Re: [PATCH] [1/2] Optimization for touch_atime

[Valerie Aurora <vaurora@redhat.com>]

On Mon, Jul 06, 2009 at 09:24:46PM +0200, Andi Kleen wrote:
> 
> Some benchmark testing shows touch_atime to be high up in profile
> logs for IO intensive workloads. Most likely that's due to the lock
> in mnt_want_write().  Unfortunately touch_atime first takes the lock,
> and then does all the other tests that could avoid atime updates (like
> noatime or relatime).
> 
> Do it the other way round -- first try to avoid the update and only
> then if that didn't succeed take the lock. That works because none of
> the atime avoidance tests rely on locking.
> 
> This also eliminates a goto.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> ---
>  fs/inode.c |   20 ++++++++++----------
>  1 file changed, 10 insertions(+), 10 deletions(-)
> 
> Index: linux-2.6.30-ak/fs/inode.c
> ===================================================================
> --- linux-2.6.30-ak.orig/fs/inode.c
> +++ linux-2.6.30-ak/fs/inode.c
> @@ -1361,31 +1361,31 @@ void touch_atime(struct vfsmount *mnt, s
>  	struct inode *inode = dentry->d_inode;
>  	struct timespec now;
>  
> -	if (mnt_want_write(mnt))
> -		return;
>  	if (inode->i_flags & S_NOATIME)
> -		goto out;
> +		return;
>  	if (IS_NOATIME(inode))
> -		goto out;
> +		return;
>  	if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
> -		goto out;
> +		return;
>  
>  	if (mnt->mnt_flags & MNT_NOATIME)
> -		goto out;
> +		return;
>  	if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
> -		goto out;
> +		return;
>  
>  	now = current_fs_time(inode->i_sb);
>  
>  	if (!relatime_need_update(mnt, inode, now))
> -		goto out;
> +		return;
>  
>  	if (timespec_equal(&inode->i_atime, &now))
> -		goto out;
> +		return;
> +
> +	if (mnt_want_write(mnt))
> +		return;
>  
>  	inode->i_atime = now;
>  	mark_inode_dirty_sync(inode);
> -out:
>  	mnt_drop_write(mnt);
>  }
>  EXPORT_SYMBOL(touch_atime);

Nice!

Reviewed-by: Valerie Aurora <vaurora@redhat.com>

-VAL