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/inode.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/inode.c')
-rw-r--r-- | fs/btrfs/inode.c | 25 |
1 files changed, 14 insertions, 11 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dfef726e84e8..140e9c045cf1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10565,6 +10565,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; struct extent_map *em = NULL; + struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, @@ -10704,13 +10705,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out; } - em = btrfs_get_chunk_map(fs_info, logical_block_start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + map = btrfs_get_chunk_map(fs_info, logical_block_start, len); + if (IS_ERR(map)) { + ret = PTR_ERR(map); goto out; } - if (em->map_lookup->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { btrfs_warn(fs_info, "swapfile must have single data profile"); ret = -EINVAL; @@ -10718,23 +10719,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, } if (device == NULL) { - device = em->map_lookup->stripes[0].dev; + device = map->stripes[0].dev; ret = btrfs_add_swapfile_pin(inode, device, false); if (ret == 1) ret = 0; else if (ret) goto out; - } else if (device != em->map_lookup->stripes[0].dev) { + } else if (device != map->stripes[0].dev) { btrfs_warn(fs_info, "swapfile must be on one device"); ret = -EINVAL; goto out; } - physical_block_start = (em->map_lookup->stripes[0].physical + - (logical_block_start - em->start)); - len = min(len, em->len - (logical_block_start - em->start)); - free_extent_map(em); - em = NULL; + physical_block_start = (map->stripes[0].physical + + (logical_block_start - map->start)); + len = min(len, map->chunk_len - (logical_block_start - map->start)); + btrfs_free_chunk_map(map); + map = NULL; bg = btrfs_lookup_block_group(fs_info, logical_block_start); if (!bg) { @@ -10787,6 +10788,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out: if (!IS_ERR_OR_NULL(em)) free_extent_map(em); + if (!IS_ERR_OR_NULL(map)) + btrfs_free_chunk_map(map); unlock_extent(io_tree, 0, isize - 1, &cached_state); |