@@ -5766,6 +5766,21 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
return ret;
}
+static inline void __get_refill_bytes(struct btrfs_block_rsv *block_rsv,
+ u64 *metadata_bytes, u64 *qgroup_bytes)
+{
+ *metadata_bytes = 0;
+ *qgroup_bytes = 0;
+
+ spin_lock(&block_rsv->lock);
+ if (block_rsv->reserved < block_rsv->size)
+ *metadata_bytes = block_rsv->size - block_rsv->reserved;
+ if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+ *qgroup_bytes = block_rsv->qgroup_rsv_size -
+ block_rsv->qgroup_rsv_reserved;
+ spin_unlock(&block_rsv->lock);
+}
+
/**
* btrfs_inode_rsv_refill - refill the inode block rsv.
* @inode - the inode we are refilling.
@@ -5781,25 +5796,37 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
{
struct btrfs_root *root = inode->root;
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
- u64 num_bytes = 0;
+ u64 num_bytes = 0, last = 0;
u64 qgroup_num_bytes = 0;
int ret = -ENOSPC;
- spin_lock(&block_rsv->lock);
- if (block_rsv->reserved < block_rsv->size)
- num_bytes = block_rsv->size - block_rsv->reserved;
- if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
- qgroup_num_bytes = block_rsv->qgroup_rsv_size -
- block_rsv->qgroup_rsv_reserved;
- spin_unlock(&block_rsv->lock);
-
+ __get_refill_bytes(block_rsv, &num_bytes, &qgroup_num_bytes);
if (num_bytes == 0)
return 0;
- ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
- if (ret)
- return ret;
- ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+ do {
+ ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
+ if (ret)
+ return ret;
+ ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+ if (ret) {
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+ last = num_bytes;
+ /*
+ * If we are fragmented we can end up with a lot of
+ * outstanding extents which will make our size be much
+ * larger than our reserved amount. If we happen to
+ * try to do a reservation here that may result in us
+ * trying to do a pretty hefty reservation, which we may
+ * not need once delalloc flushing happens. If this is
+ * the case try and do the reserve again.
+ */
+ if (flush == BTRFS_RESERVE_FLUSH_ALL)
+ __get_refill_bytes(block_rsv, &num_bytes,
+ &qgroup_num_bytes);
+ }
+ } while (ret && last != num_bytes);
+
if (!ret) {
block_rsv_add_bytes(block_rsv, num_bytes, 0);
trace_btrfs_space_reservation(root->fs_info, "delalloc",
@@ -5809,8 +5836,7 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
spin_lock(&block_rsv->lock);
block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
spin_unlock(&block_rsv->lock);
- } else
- btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
+ }
return ret;
}
With severe fragmentation we can end up with our inode rsv size being huge during writeout, which would cause us to need to make very large metadata reservations. However we may not actually need that much once writeout is complete. So instead try to make our reservation, and if we couldn't make it re-calculate our new reservation size and try again. If our reservation size doesn't change between tries then we know we are actually out of space and can error out. Signed-off-by: Josef Bacik <josef@toxicpanda.com> --- fs/btrfs/extent-tree.c | 56 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 41 insertions(+), 15 deletions(-)