From 5870ec7c8fe57a8b2c65005e5da5efc054faa3e6 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 14 Jan 2026 01:13:38 +0000 Subject: btrfs: reset block group size class when it becomes empty Block group size classes are managed consistently everywhere. Currently, btrfs_use_block_group_size_class() sets a block group's size class to specialize it for a specific allocation size. However, this size class remains "stale" even if the block group becomes completely empty (both used and reserved bytes reach zero). This happens in two scenarios: 1. When space reservations are freed (e.g., due to errors or transaction aborts) via btrfs_free_reserved_bytes(). 2. When the last extent in a block group is freed via btrfs_update_block_group(). While size classes are advisory, a stale size class can cause find_free_extent to unnecessarily skip candidate block groups during initial search loops. This undermines the purpose of size classes to reduce fragmentation by keeping block groups restricted to a specific size class when they could be reused for any size. Fix this by resetting the size class to BTRFS_BG_SZ_NONE whenever a block group's used and reserved counts both reach zero. This ensures that empty block groups are fully available for any allocation size in the next cycle. Fixes: 52bb7a2166af ("btrfs: introduce size class to block group allocator") Reviewed-by: Boris Burkov Signed-off-by: Jiasheng Jiang Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 3186ed4fd26d..5f76683b3f21 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3760,6 +3760,14 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) return ret; } +static void btrfs_maybe_reset_size_class(struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + if (btrfs_block_group_should_use_size_class(bg) && + bg->used == 0 && bg->reserved == 0) + bg->size_class = BTRFS_BG_SZ_NONE; +} + int btrfs_update_block_group(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, bool alloc) { @@ -3824,6 +3832,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, old_val -= num_bytes; cache->used = old_val; cache->pinned += num_bytes; + btrfs_maybe_reset_size_class(cache); btrfs_space_info_update_bytes_pinned(space_info, num_bytes); space_info->bytes_used -= num_bytes; space_info->disk_used -= num_bytes * factor; @@ -3952,6 +3961,7 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache, u64 num_bytes, spin_lock(&cache->lock); bg_ro = cache->ro; cache->reserved -= num_bytes; + btrfs_maybe_reset_size_class(cache); if (is_delalloc) cache->delalloc_bytes -= num_bytes; spin_unlock(&cache->lock); -- cgit v1.2.3