a22180d266
Pull btrfs update from Chris Mason: "A big set of fixes and features. In terms of line count, most of the code comes from Stefan, who added the ability to replace a single drive in place. This is different from how btrfs normally replaces drives, and is much much much faster. Josef is plowing through our synchronous write performance. This pull request does not include the DIO_OWN_WAITING patch that was discussed on the list, but it has a number of other improvements to cut down our latencies and CPU time during fsync/O_DIRECT writes. Miao Xie has a big series of fixes and is spreading out ordered operations over more CPUs. This improves performance and reduces contention. I've put in fixes for error handling around hash collisions. These are going back to individual stable kernels as I test against them. Otherwise we have a lot of fixes and cleanups, thanks everyone! raid5/6 is being rebased against the device replacement code. I'll have it posted this Friday along with a nice series of benchmarks." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (115 commits) Btrfs: fix a bug of per-file nocow Btrfs: fix hash overflow handling Btrfs: don't take inode delalloc mutex if we're a free space inode Btrfs: fix autodefrag and umount lockup Btrfs: fix permissions of empty files not affected by umask Btrfs: put raid properties into global table Btrfs: fix BUG() in scrub when first superblock reading gives EIO Btrfs: do not call file_update_time in aio_write Btrfs: only unlock and relock if we have to Btrfs: use tokens where we can in the tree log Btrfs: optimize leaf_space_used Btrfs: don't memset new tokens Btrfs: only clear dirty on the buffer if it is marked as dirty Btrfs: move checks in set_page_dirty under DEBUG Btrfs: log changed inodes based on the extent map tree Btrfs: add path->really_keep_locks Btrfs: do not mark ems as prealloc if we are writing to them Btrfs: keep track of the extents original block length Btrfs: inline csums if we're fsyncing Btrfs: don't bother copying if we're only logging the inode ...
199 lines
6.2 KiB
C
199 lines
6.2 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_ORDERED_DATA__
|
|
#define __BTRFS_ORDERED_DATA__
|
|
|
|
/* one of these per inode */
|
|
struct btrfs_ordered_inode_tree {
|
|
spinlock_t lock;
|
|
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 zlib compressed extent */
|
|
|
|
#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
|
|
|
|
#define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */
|
|
|
|
#define BTRFS_ORDERED_IOERR 6 /* We had an io error when writing this out */
|
|
|
|
#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
|
|
* has done its due diligence in updating
|
|
* the isize. */
|
|
|
|
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;
|
|
|
|
/* number of bytes that still need writing */
|
|
u64 bytes_left;
|
|
|
|
/*
|
|
* the end of the ordered extent which is behind it but
|
|
* didn't update disk_i_size. Please see the comment of
|
|
* btrfs_ordered_update_i_size();
|
|
*/
|
|
u64 outstanding_isize;
|
|
|
|
/* flags (described above) */
|
|
unsigned long flags;
|
|
|
|
/* compression algorithm */
|
|
int compress_type;
|
|
|
|
/* 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;
|
|
|
|
struct btrfs_work work;
|
|
|
|
struct completion completion;
|
|
struct btrfs_work flush_work;
|
|
struct list_head work_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)
|
|
{
|
|
spin_lock_init(&t->lock);
|
|
t->tree = RB_ROOT;
|
|
t->last = NULL;
|
|
}
|
|
|
|
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
|
|
void btrfs_remove_ordered_extent(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry);
|
|
int btrfs_dec_test_ordered_pending(struct inode *inode,
|
|
struct btrfs_ordered_extent **cached,
|
|
u64 file_offset, u64 io_size, int uptodate);
|
|
int btrfs_dec_test_first_ordered_pending(struct inode *inode,
|
|
struct btrfs_ordered_extent **cached,
|
|
u64 *file_offset, u64 io_size,
|
|
int uptodate);
|
|
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len, int type);
|
|
int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len, int type);
|
|
int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len,
|
|
int type, int compress_type);
|
|
void 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);
|
|
void 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);
|
|
struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
|
|
u64 file_offset,
|
|
u64 len);
|
|
int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
|
|
struct btrfs_ordered_extent *ordered);
|
|
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum);
|
|
int btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
|
|
void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
struct inode *inode);
|
|
void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput);
|
|
int __init ordered_data_init(void);
|
|
void ordered_data_exit(void);
|
|
#endif
|