summaryrefslogtreecommitdiff
path: root/fs/btrfs/zoned.c
diff options
context:
space:
mode:
authorChristoph Hellwig <hch@lst.de>2023-05-24 17:03:08 +0200
committerDavid Sterba <dsterba@suse.com>2023-06-19 13:59:32 +0200
commitcbfce4c7fbde23cc8bcba44822a58c728caf6ec9 (patch)
tree3cc7a0c85483da01f45d0eaef58e8c325e56b5d0 /fs/btrfs/zoned.c
parent5cfe76f846d5034058c0c4813259d5d831757c36 (diff)
btrfs: optimize the logical to physical mapping for zoned writes
The current code to store the final logical to physical mapping for a zone append write in the extent tree is rather inefficient. It first has to split the ordered extent so that there is one ordered extent per bio, so that it can look up the ordered extent on I/O completion in btrfs_record_physical_zoned and store the physical LBA returned by the block driver in the ordered extent. btrfs_rewrite_logical_zoned then has to do a lookup in the chunk tree to see what physical address the logical address for this bio / ordered extent is mapped to, and then rewrite it in the extent tree. To optimize this process, we can store the physical address assigned in the chunk tree to the original logical address and a pointer to btrfs_ordered_sum structure the in the btrfs_bio structure, and then use this information to rewrite the logical address in the btrfs_ordered_sum structure directly at I/O completion time in btrfs_record_physical_zoned. btrfs_rewrite_logical_zoned then simply updates the logical address in the extent tree and the ordered_extent itself. The code in btrfs_rewrite_logical_zoned now runs for all data I/O completions in zoned file systems, which is fine as there is no remapping to do for non-append writes to conventional zones or for relocation, and the overhead for quickly breaking out of the loop is very low. Because zoned file systems now need the ordered_sums structure to record the actual write location returned by zone append, allocate dummy structures without the csum array for them when the I/O doesn't use checksums, and free them when completing the ordered_extent. Note that the btrfs_bio doesn't grow as the new field are places into a union that is so far not used for data writes and has plenty of space left in it. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/zoned.c')
-rw-r--r--fs/btrfs/zoned.c61
1 files changed, 22 insertions, 39 deletions
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index eca49e6e0e5f..b55b0d4ee86f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1657,51 +1657,28 @@ bool btrfs_use_zone_append(struct btrfs_bio *bbio)
void btrfs_record_physical_zoned(struct btrfs_bio *bbio)
{
const u64 physical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
- struct btrfs_ordered_extent *ordered;
+ struct btrfs_ordered_sum *sum = bbio->sums;
- ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset);
- if (WARN_ON(!ordered))
- return;
-
- ordered->physical = physical;
- btrfs_put_ordered_extent(ordered);
+ if (physical < bbio->orig_physical)
+ sum->logical -= bbio->orig_physical - physical;
+ else
+ sum->logical += physical - bbio->orig_physical;
}
void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
{
struct btrfs_inode *inode = BTRFS_I(ordered->inode);
- struct btrfs_fs_info *fs_info = inode->root->fs_info;
- struct extent_map_tree *em_tree;
+ struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_map *em;
- struct btrfs_ordered_sum *sum;
- u64 orig_logical = ordered->disk_bytenr;
- struct map_lookup *map;
- u64 physical = ordered->physical;
- u64 chunk_start_phys;
- u64 logical;
+ struct btrfs_ordered_sum *sum =
+ list_first_entry(&ordered->list, typeof(*sum), list);
+ u64 logical = sum->logical;
- em = btrfs_get_chunk_map(fs_info, orig_logical, 1);
- if (IS_ERR(em))
- return;
- map = em->map_lookup;
- chunk_start_phys = map->stripes[0].physical;
-
- if (WARN_ON_ONCE(map->num_stripes > 1) ||
- WARN_ON_ONCE((map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) ||
- WARN_ON_ONCE(physical < chunk_start_phys) ||
- WARN_ON_ONCE(physical > chunk_start_phys + em->orig_block_len)) {
- free_extent_map(em);
- return;
- }
- logical = em->start + (physical - map->stripes[0].physical);
- free_extent_map(em);
-
- if (orig_logical == logical)
- return;
+ if (ordered->disk_bytenr == logical)
+ goto out;
ordered->disk_bytenr = logical;
- em_tree = &inode->extent_tree;
write_lock(&em_tree->lock);
em = search_extent_mapping(em_tree, ordered->file_offset,
ordered->num_bytes);
@@ -1709,11 +1686,17 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
free_extent_map(em);
write_unlock(&em_tree->lock);
- list_for_each_entry(sum, &ordered->list, list) {
- if (logical < orig_logical)
- sum->logical -= orig_logical - logical;
- else
- sum->logical += logical - orig_logical;
+out:
+ /*
+ * If we end up here for nodatasum I/O, the btrfs_ordered_sum structures
+ * were allocated by btrfs_alloc_dummy_sum only to record the logical
+ * addresses and don't contain actual checksums. We thus must free them
+ * here so that we don't attempt to log the csums later.
+ */
+ if ((inode->flags & BTRFS_INODE_NODATASUM) ||
+ test_bit(BTRFS_FS_STATE_NO_CSUMS, &inode->root->fs_info->fs_state)) {
+ list_del(&sum->list);
+ kfree(sum);
}
}