| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4941968E.3020201@cosmosbay.com>
Date: Thu, 11 Dec 2008 23:39:10 +0100
From: Eric Dumazet <dada1@...mosbay.com>
To: Andrew Morton <akpm@...ux-foundation.org>
CC: Ingo Molnar <mingo@...e.hu>, Christoph Hellwig <hch@...radead.org>,
David Miller <davem@...emloft.net>,
"Rafael J. Wysocki" <rjw@...k.pl>, linux-kernel@...r.kernel.org,
"kernel-testers@...r.kernel.org >> Kernel Testers List"
<kernel-testers@...r.kernel.org>, Mike Galbraith <efault@....de>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Linux Netdev List <netdev@...r.kernel.org>,
Christoph Lameter <cl@...ux-foundation.org>,
linux-fsdevel@...r.kernel.org, Al Viro <viro@...IV.linux.org.uk>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: [PATCH v3 2/7] fs: Use a percpu_counter to track nr_inodes
Avoids cache line ping pongs between cpus and prepare next patch,
because updates of nr_inodes dont need inode_lock anymore.
(socket8 bench result : no difference at this point)
Signed-off-by: Eric Dumazet <dada1@...mosbay.com>
---
fs/fs-writeback.c | 2 +-
fs/inode.c | 39 +++++++++++++++++++++++++++++++--------
include/linux/fs.h | 3 +++
kernel/sysctl.c | 4 ++--
mm/page-writeback.c | 2 +-
5 files changed, 38 insertions(+), 12 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d0ff0b8..b591cdd 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -608,7 +608,7 @@ void sync_inodes_sb(struct super_block *sb, int wait)
unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
wbc.nr_to_write = nr_dirty + nr_unstable +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused) +
+ (get_nr_inodes() - inodes_stat.nr_unused) +
nr_dirty + nr_unstable;
wbc.nr_to_write += wbc.nr_to_write / 2; /* Bit more for luck */
sync_sb_inodes(sb, &wbc);
diff --git a/fs/inode.c b/fs/inode.c
index 0487ddb..f94f889 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -96,9 +96,33 @@ static DEFINE_MUTEX(iprune_mutex);
* Statistics gathering..
*/
struct inodes_stat_t inodes_stat;
+static struct percpu_counter nr_inodes;
static struct kmem_cache * inode_cachep __read_mostly;
+int get_nr_inodes(void)
+{
+ return percpu_counter_sum_positive(&nr_inodes);
+}
+
+/*
+ * Handle nr_dentry sysctl
+ */
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+int proc_nr_inodes(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ inodes_stat.nr_inodes = get_nr_inodes();
+ return proc_dointvec(table, write, filp, buffer, lenp, ppos);
+}
+#else
+int proc_nr_inodes(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+#endif
+
static void wake_up_inode(struct inode *inode)
{
/*
@@ -306,9 +330,7 @@ static void dispose_list(struct list_head *head)
destroy_inode(inode);
nr_disposed++;
}
- spin_lock(&inode_lock);
- inodes_stat.nr_inodes -= nr_disposed;
- spin_unlock(&inode_lock);
+ percpu_counter_sub(&nr_inodes, nr_disposed);
}
/*
@@ -560,8 +582,8 @@ struct inode *new_inode(struct super_block *sb)
inode = alloc_inode(sb);
if (inode) {
+ percpu_counter_inc(&nr_inodes);
spin_lock(&inode_lock);
- inodes_stat.nr_inodes++;
list_add(&inode->i_list, &inode_in_use);
list_add(&inode->i_sb_list, &sb->s_inodes);
inode->i_ino = ++last_ino;
@@ -622,7 +644,7 @@ static struct inode * get_new_inode(struct super_block *sb, struct hlist_head *h
if (set(inode, data))
goto set_failed;
- inodes_stat.nr_inodes++;
+ percpu_counter_inc(&nr_inodes);
list_add(&inode->i_list, &inode_in_use);
list_add(&inode->i_sb_list, &sb->s_inodes);
hlist_add_head(&inode->i_hash, head);
@@ -671,7 +693,7 @@ static struct inode * get_new_inode_fast(struct super_block *sb, struct hlist_he
old = find_inode_fast(sb, head, ino);
if (!old) {
inode->i_ino = ino;
- inodes_stat.nr_inodes++;
+ percpu_counter_inc(&nr_inodes);
list_add(&inode->i_list, &inode_in_use);
list_add(&inode->i_sb_list, &sb->s_inodes);
hlist_add_head(&inode->i_hash, head);
@@ -1042,8 +1064,8 @@ void generic_delete_inode(struct inode *inode)
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
inode->i_state |= I_FREEING;
- inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
+ percpu_counter_dec(&nr_inodes);
security_inode_delete(inode);
@@ -1093,8 +1115,8 @@ static void generic_forget_inode(struct inode *inode)
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
inode->i_state |= I_FREEING;
- inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
+ percpu_counter_dec(&nr_inodes);
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
@@ -1394,6 +1416,7 @@ void __init inode_init(void)
{
int loop;
+ percpu_counter_init(&nr_inodes, 0);
/* inode slab cache */
inode_cachep = kmem_cache_create("inode_cache",
sizeof(struct inode),
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 114cb65..a789346 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -47,6 +47,7 @@ struct inodes_stat_t {
int dummy[5]; /* padding for sysctl ABI compatibility */
};
extern struct inodes_stat_t inodes_stat;
+extern int get_nr_inodes(void);
extern int leases_enable, lease_break_time;
@@ -2219,6 +2220,8 @@ int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos);
int proc_nr_dentry(struct ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos);
+int proc_nr_inodes(struct ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
int get_filesystem_list(char * buf);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 777bee7..b705f3a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1205,7 +1205,7 @@ static struct ctl_table fs_table[] = {
.data = &inodes_stat,
.maxlen = 2*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_nr_inodes,
},
{
.ctl_name = FS_STATINODE,
@@ -1213,7 +1213,7 @@ static struct ctl_table fs_table[] = {
.data = &inodes_stat,
.maxlen = 7*sizeof(int),
.mode = 0444,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_nr_inodes,
},
{
.procname = "file-nr",
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2970e35..a71a922 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -705,7 +705,7 @@ static void wb_kupdate(unsigned long arg)
next_jif = start_jif + dirty_writeback_interval;
nr_to_write = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+ (get_nr_inodes() - inodes_stat.nr_unused);
while (nr_to_write > 0) {
wbc.more_io = 0;
wbc.encountered_congestion = 0;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists