[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20081126195824.GB3541@srcf.ucam.org>
Date: Wed, 26 Nov 2008 19:58:24 +0000
From: Matthew Garrett <mjg@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org, mingo@...hat.com,
val.henson@...il.com
Subject: [PATCH 2/2] relatime: Allow making relatime the default behaviour
Allow the kernel to enable relatime on all mounts by default. This can
be configured at build time or by a kernel parameter or sysctl. Also add
an MS_NORELATIME mount option to allow the default to be overridden for
specific mount points.
Signed-off-by: Matthew Garrett <mjg@...hat.com>
---
Updated version of Ingo's patch, but adds MS_NORELATIME. util-linux will
need updating to match if this is merged.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e0f346d..eba3b07 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -616,6 +616,10 @@ and is between 256 and 4096 characters. It is defined in the file
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.
+
vt.default_utf8=
[VT]
Format=<0|1>
@@ -1847,6 +1851,10 @@ 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/Kconfig b/fs/Kconfig
index 522469a..fcd3d48 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -1546,6 +1546,29 @@ config 9P_FS
endif # NETWORK_FILESYSTEMS
+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"
diff --git a/fs/inode.c b/fs/inode.c
index 348fa16..51e9ae1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1185,6 +1185,17 @@ EXPORT_SYMBOL(bmap);
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.
diff --git a/fs/namespace.c b/fs/namespace.c
index 65b3dc8..76f30b5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1883,6 +1883,24 @@ int copy_mount_options(const void __user * data, unsigned long *where)
}
/*
+ * 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).
*
@@ -1930,6 +1948,11 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
mnt_flags |= MNT_NODIRATIME;
if (flags & MS_RELATIME)
mnt_flags |= MNT_RELATIME;
+ else if (default_relatime &&
+ !(flags & (MS_NOATIME | MS_NODIRATIME | MS_NORELATIME))) {
+ mnt_flags |= MNT_RELATIME;
+ flags |= MS_RELATIME;
+ }
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0dcdd94..a4db010 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,6 +135,7 @@ extern int dir_notify_enable;
#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
+#define MS_NORELATIME (1<<24) /* Disable relatie even if the default */
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
diff --git a/include/linux/mount.h b/include/linux/mount.h
index cab2a85..71c7bc0 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -112,4 +112,7 @@ 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 default_relatime;
+extern int relatime_interval;
+
#endif /* _LINUX_MOUNT_H */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9d048fa..872c3d3 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 +1335,22 @@ static struct 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,
+ },
+ {
+ .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@...f.ucam.org
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists