aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/super.c
diff options
context:
space:
mode:
authorYan Zheng <zheng.yan@oracle.com>2009-06-10 10:45:14 -0400
committerChris Mason <chris.mason@oracle.com>2009-06-10 11:29:46 -0400
commit5d4f98a28c7d334091c1b7744f48a1acdd2a4ae0 (patch)
treec611d7d824cbcdb777dd2d8e33e2ed1c5df8a9c6 /fs/btrfs/super.c
parent5c939df56c3ea018b58e5aa76181284c2053d699 (diff)
Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE)
This commit introduces a new kind of back reference for btrfs metadata. Once a filesystem has been mounted with this commit, IT WILL NO LONGER BE MOUNTABLE BY OLDER KERNELS. When a tree block in subvolume tree is cow'd, the reference counts of all extents it points to are increased by one. At transaction commit time, the old root of the subvolume is recorded in a "dead root" data structure, and the btree it points to is later walked, dropping reference counts and freeing any blocks where the reference count goes to 0. The increments done during cow and decrements done after commit cancel out, and the walk is a very expensive way to go about freeing the blocks that are no longer referenced by the new btree root. This commit reduces the transaction overhead by avoiding the need for dead root records. When a non-shared tree block is cow'd, we free the old block at once, and the new block inherits old block's references. When a tree block with reference count > 1 is cow'd, we increase the reference counts of all extents the new block points to by one, and decrease the old block's reference count by one. This dead tree avoidance code removes the need to modify the reference counts of lower level extents when a non-shared tree block is cow'd. But we still need to update back ref for all pointers in the block. This is because the location of the block is recorded in the back ref item. We can solve this by introducing a new type of back ref. The new back ref provides information about pointer's key, level and in which tree the pointer lives. This information allow us to find the pointer by searching the tree. The shortcoming of the new back ref is that it only works for pointers in tree blocks referenced by their owner trees. This is mostly a problem for snapshots, where resolving one of these fuzzy back references would be O(number_of_snapshots) and quite slow. The solution used here is to use the fuzzy back references in the common case where a given tree block is only referenced by one root, and use the full back references when multiple roots have a reference on a given block. This commit adds per subvolume red-black tree to keep trace of cached inodes. The red-black tree helps the balancing code to find cached inodes whose inode numbers within a given range. This commit improves the balancing code by introducing several data structures to keep the state of balancing. The most important one is the back ref cache. It caches how the upper level tree blocks are referenced. This greatly reduce the overhead of checking back ref. The improved balancing code scales significantly better with a large number of snapshots. This is a very large commit and was written in a number of pieces. But, they depend heavily on the disk format change and were squashed together to make sure git bisect didn't end up in a bad state wrt space balancing or the format change. Signed-off-by: Yan Zheng <zheng.yan@oracle.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/super.c')
-rw-r--r--fs/btrfs/super.c26
1 files changed, 9 insertions, 17 deletions
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2ff7cd2db25f..e9ef8c3307fe 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -52,7 +52,6 @@
52#include "export.h" 52#include "export.h"
53#include "compression.h" 53#include "compression.h"
54 54
55
56static struct super_operations btrfs_super_ops; 55static struct super_operations btrfs_super_ops;
57 56
58static void btrfs_put_super(struct super_block *sb) 57static void btrfs_put_super(struct super_block *sb)
@@ -322,7 +321,7 @@ static int btrfs_fill_super(struct super_block *sb,
322 struct dentry *root_dentry; 321 struct dentry *root_dentry;
323 struct btrfs_super_block *disk_super; 322 struct btrfs_super_block *disk_super;
324 struct btrfs_root *tree_root; 323 struct btrfs_root *tree_root;
325 struct btrfs_inode *bi; 324 struct btrfs_key key;
326 int err; 325 int err;
327 326
328 sb->s_maxbytes = MAX_LFS_FILESIZE; 327 sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -341,23 +340,15 @@ static int btrfs_fill_super(struct super_block *sb,
341 } 340 }
342 sb->s_fs_info = tree_root; 341 sb->s_fs_info = tree_root;
343 disk_super = &tree_root->fs_info->super_copy; 342 disk_super = &tree_root->fs_info->super_copy;
344 inode = btrfs_iget_locked(sb, BTRFS_FIRST_FREE_OBJECTID,
345 tree_root->fs_info->fs_root);
346 bi = BTRFS_I(inode);
347 bi->location.objectid = inode->i_ino;
348 bi->location.offset = 0;
349 bi->root = tree_root->fs_info->fs_root;
350
351 btrfs_set_key_type(&bi->location, BTRFS_INODE_ITEM_KEY);
352 343
353 if (!inode) { 344 key.objectid = BTRFS_FIRST_FREE_OBJECTID;
354 err = -ENOMEM; 345 key.type = BTRFS_INODE_ITEM_KEY;
346 key.offset = 0;
347 inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root);
348 if (IS_ERR(inode)) {
349 err = PTR_ERR(inode);
355 goto fail_close; 350 goto fail_close;
356 } 351 }
357 if (inode->i_state & I_NEW) {
358 btrfs_read_locked_inode(inode);
359 unlock_new_inode(inode);
360 }
361 352
362 root_dentry = d_alloc_root(inode); 353 root_dentry = d_alloc_root(inode);
363 if (!root_dentry) { 354 if (!root_dentry) {
@@ -584,7 +575,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
584 if (btrfs_super_log_root(&root->fs_info->super_copy) != 0) 575 if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
585 return -EINVAL; 576 return -EINVAL;
586 577
587 ret = btrfs_cleanup_reloc_trees(root); 578 /* recover relocation */
579 ret = btrfs_recover_relocation(root);
588 WARN_ON(ret); 580 WARN_ON(ret);
589 581
590 ret = btrfs_cleanup_fs_roots(root->fs_info); 582 ret = btrfs_cleanup_fs_roots(root->fs_info);