From: npiggin@suse.de
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [patch 20/27] fs: icache lock s_inodes list
Date: Sat, 25 Apr 2009 11:20:40 +1000 [thread overview]
Message-ID: <20090425012211.943152128@suse.de> (raw)
In-Reply-To: 20090425012020.457460929@suse.de
[-- Attachment #1: fs-inode_lock-scale.patch --]
[-- Type: text/plain, Size: 7498 bytes --]
Protect sb->s_inodes with a new lock, sb_inode_list_lock.
---
fs/drop_caches.c | 4 ++++
fs/fs-writeback.c | 4 ++++
fs/hugetlbfs/inode.c | 2 ++
fs/inode.c | 12 ++++++++++++
fs/notify/inotify/inotify.c | 2 ++
fs/quota/dquot.c | 6 ++++++
include/linux/writeback.h | 1 +
7 files changed, 31 insertions(+)
Index: linux-2.6/fs/drop_caches.c
===================================================================
--- linux-2.6.orig/fs/drop_caches.c
+++ linux-2.6/fs/drop_caches.c
@@ -17,18 +17,22 @@ static void drop_pagecache_sb(struct sup
struct inode *inode, *toput_inode = NULL;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
if (inode->i_mapping->nrpages == 0)
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
__invalidate_mapping_pages(inode->i_mapping, 0, -1, true);
iput(toput_inode);
toput_inode = inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(toput_inode);
}
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c
+++ linux-2.6/fs/fs-writeback.c
@@ -553,6 +553,7 @@ void generic_sync_sb_inodes(struct super
* In which case, the inode may not be on the dirty list, but
* we still have to wait for that writeout.
*/
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;
@@ -563,6 +564,7 @@ void generic_sync_sb_inodes(struct super
if (mapping->nrpages == 0)
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
/*
* We hold a reference to 'inode' so it couldn't have
@@ -580,7 +582,9 @@ void generic_sync_sb_inodes(struct super
cond_resched();
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
} else
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c
+++ linux-2.6/fs/inode.c
@@ -83,6 +83,7 @@ static struct hlist_head *inode_hashtabl
* the i_state of an inode while it is in use..
*/
DEFINE_SPINLOCK(inode_lock);
+DEFINE_SPINLOCK(sb_inode_list_lock);
/*
* iprune_mutex provides exclusion between the kswapd or try_to_free_pages
@@ -329,7 +330,9 @@ static void dispose_list(struct list_hea
spin_lock(&inode_lock);
hlist_del_init(&inode->i_hash);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
wake_up_inode(inode);
@@ -361,6 +364,7 @@ static int invalidate_list(struct list_h
* shrink_icache_memory() away.
*/
cond_resched_lock(&inode_lock);
+ cond_resched_lock(&sb_inode_list_lock);
next = next->next;
if (tmp == head)
@@ -398,8 +402,10 @@ int invalidate_inodes(struct super_block
mutex_lock(&iprune_mutex);
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
inotify_unmount_inodes(&sb->s_inodes);
busy = invalidate_list(&sb->s_inodes, &throw_away);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
dispose_list(&throw_away);
@@ -584,7 +590,9 @@ __inode_add_to_lists(struct super_block
{
inodes_stat.nr_inodes++;
list_add(&inode->i_list, &inode_in_use);
+ spin_lock(&sb_inode_list_lock);
list_add(&inode->i_sb_list, &sb->s_inodes);
+ spin_unlock(&sb_inode_list_lock);
if (head)
hlist_add_head(&inode->i_hash, head);
}
@@ -1159,7 +1167,9 @@ void generic_delete_inode(struct inode *
const struct super_operations *op = inode->i_sb->s_op;
list_del_init(&inode->i_list);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
@@ -1213,7 +1223,9 @@ static void generic_forget_inode(struct
hlist_del_init(&inode->i_hash);
}
list_del_init(&inode->i_list);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
Index: linux-2.6/fs/notify/inotify/inotify.c
===================================================================
--- linux-2.6.orig/fs/notify/inotify/inotify.c
+++ linux-2.6/fs/notify/inotify/inotify.c
@@ -430,6 +430,7 @@ void inotify_unmount_inodes(struct list_
* will be added since the umount has begun. Finally,
* iprune_mutex keeps shrink_icache_memory() away.
*/
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
if (need_iput_tmp)
@@ -452,6 +453,7 @@ void inotify_unmount_inodes(struct list_
iput(inode);
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
}
EXPORT_SYMBOL_GPL(inotify_unmount_inodes);
Index: linux-2.6/fs/quota/dquot.c
===================================================================
--- linux-2.6.orig/fs/quota/dquot.c
+++ linux-2.6/fs/quota/dquot.c
@@ -822,6 +822,7 @@ static void add_dquot_ref(struct super_b
struct inode *inode, *old_inode = NULL;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
@@ -831,6 +832,7 @@ static void add_dquot_ref(struct super_b
continue;
__iget(inode);
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
@@ -842,7 +844,9 @@ static void add_dquot_ref(struct super_b
* keep the reference and iput it later. */
old_inode = inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
iput(old_inode);
}
@@ -914,6 +918,7 @@ static void remove_dquot_ref(struct supe
struct inode *inode;
spin_lock(&inode_lock);
+ spin_lock(&sb_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
/*
* We have to scan also I_NEW inodes because they can already
@@ -924,6 +929,7 @@ static void remove_dquot_ref(struct supe
if (!IS_NOQUOTA(inode))
remove_inode_dquot_ref(inode, type, tofree_head);
}
+ spin_unlock(&sb_inode_list_lock);
spin_unlock(&inode_lock);
}
Index: linux-2.6/include/linux/writeback.h
===================================================================
--- linux-2.6.orig/include/linux/writeback.h
+++ linux-2.6/include/linux/writeback.h
@@ -10,6 +10,7 @@
struct backing_dev_info;
extern spinlock_t inode_lock;
+extern spinlock_t sb_inode_list_lock;
extern struct list_head inode_in_use;
extern struct list_head inode_unused;
Index: linux-2.6/fs/hugetlbfs/inode.c
===================================================================
--- linux-2.6.orig/fs/hugetlbfs/inode.c
+++ linux-2.6/fs/hugetlbfs/inode.c
@@ -413,7 +413,9 @@ static void hugetlbfs_forget_inode(struc
hlist_del_init(&inode->i_hash);
}
list_del_init(&inode->i_list);
+ spin_lock(&sb_inode_list_lock);
list_del_init(&inode->i_sb_list);
+ spin_unlock(&sb_inode_list_lock);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
next prev parent reply other threads:[~2009-04-25 1:28 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-25 1:20 [patch 00/27] [rfc] vfs scalability patchset npiggin
2009-04-25 1:20 ` [patch 01/27] fs: cleanup files_lock npiggin
2009-04-25 3:20 ` Al Viro
2009-04-25 5:35 ` Eric W. Biederman
2009-04-26 6:12 ` Nick Piggin
2009-04-25 9:42 ` Alan Cox
2009-04-26 6:15 ` Nick Piggin
2009-04-25 1:20 ` [patch 02/27] fs: scale files_lock npiggin
2009-04-25 3:32 ` Al Viro
2009-04-25 1:20 ` [patch 03/27] fs: mnt_want_write speedup npiggin
2009-04-25 1:20 ` [patch 04/27] fs: introduce mnt_clone_write npiggin
2009-04-25 3:35 ` Al Viro
2009-04-25 1:20 ` [patch 05/27] fs: brlock vfsmount_lock npiggin
2009-04-25 3:50 ` Al Viro
2009-04-26 6:36 ` Nick Piggin
2009-04-25 1:20 ` [patch 06/27] fs: dcache fix LRU ordering npiggin
2009-04-25 1:20 ` [patch 07/27] fs: dcache scale hash npiggin
2009-04-25 1:20 ` [patch 08/27] fs: dcache scale lru npiggin
2009-04-25 1:20 ` [patch 09/27] fs: dcache scale nr_dentry npiggin
2009-04-25 1:20 ` [patch 10/27] fs: dcache scale dentry refcount npiggin
2009-04-25 1:20 ` [patch 11/27] fs: dcache scale d_unhashed npiggin
2009-04-25 1:20 ` [patch 12/27] fs: dcache scale subdirs npiggin
2009-04-25 1:20 ` [patch 13/27] fs: scale inode alias list npiggin
2009-04-25 1:20 ` [patch 14/27] fs: use RCU / seqlock logic for reverse and multi-step operaitons npiggin
2009-04-25 1:20 ` [patch 15/27] fs: dcache remove dcache_lock npiggin
2009-04-25 1:20 ` [patch 16/27] fs: dcache reduce dput locking npiggin
2009-04-25 1:20 ` [patch 17/27] fs: dcache per-bucket dcache hash locking npiggin
2009-04-25 1:20 ` [patch 18/27] fs: dcache reduce dcache_inode_lock npiggin
2009-04-25 1:20 ` [patch 19/27] fs: dcache per-inode inode alias locking npiggin
2009-04-25 1:20 ` npiggin [this message]
2009-04-25 1:20 ` [patch 21/27] fs: icache lock inode hash npiggin
2009-04-25 1:20 ` [patch 22/27] fs: icache lock i_state npiggin
2009-04-25 1:20 ` [patch 23/27] fs: icache lock i_count npiggin
2009-04-25 1:20 ` [patch 24/27] fs: icache atomic inodes_stat npiggin
2009-04-25 1:20 ` [patch 25/27] fs: icache lock lru/writeback lists npiggin
2009-04-25 1:20 ` [patch 26/27] fs: icache protect inode state npiggin
2009-04-25 1:20 ` [patch 27/27] fs: icache remove inode_lock npiggin
2009-04-25 4:18 ` [patch 00/27] [rfc] vfs scalability patchset Al Viro
2009-04-25 5:02 ` Nick Piggin
2009-04-25 8:01 ` Christoph Hellwig
2009-04-25 8:06 ` Al Viro
2009-04-28 9:09 ` Christoph Hellwig
2009-04-28 9:48 ` Nick Piggin
2009-04-28 10:58 ` Peter Zijlstra
2009-04-28 11:32 ` Eric W. Biederman
2009-04-30 6:14 ` Nick Piggin
2009-04-25 19:08 ` Eric W. Biederman
2009-04-25 19:31 ` Al Viro
2009-04-25 20:29 ` Eric W. Biederman
2009-04-25 22:05 ` Theodore Tso
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=20090425012211.943152128@suse.de \
--to=npiggin@suse.de \
--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).