diff options
author | Li Zefan <lizf@cn.fujitsu.com> | 2011-04-20 10:06:11 +0800 |
---|---|---|
committer | Li Zefan <lizf@cn.fujitsu.com> | 2011-04-25 16:46:04 +0800 |
commit | 581bb050941b4f220f84d3e5ed6dace3d42dd382 (patch) | |
tree | 5ebd56af5eb3612f508419b188dfc18e959e7c94 /fs/btrfs/disk-io.c | |
parent | 34d52cb6c50b5a43901709998f59fb1c5a43dc4a (diff) | |
download | op-kernel-dev-581bb050941b4f220f84d3e5ed6dace3d42dd382.zip op-kernel-dev-581bb050941b4f220f84d3e5ed6dace3d42dd382.tar.gz |
Btrfs: Cache free inode numbers in memory
Currently btrfs stores the highest objectid of the fs tree, and it always
returns (highest+1) inode number when we create a file, so inode numbers
won't be reclaimed when we delete files, so we'll run out of inode numbers
as we keep create/delete files in 32bits machines.
This fixes it, and it works similarly to how we cache free space in block
cgroups.
We start a kernel thread to read the file tree. By scanning inode items,
we know which chunks of inode numbers are free, and we cache them in
an rb-tree.
Because we are searching the commit root, we have to carefully handle the
cross-transaction case.
The rb-tree is a hybrid extent+bitmap tree, so if we have too many small
chunks of inode numbers, we'll use bitmaps. Initially we allow 16K ram
of extents, and a bitmap will be used if we exceed this threshold. The
extents threshold is adjusted in runtime.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r-- | fs/btrfs/disk-io.c | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ef6865c..d02683b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -41,6 +41,7 @@ #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" +#include "inode-map.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@ -1327,6 +1328,19 @@ again: if (IS_ERR(root)) return root; + root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); + if (!root->free_ino_ctl) + goto fail; + root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), + GFP_NOFS); + if (!root->free_ino_pinned) + goto fail; + + btrfs_init_free_ino_ctl(root); + mutex_init(&root->fs_commit_mutex); + spin_lock_init(&root->cache_lock); + init_waitqueue_head(&root->cache_wait); + set_anon_super(&root->anon_super, NULL); if (btrfs_root_refs(&root->root_item) == 0) { @@ -2483,6 +2497,8 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); + __btrfs_remove_free_space_cache(root->free_ino_pinned); + __btrfs_remove_free_space_cache(root->free_ino_ctl); free_fs_root(root); return 0; } @@ -2496,6 +2512,8 @@ static void free_fs_root(struct btrfs_root *root) } free_extent_buffer(root->node); free_extent_buffer(root->commit_root); + kfree(root->free_ino_ctl); + kfree(root->free_ino_pinned); kfree(root->name); kfree(root); } |