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 10/52] fs: dcache scale lru
Date: Thu, 24 Jun 2010 13:02:22 +1000 [thread overview]
Message-ID: <20100624030727.176185416@suse.de> (raw)
In-Reply-To: 20100624030212.676457061@suse.de
[-- Attachment #1: fs-dcache-scale-d_lru.patch --]
[-- Type: text/plain, Size: 8027 bytes --]
Add a new lock, dcache_lru_lock, to protect the dcache hash table from
concurrent modification. d_lru is also protected by d_lock.
Move lru scanning out from underneath dcache_lock.
XXX Maybe do that in another patch
Signed-off-by: Nick Piggin <npiggin@suse.de>
---
fs/dcache.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++------------
1 file changed, 85 insertions(+), 20 deletions(-)
Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c
+++ linux-2.6/fs/dcache.c
@@ -37,11 +37,19 @@
/*
* Usage:
- * dcache_hash_lock protects dcache hash table
+ * dcache_hash_lock protects:
+ * - the dcache hash table
+ * dcache_lru_lock protects:
+ * - the dcache lru lists and counters
+ * d_lock protects:
+ * - d_flags
+ * - d_name
+ * - d_lru
*
* Ordering:
* dcache_lock
* dentry->d_lock
+ * dcache_lru_lock
* dcache_hash_lock
*
* if (dentry1 < dentry2)
@@ -52,6 +60,7 @@ int sysctl_vfs_cache_pressure __read_mos
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_hash_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
@@ -138,37 +147,56 @@ static void dentry_iput(struct dentry *
}
/*
- * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held.
+ * dentry_lru_(add|add_tail|del|del_init) must be called with d_lock held
+ * to protect list_empty(d_lru) condition.
*/
static void dentry_lru_add(struct dentry *dentry)
{
+ spin_lock(&dcache_lru_lock);
list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
dentry_stat.nr_unused++;
+ spin_unlock(&dcache_lru_lock);
}
static void dentry_lru_add_tail(struct dentry *dentry)
{
+ spin_lock(&dcache_lru_lock);
list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
dentry->d_sb->s_nr_dentry_unused++;
dentry_stat.nr_unused++;
+ spin_unlock(&dcache_lru_lock);
+}
+
+static void __dentry_lru_del(struct dentry *dentry)
+{
+ list_del(&dentry->d_lru);
+ dentry->d_sb->s_nr_dentry_unused--;
+ dentry_stat.nr_unused--;
+}
+
+static void __dentry_lru_del_init(struct dentry *dentry)
+{
+ list_del_init(&dentry->d_lru);
+ dentry->d_sb->s_nr_dentry_unused--;
+ dentry_stat.nr_unused--;
}
static void dentry_lru_del(struct dentry *dentry)
{
if (!list_empty(&dentry->d_lru)) {
- list_del(&dentry->d_lru);
- dentry->d_sb->s_nr_dentry_unused--;
- dentry_stat.nr_unused--;
+ spin_lock(&dcache_lru_lock);
+ __dentry_lru_del(dentry);
+ spin_unlock(&dcache_lru_lock);
}
}
static void dentry_lru_del_init(struct dentry *dentry)
{
if (likely(!list_empty(&dentry->d_lru))) {
- list_del_init(&dentry->d_lru);
- dentry->d_sb->s_nr_dentry_unused--;
- dentry_stat.nr_unused--;
+ spin_lock(&dcache_lru_lock);
+ __dentry_lru_del_init(dentry);
+ spin_unlock(&dcache_lru_lock);
}
}
@@ -179,6 +207,8 @@ static void dentry_lru_del_init(struct d
* The dentry must already be unhashed and removed from the LRU.
*
* If this is the root of the dentry tree, return NULL.
+ *
+ * dcache_lock and d_lock must be held by caller, are dropped by d_kill.
*/
static struct dentry *d_kill(struct dentry *dentry)
__releases(dentry->d_lock)
@@ -333,11 +363,19 @@ int d_invalidate(struct dentry * dentry)
EXPORT_SYMBOL(d_invalidate);
/* This should be called _only_ with dcache_lock held */
+static inline struct dentry * __dget_locked_dlock(struct dentry *dentry)
+{
+ atomic_inc(&dentry->d_count);
+ dentry_lru_del_init(dentry);
+ return dentry;
+}
static inline struct dentry * __dget_locked(struct dentry *dentry)
{
atomic_inc(&dentry->d_count);
+ spin_lock(&dentry->d_lock);
dentry_lru_del_init(dentry);
+ spin_unlock(&dentry->d_lock);
return dentry;
}
@@ -416,7 +454,7 @@ restart:
list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!atomic_read(&dentry->d_count)) {
- __dget_locked(dentry);
+ __dget_locked_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
@@ -449,17 +487,18 @@ static void prune_one_dentry(struct dent
* Prune ancestors. Locking is simpler than in dput(),
* because dcache_lock needs to be taken anyway.
*/
- spin_lock(&dcache_lock);
while (dentry) {
- if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock))
+ spin_lock(&dcache_lock);
+ if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock)) {
+ spin_unlock(&dcache_lock);
return;
+ }
if (dentry->d_op && dentry->d_op->d_delete)
dentry->d_op->d_delete(dentry);
dentry_lru_del_init(dentry);
__d_drop(dentry);
dentry = d_kill(dentry);
- spin_lock(&dcache_lock);
}
}
@@ -480,10 +519,11 @@ static void __shrink_dcache_sb(struct su
BUG_ON(!sb);
BUG_ON((flags & DCACHE_REFERENCED) && count == NULL);
- spin_lock(&dcache_lock);
if (count != NULL)
/* called from prune_dcache() and shrink_dcache_parent() */
cnt = *count;
+relock:
+ spin_lock(&dcache_lru_lock);
restart:
if (count == NULL)
list_splice_init(&sb->s_dentry_lru, &tmp);
@@ -493,7 +533,10 @@ restart:
struct dentry, d_lru);
BUG_ON(dentry->d_sb != sb);
- spin_lock(&dentry->d_lock);
+ if (!spin_trylock(&dentry->d_lock)) {
+ spin_unlock(&dcache_lru_lock);
+ goto relock;
+ }
/*
* If we are honouring the DCACHE_REFERENCED flag and
* the dentry has this flag set, don't free it. Clear
@@ -511,13 +554,22 @@ restart:
if (!cnt)
break;
}
- cond_resched_lock(&dcache_lock);
+ cond_resched_lock(&dcache_lru_lock);
}
}
+ spin_unlock(&dcache_lru_lock);
+
+ spin_lock(&dcache_lock);
+again:
+ spin_lock(&dcache_lru_lock); /* lru_lock also protects tmp list */
while (!list_empty(&tmp)) {
dentry = list_entry(tmp.prev, struct dentry, d_lru);
- dentry_lru_del_init(dentry);
- spin_lock(&dentry->d_lock);
+
+ if (!spin_trylock(&dentry->d_lock)) {
+ spin_unlock(&dcache_lru_lock);
+ goto again;
+ }
+ __dentry_lru_del_init(dentry);
/*
* We found an inuse dentry which was not removed from
* the LRU because of laziness during lookup. Do not free
@@ -527,17 +579,22 @@ restart:
spin_unlock(&dentry->d_lock);
continue;
}
+
+ spin_unlock(&dcache_lru_lock);
prune_one_dentry(dentry);
- /* dentry->d_lock was dropped in prune_one_dentry() */
- cond_resched_lock(&dcache_lock);
+ /* dcache_lock and dentry->d_lock dropped */
+ spin_lock(&dcache_lock);
+ spin_lock(&dcache_lru_lock);
}
+ spin_unlock(&dcache_lock);
+
if (count == NULL && !list_empty(&sb->s_dentry_lru))
goto restart;
if (count != NULL)
*count = cnt;
if (!list_empty(&referenced))
list_splice(&referenced, &sb->s_dentry_lru);
- spin_unlock(&dcache_lock);
+ spin_unlock(&dcache_lru_lock);
}
/**
@@ -645,7 +702,9 @@ static void shrink_dcache_for_umount_sub
/* detach this root from the system */
spin_lock(&dcache_lock);
+ spin_lock(&dentry->d_lock);
dentry_lru_del_init(dentry);
+ spin_unlock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dcache_lock);
@@ -659,7 +718,9 @@ static void shrink_dcache_for_umount_sub
spin_lock(&dcache_lock);
list_for_each_entry(loop, &dentry->d_subdirs,
d_u.d_child) {
+ spin_lock(&loop->d_lock);
dentry_lru_del_init(loop);
+ spin_unlock(&loop->d_lock);
__d_drop(loop);
cond_resched_lock(&dcache_lock);
}
@@ -843,13 +904,17 @@ resume:
struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
next = tmp->next;
+ spin_lock(&dentry->d_lock);
dentry_lru_del_init(dentry);
+ spin_unlock(&dentry->d_lock);
/*
* move only zero ref count dentries to the end
* of the unused list for prune_dcache
*/
if (!atomic_read(&dentry->d_count)) {
+ spin_lock(&dentry->d_lock);
dentry_lru_add_tail(dentry);
+ spin_unlock(&dentry->d_lock);
found++;
}
next prev parent reply other threads:[~2010-06-24 3:15 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 ` npiggin [this message]
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 ` [patch 48/52] fs: icache split IO and LRU lists npiggin
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=20100624030727.176185416@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).