From: npiggin@suse.de
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: John Stultz <johnstul@us.ibm.com>, Frank Mayhar <fmayhar@google.com>
Subject: [patch 48/52] fs: icache split IO and LRU lists
Date: Thu, 24 Jun 2010 13:03:00 +1000 [thread overview]
Message-ID: <20100624030733.354313412@suse.de> (raw)
In-Reply-To: 20100624030212.676457061@suse.de
[-- Attachment #1: fs-inode-split-lists.patch --]
[-- Type: text/plain, Size: 9887 bytes --]
Split inode reclaim and writeback lists in preparation to scale them up
(per-bdi locking for i_io and per-zone locking for i_lru)
Signed-off-by: Nick Piggin <npiggin@suse.de>
--
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c
+++ linux-2.6/fs/fs-writeback.c
@@ -291,11 +291,11 @@ static void redirty_tail(struct inode *i
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_io);
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_io, &wb->b_dirty);
}
/*
@@ -306,7 +306,7 @@ static void requeue_io(struct inode *ino
struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
assert_spin_locked(&wb_inode_list_lock);
- list_move(&inode->i_list, &wb->b_more_io);
+ list_move(&inode->i_io, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -348,14 +348,14 @@ static void move_expired_inodes(struct l
assert_spin_locked(&wb_inode_list_lock);
while (!list_empty(delaying_queue)) {
- inode = list_entry(delaying_queue->prev, struct inode, i_list);
+ inode = list_entry(delaying_queue->prev, struct inode, i_io);
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_io, &tmp);
}
/* just one sb in list, splice to dispatch_queue and we're done */
@@ -366,12 +366,12 @@ static void move_expired_inodes(struct l
/* 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_io);
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_io);
if (inode->i_sb == sb)
- list_move(&inode->i_list, dispatch_queue);
+ list_move(&inode->i_io, dispatch_queue);
}
}
}
@@ -556,7 +556,11 @@ select_queue:
}
} else {
/* The inode is clean */
- list_move(&inode->i_list, &inode_unused);
+ list_del_init(&inode->i_io);
+ if (list_empty(&inode->i_lru)) {
+ list_add(&inode->i_lru, &inode_unused);
+ inodes_stat.nr_unused++;
+ }
}
}
inode_sync_complete(inode);
@@ -623,7 +627,7 @@ again:
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_io);
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&wb_inode_list_lock);
spin_lock(&wb_inode_list_lock);
@@ -696,7 +700,7 @@ again:
while (!list_empty(&wb->b_io)) {
struct inode *inode = list_entry(wb->b_io.prev,
- struct inode, i_list);
+ struct inode, i_io);
struct super_block *sb = inode->i_sb;
enum sb_pin_state state;
@@ -845,7 +849,7 @@ retry:
spin_lock(&wb_inode_list_lock);
if (!list_empty(&wb->b_more_io)) {
inode = list_entry(wb->b_more_io.prev,
- struct inode, i_list);
+ struct inode, i_io);
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&wb_inode_list_lock);
goto retry;
@@ -1164,7 +1168,7 @@ void __mark_inode_dirty(struct inode *in
inode->dirtied_when = jiffies;
spin_lock(&wb_inode_list_lock);
- list_move(&inode->i_list, &wb->b_dirty);
+ list_move(&inode->i_io, &wb->b_dirty);
spin_unlock(&wb_inode_list_lock);
}
}
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h
+++ linux-2.6/include/linux/fs.h
@@ -726,7 +726,8 @@ struct posix_acl;
struct inode {
struct hlist_bl_node i_hash;
- struct list_head i_list; /* backing dev IO list */
+ struct list_head i_io; /* backing dev IO list */
+ struct list_head i_lru;
struct list_head i_sb_list;
union {
struct list_head i_dentry;
Index: linux-2.6/mm/backing-dev.c
===================================================================
--- linux-2.6.orig/mm/backing-dev.c
+++ linux-2.6/mm/backing-dev.c
@@ -80,11 +80,11 @@ static int bdi_debug_stats_show(struct s
spin_lock(&wb_inode_list_lock);
list_for_each_entry(wb, &bdi->wb_list, list) {
nr_wb++;
- list_for_each_entry(inode, &wb->b_dirty, i_list)
+ list_for_each_entry(inode, &wb->b_dirty, i_io)
nr_dirty++;
- list_for_each_entry(inode, &wb->b_io, i_list)
+ list_for_each_entry(inode, &wb->b_io, i_io)
nr_io++;
- list_for_each_entry(inode, &wb->b_more_io, i_list)
+ list_for_each_entry(inode, &wb->b_more_io, i_io)
nr_more_io++;
}
spin_unlock(&wb_inode_list_lock);
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c
+++ linux-2.6/fs/inode.c
@@ -35,12 +35,13 @@
* inode_hash_bucket lock protects:
* inode hash table, i_hash
* wb_inode_list_lock protects:
- * inode_in_use, inode_unused, b_io, b_more_io, b_dirty, i_list
+ * inode_in_use, inode_unused, b_io, b_more_io, b_dirty, i_io, i_lru
* inode->i_lock protects:
* i_state
* i_count
* i_hash
- * i_list
+ * i_io
+ * i_lru
* i_sb_list
*
* Ordering:
@@ -313,6 +314,7 @@ static void i_callback(struct rcu_head *
void destroy_inode(struct inode *inode)
{
+ BUG_ON(!list_empty(&inode->i_io));
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
@@ -331,7 +333,8 @@ void inode_init_once(struct inode *inode
INIT_HLIST_BL_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_io);
+ 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);
@@ -401,8 +404,8 @@ static void dispose_list(struct list_hea
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);
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
@@ -436,13 +439,14 @@ static int invalidate_sb_inodes(struct s
invalidate_inode_buffers(inode);
if (!inode->i_count) {
spin_lock(&wb_inode_list_lock);
- list_del(&inode->i_list);
+ list_del_init(&inode->i_io);
+ list_del(&inode->i_lru);
inodes_stat.nr_unused--;
spin_unlock(&wb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
- list_add(&inode->i_list, dispose);
+ list_add(&inode->i_lru, dispose);
continue;
}
spin_unlock(&inode->i_lock);
@@ -511,26 +515,26 @@ again:
if (list_empty(&inode_unused))
break;
- inode = list_entry(inode_unused.prev, struct inode, i_list);
+ inode = list_entry(inode_unused.prev, struct inode, i_lru);
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&wb_inode_list_lock);
goto again;
}
if (inode->i_count || (inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_list);
+ list_del_init(&inode->i_lru);
spin_unlock(&inode->i_lock);
inodes_stat.nr_unused--;
continue;
}
if (inode->i_state) {
- list_move(&inode->i_list, &inode_unused);
+ list_move(&inode->i_lru, &inode_unused);
inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
continue;
}
if (inode_has_buffers(inode) || inode->i_data.nrpages) {
- list_move(&inode->i_list, &inode_unused);
+ list_move(&inode->i_lru, &inode_unused);
spin_unlock(&wb_inode_list_lock);
__iget(inode);
spin_unlock(&inode->i_lock);
@@ -542,7 +546,7 @@ again:
spin_lock(&wb_inode_list_lock);
continue;
}
- list_move(&inode->i_list, &freeable);
+ list_move(&inode->i_lru, &freeable);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
@@ -1395,11 +1399,15 @@ void generic_delete_inode(struct inode *
{
const struct super_operations *op = inode->i_sb->s_op;
- if (!list_empty(&inode->i_list)) {
+ if (!list_empty(&inode->i_lru)) {
spin_lock(&wb_inode_list_lock);
- list_del_init(&inode->i_list);
- if (!inode->i_state)
- inodes_stat.nr_unused--;
+ list_del_init(&inode->i_lru);
+ inodes_stat.nr_unused--;
+ spin_unlock(&wb_inode_list_lock);
+ }
+ if (!list_empty(&inode->i_io)) {
+ spin_lock(&wb_inode_list_lock);
+ list_del_init(&inode->i_io);
spin_unlock(&wb_inode_list_lock);
}
inode_sb_list_del(inode);
@@ -1451,9 +1459,9 @@ int generic_detach_inode(struct inode *i
if (sb->s_flags & MS_ACTIVE) {
inode->i_state |= I_REFERENCED;
if (!(inode->i_state & (I_DIRTY|I_SYNC)) &&
- list_empty(&inode->i_list)) {
+ list_empty(&inode->i_lru)) {
spin_lock(&wb_inode_list_lock);
- list_add(&inode->i_list, &inode_unused);
+ list_add(&inode->i_lru, &inode_unused);
inodes_stat.nr_unused++;
spin_unlock(&wb_inode_list_lock);
}
@@ -1469,11 +1477,15 @@ int generic_detach_inode(struct inode *i
inode->i_state &= ~I_WILL_FREE;
__remove_inode_hash(inode);
}
- if (!list_empty(&inode->i_list)) {
+ if (!list_empty(&inode->i_lru)) {
spin_lock(&wb_inode_list_lock);
- list_del_init(&inode->i_list);
- if (!inode->i_state)
- inodes_stat.nr_unused--;
+ list_del_init(&inode->i_lru);
+ inodes_stat.nr_unused--;
+ spin_unlock(&wb_inode_list_lock);
+ }
+ if (!list_empty(&inode->i_io)) {
+ spin_lock(&wb_inode_list_lock);
+ list_del_init(&inode->i_io);
spin_unlock(&wb_inode_list_lock);
}
inode_sb_list_del(inode);
next prev parent reply other threads:[~2010-06-24 3:17 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-24 3:02 [patch 00/52] vfs scalability patches updated npiggin
2010-06-24 3:02 ` [patch 01/52] kernel: add bl_list npiggin
2010-06-24 6:04 ` Eric Dumazet
2010-06-24 14:42 ` Nick Piggin
2010-06-24 16:01 ` Eric Dumazet
2010-06-28 21:37 ` Paul E. McKenney
2010-06-29 6:30 ` Nick Piggin
2010-06-24 3:02 ` [patch 02/52] fs: fix superblock iteration race npiggin
2010-06-29 13:02 ` Christoph Hellwig
2010-06-29 14:56 ` Nick Piggin
2010-06-29 17:35 ` Linus Torvalds
2010-06-29 17:41 ` Nick Piggin
2010-06-29 17:52 ` Linus Torvalds
2010-06-29 17:58 ` Linus Torvalds
2010-06-29 20:04 ` Chris Clayton
2010-06-29 20:14 ` Nick Piggin
2010-06-29 20:38 ` Chris Clayton
2010-06-30 7:13 ` Chris Clayton
2010-06-30 12:51 ` Al Viro
2010-06-24 3:02 ` [patch 03/52] fs: fs_struct rwlock to spinlock npiggin
2010-06-24 3:02 ` [patch 04/52] fs: cleanup files_lock npiggin
2010-06-24 3:02 ` [patch 05/52] lglock: introduce special lglock and brlock spin locks npiggin
2010-06-24 18:15 ` Thomas Gleixner
2010-06-25 6:22 ` Nick Piggin
2010-06-25 9:50 ` Thomas Gleixner
2010-06-25 10:11 ` Nick Piggin
2010-06-24 3:02 ` [patch 06/52] fs: scale files_lock npiggin
2010-06-24 7:52 ` Peter Zijlstra
2010-06-24 15:00 ` Nick Piggin
2010-06-24 3:02 ` [patch 07/52] fs: brlock vfsmount_lock npiggin
2010-06-24 3:02 ` [patch 08/52] fs: scale mntget/mntput npiggin
2010-06-24 3:02 ` [patch 09/52] fs: dcache scale hash npiggin
2010-06-24 3:02 ` [patch 10/52] fs: dcache scale lru npiggin
2010-06-24 3:02 ` [patch 11/52] fs: dcache scale nr_dentry npiggin
2010-06-24 3:02 ` [patch 12/52] fs: dcache scale dentry refcount npiggin
2010-06-24 3:02 ` [patch 13/52] fs: dcache scale d_unhashed npiggin
2010-06-24 3:02 ` [patch 14/52] fs: dcache scale subdirs npiggin
2010-06-24 7:56 ` Peter Zijlstra
2010-06-24 9:50 ` Andi Kleen
2010-06-24 15:53 ` Nick Piggin
2010-06-24 3:02 ` [patch 15/52] fs: dcache scale inode alias list npiggin
2010-06-24 3:02 ` [patch 16/52] fs: dcache RCU for multi-step operaitons npiggin
2010-06-24 7:58 ` Peter Zijlstra
2010-06-24 15:03 ` Nick Piggin
2010-06-24 17:22 ` john stultz
2010-06-24 17:26 ` john stultz
2010-06-25 6:45 ` Nick Piggin
2010-06-24 3:02 ` [patch 17/52] fs: dcache remove dcache_lock npiggin
2010-06-24 3:02 ` [patch 18/52] fs: dcache reduce dput locking npiggin
2010-06-24 3:02 ` [patch 19/52] fs: dcache per-bucket dcache hash locking npiggin
2010-06-24 3:02 ` [patch 20/52] fs: dcache reduce dcache_inode_lock npiggin
2010-06-24 3:02 ` [patch 21/52] fs: dcache per-inode inode alias locking npiggin
2010-06-24 3:02 ` [patch 22/52] fs: dcache rationalise dget variants npiggin
2010-06-24 3:02 ` [patch 23/52] fs: dcache percpu nr_dentry npiggin
2010-06-24 3:02 ` [patch 24/52] fs: dcache reduce d_parent locking npiggin
2010-06-24 8:44 ` Peter Zijlstra
2010-06-24 15:07 ` Nick Piggin
2010-06-24 15:32 ` Paul E. McKenney
2010-06-24 16:05 ` Nick Piggin
2010-06-24 16:41 ` Paul E. McKenney
2010-06-28 21:50 ` Paul E. McKenney
2010-07-07 14:35 ` Nick Piggin
2010-06-24 3:02 ` [patch 25/52] fs: dcache DCACHE_REFERENCED improve npiggin
2010-06-24 3:02 ` [patch 26/52] fs: icache lock s_inodes list npiggin
2010-06-24 3:02 ` [patch 27/52] fs: icache lock inode hash npiggin
2010-06-24 3:02 ` [patch 28/52] fs: icache lock i_state npiggin
2010-06-24 3:02 ` [patch 29/52] fs: icache lock i_count npiggin
2010-06-30 7:27 ` Dave Chinner
2010-06-30 12:05 ` Nick Piggin
2010-07-01 2:36 ` Dave Chinner
2010-07-01 7:54 ` Nick Piggin
2010-07-01 9:36 ` Nick Piggin
2010-07-01 16:21 ` Frank Mayhar
2010-07-03 2:03 ` Andrew Morton
2010-07-03 3:41 ` Nick Piggin
2010-07-03 4:31 ` Andrew Morton
2010-07-03 5:06 ` Nick Piggin
2010-07-03 5:18 ` Nick Piggin
2010-07-05 22:41 ` Dave Chinner
2010-07-06 4:34 ` Nick Piggin
2010-07-06 10:38 ` Theodore Tso
2010-07-06 13:04 ` Nick Piggin
2010-07-07 17:00 ` Frank Mayhar
2010-06-24 3:02 ` [patch 30/52] fs: icache lock lru/writeback lists npiggin
2010-06-24 8:58 ` Peter Zijlstra
2010-06-24 15:09 ` Nick Piggin
2010-06-24 15:13 ` Peter Zijlstra
2010-06-24 3:02 ` [patch 31/52] fs: icache atomic inodes_stat npiggin
2010-06-24 3:02 ` [patch 32/52] fs: icache protect inode state npiggin
2010-06-24 3:02 ` [patch 33/52] fs: icache atomic last_ino, iunique lock npiggin
2010-06-24 3:02 ` [patch 34/52] fs: icache remove inode_lock npiggin
2010-06-24 3:02 ` [patch 35/52] fs: icache factor hash lock into functions npiggin
2010-06-24 3:02 ` [patch 36/52] fs: icache per-bucket inode hash locks npiggin
2010-06-24 3:02 ` [patch 37/52] fs: icache lazy lru npiggin
2010-06-24 9:52 ` Andi Kleen
2010-06-24 15:59 ` Nick Piggin
2010-06-30 8:38 ` Dave Chinner
2010-06-30 12:06 ` Nick Piggin
2010-07-01 2:46 ` Dave Chinner
2010-07-01 7:57 ` Nick Piggin
2010-06-24 3:02 ` [patch 38/52] fs: icache RCU free inodes npiggin
2010-06-30 8:57 ` Dave Chinner
2010-06-30 12:07 ` Nick Piggin
2010-06-24 3:02 ` [patch 39/52] fs: icache rcu walk for i_sb_list npiggin
2010-06-24 3:02 ` [patch 40/52] fs: dcache improve scalability of pseudo filesystems npiggin
2010-06-24 3:02 ` [patch 41/52] fs: icache reduce atomics npiggin
2010-06-24 3:02 ` [patch 42/52] fs: icache per-cpu last_ino allocator npiggin
2010-06-24 9:48 ` Andi Kleen
2010-06-24 15:52 ` Nick Piggin
2010-06-24 16:19 ` Andi Kleen
2010-06-24 16:38 ` Nick Piggin
2010-06-24 3:02 ` [patch 43/52] fs: icache per-cpu nr_inodes counter npiggin
2010-06-24 3:02 ` [patch 44/52] fs: icache per-CPU sb inode lists and locks npiggin
2010-06-30 9:26 ` Dave Chinner
2010-06-30 12:08 ` Nick Piggin
2010-07-01 3:12 ` Dave Chinner
2010-07-01 8:00 ` Nick Piggin
2010-06-24 3:02 ` [patch 45/52] fs: icache RCU hash lookups npiggin
2010-06-24 3:02 ` [patch 46/52] fs: icache reduce locking npiggin
2010-06-24 3:02 ` [patch 47/52] fs: keep inode with backing-dev npiggin
2010-06-24 3:03 ` npiggin [this message]
2010-06-24 3:03 ` [patch 49/52] fs: icache scale writeback list locking npiggin
2010-06-24 3:03 ` [patch 50/52] mm: implement per-zone shrinker npiggin
2010-06-24 10:06 ` Andi Kleen
2010-06-24 16:00 ` Nick Piggin
2010-06-24 16:27 ` Andi Kleen
2010-06-24 16:32 ` Andi Kleen
2010-06-24 16:37 ` Andi Kleen
2010-06-30 6:28 ` Dave Chinner
2010-06-30 12:03 ` Nick Piggin
2010-06-24 3:03 ` [patch 51/52] fs: per-zone dentry and inode LRU npiggin
2010-06-30 10:09 ` Dave Chinner
2010-06-30 12:13 ` Nick Piggin
2010-06-24 3:03 ` [patch 52/52] fs: icache less I_FREEING time npiggin
2010-06-30 10:13 ` Dave Chinner
2010-06-30 12:14 ` Nick Piggin
2010-07-01 3:33 ` Dave Chinner
2010-07-01 8:06 ` Nick Piggin
2010-06-25 7:12 ` [patch 00/52] vfs scalability patches updated Christoph Hellwig
2010-06-25 8:05 ` Nick Piggin
2010-06-30 11:30 ` Dave Chinner
2010-06-30 12:40 ` Nick Piggin
2010-07-01 3:56 ` Dave Chinner
2010-07-01 8:20 ` Nick Piggin
2010-07-01 17:36 ` Andi Kleen
2010-07-01 17:23 ` Nick Piggin
2010-07-01 17:28 ` Andi Kleen
2010-07-06 17:49 ` Nick Piggin
2010-07-01 17:35 ` Linus Torvalds
2010-07-01 17:52 ` Nick Piggin
2010-07-02 4:01 ` Paul E. McKenney
2010-06-30 17:08 ` Frank Mayhar
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=20100624030733.354313412@suse.de \
--to=npiggin@suse.de \
--cc=fmayhar@google.com \
--cc=johnstul@us.ibm.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).