linux/fs/btrfs/btrfs_inode.h
Chris Mason 5a3f23d515 Btrfs: add extra flushing for renames and truncates
Renames and truncates are both common ways to replace old data with new
data.  The filesystem can make an effort to make sure the new data is
on disk before actually replacing the old data.

This is especially important for rename, which many application use as
though it were atomic for both the data and the metadata involved.  The
current btrfs code will happily replace a file that is fully on disk
with one that was just created and still has pending IO.

If we crash after transaction commit but before the IO is done, we'll end
up replacing a good file with a zero length file.  The solution used
here is to create a list of inodes that need special ordering and force
them to disk before the commit is done.  This is similar to the
ext3 style data=ordering, except it is only done on selected files.

Btrfs is able to get away with this because it does not wait on commits
very often, even for fsync (which use a sub-commit).

For renames, we order the file when it wasn't already
on disk and when it is replacing an existing file.  Larger files
are sent to filemap_flush right away (before the transaction handle is
opened).

For truncates, we order if the file goes from non-zero size down to
zero size.  This is a little different, because at the time of the
truncate the file has no dirty bytes to order.  But, we flag the inode
so that it is added to the ordered list on close (via release method).  We
also immediately add it to the ordered list of the current transaction
so that we can try to flush down any writes the application sneaks in
before commit.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-03-31 14:27:58 -04:00

158 lines
4.2 KiB
C

/*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#ifndef __BTRFS_I__
#define __BTRFS_I__
#include "extent_map.h"
#include "extent_io.h"
#include "ordered-data.h"
/* in memory btrfs inode */
struct btrfs_inode {
/* which subvolume this inode belongs to */
struct btrfs_root *root;
/* key used to find this inode on disk. This is used by the code
* to read in roots of subvolumes
*/
struct btrfs_key location;
/* the extent_tree has caches of all the extent mappings to disk */
struct extent_map_tree extent_tree;
/* the io_tree does range state (DIRTY, LOCKED etc) */
struct extent_io_tree io_tree;
/* special utility tree used to record which mirrors have already been
* tried when checksums fail for a given block
*/
struct extent_io_tree io_failure_tree;
/* held while inesrting or deleting extents from files */
struct mutex extent_mutex;
/* held while logging the inode in tree-log.c */
struct mutex log_mutex;
/* used to order data wrt metadata */
struct btrfs_ordered_inode_tree ordered_tree;
/* standard acl pointers */
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
/* for keeping track of orphaned inodes */
struct list_head i_orphan;
/* list of all the delalloc inodes in the FS. There are times we need
* to write all the delalloc pages to disk, and this list is used
* to walk them all.
*/
struct list_head delalloc_inodes;
/*
* list for tracking inodes that must be sent to disk before a
* rename or truncate commit
*/
struct list_head ordered_operations;
/* the space_info for where this inode's data allocations are done */
struct btrfs_space_info *space_info;
/* full 64 bit generation number, struct vfs_inode doesn't have a big
* enough field for this.
*/
u64 generation;
/* sequence number for NFS changes */
u64 sequence;
/*
* transid of the trans_handle that last modified this inode
*/
u64 last_trans;
/*
* transid that last logged this inode
*/
u64 logged_trans;
/* total number of bytes pending delalloc, used by stat to calc the
* real block usage of the file
*/
u64 delalloc_bytes;
/* total number of bytes that may be used for this inode for
* delalloc
*/
u64 reserved_bytes;
/*
* the size of the file stored in the metadata on disk. data=ordered
* means the in-memory i_size might be larger than the size on disk
* because not all the blocks are written yet.
*/
u64 disk_i_size;
/* flags field from the on disk inode */
u32 flags;
/*
* if this is a directory then index_cnt is the counter for the index
* number for new files that are created
*/
u64 index_cnt;
/* the start of block group preferred for allocations. */
u64 block_group;
/* the fsync log has some corner cases that mean we have to check
* directories to see if any unlinks have been done before
* the directory was logged. See tree-log.c for all the
* details
*/
u64 last_unlink_trans;
/*
* ordered_data_close is set by truncate when a file that used
* to have good data has been truncated to zero. When it is set
* the btrfs file release call will add this inode to the
* ordered operations list so that we make sure to flush out any
* new data the application may have written before commit.
*
* yes, its silly to have a single bitflag, but we might grow more
* of these.
*/
unsigned ordered_data_close:1;
struct inode vfs_inode;
};
static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
{
return container_of(inode, struct btrfs_inode, vfs_inode);
}
static inline void btrfs_i_size_write(struct inode *inode, u64 size)
{
inode->i_size = size;
BTRFS_I(inode)->disk_i_size = size;
}
#endif