@@ -3790,23 +3790,35 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
spin_unlock(&fs_info->relocation_bg_lock);
if (skip)
return 1;
+
/* Check RO and no space case before trying to activate it */
spin_lock(&block_group->lock);
if (block_group->ro ||
block_group->alloc_offset == block_group->zone_capacity) {
- spin_unlock(&block_group->lock);
- return 1;
+ ret = 1;
+ /*
+ * May need to clear fs_info->{treelog,data_reloc}_bg.
+ * Return the error after taking the locks.
+ */
}
spin_unlock(&block_group->lock);
- if (!btrfs_zone_activate(block_group))
- return 1;
+ if (!ret && !btrfs_zone_activate(block_group)) {
+ ret = 1;
+ /*
+ * May need to clear fs_info->{treelog,data_reloc}_bg.
+ * Return the error after taking the locks.
+ */
+ }
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
spin_lock(&fs_info->treelog_bg_lock);
spin_lock(&fs_info->relocation_bg_lock);
+ if (ret)
+ goto out;
+
ASSERT(!ffe_ctl->for_treelog ||
block_group->start == fs_info->treelog_bg ||
fs_info->treelog_bg == 0);
Allocating an extent from a block group can fail for various reasons. When an allocation from a dedicated block group (for tree-log or relocation data) fails, we need to unregister it as a dedicated one so that we can allocate a new block group for the dedicated one. However, we are returning early when the block group in case it is read-only, fully used, or not be able to activate the zone. As a result, we keep the non-usable block group as a dedicated one, leading to further allocation failure. With many block groups, the allocator will iterate hopeless loop to find a free extent, results in a hung task. Fix the issue by delaying the return and doing the proper cleanups. Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> --- fs/btrfs/extent-tree.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-)