[patch] implement smarter atime updates support

[Ingo Molnar <mingo@elte.hu>]

* Ingo Molnar <mingo@elte.hu> wrote:

> tested it by moving the date forward:
> 
>   # date
>   Sun Aug  5 22:55:14 CEST 2007
>   # date -s "Tue Aug  7 22:55:14 CEST 2007"
>   Tue Aug  7 22:55:14 CEST 2007
> 
> access to a file did not generate disk IO before the date was set, and 
> it generated exactly one IO after the date was set.
> 
> ( should i perhaps reduce the number of boot options and only use a
>   single "norelatime_default" boot option to turn this off? )

ok, cleaned it up some more: only a single, consistent boot option and 
all the switches (be that config, boot or sysctl) are now called 
"default_relatime". Also, got rid of that #ifdef ugliness in namespace.c 
via a cleaner Kconfig solution (suggested by Peter Zijlstra).

	Ingo

---------------------------->
Subject: [patch] implement smarter atime updates support
From: Ingo Molnar <mingo@elte.hu>

change relatime updates to be performed once per day. This makes
relatime a compatible solution for HSM, mailer-notification and
tmpwatch applications too.

also add the CONFIG_DEFAULT_RELATIME kernel option, which makes
"norelatime" the default for all mounts without an extra kernel
boot option.

add the "default_relatime=0" boot option to turn this off.

also add the /proc/sys/kernel/default_relatime flag which can be changed
runtime to modify the behavior of subsequent new mounts.

tested by moving the date forward:

   # date
   Sun Aug  5 22:55:14 CEST 2007
   # date -s "Tue Aug  7 22:55:14 CEST 2007"
   Tue Aug  7 22:55:14 CEST 2007

access to a file did not generate disk IO before the date was set, and
it generated exactly one IO after the date was set.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/kernel-parameters.txt |    4 +++
 fs/Kconfig                          |   22 ++++++++++++++++
 fs/inode.c                          |   48 ++++++++++++++++++++++++++----------
 fs/namespace.c                      |   25 ++++++++++++++++++
 include/linux/mount.h               |    2 +
 kernel/sysctl.c                     |    9 ++++++
 6 files changed, 97 insertions(+), 13 deletions(-)

Index: linux/Documentation/kernel-parameters.txt
===================================================================
--- linux.orig/Documentation/kernel-parameters.txt
+++ linux/Documentation/kernel-parameters.txt
@@ -525,6 +525,10 @@ and is between 256 and 4096 characters. 
 			This is a 16-member array composed of values
 			ranging from 0-255.
 
+	default_relatime=
+			[FS] mount all filesystems with relative atime
+			updates by default.
+
 	default_utf8=   [VT]
 			Format=<0|1>
 			Set system-wide default UTF-8 mode for all tty's.
Index: linux/fs/Kconfig
===================================================================
--- linux.orig/fs/Kconfig
+++ linux/fs/Kconfig
@@ -2060,6 +2060,28 @@ config 9P_FS
 
 endmenu
 
+config DEFAULT_RELATIME
+	bool "Mount all filesystems with relatime by default"
+	default y
+	help
+	  If you say Y here, all your filesystems will be mounted
+	  with the "relatime" mount option. This eliminates many atime
+	  ('file last accessed' timestamp) updates (which otherwise
+	  is performed on every file access and generates a write
+	  IO to the inode) and thus speeds up IO. Atime is still updated,
+	  but only once per day.
+
+	  The mtime ('file last modified') and ctime ('file created')
+	  timestamp are unaffected by this change.
+
+	  Use the "norelatime" kernel boot option to turn off this
+	  feature.
+
+config DEFAULT_RELATIME_VAL
+	int
+	default "1" if DEFAULT_RELATIME
+	default "0"
+
 if BLOCK
 menu "Partition Types"
 
Index: linux/fs/inode.c
===================================================================
--- linux.orig/fs/inode.c
+++ linux/fs/inode.c
@@ -1162,6 +1162,36 @@ sector_t bmap(struct inode * inode, sect
 }
 EXPORT_SYMBOL(bmap);
 
+/*
+ * With relative atime, only update atime if the
+ * previous atime is earlier than either the ctime or
+ * mtime.
+ */
+static int relatime_need_update(struct inode *inode, struct timespec now)
+{
+	/*
+	 * Is mtime younger than atime? If yes, update atime:
+	 */
+	if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0)
+		return 1;
+	/*
+	 * Is ctime younger than atime? If yes, update atime:
+	 */
+	if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0)
+		return 1;
+
+	/*
+	 * Is the previous atime value older than a day? If yes,
+	 * update atime:
+	 */
+	if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60)
+		return 1;
+	/*
+	 * Good, we can skip the atime update:
+	 */
+	return 0;
+}
+
 /**
  *	touch_atime	-	update the access time
  *	@mnt: mount the inode is accessed on
@@ -1191,22 +1221,14 @@ void touch_atime(struct vfsmount *mnt, s
 			return;
 		if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
 			return;
-
-		if (mnt->mnt_flags & MNT_RELATIME) {
-			/*
-			 * With relative atime, only update atime if the
-			 * previous atime is earlier than either the ctime or
-			 * mtime.
-			 */
-			if (timespec_compare(&inode->i_mtime,
-						&inode->i_atime) < 0 &&
-			    timespec_compare(&inode->i_ctime,
-						&inode->i_atime) < 0)
+	}
+	now = current_fs_time(inode->i_sb);
+	if (mnt) {
+		if (mnt->mnt_flags & MNT_RELATIME)
+			if (!relatime_need_update(inode, now))
 				return;
-		}
 	}
 
-	now = current_fs_time(inode->i_sb);
 	if (timespec_equal(&inode->i_atime, &now))
 		return;
 
Index: linux/fs/namespace.c
===================================================================
--- linux.orig/fs/namespace.c
+++ linux/fs/namespace.c
@@ -1107,6 +1107,8 @@ int do_add_mount(struct vfsmount *newmnt
 		goto unlock;
 
 	newmnt->mnt_flags = mnt_flags;
+	WARN_ON_ONCE(newmnt->mnt_flags & MNT_RELATIME);
+
 	if ((err = graft_tree(newmnt, nd)))
 		goto unlock;
 
@@ -1362,6 +1364,24 @@ int copy_mount_options(const void __user
 }
 
 /*
+ * Allow users to disable (or enable) atime updates via a .config
+ * option or via the boot line, or via /proc/sys/fs/default_relatime:
+ */
+int default_relatime __read_mostly = CONFIG_DEFAULT_RELATIME_VAL;
+
+static int __init set_default_relatime(char *str)
+{
+	get_option(&str, &default_relatime);
+
+	printk(KERN_INFO "Mount all filesystems with"
+		"default relative atime updates: %s.\n",
+		default_relatime ? "enabled" : "disabled");
+
+	return 1;
+}
+__setup("default_relatime=", set_default_relatime);
+
+/*
  * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
  * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
  *
@@ -1409,6 +1429,11 @@ long do_mount(char *dev_name, char *dir_
 		mnt_flags |= MNT_NODIRATIME;
 	if (flags & MS_RELATIME)
 		mnt_flags |= MNT_RELATIME;
+	else if (default_relatime &&
+				!(flags & (MNT_NOATIME | MNT_NODIRATIME))) {
+		mnt_flags |= MNT_RELATIME;
+		flags |= MS_RELATIME;
+	}
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME);
Index: linux/include/linux/mount.h
===================================================================
--- linux.orig/include/linux/mount.h
+++ linux/include/linux/mount.h
@@ -103,5 +103,7 @@ extern void shrink_submounts(struct vfsm
 extern spinlock_t vfsmount_lock;
 extern dev_t name_to_dev_t(char *name);
 
+extern int default_relatime;
+
 #endif
 #endif /* _LINUX_MOUNT_H */
Index: linux/kernel/sysctl.c
===================================================================
--- linux.orig/kernel/sysctl.c
+++ linux/kernel/sysctl.c
@@ -30,6 +30,7 @@
 #include <linux/capability.h>
 #include <linux/smp_lock.h>
 #include <linux/fs.h>
+#include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
@@ -1206,6 +1207,14 @@ static ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "default_relatime",
+		.data		= &default_relatime,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/