diff options
author | Filipe Manana <fdmanana@suse.com> | 2023-11-21 13:38:38 +0000 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2023-12-15 20:27:02 +0100 |
commit | 7dc66abb5a47778d7db327783a0ba172b8cff0b5 (patch) | |
tree | 66fef581a2f31904aae1c15f9fdbbc7aec798132 /fs/btrfs/dev-replace.c | |
parent | ebb0beca6c6a2d33f809a74bad63261651237833 (diff) | |
download | linux-stable-7dc66abb5a47778d7db327783a0ba172b8cff0b5.tar.gz linux-stable-7dc66abb5a47778d7db327783a0ba172b8cff0b5.tar.bz2 linux-stable-7dc66abb5a47778d7db327783a0ba172b8cff0b5.zip |
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 <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/dev-replace.c')
-rw-r--r-- | fs/btrfs/dev-replace.c | 28 |
1 files changed, 12 insertions, 16 deletions
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f9544fda38e9..1502d664c892 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -550,8 +550,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, u64 physical) { struct btrfs_fs_info *fs_info = cache->fs_info; - struct extent_map *em; - struct map_lookup *map; + struct btrfs_chunk_map *map; u64 chunk_offset = cache->start; int num_extents, cur_extent; int i; @@ -567,9 +566,8 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, } spin_unlock(&cache->lock); - em = btrfs_get_chunk_map(fs_info, chunk_offset, 1); - ASSERT(!IS_ERR(em)); - map = em->map_lookup; + map = btrfs_get_chunk_map(fs_info, chunk_offset, 1); + ASSERT(!IS_ERR(map)); num_extents = 0; cur_extent = 0; @@ -583,7 +581,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, cur_extent = i; } - free_extent_map(em); + btrfs_free_chunk_map(map); if (num_extents > 1 && cur_extent < num_extents - 1) { /* @@ -812,25 +810,23 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( struct btrfs_device *srcdev, struct btrfs_device *tgtdev) { - struct extent_map_tree *em_tree = &fs_info->mapping_tree; - struct extent_map *em; - struct map_lookup *map; u64 start = 0; int i; - write_lock(&em_tree->lock); + write_lock(&fs_info->mapping_tree_lock); do { - em = lookup_extent_mapping(em_tree, start, (u64)-1); - if (!em) + struct btrfs_chunk_map *map; + + map = btrfs_find_chunk_map_nolock(fs_info, start, U64_MAX); + if (!map) break; - map = em->map_lookup; for (i = 0; i < map->num_stripes; i++) if (srcdev == map->stripes[i].dev) map->stripes[i].dev = tgtdev; - start = em->start + em->len; - free_extent_map(em); + start = map->start + map->chunk_len; + btrfs_free_chunk_map(map); } while (start); - write_unlock(&em_tree->lock); + write_unlock(&fs_info->mapping_tree_lock); } static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, |