btrfs: remove not needed mod_start and mod_len from struct extent_map

The mod_start and mod_len fields of struct extent_map were introduced by
commit 4e2f84e63d ("Btrfs: improve fsync by filtering extents that we
want") in order to avoid too low performance when fsyncing a file that
keeps getting extent maps merge, because it resulted in each fsync logging
again csum ranges that were already merged before.

We don't need this anymore as extent maps in the list of modified extents
are never merged with other extent maps and once we log an extent map we
remove it from the list of modified extent maps, so it's never logged
twice.

So remove the mod_start and mod_len fields from struct extent_map and use
instead the start and len fields when logging checksums in the fast fsync
path. This also makes EXTENT_FLAG_FILLING unused so remove it as well.

Running the reproducer from the commit mentioned before, with a larger
number of extents and against a null block device, so that IO is fast
and we can better see any impact from searching checksums items and
logging them, gave the following results from dd:

Before this change:

   409600000 bytes (410 MB, 391 MiB) copied, 22.948 s, 17.8 MB/s

After this change:

   409600000 bytes (410 MB, 391 MiB) copied, 22.9997 s, 17.8 MB/s

So no changes in throughput.
The test was done in a release kernel (non-debug, Debian's default kernel
config) and its steps are the following:

   $ mkfs.btrfs -f /dev/nullb0
   $ mount /dev/sdb /mnt
   $ dd if=/dev/zero of=/mnt/foobar bs=4k count=100000 oflag=sync
   $ umount /mnt

This also reduces the size of struct extent_map from 128 bytes down to 112
bytes, so now we can have 36 extents maps per 4K page instead of 32.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Filipe Manana 2024-04-02 14:24:00 +01:00 committed by David Sterba
parent 5f2fb819f6
commit 2e438442ba
5 changed files with 4 additions and 29 deletions

View File

@ -252,8 +252,6 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
em->len += merge->len;
em->block_len += merge->block_len;
em->block_start = merge->block_start;
em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
em->mod_start = merge->mod_start;
em->generation = max(em->generation, merge->generation);
em->flags |= EXTENT_FLAG_MERGED;
@ -271,7 +269,6 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
em->block_len += merge->block_len;
rb_erase_cached(&merge->rb_node, &tree->map);
RB_CLEAR_NODE(&merge->rb_node);
em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
em->generation = max(em->generation, merge->generation);
em->flags |= EXTENT_FLAG_MERGED;
free_extent_map(merge);
@ -300,7 +297,6 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
struct extent_map_tree *tree = &inode->extent_tree;
int ret = 0;
struct extent_map *em;
bool prealloc = false;
write_lock(&tree->lock);
em = lookup_extent_mapping(tree, start, len);
@ -325,21 +321,9 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
em->generation = gen;
em->flags &= ~EXTENT_FLAG_PINNED;
em->mod_start = em->start;
em->mod_len = em->len;
if (em->flags & EXTENT_FLAG_FILLING) {
prealloc = true;
em->flags &= ~EXTENT_FLAG_FILLING;
}
try_merge_map(tree, em);
if (prealloc) {
em->mod_start = em->start;
em->mod_len = em->len;
}
out:
write_unlock(&tree->lock);
free_extent_map(em);
@ -361,8 +345,6 @@ static inline void setup_extent_mapping(struct extent_map_tree *tree,
int modified)
{
refcount_inc(&em->refs);
em->mod_start = em->start;
em->mod_len = em->len;
ASSERT(list_empty(&em->list));

View File

@ -30,8 +30,6 @@ enum {
ENUM_BIT(EXTENT_FLAG_PREALLOC),
/* Logging this extent */
ENUM_BIT(EXTENT_FLAG_LOGGING),
/* Filling in a preallocated extent */
ENUM_BIT(EXTENT_FLAG_FILLING),
/* This em is merged from two or more physically adjacent ems */
ENUM_BIT(EXTENT_FLAG_MERGED),
};
@ -46,8 +44,6 @@ struct extent_map {
/* all of these are in bytes */
u64 start;
u64 len;
u64 mod_start;
u64 mod_len;
u64 orig_start;
u64 orig_block_len;
u64 ram_bytes;

View File

@ -7337,9 +7337,7 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
em->ram_bytes = ram_bytes;
em->generation = -1;
em->flags |= EXTENT_FLAG_PINNED;
if (type == BTRFS_ORDERED_PREALLOC)
em->flags |= EXTENT_FLAG_FILLING;
else if (type == BTRFS_ORDERED_COMPRESSED)
if (type == BTRFS_ORDERED_COMPRESSED)
extent_map_set_compression(em, compress_type);
ret = btrfs_replace_extent_map_range(inode, em, true);

View File

@ -4574,8 +4574,8 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
struct btrfs_root *csum_root;
u64 csum_offset;
u64 csum_len;
u64 mod_start = em->mod_start;
u64 mod_len = em->mod_len;
u64 mod_start = em->start;
u64 mod_len = em->len;
LIST_HEAD(ordered_sums);
int ret = 0;

View File

@ -277,8 +277,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
{ EXTENT_FLAG_COMPRESS_LZO, "COMPRESS_LZO" },\
{ EXTENT_FLAG_COMPRESS_ZSTD, "COMPRESS_ZSTD" },\
{ EXTENT_FLAG_PREALLOC, "PREALLOC" },\
{ EXTENT_FLAG_LOGGING, "LOGGING" },\
{ EXTENT_FLAG_FILLING, "FILLING" })
{ EXTENT_FLAG_LOGGING, "LOGGING" })
TRACE_EVENT_CONDITION(btrfs_get_extent,