From 7dc66abb5a47778d7db327783a0ba172b8cff0b5 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 21 Nov 2023 13:38:38 +0000 Subject: btrfs: use a dedicated data structure for chunk maps Currently we abuse the extent_map structure for two purposes: 1) To actually represent extents for inodes; 2) To represent chunk mappings. This is odd and has several disadvantages: 1) To create a chunk map, we need to do two memory allocations: one for an extent_map structure and another one for a map_lookup structure, so more potential for an allocation failure and more complicated code to manage and link two structures; 2) For a chunk map we actually only use 3 fields (24 bytes) of the respective extent map structure: the 'start' field to have the logical start address of the chunk, the 'len' field to have the chunk's size, and the 'orig_block_len' field to contain the chunk's stripe size. Besides wasting a memory, it's also odd and not intuitive at all to have the stripe size in a field named 'orig_block_len'. We are also using 'block_len' of the extent_map structure to contain the chunk size, so we have 2 fields for the same value, 'len' and 'block_len', which is pointless; 3) When an extent map is associated to a chunk mapping, we set the bit EXTENT_FLAG_FS_MAPPING on its flags and then make its member named 'map_lookup' point to the associated map_lookup structure. This means that for an extent map associated to an inode extent, we are not using this 'map_lookup' pointer, so wasting 8 bytes (on a 64 bits platform); 4) Extent maps associated to a chunk mapping are never merged or split so it's pointless to use the existing extent map infrastructure. So add a dedicated data structure named 'btrfs_chunk_map' to represent chunk mappings, this is basically the existing map_lookup structure with some extra fields: 1) 'start' to contain the chunk logical address; 2) 'chunk_len' to contain the chunk's length; 3) 'stripe_size' for the stripe size; 4) 'rb_node' for insertion into a rb tree; 5) 'refs' for reference counting. This way we do a single memory allocation for chunk mappings and we don't waste memory for them with unused/unnecessary fields from an extent_map. We also save 8 bytes from the extent_map structure by removing the 'map_lookup' pointer, so the size of struct extent_map is reduced from 144 bytes down to 136 bytes, and we can now have 30 extents map per 4K page instead of 28. Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7d8d175d5a59..17ec983ea672 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2720,7 +2720,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&fs_info->allocated_ebs); spin_lock_init(&fs_info->eb_leak_lock); #endif - extent_map_tree_init(&fs_info->mapping_tree); + fs_info->mapping_tree = RB_ROOT_CACHED; + rwlock_init(&fs_info->mapping_tree_lock); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); @@ -3604,7 +3605,7 @@ fail_sb_buffer: btrfs_stop_all_workers(fs_info); btrfs_free_block_groups(fs_info); fail_alloc: - btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_mapping_tree_free(fs_info); iput(fs_info->btree_inode); fail: @@ -4387,7 +4388,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) iput(fs_info->btree_inode); - btrfs_mapping_tree_free(&fs_info->mapping_tree); + btrfs_mapping_tree_free(fs_info); btrfs_close_devices(fs_info->fs_devices); } -- cgit v1.2.3