wb->b_dirty);
+ list_move(&inode->i_wb_list, &wb->b_dirty);
}
/*
@@ -186,7 +186,7 @@ static void requeue_io(struct inode *inode)
{
struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
- list_move(&inode->i_list, &wb->b_more_io);
+ list_move(&inode->i_wb_list, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -227,14 +227,15 @@ static void move_expired_inodes(struct list_head *delaying_queue,
int do_sb_sort = 0;
while (!list_empty(delaying_queue)) {
- inode = list_entry(delaying_queue->prev, struct inode, i_list);
+ inode = list_entry(delaying_queue->prev,
+ struct inode, i_wb_list);
if (older_than_this &&
inode_dirtied_after(inode, *older_than_this))
break;
if (sb && sb != inode->i_sb)
do_sb_sort = 1;
sb = inode->i_sb;
- list_move(&inode->i_list, &tmp);
+ list_move(&inode->i_wb_list, &tmp);
}
/* just one sb in list, splice to dispatch_queue and we're done */
@@ -245,12 +246,12 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/* Move inodes from one superblock together */
while (!list_empty(&tmp)) {
- inode = list_entry(tmp.prev, struct inode, i_list);
+ inode = list_entry(tmp.prev, struct inode, i_wb_list);
sb = inode->i_sb;
list_for_each_prev_safe(pos, node, &tmp) {
- inode = list_entry(pos, struct inode, i_list);
+ inode = list_entry(pos, struct inode, i_wb_list);
if (inode->i_sb == sb)
- list_move(&inode->i_list, dispatch_queue);
+ list_move(&inode->i_wb_list, dispatch_queue);
}
}
}
@@ -415,7 +416,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
* does not move dirty inodes to the LRU and dirty
* inodes are removed from the LRU during scanning.
*/
- list_del_init(&inode->i_list);
+ list_del_init(&inode->i_wb_list);
if (!atomic_read(&inode->i_count))
inode_lru_list_add(inode);
}
@@ -466,7 +467,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
while (!list_empty(&wb->b_io)) {
long pages_skipped;
struct inode *inode = list_entry(wb->b_io.prev,
- struct inode, i_list);
+ struct inode, i_wb_list);
if (inode->i_sb != sb) {
if (only_this_sb) {
@@ -537,7 +538,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
while (!list_empty(&wb->b_io)) {
struct inode *inode = list_entry(wb->b_io.prev,
- struct inode, i_list);
+ struct inode, i_wb_list);
struct super_block *sb = inode->i_sb;
if (!pin_sb_for_writeback(sb)) {
@@ -676,7 +677,7 @@ static long wb_writeback(struct bdi_writeback *wb,
spin_lock(&inode_lock);
if (!list_empty(&wb->b_more_io)) {
inode = list_entry(wb->b_more_io.prev,
- struct inode, i_list);
+ struct inode, i_wb_list);
trace_wbc_writeback_wait(&wbc, wb->bdi);
inode_wait_for_writeback(inode);
}
@@ -990,7 +991,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
}
inode->dirtied_when = jiffies;
- list_move(&inode->i_list, &bdi->wb.b_dirty);
+ list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
}
}
out:
diff --git a/fs/inode.c b/fs/inode.c
index 5dd74b4..fd65368 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -72,7 +72,7 @@ static unsigned int i_hash_shift __read_mostly;
* allowing for low-overhead inode sync() operations.
*/
-LIST_HEAD(inode_unused);
+static LIST_HEAD(inode_lru);
static struct hlist_head *inode_hashtable __read_mostly;
/*
@@ -272,6 +272,7 @@ EXPORT_SYMBOL(__destroy_inode);
void destroy_inode(struct inode *inode)
{
+ BUG_ON(!list_empty(&inode->i_lru));
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
@@ -290,7 +291,8 @@ void inode_init_once(struct inode *inode)
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
- INIT_LIST_HEAD(&inode->i_list);
+ INIT_LIST_HEAD(&inode->i_wb_list);
+ INIT_LIST_HEAD(&inode->i_lru);
INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
spin_lock_init(&inode->i_data.tree_lock);
spin_lock_init(&inode->i_data.i_mmap_lock);
@@ -322,14 +324,16 @@ void __iget(struct inode *inode)
void inode_lru_list_add(struct inode *inode)
{
- list_add(&inode->i_list, &inode_unused);
- percpu_counter_inc(&nr_inodes_unused);
+ if (list_empty(&inode->i_lru)) {
+ list_add(&inode->i_lru, &inode_lru);
+ percpu_counter_inc(&nr_inodes_unused);
+ }
}
void inode_lru_list_del(struct inode *inode)
{
- if (!list_empty(&inode->i_list)) {
- list_del_init(&inode->i_list);
+ if (!list_empty(&inode->i_lru)) {
+ list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
}
}
@@ -375,8 +379,8 @@ static void dispose_list(struct list_head *head)
while (!list_empty(head)) {
struct inode *inode;
- inode = list_first_entry(head, struct inode, i_list);
- list_del_init(&inode->i_list);
+ inode = list_first_entry(head, struct inode, i_lru);
+ list_del_init(&inode->i_lru);
evict(inode);
@@ -421,7 +425,7 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
if (!atomic_read(&inode->i_count)) {
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
- list_move(&inode->i_list, dispose);
+ list_move(&inode->i_lru, dispose);
percpu_counter_dec(&nr_inodes_unused);
continue;
}
@@ -496,10 +500,10 @@ static void prune_icache(int nr_to_scan)
for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
struct inode *inode;
- if (list_empty(&inode_unused))
+ if (list_empty(&inode_lru))
break;
- inode = list_entry(inode_unused.prev, struct inode, i_list);
+ inode = list_entry(inode_lru.prev, struct inode, i_lru);
/*
* Referenced or dirty inodes are still in use. Give them
@@ -507,14 +511,14 @@ static void prune_icache(int nr_to_scan)
*/
if (atomic_read(&inode->i_count) ||
(inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_list);
+ list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
continue;
}
/* recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
- list_move(&inode->i_list, &inode_unused);
+ list_move(&inode->i_lru, &inode_lru);
inode->i_state &= ~I_REFERENCED;
continue;
}
@@ -533,11 +537,12 @@ static void prune_icache(int nr_to_scan)
* on it.
*/
if (!can_unuse(inode)) {
- list_move(&inode->i_list, &inode_unused);
+ list_move(&inode->i_lru, &inode_lru);
continue;
}
}
- list_move(&inode->i_list, &freeable);
+ list_move(&inode->i_lru, &freeable);
+ list_del_init(&inode->i_wb_list);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
percpu_counter_dec(&nr_inodes_unused);
@@ -1268,10 +1273,8 @@ static void iput_final(struct inode *inode)
if (!drop) {
if (sb->s_flags & MS_ACTIVE) {
inode->i_state |= I_REFERENCED;
- if (!(inode->i_state & (I_DIRTY|I_SYNC))) {
- list_del_init(&inode->i_list);
+ if (!(inode->i_state & (I_DIRTY|I_SYNC)))
inode_lru_list_add(inode);
- }
spin_unlock(&inode_lock);
return;
}
@@ -1284,6 +1287,7 @@ static void iput_final(struct inode *inode)
inode->i_state &= ~I_WILL_FREE;
hlist_del_init(&inode->i_hash);
}
+ list_del_init(&inode->i_wb_list);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index d01aff4..62756b4 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -504,7 +504,8 @@ nilfs_mdt_new_common(struct the_nilfs *nilfs, struct super_block *sb,
#endif
inode->dirtied_when = 0;
- INIT_LIST_HEAD(&inode->i_list);
+ INIT_LIST_HEAD(&inode->i_wb_list);
+ INIT_LIST_HEAD(&inode->i_lru);
INIT_LIST_HEAD(&inode->i_sb_list);
inode->i_state = 0;
#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index af1d516..90d2b47 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -725,7 +725,8 @@ struct posix_acl;
struct inode {
struct hlist_node i_hash;
- struct list_head i_list; /* backing dev IO list */
+ struct list_head i_wb_list; /* backing dev IO list */
+ struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
struct list_head i_dentry;
unsigned long i_ino;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index f956b66..242b6f8 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -10,7 +10,6 @@
struct backing_dev_info;
extern spinlock_t inode_lock;
-extern struct list_head inode_unused;
/*
* fs/fs-writeback.c
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 65d4204..15d5097 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -74,11 +74,11 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
nr_wb = nr_dirty = nr_io = nr_more_io = 0;
spin_lock(&inode_lock);
- list_for_each_entry(inode, &wb->b_dirty, i_list)
+ list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
nr_dirty++;
- list_for_each_entry(inode, &wb->b_io, i_list)
+ list_for_each_entry(inode, &wb->b_io, i_wb_list)
nr_io++;
- list_for_each_entry(inode, &wb->b_more_io, i_list)
+ list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
nr_more_io++;
spin_unlock(&inode_lock);
--
1.7.1
next prev parent reply other threads:[~2010-10-16 8:13 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-16 8:13 Inode Lock Scalability V4 Dave Chinner
2010-10-16 8:13 ` [PATCH 01/19] fs: switch bdev inode bdi's correctly Dave Chinner
2010-10-16 9:30 ` Nick Piggin
2010-10-16 16:31 ` Christoph Hellwig
2010-10-16 8:13 ` [PATCH 02/19] kernel: add bl_list Dave Chinner
2010-10-16 9:51 ` Nick Piggin
2010-10-16 16:32 ` Christoph Hellwig
2010-10-16 8:13 ` [PATCH 03/19] fs: Convert nr_inodes and nr_unused to per-cpu counters Dave Chinner
2010-10-16 8:29 ` Eric Dumazet
2010-10-16 10:04 ` Dave Chinner
2010-10-16 10:27 ` Eric Dumazet
2010-10-16 17:26 ` Peter Zijlstra
2010-10-17 1:09 ` Dave Chinner
2010-10-17 1:12 ` Christoph Hellwig
2010-10-17 2:16 ` Dave Chinner
2010-10-16 8:13 ` [PATCH 04/19] fs: Implement lazy LRU updates for inodes Dave Chinner
2010-10-16 9:29 ` Nick Piggin
2010-10-16 16:59 ` Christoph Hellwig
2010-10-16 17:29 ` Nick Piggin
2010-10-16 17:34 ` Nick Piggin
2010-10-17 0:47 ` Christoph Hellwig
2010-10-17 0:47 ` Christoph Hellwig
2010-10-17 2:09 ` Nick Piggin
2010-10-17 1:53 ` Dave Chinner
2010-10-16 8:13 ` Dave Chinner [this message]
2010-10-16 8:14 ` [PATCH 06/19] fs: Clean up inode reference counting Dave Chinner
2010-10-16 8:14 ` [PATCH 07/19] exofs: use iput() for inode reference count decrements Dave Chinner
2010-10-16 8:14 ` [PATCH 08/19] fs: rework icount to be a locked variable Dave Chinner
2010-10-16 8:14 ` [PATCH 09/19] fs: Factor inode hash operations into functions Dave Chinner
2010-10-16 8:14 ` [PATCH 10/19] fs: Introduce per-bucket inode hash locks Dave Chinner
2010-10-16 8:14 ` [PATCH 11/19] fs: add a per-superblock lock for the inode list Dave Chinner
2010-10-16 8:14 ` [PATCH 12/19] fs: split locking of inode writeback and LRU lists Dave Chinner
2010-10-16 8:14 ` [PATCH 13/19] fs: Protect inode->i_state with the inode->i_lock Dave Chinner
2010-10-16 8:14 ` [PATCH 14/19] fs: introduce a per-cpu last_ino allocator Dave Chinner
2010-10-16 8:14 ` [PATCH 15/19] fs: Make iunique independent of inode_lock Dave Chinner
2010-10-16 8:14 ` [PATCH 16/19] fs: icache remove inode_lock Dave Chinner
2010-10-16 8:14 ` [PATCH 17/19] fs: Reduce inode I_FREEING and factor inode disposal Dave Chinner
2010-10-17 1:30 ` Christoph Hellwig
2010-10-17 2:49 ` Nick Piggin
2010-10-17 4:13 ` Dave Chinner
2010-10-17 4:35 ` Nick Piggin
2010-10-17 5:13 ` Nick Piggin
2010-10-17 6:52 ` Dave Chinner
2010-10-17 7:05 ` Nick Piggin
2010-10-17 23:39 ` Dave Chinner
2010-10-18 21:27 ` Sage Weil
2010-10-19 3:54 ` Nick Piggin
2010-10-16 8:14 ` [PATCH 18/19] fs: split __inode_add_to_list Dave Chinner
2010-10-16 8:14 ` [PATCH 19/19] fs: do not assign default i_ino in new_inode Dave Chinner
2010-10-16 9:09 ` Eric Dumazet
2010-10-16 16:35 ` Christoph Hellwig
2010-10-18 9:11 ` Eric Dumazet
2010-10-18 14:48 ` Christoph Hellwig
2010-10-16 17:55 ` Inode Lock Scalability V4 Nick Piggin
2010-10-17 2:47 ` Dave Chinner
2010-10-17 2:55 ` Nick Piggin
2010-10-17 2:57 ` Nick Piggin
2010-10-17 6:10 ` Dave Chinner
2010-10-17 6:34 ` Nick Piggin
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=1287216853-17634-6-git-send-email-david@fromorbit.com \
--to=david@fromorbit.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.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).