From: npiggin@kernel.dk
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [patch 10/35] fs: icache atomic inodes_stat
Date: Tue, 19 Oct 2010 14:42:26 +1100 [thread overview]
Message-ID: <20101019034656.515395530@kernel.dk> (raw)
In-Reply-To: 20101019034216.319085068@kernel.dk
[-- Attachment #1: fs-inode_lock-scale-5.patch --]
[-- Type: text/plain, Size: 5402 bytes --]
Protect inodes_stat statistics with atomic ops rather than inode_lock.
Also move nr_inodes statistic into low level inode init and teardown
functions in anticipation of future patches which skip putting some
inodes (eg. sockets) onto sb list.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
fs/fs-writeback.c | 6 ++++--
fs/inode.c | 28 +++++++++++++---------------
include/linux/fs.h | 11 ++++++++---
3 files changed, 25 insertions(+), 20 deletions(-)
Index: linux-2.6/fs/fs-writeback.c
===================================================================
--- linux-2.6.orig/fs/fs-writeback.c 2010-10-19 14:37:09.000000000 +1100
+++ linux-2.6/fs/fs-writeback.c 2010-10-19 14:37:31.000000000 +1100
@@ -772,7 +772,8 @@
wb->last_old_flush = jiffies;
nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+ (atomic_read(&inodes_stat.nr_inodes) -
+ atomic_read(&inodes_stat.nr_unused));
if (nr_pages) {
struct wb_writeback_work work = {
@@ -1156,7 +1157,8 @@
WARN_ON(!rwsem_is_locked(&sb->s_umount));
work.nr_pages = nr_dirty + nr_unstable +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+ (atomic_read(&inodes_stat.nr_inodes) -
+ atomic_read(&inodes_stat.nr_unused));
bdi_queue_work(sb->s_bdi, &work);
wait_for_completion(&done);
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c 2010-10-19 14:37:09.000000000 +1100
+++ linux-2.6/fs/inode.c 2010-10-19 14:37:56.000000000 +1100
@@ -122,7 +122,10 @@
/*
* Statistics gathering..
*/
-struct inodes_stat_t inodes_stat;
+struct inodes_stat_t inodes_stat = {
+ .nr_inodes = ATOMIC_INIT(0),
+ .nr_unused = ATOMIC_INIT(0),
+};
static struct kmem_cache *inode_cachep __read_mostly;
@@ -213,6 +216,8 @@
inode->i_fsnotify_mask = 0;
#endif
+ atomic_inc(&inodes_stat.nr_inodes);
+
return 0;
out:
return -ENOMEM;
@@ -253,6 +258,7 @@
if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_default_acl);
#endif
+ atomic_dec(&inodes_stat.nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);
@@ -313,7 +319,7 @@
list_move(&inode->i_list, &inode_in_use);
spin_unlock(&wb_inode_list_lock);
}
- inodes_stat.nr_unused--;
+ atomic_dec(&inodes_stat.nr_unused);
}
void end_writeback(struct inode *inode)
@@ -354,8 +360,6 @@
*/
static void dispose_list(struct list_head *head)
{
- int nr_disposed = 0;
-
while (!list_empty(head)) {
struct inode *inode;
@@ -375,11 +379,7 @@
wake_up_inode(inode);
destroy_inode(inode);
- nr_disposed++;
}
- spin_lock(&inode_lock);
- inodes_stat.nr_inodes -= nr_disposed;
- spin_unlock(&inode_lock);
}
/*
@@ -428,7 +428,7 @@
busy = 1;
}
/* only unused inodes may be cached with i_count zero */
- inodes_stat.nr_unused -= count;
+ atomic_sub(count, &inodes_stat.nr_unused);
return busy;
}
@@ -545,7 +545,7 @@
spin_unlock(&inode->i_lock);
nr_pruned++;
}
- inodes_stat.nr_unused -= nr_pruned;
+ atomic_sub(nr_pruned, &inodes_stat.nr_unused);
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
else
@@ -574,7 +574,7 @@
unsigned long nr;
shrinker_add_scan(&nr_to_scan, scanned, global,
- inodes_stat.nr_unused,
+ atomic_read(&inodes_stat.nr_unused),
SHRINK_DEFAULT_SEEKS * 100 / sysctl_vfs_cache_pressure);
/*
* Nasty deadlock avoidance. We may hold various FS locks,
@@ -680,7 +680,6 @@
__inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
struct inode *inode)
{
- inodes_stat.nr_inodes++;
spin_lock(&sb_inode_list_lock);
list_add(&inode->i_sb_list, &sb->s_inodes);
spin_unlock(&sb_inode_list_lock);
@@ -1344,7 +1343,7 @@
list_move(&inode->i_list, &inode_unused);
spin_unlock(&wb_inode_list_lock);
}
- inodes_stat.nr_unused++;
+ atomic_inc(&inodes_stat.nr_unused);
if (sb->s_flags & MS_ACTIVE) {
spin_unlock(&inode->i_lock);
spin_unlock(&sb_inode_list_lock);
@@ -1362,10 +1361,10 @@
spin_lock(&inode->i_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_WILL_FREE;
- inodes_stat.nr_unused--;
spin_lock(&inode_hash_lock);
hlist_del_init(&inode->i_hash);
spin_unlock(&inode_hash_lock);
+ atomic_dec(&inodes_stat.nr_unused);
}
spin_lock(&wb_inode_list_lock);
list_del_init(&inode->i_list);
@@ -1374,7 +1373,6 @@
spin_unlock(&sb_inode_list_lock);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
- inodes_stat.nr_inodes--;
spin_unlock(&inode->i_lock);
spin_unlock(&inode_lock);
evict(inode);
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h 2010-10-19 14:37:09.000000000 +1100
+++ linux-2.6/include/linux/fs.h 2010-10-19 14:37:31.000000000 +1100
@@ -40,12 +40,17 @@
};
struct inodes_stat_t {
- int nr_inodes;
- int nr_unused;
+ /*
+ * Using atomics here is a hack which should just happen to
+ * work on all architectures today. Not a big deal though,
+ * because it goes away and gets fixed properly later in the
+ * inode scaling series.
+ */
+ atomic_t nr_inodes;
+ atomic_t nr_unused;
int dummy[5]; /* padding for sysctl ABI compatibility */
};
-
#define NR_FILE 8192 /* this can well be larger on a larger system */
#define MAY_EXEC 1
next prev parent reply other threads:[~2010-10-19 3:56 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 ` npiggin [this message]
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 ` [patch 16/35] fs: icache lazy inode lru npiggin
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=20101019034656.515395530@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).