[RRC PATCH 2/2] vfs: Use per-cpu list for superblock's inode list

From: Waiman Long
Date: Tue Feb 16 2016 - 20:32:22 EST

When many threads are trying to add or delete inode to or from
a superblock's s_inodes list, spinlock contention on the list can
become a performance bottleneck.

This patch changes the s_inodes field to become a per-cpu list with
per-cpu spinlocks.

With an exit microbenchmark that creates a large number of threads,
attachs many inodes to them and then exits. The runtimes of that
microbenchmark with 1000 threads before and after the patch on a
4-socket Intel E7-4820 v3 system (40 cores, 80 threads) were as
follows:

Kernel Elapsed Time System Time
------ ------------ -----------
Vanilla 4.5-rc4 65.29s 82m14s
Patched 4.5-rc4 22.81s 23m03s

Before the patch, spinlock contention at the inode_sb_list_add()
function at the startup phase and the inode_sb_list_del() function at
the exit phase were about 79% and 93% of total CPU time respectively
(as measured by perf). After the patch, the percpu_list_add()
function consumed only about 0.04% of CPU time at startup phase. The
percpu_list_del() function consumed about 0.4% of CPU time at exit
phase. There were still some spinlock contention, but they happened
elsewhere.

Signed-off-by: Waiman Long <Waiman.Long@xxxxxxx>
---
fs/block_dev.c | 16 +++++++---------
fs/drop_caches.c | 11 +++++------
fs/fs-writeback.c | 16 +++++++---------
fs/inode.c | 43 +++++++++++++++++--------------------------
fs/notify/inode_mark.c | 22 +++++++++++-----------
fs/quota/dquot.c | 23 ++++++++++-------------
fs/super.c | 7 ++++---
include/linux/fs.h | 8 ++++----
8 files changed, 65 insertions(+), 81 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 39b3a17..30b12cb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1866,8 +1866,8 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
struct inode *inode, *old_inode = NULL;

- spin_lock(&blockdev_superblock->s_inode_list_lock);
- list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ blockdev_superblock->s_inodes_cpu, i_sb_list) {
struct address_space *mapping = inode->i_mapping;

spin_lock(&inode->i_lock);
@@ -1878,22 +1878,20 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&blockdev_superblock->s_inode_list_lock);
+ spin_unlock(percpu_lock);
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
- * s_inode_list_lock We cannot iput the inode now as we can
+ * percpu_lock. We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
- * s_inode_list_lock. So we keep the reference and iput it
- * later.
+ * percpu_lock. So we keep the reference and iput it later.
*/
iput(old_inode);
old_inode = inode;

func(I_BDEV(inode), arg);

- spin_lock(&blockdev_superblock->s_inode_list_lock);
- }
- spin_unlock(&blockdev_superblock->s_inode_list_lock);
+ spin_lock(percpu_lock);
+ } end_all_percpu_list_entries(percpu_lock)
iput(old_inode);
}
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index d72d52b..c091d91 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -17,8 +17,8 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
{
struct inode *inode, *toput_inode = NULL;

- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
(inode->i_mapping->nrpages == 0)) {
@@ -27,15 +27,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_list_lock);
+ spin_unlock(percpu_lock);

invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;

- spin_lock(&sb->s_inode_list_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ spin_lock(percpu_lock);
+ } end_all_percpu_list_entries(percpu_lock)
iput(toput_inode);
}

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6915c95..3fcacb5 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2115,7 +2115,6 @@ static void wait_sb_inodes(struct super_block *sb)
WARN_ON(!rwsem_is_locked(&sb->s_umount));

mutex_lock(&sb->s_sync_lock);
- spin_lock(&sb->s_inode_list_lock);

/*
* Data integrity sync. Must wait for all pages under writeback,
@@ -2124,7 +2123,8 @@ static void wait_sb_inodes(struct super_block *sb)
* In which case, the inode may not be on the dirty list, but
* we still have to wait for that writeout.
*/
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
struct address_space *mapping = inode->i_mapping;

spin_lock(&inode->i_lock);
@@ -2135,15 +2135,14 @@ static void wait_sb_inodes(struct super_block *sb)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_list_lock);
+ spin_unlock(percpu_lock);

/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
- * s_inode_list_lock. We cannot iput the inode now as we can
+ * percpu_lock. We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
- * s_inode_list_lock. So we keep the reference and iput it
- * later.
+ * percpu_lock. So we keep the reference and iput it later.
*/
iput(old_inode);
old_inode = inode;
@@ -2157,9 +2156,8 @@ static void wait_sb_inodes(struct super_block *sb)

cond_resched();

- spin_lock(&sb->s_inode_list_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ spin_lock(percpu_lock);
+ } end_all_percpu_list_entries(percpu_lock)
iput(old_inode);
mutex_unlock(&sb->s_sync_lock);
}
diff --git a/fs/inode.c b/fs/inode.c
index 9f62db3..15c82e7 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -28,8 +28,8 @@
* inode->i_state, inode->i_hash, __iget()
* Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
- * inode->i_sb->s_inode_list_lock protects:
- * inode->i_sb->s_inodes, inode->i_sb_list
+ * inode->i_sb->s_inodes_cpu->lock protects:
+ * inode->i_sb->s_inodes_cpu, inode->i_sb_list
* bdi->wb.list_lock protects:
* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
* inode_hash_lock protects:
@@ -37,7 +37,7 @@
*
* Lock ordering:
*
- * inode->i_sb->s_inode_list_lock
+ * inode->i_sb->s_inodes_cpu->lock
* inode->i_lock
* Inode LRU list locks
*
@@ -45,7 +45,7 @@
* inode->i_lock
*
* inode_hash_lock
- * inode->i_sb->s_inode_list_lock
+ * inode->i_sb->s_inodes_cpu->lock
* inode->i_lock
*
* iunique_lock
@@ -424,19 +424,14 @@ static void inode_lru_list_del(struct inode *inode)
*/
void inode_sb_list_add(struct inode *inode)
{
- spin_lock(&inode->i_sb->s_inode_list_lock);
- list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
- spin_unlock(&inode->i_sb->s_inode_list_lock);
+ percpu_list_add(&inode->i_sb_list, inode->i_sb->s_inodes_cpu);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);

static inline void inode_sb_list_del(struct inode *inode)
{
- if (!list_empty(&inode->i_sb_list)) {
- spin_lock(&inode->i_sb->s_inode_list_lock);
- list_del_init(&inode->i_sb_list);
- spin_unlock(&inode->i_sb->s_inode_list_lock);
- }
+ if (!list_empty(&inode->i_sb_list.list))
+ percpu_list_del(&inode->i_sb_list);
}

static unsigned long hash(struct super_block *sb, unsigned long hashval)
@@ -590,12 +585,12 @@ static void dispose_list(struct list_head *head)
*/
void evict_inodes(struct super_block *sb)
{
- struct inode *inode, *next;
+ struct inode *inode;
LIST_HEAD(dispose);

again:
- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;

@@ -616,13 +611,12 @@ again:
* bit so we don't livelock.
*/
if (need_resched()) {
- spin_unlock(&sb->s_inode_list_lock);
+ spin_unlock(percpu_lock);
cond_resched();
dispose_list(&dispose);
goto again;
}
- }
- spin_unlock(&sb->s_inode_list_lock);
+ } end_all_percpu_list_entries(percpu_lock)

dispose_list(&dispose);
}
@@ -640,11 +634,11 @@ again:
int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
int busy = 0;
- struct inode *inode, *next;
+ struct inode *inode;
LIST_HEAD(dispose);

- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
spin_unlock(&inode->i_lock);
@@ -665,8 +659,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ } end_all_percpu_list_entries(percpu_lock)

dispose_list(&dispose);

@@ -881,7 +874,7 @@ struct inode *new_inode_pseudo(struct super_block *sb)
spin_lock(&inode->i_lock);
inode->i_state = 0;
spin_unlock(&inode->i_lock);
- INIT_LIST_HEAD(&inode->i_sb_list);
+ INIT_PERCPU_LIST_ENTRY(&inode->i_sb_list);
}
return inode;
}
@@ -902,8 +895,6 @@ struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;

- spin_lock_prefetch(&sb->s_inode_list_lock);
-
inode = new_inode_pseudo(sb);
if (inode)
inode_sb_list_add(inode);
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 741077d..96bcd4a 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -146,14 +146,15 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
* @sb: superblock being unmounted.
*
* Called during unmount with no locks held, so needs to be safe against
- * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
+ * concurrent modifiers. We temporarily drop sb->s_inodes_cpu->lock and CAN
+ * block.
*/
void fsnotify_unmount_inodes(struct super_block *sb)
{
- struct inode *inode, *next_i, *need_iput = NULL;
+ struct inode *inode, *need_iput = NULL;

- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry_safe(inode, next_i, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries(inode, next_i, percpu_head, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
struct inode *need_iput_tmp;

/*
@@ -189,7 +190,7 @@ void fsnotify_unmount_inodes(struct super_block *sb)
spin_unlock(&inode->i_lock);

/* In case the dropping of a reference would nuke next_i. */
- while (&next_i->i_sb_list != &sb->s_inodes) {
+ while (&next_i->i_sb_list.list != percpu_head) {
spin_lock(&next_i->i_lock);
if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
atomic_read(&next_i->i_count)) {
@@ -199,16 +200,16 @@ void fsnotify_unmount_inodes(struct super_block *sb)
break;
}
spin_unlock(&next_i->i_lock);
- next_i = list_next_entry(next_i, i_sb_list);
+ next_i = list_next_entry(next_i, i_sb_list.list);
}

/*
- * We can safely drop s_inode_list_lock here because either
+ * We can safely drop percpu_lock here because either
* we actually hold references on both inode and next_i or
* end of list. Also no new inodes will be added since the
* umount has begun.
*/
- spin_unlock(&sb->s_inode_list_lock);
+ spin_unlock(percpu_lock);

if (need_iput_tmp)
iput(need_iput_tmp);
@@ -220,7 +221,6 @@ void fsnotify_unmount_inodes(struct super_block *sb)

iput(inode);

- spin_lock(&sb->s_inode_list_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ spin_lock(percpu_lock);
+ } end_all_percpu_list_entries(percpu_lock)
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 3c3b81b..0123ef4 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -928,8 +928,8 @@ static void add_dquot_ref(struct super_block *sb, int type)
int reserved = 0;
#endif

- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, percpu_lock,
+ sb->s_inodes_cpu, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
!atomic_read(&inode->i_writecount) ||
@@ -939,7 +939,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
}
__iget(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&sb->s_inode_list_lock);
+ spin_unlock(percpu_lock);

#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
@@ -951,15 +951,13 @@ static void add_dquot_ref(struct super_block *sb, int type)
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
- * s_inode_list_lock. We cannot iput the inode now as we can be
+ * percpu_lock. We cannot iput the inode now as we can be
* holding the last reference and we cannot iput it under
- * s_inode_list_lock. So we keep the reference and iput it
- * later.
+ * percpu_lock. So we keep the reference and iput it later.
*/
old_inode = inode;
- spin_lock(&sb->s_inode_list_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ spin_lock(percpu_lock);
+ } end_all_percpu_list_entries(percpu_lock)
iput(old_inode);

#ifdef CONFIG_QUOTA_DEBUG
@@ -1028,8 +1026,8 @@ static void remove_dquot_ref(struct super_block *sb, int type,
struct inode *inode;
int reserved = 0;

- spin_lock(&sb->s_inode_list_lock);
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ for_all_percpu_list_entries_simple(inode, lock, sb->s_inodes_cpu,
+ i_sb_list) {
/*
* We have to scan also I_NEW inodes because they can already
* have quota pointer initialized. Luckily, we need to touch
@@ -1043,8 +1041,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
remove_inode_dquot_ref(inode, type, tofree_head);
}
spin_unlock(&dq_data_lock);
- }
- spin_unlock(&sb->s_inode_list_lock);
+ } end_all_percpu_list_entries(lock)
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
printk(KERN_WARNING "VFS (%s): Writes happened after quota"
diff --git a/fs/super.c b/fs/super.c
index 1182af8..1db4f37 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -163,6 +163,7 @@ static void destroy_super(struct super_block *s)
{
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
+ free_percpu_list_head(&s->s_inodes_cpu);
security_sb_free(s);
WARN_ON(!list_empty(&s->s_mounts));
kfree(s->s_subtype);
@@ -204,9 +205,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
mutex_init(&s->s_sync_lock);
- INIT_LIST_HEAD(&s->s_inodes);
- spin_lock_init(&s->s_inode_list_lock);

+ if (init_percpu_list_head(&s->s_inodes_cpu))
+ goto fail;
if (list_lru_init_memcg(&s->s_dentry_lru))
goto fail;
if (list_lru_init_memcg(&s->s_inode_lru))
@@ -426,7 +427,7 @@ void generic_shutdown_super(struct super_block *sb)
if (sop->put_super)
sop->put_super(sb);

- if (!list_empty(&sb->s_inodes)) {
+ if (!percpu_list_empty(sb->s_inodes_cpu)) {
printk("VFS: Busy inodes after unmount of %s. "
"Self-destruct in 5 seconds. Have a nice day...\n",
sb->s_id);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae68100..efedc59 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -27,6 +27,7 @@
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
+#include <linux/percpu-list.h>
#include <linux/percpu-rwsem.h>
#include <linux/blk_types.h>
#include <linux/workqueue.h>
@@ -648,7 +649,7 @@ struct inode {
u16 i_wb_frn_history;
#endif
struct list_head i_lru; /* inode LRU list */
- struct list_head i_sb_list;
+ struct percpu_list i_sb_list;
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
@@ -1397,9 +1398,8 @@ struct super_block {
*/
int s_stack_depth;

- /* s_inode_list_lock protects s_inodes */
- spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
- struct list_head s_inodes; /* all inodes */
+ /* The percpu locks protect s_inodes_cpu */
+ PERCPU_LIST_HEAD(s_inodes_cpu); /* all inodes */
};

extern struct timespec current_fs_time(struct super_block *sb);
--
1.7.1