From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Eric Dumazet <dada1@cosmosbay.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Ingo Molnar <mingo@elte.hu>,
Christoph Hellwig <hch@infradead.org>,
David Miller <davem@davemloft.net>,
"Rafael J. Wysocki" <rjw@sisk.pl>,
linux-kernel@vger.kernel.org,
"kernel-testers@vger.kernel.org >> Kernel Testers List"
<kernel-testers@vger.kernel.org>, Mike Galbraith <efault@gmx.de>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Linux Netdev List <netdev@vger.kernel.org>,
Christoph Lameter <cl@linux-foundation.org>,
linux-fsdevel@vger.kernel.org, Al Viro <viro@ZenIV.linux.org.uk>
Subject: Re: [PATCH v3 5/7] fs: new_inode_single() and iput_single()
Date: Tue, 16 Dec 2008 13:41:11 -0800 [thread overview]
Message-ID: <20081216214111.GP6681@linux.vnet.ibm.com> (raw)
In-Reply-To: <494196C7.2050005@cosmosbay.com>
On Thu, Dec 11, 2008 at 11:40:07PM +0100, Eric Dumazet wrote:
> Goal of this patch is to not touch inode_lock for socket/pipes/anonfd
> inodes allocation/freeing.
>
> SINGLE dentries are attached to inodes that dont need to be linked
> in a list of inodes, being "inode_in_use" or "sb->s_inodes"
> As inode_lock was taken only to protect these lists, we avoid taking it
> as well.
>
> Using iput_single() from dput_single() avoids taking inode_lock
> at freeing time.
>
> This patch has a very noticeable effect, because we avoid dirtying of
> three contended cache lines in new_inode(), and five cache lines in iput()
>
> ("socketallocbench -n 8" result : from 19.9s to 3.01s)
Nice!
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
> ---
> fs/anon_inodes.c | 2 +-
> fs/dcache.c | 2 +-
> fs/inode.c | 29 ++++++++++++++++++++---------
> fs/pipe.c | 2 +-
> include/linux/fs.h | 12 +++++++++++-
> net/socket.c | 2 +-
> 6 files changed, 35 insertions(+), 14 deletions(-)
>
> diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
> index 8bf83cb..89fd36d 100644
> --- a/fs/anon_inodes.c
> +++ b/fs/anon_inodes.c
> @@ -125,7 +125,7 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
> */
> static struct inode *anon_inode_mkinode(void)
> {
> - struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
> + struct inode *inode = new_inode_single(anon_inode_mnt->mnt_sb);
>
> if (!inode)
> return ERR_PTR(-ENOMEM);
> diff --git a/fs/dcache.c b/fs/dcache.c
> index af3bfb3..3363853 100644
> --- a/fs/dcache.c
> +++ b/fs/dcache.c
> @@ -231,7 +231,7 @@ static void dput_single(struct dentry *dentry)
> return;
> inode = dentry->d_inode;
> if (inode)
> - iput(inode);
> + iput_single(inode);
> d_free(dentry);
> }
>
> diff --git a/fs/inode.c b/fs/inode.c
> index dc8e72a..0fdfe1b 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -221,6 +221,13 @@ void destroy_inode(struct inode *inode)
> kmem_cache_free(inode_cachep, (inode));
> }
>
> +void iput_single(struct inode *inode)
> +{
> + if (atomic_dec_and_test(&inode->i_count)) {
> + destroy_inode(inode);
> + percpu_counter_dec(&nr_inodes);
> + }
> +}
>
> /*
> * These are initializations that only need to be done
> @@ -587,8 +594,9 @@ static int last_ino_get(void)
> #endif
>
> /**
> - * new_inode - obtain an inode
> + * __new_inode - obtain an inode
> * @sb: superblock
> + * @single: if true, dont link new inode in a list
> *
> * Allocates a new inode for given superblock. The default gfp_mask
> * for allocations related to inode->i_mapping is GFP_HIGHUSER_PAGECACHE.
> @@ -598,7 +606,7 @@ static int last_ino_get(void)
> * newly created inode's mapping
> *
> */
> -struct inode *new_inode(struct super_block *sb)
> +struct inode *__new_inode(struct super_block *sb, int single)
> {
> /*
> * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
> @@ -607,22 +615,25 @@ struct inode *new_inode(struct super_block *sb)
> */
> struct inode * inode;
>
> - spin_lock_prefetch(&inode_lock);
> -
> inode = alloc_inode(sb);
> if (inode) {
> percpu_counter_inc(&nr_inodes);
> inode->i_state = 0;
> inode->i_ino = last_ino_get();
> - spin_lock(&inode_lock);
> - list_add(&inode->i_list, &inode_in_use);
> - list_add(&inode->i_sb_list, &sb->s_inodes);
> - spin_unlock(&inode_lock);
> + if (single) {
> + INIT_LIST_HEAD(&inode->i_list);
> + INIT_LIST_HEAD(&inode->i_sb_list);
> + } else {
> + spin_lock(&inode_lock);
> + list_add(&inode->i_list, &inode_in_use);
> + list_add(&inode->i_sb_list, &sb->s_inodes);
> + spin_unlock(&inode_lock);
> + }
> }
> return inode;
> }
>
> -EXPORT_SYMBOL(new_inode);
> +EXPORT_SYMBOL(__new_inode);
>
> void unlock_new_inode(struct inode *inode)
> {
> diff --git a/fs/pipe.c b/fs/pipe.c
> index 4de6dd5..8c51a0d 100644
> --- a/fs/pipe.c
> +++ b/fs/pipe.c
> @@ -865,7 +865,7 @@ static struct dentry_operations pipefs_dentry_operations = {
>
> static struct inode * get_pipe_inode(void)
> {
> - struct inode *inode = new_inode(pipe_mnt->mnt_sb);
> + struct inode *inode = new_inode_single(pipe_mnt->mnt_sb);
> struct pipe_inode_info *pipe;
>
> if (!inode)
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index a789346..a702d81 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1899,7 +1899,17 @@ extern void __iget(struct inode * inode);
> extern void iget_failed(struct inode *);
> extern void clear_inode(struct inode *);
> extern void destroy_inode(struct inode *);
> -extern struct inode *new_inode(struct super_block *);
> +extern struct inode *__new_inode(struct super_block *, int);
> +static inline struct inode *new_inode(struct super_block *sb)
> +{
> + return __new_inode(sb, 0);
> +}
> +static inline struct inode *new_inode_single(struct super_block *sb)
> +{
> + return __new_inode(sb, 1);
> +}
> +extern void iput_single(struct inode *);
> +
> extern int should_remove_suid(struct dentry *);
> extern int file_remove_suid(struct file *);
>
> diff --git a/net/socket.c b/net/socket.c
> index 353c928..4017409 100644
> --- a/net/socket.c
> +++ b/net/socket.c
> @@ -464,7 +464,7 @@ static struct socket *sock_alloc(void)
> struct inode *inode;
> struct socket *sock;
>
> - inode = new_inode(sock_mnt->mnt_sb);
> + inode = new_inode_single(sock_mnt->mnt_sb);
> if (!inode)
> return NULL;
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2008-12-16 21:41 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <Pine.LNX.4.64.0811201727070.9089@quilx.com>
[not found] ` <20081121083044.GL16242@elte.hu>
[not found] ` <49267694.1030506@cosmosbay.com>
[not found] ` <20081121.010508.40225532.davem@davemloft.net>
[not found] ` <4926AEDB.10007@cosmosbay.com>
[not found] ` <4926D022.5060008@cosmosbay.com>
2008-11-21 15:36 ` [PATCH] fs: pipe/sockets/anon dentries should not have a parent Christoph Hellwig
2008-11-21 17:58 ` [PATCH] fs: pipe/sockets/anon dentries should have themselves as parent Eric Dumazet
[not found] ` <4926F6C5.9030108-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-11-21 18:43 ` Matthew Wilcox
2008-11-23 3:53 ` Eric Dumazet
[not found] ` <20081121152148.GA20388@elte.hu>
[not found] ` <4926D39D.9050603@cosmosbay.com>
[not found] ` <20081121153453.GA23713@elte.hu>
[not found] ` <492DDB6A.8090806@cosmosbay.com>
2008-11-29 8:43 ` [PATCH v2 0/5] fs: Scalability of sockets/pipes allocation/deallocation on SMP Eric Dumazet
2008-12-11 22:38 ` [PATCH v3 0/7] " Eric Dumazet
2008-12-11 22:38 ` [PATCH v3 1/7] fs: Use a percpu_counter to track nr_dentry Eric Dumazet
2007-07-24 1:24 ` Nick Piggin
[not found] ` <49419680.8010409-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-12-16 21:04 ` Paul E. McKenney
2008-12-11 22:39 ` [PATCH v3 2/7] fs: Use a percpu_counter to track nr_inodes Eric Dumazet
[not found] ` <4941968E.3020201-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2007-07-24 1:30 ` Nick Piggin
[not found] ` <200707241130.56767.nickpiggin-/E1597aS9LT0CCvOHzKKcA@public.gmane.org>
2008-12-12 5:11 ` Eric Dumazet
2008-12-16 21:10 ` Paul E. McKenney
2008-12-11 22:39 ` [PATCH v3 3/7] fs: Introduce a per_cpu last_ino allocator Eric Dumazet
2007-07-24 1:34 ` Nick Piggin
2008-12-16 21:26 ` Paul E. McKenney
2008-12-11 22:39 ` [PATCH v3 4/7] fs: Introduce SINGLE dentries for pipes, socket, anon fd Eric Dumazet
[not found] ` <494196AA.6080002-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-12-16 21:40 ` Paul E. McKenney
2008-12-11 22:40 ` [PATCH v3 5/7] fs: new_inode_single() and iput_single() Eric Dumazet
2008-12-16 21:41 ` Paul E. McKenney [this message]
[not found] ` <493100B0.6090104-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-12-11 22:40 ` [PATCH v3 6/7] fs: struct file move from call_rcu() to SLAB_DESTROY_BY_RCU Eric Dumazet
2007-07-24 1:13 ` Nick Piggin
2008-12-12 2:50 ` Nick Piggin
2008-12-12 4:45 ` Eric Dumazet
[not found] ` <4941EC65.5040903-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-12-12 16:48 ` Eric Dumazet
[not found] ` <494295C6.2020906-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-12-13 2:07 ` Christoph Lameter
[not found] ` <Pine.LNX.4.64.0812121958470.15781-dRBSpnHQED8AvxtiuMwx3w@public.gmane.org>
2008-12-17 20:25 ` Eric Dumazet
2008-12-13 1:41 ` Christoph Lameter
2008-12-11 22:41 ` [PATCH v3 7/7] fs: MS_NOREFCOUNT Eric Dumazet
[not found] ` <492DDB6A.8090806-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-11-29 8:43 ` [PATCH v2 1/5] fs: Use a percpu_counter to track nr_dentry Eric Dumazet
2008-11-29 8:43 ` [PATCH v2 2/5] fs: Use a percpu_counter to track nr_inodes Eric Dumazet
2008-11-29 8:44 ` [PATCH v2 4/5] fs: Introduce SINGLE dentries for pipes, socket, anon fd Eric Dumazet
[not found] ` <493100E7.3030907-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2008-11-29 10:38 ` Jörn Engel
[not found] ` <20081129103836.GA11959-PCqxUs/MD9bYtjvyW6yDsg@public.gmane.org>
2008-11-29 11:14 ` Eric Dumazet
2008-11-29 8:45 ` [PATCH v2 5/5] fs: new_inode_single() and iput_single() Eric Dumazet
2008-11-29 11:14 ` Jörn Engel
2008-11-29 8:44 ` [PATCH v2 3/5] fs: Introduce a per_cpu last_ino allocator Eric Dumazet
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=20081216214111.GP6681@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=cl@linux-foundation.org \
--cc=dada1@cosmosbay.com \
--cc=davem@davemloft.net \
--cc=efault@gmx.de \
--cc=hch@infradead.org \
--cc=kernel-testers@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=netdev@vger.kernel.org \
--cc=rjw@sisk.pl \
--cc=viro@ZenIV.linux.org.uk \
/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).