From: npiggin@kernel.dk
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [patch 16/35] fs: icache lazy inode lru
Date: Tue, 19 Oct 2010 14:42:32 +1100 [thread overview]
Message-ID: <20101019034657.147371115@kernel.dk> (raw)
In-Reply-To: 20101019034216.319085068@kernel.dk
[-- Attachment #1: fs-inode_lock-scale-10.patch --]
[-- Type: text/plain, Size: 8964 bytes --]
Impelemnt lazy inode lru similarly to dcache. That is, avoid moving inode
around the LRU list in iget/iput operations and defer the refcount check
to reclaim-time. Use a flag, I_REFERENCED, to tell reclaim that iget has
touched the inode in the past.
This will reduce lock acquisition, and will also improve lock ordering
with subsequent patches.
The global inode_in_use list goes away, and !list_empty(&inode->i_list)
invariant goes away.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
fs/fs-writeback.c | 7 ---
fs/inode.c | 98 ++++++++++++++++++++++------------------------
include/linux/fs.h | 20 ++++++---
include/linux/writeback.h | 1
4 files changed, 61 insertions(+), 65 deletions(-)
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c 2010-10-19 14:18:59.000000000 +1100
+++ linux-2.6/fs/inode.c 2010-10-19 14:19:29.000000000 +1100
@@ -94,7 +94,6 @@
* allowing for low-overhead inode sync() operations.
*/
-LIST_HEAD(inode_in_use);
LIST_HEAD(inode_unused);
struct inode_hash_bucket {
@@ -299,6 +298,7 @@
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_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);
@@ -320,25 +320,6 @@
inode_init_once(inode);
}
-/*
- * i_lock must be held
- */
-void __iget(struct inode *inode)
-{
- assert_spin_locked(&inode->i_lock);
-
- inode->i_count++;
- if (inode->i_count > 1)
- return;
-
- if (!(inode->i_state & (I_DIRTY|I_SYNC))) {
- spin_lock(&wb_inode_list_lock);
- list_move(&inode->i_list, &inode_in_use);
- spin_unlock(&wb_inode_list_lock);
- }
- atomic_dec(&inodes_stat.nr_unused);
-}
-
void end_writeback(struct inode *inode)
{
might_sleep();
@@ -383,7 +364,7 @@
struct inode *inode;
inode = list_first_entry(head, struct inode, i_list);
- list_del(&inode->i_list);
+ list_del_init(&inode->i_list);
evict(inode);
@@ -432,11 +413,12 @@
invalidate_inode_buffers(inode);
if (!inode->i_count) {
spin_lock(&wb_inode_list_lock);
- list_move(&inode->i_list, dispose);
+ list_del(&inode->i_list);
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);
count++;
continue;
}
@@ -476,7 +458,7 @@
static int can_unuse(struct inode *inode)
{
- if (inode->i_state)
+ if (inode->i_state & ~I_REFERENCED)
return 0;
if (inode_has_buffers(inode))
return 0;
@@ -504,13 +486,12 @@
{
LIST_HEAD(freeable);
int nr_pruned = 0;
- int nr_scanned;
unsigned long reap = 0;
down_read(&iprune_sem);
again:
spin_lock(&wb_inode_list_lock);
- for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
+ for (; nr_to_scan; nr_to_scan--) {
struct inode *inode;
if (list_empty(&inode_unused))
@@ -522,34 +503,47 @@
spin_unlock(&wb_inode_list_lock);
goto again;
}
- if (inode->i_state || inode->i_count) {
+ if (inode->i_count || (inode->i_state & ~I_REFERENCED)) {
+ list_del_init(&inode->i_list);
+ spin_unlock(&inode->i_lock);
+ atomic_dec(&inodes_stat.nr_unused);
+ continue;
+ }
+ if (inode->i_state & I_REFERENCED) {
list_move(&inode->i_list, &inode_unused);
+ inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
continue;
}
if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ /*
+ * Move back to the head of the unused list in case the
+ * invalidations failed. Could improve this by going to
+ * the head of the list only if invalidation fails.
+ *
+ * We'll try to get it back if it becomes freeable.
+ */
+ list_move(&inode->i_list, &inode_unused);
spin_unlock(&wb_inode_list_lock);
__iget(inode);
spin_unlock(&inode->i_lock);
+
if (remove_inode_buffers(inode))
reap += invalidate_mapping_pages(&inode->i_data,
0, -1);
iput(inode);
-again2:
spin_lock(&wb_inode_list_lock);
-
- if (inode != list_entry(inode_unused.next,
- struct inode, i_list))
- continue; /* wrong inode or list_empty */
- if (!spin_trylock(&inode->i_lock)) {
- spin_unlock(&wb_inode_list_lock);
- goto again2;
- }
- if (!can_unuse(inode)) {
- spin_unlock(&inode->i_lock);
- continue;
+ if (inode == list_entry(inode_unused.next,
+ struct inode, i_list)) {
+ if (spin_trylock(&inode->i_lock)) {
+ if (can_unuse(inode))
+ goto freeable;
+ spin_unlock(&inode->i_lock);
+ }
}
+ continue;
}
+freeable:
list_move(&inode->i_list, &freeable);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
@@ -695,9 +689,6 @@
{
list_add(&inode->i_sb_list, &sb->s_inodes);
spin_unlock(&sb_inode_list_lock);
- spin_lock(&wb_inode_list_lock);
- list_add(&inode->i_list, &inode_in_use);
- spin_unlock(&wb_inode_list_lock);
if (b) {
spin_lock_bucket(b);
hlist_bl_add_head(&inode->i_hash, &b->head);
@@ -1371,13 +1362,15 @@
drop = generic_drop_inode(inode);
if (!drop) {
- if (!(inode->i_state & (I_DIRTY|I_SYNC))) {
- spin_lock(&wb_inode_list_lock);
- list_move(&inode->i_list, &inode_unused);
- spin_unlock(&wb_inode_list_lock);
- }
- atomic_inc(&inodes_stat.nr_unused);
if (sb->s_flags & MS_ACTIVE) {
+ inode->i_state |= I_REFERENCED;
+ if (!(inode->i_state & (I_DIRTY|I_SYNC)) &&
+ list_empty(&inode->i_list)) {
+ spin_lock(&wb_inode_list_lock);
+ list_add(&inode->i_list, &inode_unused);
+ spin_unlock(&wb_inode_list_lock);
+ atomic_inc(&inodes_stat.nr_unused);
+ }
spin_unlock(&inode->i_lock);
spin_unlock(&sb_inode_list_lock);
return;
@@ -1392,11 +1385,14 @@
WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_WILL_FREE;
__remove_inode_hash(inode);
- atomic_dec(&inodes_stat.nr_unused);
}
- spin_lock(&wb_inode_list_lock);
- list_del_init(&inode->i_list);
- spin_unlock(&wb_inode_list_lock);
+ if (!list_empty(&inode->i_list)) {
+ spin_lock(&wb_inode_list_lock);
+ list_del_init(&inode->i_list);
+ spin_unlock(&wb_inode_list_lock);
+ if (!inode->i_state)
+ atomic_dec(&inodes_stat.nr_unused);
+ }
list_del_init(&inode->i_sb_list);
spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h 2010-10-19 14:18:59.000000000 +1100
+++ linux-2.6/include/linux/fs.h 2010-10-19 14:19:28.000000000 +1100
@@ -1637,16 +1637,17 @@
*
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
-#define I_DIRTY_SYNC 1
-#define I_DIRTY_DATASYNC 2
-#define I_DIRTY_PAGES 4
+#define I_DIRTY_SYNC 0x01
+#define I_DIRTY_DATASYNC 0x02
+#define I_DIRTY_PAGES 0x04
#define __I_NEW 3
#define I_NEW (1 << __I_NEW)
-#define I_WILL_FREE 16
-#define I_FREEING 32
-#define I_CLEAR 64
+#define I_WILL_FREE 0x10
+#define I_FREEING 0x20
+#define I_CLEAR 0x40
#define __I_SYNC 7
#define I_SYNC (1 << __I_SYNC)
+#define I_REFERENCED 0x100
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
@@ -2187,7 +2188,6 @@
extern int insert_inode_locked(struct inode *);
extern void unlock_new_inode(struct inode *);
-extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void end_writeback(struct inode *);
extern void destroy_inode(struct inode *);
@@ -2401,6 +2401,12 @@
extern void save_mount_options(struct super_block *sb, char *options);
extern void replace_mount_options(struct super_block *sb, char *options);
+static inline void __iget(struct inode *inode)
+{
+ assert_spin_locked(&inode->i_lock);
+ inode->i_count++;
+}
+
static inline ino_t parent_ino(struct dentry *dentry)
{
ino_t res;
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c 2010-10-19 14:18:59.000000000 +1100
+++ linux-2.6/fs/fs-writeback.c 2010-10-19 14:19:25.000000000 +1100
@@ -416,14 +416,9 @@
* completion.
*/
redirty_tail(inode);
- } else if (inode->i_count) {
- /*
- * The inode is clean, inuse
- */
- list_move(&inode->i_list, &inode_in_use);
} else {
/*
- * The inode is clean, unused
+ * The inode is clean
*/
list_move(&inode->i_list, &inode_unused);
}
Index: linux-2.6/include/linux/writeback.h
===================================================================
--- linux-2.6.orig/include/linux/writeback.h 2010-10-19 14:18:59.000000000 +1100
+++ linux-2.6/include/linux/writeback.h 2010-10-19 14:19:23.000000000 +1100
@@ -11,7 +11,6 @@
extern spinlock_t sb_inode_list_lock;
extern spinlock_t wb_inode_list_lock;
-extern struct list_head inode_in_use;
extern struct list_head inode_unused;
/*
next prev parent reply other threads:[~2010-10-19 4:01 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-19 3:42 [patch 00/35] my inode scaling series for review npiggin
2010-10-19 3:42 ` [patch 01/35] bit_spinlock: add required includes npiggin
2010-10-19 3:42 ` [patch 02/35] kernel: add bl_list npiggin
2010-10-19 3:42 ` [patch 03/35] mm: implement per-zone shrinker npiggin
2010-10-19 4:49 ` KOSAKI Motohiro
2010-10-19 5:33 ` Nick Piggin
2010-10-19 5:40 ` KOSAKI Motohiro
2010-10-19 3:42 ` [patch 04/35] vfs: convert inode and dentry caches to " npiggin
2010-10-19 3:42 ` [patch 05/35] fs: icache lock s_inodes list npiggin
2010-10-19 3:42 ` [patch 06/35] fs: icache lock inode hash npiggin
2010-10-19 3:42 ` [patch 07/35] fs: icache lock i_state npiggin
2010-10-19 10:47 ` Miklos Szeredi
2010-10-19 17:06 ` Peter Zijlstra
2010-10-19 3:42 ` [patch 08/35] fs: icache lock i_count npiggin
2010-10-19 10:16 ` Boaz Harrosh
2010-10-20 2:14 ` Nick Piggin
2010-10-19 3:42 ` [patch 09/35] fs: icache lock lru/writeback lists npiggin
2010-10-19 3:42 ` [patch 10/35] fs: icache atomic inodes_stat npiggin
2010-10-19 3:42 ` [patch 11/35] fs: icache lock inode state npiggin
2010-10-19 3:42 ` [patch 12/35] fs: inode atomic last_ino, iunique lock npiggin
2010-10-19 3:42 ` [patch 13/35] fs: icache remove inode_lock npiggin
2010-10-19 3:42 ` [patch 14/35] fs: icache factor hash lock into functions npiggin
2010-10-19 3:42 ` [patch 15/35] fs: icache per-bucket inode hash locks npiggin
2010-10-19 3:42 ` npiggin [this message]
2010-10-19 3:42 ` [patch 17/35] fs: icache RCU free inodes npiggin
2010-10-19 3:42 ` [patch 18/35] fs: avoid inode RCU freeing for pseudo fs npiggin
2010-10-19 3:42 ` [patch 19/35] fs: icache remove redundant i_sb_list umount locking npiggin
2010-10-20 12:46 ` Al Viro
2010-10-20 13:03 ` Nick Piggin
2010-10-20 13:27 ` Al Viro
2010-10-19 3:42 ` [patch 20/35] fs: icache rcu walk for i_sb_list npiggin
2010-10-19 3:42 ` [patch 21/35] fs: icache per-cpu nr_inodes, non-atomic nr_unused counters npiggin
2010-10-19 3:42 ` [patch 22/35] fs: icache per-cpu last_ino allocator npiggin
2010-10-19 3:42 ` [patch 23/35] fs: icache use per-CPU lists and locks for sb inode lists npiggin
2010-10-19 15:33 ` Miklos Szeredi
2010-10-20 2:37 ` Nick Piggin
2010-10-19 3:42 ` [patch 24/35] fs: icache use RCU to avoid locking in hash lookups npiggin
2010-10-19 3:42 ` [patch 25/35] fs: icache reduce some locking overheads npiggin
2010-10-19 3:42 ` [patch 26/35] fs: icache alloc anonymous inode allocation npiggin
2010-10-19 15:50 ` Miklos Szeredi
2010-10-20 2:38 ` Nick Piggin
2010-10-19 16:33 ` Christoph Hellwig
2010-10-20 3:07 ` Nick Piggin
2010-10-19 3:42 ` [patch 27/35] fs: icache split IO and LRU lists npiggin
2010-10-19 16:12 ` Miklos Szeredi
2010-10-20 2:41 ` Nick Piggin
2010-10-19 3:42 ` [patch 28/35] fs: icache split writeback and lru locks npiggin
2010-10-19 3:42 ` [patch 29/35] fs: icache per-bdi writeback list locking npiggin
2010-10-19 3:42 ` [patch 30/35] fs: icache lazy LRU avoid LRU locking after IO operation npiggin
2010-10-19 3:42 ` [patch 31/35] fs: icache per-zone inode LRU npiggin
2010-10-19 12:38 ` Dave Chinner
2010-10-20 2:35 ` Nick Piggin
2010-10-20 3:12 ` Nick Piggin
2010-10-20 9:43 ` Dave Chinner
2010-10-20 10:02 ` Nick Piggin
2010-10-20 3:14 ` KOSAKI Motohiro
2010-10-20 3:20 ` Nick Piggin
2010-10-20 3:29 ` KOSAKI Motohiro
2010-10-20 10:19 ` Dave Chinner
2010-10-20 10:41 ` Nick Piggin
2010-10-19 3:42 ` [patch 32/35] fs: icache minimise I_FREEING latency npiggin
2010-10-19 3:42 ` [patch 33/35] fs: icache introduce inode_get/inode_get_ilock npiggin
2010-10-19 10:17 ` Boaz Harrosh
2010-10-20 2:17 ` Nick Piggin
2010-10-19 3:42 ` [patch 34/35] fs: inode rename i_count to i_refs npiggin
2010-10-19 3:42 ` [patch 35/35] fs: icache document more lock orders npiggin
2010-10-19 16:22 ` [patch 00/35] my inode scaling series for review Christoph Hellwig
2010-10-20 3:05 ` Nick Piggin
2010-10-20 13:14 ` Al Viro
2010-10-20 13:59 ` 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=20101019034657.147371115@kernel.dk \
--to=npiggin@kernel.dk \
--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).