[PATCH v4] relatime: Make relatime smarter

[Matthew Garrett]

Make relatime smarter
    
Allow atime to be updated once per day even with relatime. This lets
utilities like tmpreaper (which delete files based on last access time)
continue working. The time between atime updates can be configured at boot
with the relatime_interval kernel argument, or at runtime through a sysctl.
    
Signed-off-by: Matthew Garrett <mjg@xxxxxxxxxx>

---

Adds Christoph's suggestions.

 Documentation/kernel-parameters.txt |    4 ++
 fs/inode.c                          |   63 ++++++++++++++++++++++++++++++-----
 include/linux/mount.h               |    2 +
 kernel/sysctl.c                     |    9 +++++
 4 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e0f346d..6d0dc0a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1847,6 +1847,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			[KNL, SMP] Set scheduler's default relax_domain_level.
 			See Documentation/cpusets.txt.
 
+	relatime_interval=
+			[FS] relative atime update frequency, in seconds.
+			(default: 1 day: 86400 seconds)
+
 	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
 
 	reservetop=	[X86-32]
diff --git a/fs/inode.c b/fs/inode.c
index 0487ddb..4899063 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1179,6 +1179,56 @@ sector_t bmap(struct inode * inode, sector_t block)
 }
 EXPORT_SYMBOL(bmap);
 
+/*
+ * Relative atime updates frequency (default: 1 day):
+ */
+int relatime_interval __read_mostly = 24*60*60;
+
+/*
+ * Allow overriding the default relatime value on the kernel command line
+ */
+static int __init set_relatime_interval(char *str)
+{
+	get_option(&str, &relatime_interval);
+
+	return 1;
+}
+__setup("relatime_interval=", set_relatime_interval);
+
+/*
+ * With relative atime, only update atime if the
+ * previous atime is earlier than either the ctime or
+ * mtime.
+ */
+static int atime_need_update(struct vfsmount *mnt, struct inode *inode,
+			     struct timespec now)
+{
+
+	if (!(mnt->mnt_flags & MNT_RELATIME))
+		return 1;
+	/*
+	 * 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 the update interval?
+	 * If yes, update atime:
+	 */
+	if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= relatime_interval)
+		return 1;
+	/*
+	 * Good, we can skip the atime update:
+	 */
+	return 0;
+}
+
 /**
  *	touch_atime	-	update the access time
  *	@mnt: mount the inode is accessed on
@@ -1206,17 +1256,12 @@ void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
 		goto out;
 	if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
 		goto out;
-	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)
-			goto out;
-	}
 
 	now = current_fs_time(inode->i_sb);
+
+	if (!atime_need_update(mnt, inode, now))
+		goto out;
+
 	if (timespec_equal(&inode->i_atime, &now))
 		goto out;
 
diff --git a/include/linux/mount.h b/include/linux/mount.h
index cab2a85..978fb10 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -112,4 +112,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts);
 extern spinlock_t vfsmount_lock;
 extern dev_t name_to_dev_t(char *name);
 
+extern int relatime_interval;
+
 #endif /* _LINUX_MOUNT_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9d048fa..f085ad6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -29,6 +29,7 @@
 #include <linux/utsname.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>
@@ -1334,6 +1335,14 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "relatime_interval",
+		.data		= &relatime_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
 		.ctl_name	= CTL_UNNUMBERED,

-- 
Matthew Garrett | mjg59@xxxxxxxxxxxxx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/