5a3f23d515
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>
162 lines
5 KiB
C
162 lines
5 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_ORDERED_DATA__
|
|
#define __BTRFS_ORDERED_DATA__
|
|
|
|
/* one of these per inode */
|
|
struct btrfs_ordered_inode_tree {
|
|
struct mutex mutex;
|
|
struct rb_root tree;
|
|
struct rb_node *last;
|
|
};
|
|
|
|
/*
|
|
* these are used to collect checksums done just before bios submission.
|
|
* They are attached via a list into the ordered extent, and
|
|
* checksum items are inserted into the tree after all the blocks in
|
|
* the ordered extent are on disk
|
|
*/
|
|
struct btrfs_sector_sum {
|
|
/* bytenr on disk */
|
|
u64 bytenr;
|
|
u32 sum;
|
|
};
|
|
|
|
struct btrfs_ordered_sum {
|
|
/* bytenr is the start of this extent on disk */
|
|
u64 bytenr;
|
|
|
|
/*
|
|
* this is the length in bytes covered by the sums array below.
|
|
*/
|
|
unsigned long len;
|
|
struct list_head list;
|
|
/* last field is a variable length array of btrfs_sector_sums */
|
|
struct btrfs_sector_sum sums[];
|
|
};
|
|
|
|
/*
|
|
* bits for the flags field:
|
|
*
|
|
* BTRFS_ORDERED_IO_DONE is set when all of the blocks are written.
|
|
* It is used to make sure metadata is inserted into the tree only once
|
|
* per extent.
|
|
*
|
|
* BTRFS_ORDERED_COMPLETE is set when the extent is removed from the
|
|
* rbtree, just before waking any waiters. It is used to indicate the
|
|
* IO is done and any metadata is inserted into the tree.
|
|
*/
|
|
#define BTRFS_ORDERED_IO_DONE 0 /* set when all the pages are written */
|
|
|
|
#define BTRFS_ORDERED_COMPLETE 1 /* set when removed from the tree */
|
|
|
|
#define BTRFS_ORDERED_NOCOW 2 /* set when we want to write in place */
|
|
|
|
#define BTRFS_ORDERED_COMPRESSED 3 /* writing a compressed extent */
|
|
|
|
#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
|
|
|
|
struct btrfs_ordered_extent {
|
|
/* logical offset in the file */
|
|
u64 file_offset;
|
|
|
|
/* disk byte number */
|
|
u64 start;
|
|
|
|
/* ram length of the extent in bytes */
|
|
u64 len;
|
|
|
|
/* extent length on disk */
|
|
u64 disk_len;
|
|
|
|
/* flags (described above) */
|
|
unsigned long flags;
|
|
|
|
/* reference count */
|
|
atomic_t refs;
|
|
|
|
/* the inode we belong to */
|
|
struct inode *inode;
|
|
|
|
/* list of checksums for insertion when the extent io is done */
|
|
struct list_head list;
|
|
|
|
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
|
|
wait_queue_head_t wait;
|
|
|
|
/* our friendly rbtree entry */
|
|
struct rb_node rb_node;
|
|
|
|
/* a per root list of all the pending ordered extents */
|
|
struct list_head root_extent_list;
|
|
};
|
|
|
|
|
|
/*
|
|
* calculates the total size you need to allocate for an ordered sum
|
|
* structure spanning 'bytes' in the file
|
|
*/
|
|
static inline int btrfs_ordered_sum_size(struct btrfs_root *root,
|
|
unsigned long bytes)
|
|
{
|
|
unsigned long num_sectors = (bytes + root->sectorsize - 1) /
|
|
root->sectorsize;
|
|
num_sectors++;
|
|
return sizeof(struct btrfs_ordered_sum) +
|
|
num_sectors * sizeof(struct btrfs_sector_sum);
|
|
}
|
|
|
|
static inline void
|
|
btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
|
|
{
|
|
mutex_init(&t->mutex);
|
|
t->tree.rb_node = NULL;
|
|
t->last = NULL;
|
|
}
|
|
|
|
int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
|
|
int btrfs_remove_ordered_extent(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry);
|
|
int btrfs_dec_test_ordered_pending(struct inode *inode,
|
|
u64 file_offset, u64 io_size);
|
|
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len, int tyep);
|
|
int btrfs_add_ordered_sum(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry,
|
|
struct btrfs_ordered_sum *sum);
|
|
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
|
|
u64 file_offset);
|
|
void btrfs_start_ordered_extent(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry, int wait);
|
|
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
|
|
struct btrfs_ordered_extent *
|
|
btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
|
|
int btrfs_ordered_update_i_size(struct inode *inode,
|
|
struct btrfs_ordered_extent *ordered);
|
|
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum);
|
|
int btrfs_wait_on_page_writeback_range(struct address_space *mapping,
|
|
pgoff_t start, pgoff_t end);
|
|
int btrfs_fdatawrite_range(struct address_space *mapping, loff_t start,
|
|
loff_t end, int sync_mode);
|
|
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nocow_only);
|
|
int btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
|
|
int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
struct inode *inode);
|
|
#endif
|