[RFC] introduce sys_syncat to sync a single file system
From: Sage Weil
Date: Thu Mar 03 2011 - 01:34:12 EST
It is frequently useful to sync a single file system, instead of all
mounted file systems via sync(2):
- On machines with many of mounts, it is not at all uncommon for some of
them to hang (e.g. unresponsive NFS server). sync(2) will get stuck on
those and may never get to the one you do care about (e.g., /).
- Some applications (Ceph, dpkg) write lots of data to the file system and
then want to make sure it is flushed to disk. Calling fsync(2) on each
file introduces unnecessary ordering constraints that result in a large
amount of sub-optimal writeback/flush/commit behavior by the file
system.
There are currently two ways (that I know of) to sync a single super_block:
- BLKFLSBUF ioctl on the block device: That also invalidates the bdev
mapping, which isn't usually desirable, and doesn't work for non-block
file systems.
- 'mount -o remount,rw' will call sync_filesystem as an artifact of the
current implemention. Relying on this little-known side effect for
something like data safety sounds foolish.
Both of these approaches require root privileges, which some applications
do not have (nor should they need?) given that sync(2) is an unprivileged
operation.
This patch introduces a new system call syncat(2) that mimics the existing
*at() interfaces by taking an fd and/or path. The fd can be either an
open file descriptor or AT_FDCWD, and the pathname can be either a path or
(unlike the usual *at() style interface) NULL. Only the file system for
the referenced file is synced.
The syscall approach is motivated by comments by Al and Christoph at the
last LSF. A simpler ioctl was also proposed a while back, see
http://marc.info/?l=linux-fsdevel&m=127970513829285&w=2
Is this a reasonable approach? (Patch below is compile tested only. :)
---
arch/x86/ia32/ia32entry.S | 1 +
arch/x86/include/asm/unistd_32.h | 3 +-
arch/x86/include/asm/unistd_64.h | 2 +
arch/x86/kernel/syscall_table_32.S | 1 +
fs/sync.c | 43 ++++++++++++++++++++++++++++++++++++
5 files changed, 49 insertions(+), 1 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 518bb99..1d610e4 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -851,4 +851,5 @@ ia32_sys_call_table:
.quad sys_fanotify_init
.quad sys32_fanotify_mark
.quad sys_prlimit64 /* 340 */
+ .quad sys_syncat
ia32_syscall_end:
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index b766a5e..350bf94 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -346,10 +346,11 @@
#define __NR_fanotify_init 338
#define __NR_fanotify_mark 339
#define __NR_prlimit64 340
+#define __NR_syncat 341
#ifdef __KERNEL__
-#define NR_syscalls 341
+#define NR_syscalls 342
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 363e9b8..1ea0953 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -669,6 +669,8 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
#define __NR_prlimit64 302
__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_syncat 303
+__SYSCALL(__NR_syncat, sys_syncat)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index b35786d..12de607 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -340,3 +340,4 @@ ENTRY(sys_call_table)
.long sys_fanotify_init
.long sys_fanotify_mark
.long sys_prlimit64 /* 340 */
+ .long sys_syncat
diff --git a/fs/sync.c b/fs/sync.c
index ba76b96..a57dfe4 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -7,6 +7,7 @@
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
@@ -128,6 +129,48 @@ void emergency_sync(void)
}
}
+/*
+ * sync a single super
+ */
+SYSCALL_DEFINE3(syncat, int, dfd, const char __user *, filename, int, flags)
+{
+ struct path path;
+ struct file *file = 0;
+ struct super_block *sb;
+ int ret = -EINVAL;
+ int lookup_flags = 0;
+ int fput_needed = 0;
+
+ if ((flags & ~AT_SYMLINK_NOFOLLOW) != 0)
+ goto out;
+
+ if (!(flags & AT_SYMLINK_NOFOLLOW))
+ lookup_flags |= LOOKUP_FOLLOW;
+
+ if (filename) {
+ ret = user_path_at(dfd, filename, 0, &path);
+ if (ret)
+ goto out;
+ sb = path.dentry->d_sb;
+ } else {
+ file = fget_light(dfd, &fput_needed);
+ ret = -EBADF;
+ if (!file)
+ goto out;
+ sb = file->f_dentry->d_sb;
+ }
+
+ down_read(&sb->s_umount);
+ ret = sync_filesystem(sb);
+ up_read(&sb->s_umount);
+
+ if (filename)
+ path_put(&path);
+ fput_light(file, fput_needed);
+out:
+ return ret;
+}
+
/**
* vfs_fsync_range - helper to sync a range of data & metadata to disk
* @file: file to sync
--
1.7.0.4
--
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/