[PATCH 0/2][v2] Rework the worst case calculations for space reservation

[PATCH 0/2][v2] Rework the worst case calculations for space reservation

[Josef Bacik]

v1->v2:
- dropped "btrfs: global reserve fallback should use metadata_size", turns out
  I was testing without my evict changes in place so we don't even need this in
  the first place, but it is also wrong because we need to reserve space for the
  orphan item which is an insert.
- Added the reviewed-by's.

-- Original email --
We have two worst case calculations for space reservation, one that takes into
account splitting at every level when cow'ing down the btree, and another that
doesn't account for splitting at all.  The first is used everywhere, and the
second is used mostly for truncate.

However we also do not split when we're only changing an item, so for example
updating the inode item.  So the name for this helper is wrong, because it can
be used for in-place updates as well as for truncates.  Rename the helpers and
then use the smaller worst-case reservation for inode updates in a few places.

As a rule we still want to use the insert calculation when we can't be sure what
kind of operation is going to end up happening.  But for things like delayed
inode updates and file writes where we know there is going to be an existing
inode item we can use the smaller reservation.  Thanks,

Josef

[PATCH 1/2] btrfs: rename the btrfs_calc_*_metadata_size helpers

[Josef Bacik]

btrfs_calc_trunc_metadata_size differs from trans_metadata_size in that
it doesn't take into account any splitting at the levels, because
truncate will never split nodes.  However truncate _and_ changing will
never split nodes, so rename btrfs_calc_trunc_metadata_size to
btrfs_calc_metadata_size.  Also btrfs_calc_trans_metadata_size is purely
for inserting items, so rename this to btrfs_calc_insert_metadata_size.
Making these clearer will help when I start using them differently in
upcoming patches.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/block-group.c      |  4 ++--
 fs/btrfs/ctree.h            | 14 +++++++++-----
 fs/btrfs/delalloc-space.c   |  8 ++++----
 fs/btrfs/delayed-inode.c    |  4 ++--
 fs/btrfs/delayed-ref.c      |  8 ++++----
 fs/btrfs/file.c             |  4 ++--
 fs/btrfs/free-space-cache.c |  4 ++--
 fs/btrfs/inode-map.c        |  2 +-
 fs/btrfs/inode.c            |  6 +++---
 fs/btrfs/props.c            |  2 +-
 fs/btrfs/root-tree.c        |  2 +-
 fs/btrfs/space-info.c       |  2 +-
 fs/btrfs/transaction.c      |  4 ++--
 13 files changed, 34 insertions(+), 30 deletions(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index afae5c731904..3147e840f839 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -3014,8 +3014,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 	num_devs = get_profile_num_devs(fs_info, type);
 
 	/* num_devs device items to update and 1 chunk item to add or remove */
-	thresh = btrfs_calc_trunc_metadata_size(fs_info, num_devs) +
-		btrfs_calc_trans_metadata_size(fs_info, 1);
+	thresh = btrfs_calc_metadata_size(fs_info, num_devs) +
+		btrfs_calc_insert_metadata_size(fs_info, 1);
 
 	if (left < thresh && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(fs_info, "left=%llu, need=%llu, flags=%llu",
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b161224b5a0b..66fb41cadbfa 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2450,17 +2450,21 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 
 u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
 
-static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
-						 unsigned num_items)
+/*
+ * Use this if we would be adding new items, as we could split nodes as we cow
+ * down the tree.
+ */
+static inline u64 btrfs_calc_insert_metadata_size(struct btrfs_fs_info *fs_info,
+						  unsigned num_items)
 {
 	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
- * Doing a truncate won't result in new nodes or leaves, just what we need for
- * COW.
+ * Doing a truncate or a modification won't result in new nodes or leaves, just
+ * what we need for COW.
  */
-static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
+static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
 	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 1fc6bef3ccdf..2412be4a3de2 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -252,12 +252,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	lockdep_assert_held(&inode->lock);
 	outstanding_extents = inode->outstanding_extents;
 	if (outstanding_extents)
-		reserve_size = btrfs_calc_trans_metadata_size(fs_info,
+		reserve_size = btrfs_calc_insert_metadata_size(fs_info,
 						outstanding_extents + 1);
 	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
 						 inode->csum_bytes);
-	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
-						       csum_leaves);
+	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
+							csum_leaves);
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -280,7 +280,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
 
 	/* We add one for the inode update at finish ordered time */
-	*meta_reserve = btrfs_calc_trans_metadata_size(fs_info,
+	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
 						nr_extents + csum_leaves + 1);
 	*qgroup_reserve = nr_extents * fs_info->nodesize;
 }
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6858a05606dd..de87ea7ce84d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -558,7 +558,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+	num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
 
 	/*
 	 * Here we migrate space rsv from transaction rsv, since have already
@@ -612,7 +612,7 @@ static int btrfs_delayed_inode_reserve_metadata(
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+	num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
 
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 3822edbf54a7..df3bd880061d 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -79,7 +79,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans)
 void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
 {
 	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
-	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, nr);
+	u64 num_bytes = btrfs_calc_insert_metadata_size(fs_info, nr);
 	u64 released = 0;
 
 	released = __btrfs_block_rsv_release(fs_info, block_rsv, num_bytes,
@@ -105,8 +105,8 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
 	if (!trans->delayed_ref_updates)
 		return;
 
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info,
-						   trans->delayed_ref_updates);
+	num_bytes = btrfs_calc_insert_metadata_size(fs_info,
+						    trans->delayed_ref_updates);
 	spin_lock(&delayed_rsv->lock);
 	delayed_rsv->size += num_bytes;
 	delayed_rsv->full = 0;
@@ -174,7 +174,7 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
 				  enum btrfs_reserve_flush_enum flush)
 {
 	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
-	u64 limit = btrfs_calc_trans_metadata_size(fs_info, 1);
+	u64 limit = btrfs_calc_insert_metadata_size(fs_info, 1);
 	u64 num_bytes = 0;
 	int ret = -ENOSPC;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b31991f0f440..1cb694c96500 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2511,7 +2511,7 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path,
 			   struct btrfs_trans_handle **trans_out)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	u64 min_size = btrfs_calc_trans_metadata_size(fs_info, 1);
+	u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1);
 	u64 ino_size = round_up(inode->i_size, fs_info->sectorsize);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans = NULL;
@@ -2530,7 +2530,7 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path,
 		ret = -ENOMEM;
 		goto out;
 	}
-	rsv->size = btrfs_calc_trans_metadata_size(fs_info, 1);
+	rsv->size = btrfs_calc_insert_metadata_size(fs_info, 1);
 	rsv->failfast = 1;
 
 	/*
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index faaf57a7c289..265dc75f7a7a 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -211,8 +211,8 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 	int ret;
 
 	/* 1 for slack space, 1 for updating the inode */
-	needed_bytes = btrfs_calc_trunc_metadata_size(fs_info, 1) +
-		btrfs_calc_trans_metadata_size(fs_info, 1);
+	needed_bytes = btrfs_calc_insert_metadata_size(fs_info, 1) +
+		btrfs_calc_metadata_size(fs_info, 1);
 
 	spin_lock(&rsv->lock);
 	if (rsv->reserved < needed_bytes)
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 86031cdfc356..63cad7865d75 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -436,7 +436,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	 * 1 item for free space object
 	 * 3 items for pre-allocation
 	 */
-	trans->bytes_reserved = btrfs_calc_trans_metadata_size(fs_info, 10);
+	trans->bytes_reserved = btrfs_calc_insert_metadata_size(fs_info, 10);
 	ret = btrfs_block_rsv_add(root, trans->block_rsv,
 				  trans->bytes_reserved,
 				  BTRFS_RESERVE_NO_FLUSH);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e12fcd3adcc8..aece5dd0e7a8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5373,7 +5373,7 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	struct btrfs_trans_handle *trans;
-	u64 delayed_refs_extra = btrfs_calc_trans_metadata_size(fs_info, 1);
+	u64 delayed_refs_extra = btrfs_calc_insert_metadata_size(fs_info, 1);
 	int ret;
 
 	/*
@@ -5462,7 +5462,7 @@ void btrfs_evict_inode(struct inode *inode)
 	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
 	if (!rsv)
 		goto no_delete;
-	rsv->size = btrfs_calc_trunc_metadata_size(fs_info, 1);
+	rsv->size = btrfs_calc_metadata_size(fs_info, 1);
 	rsv->failfast = 1;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
@@ -9076,7 +9076,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
 	int ret;
 	struct btrfs_trans_handle *trans;
 	u64 mask = fs_info->sectorsize - 1;
-	u64 min_size = btrfs_calc_trunc_metadata_size(fs_info, 1);
+	u64 min_size = btrfs_calc_metadata_size(fs_info, 1);
 
 	if (!skip_writeback) {
 		ret = btrfs_wait_ordered_range(inode, inode->i_size & (~mask),
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index e0469816c678..1e664e0b59b8 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -362,7 +362,7 @@ static int inherit_props(struct btrfs_trans_handle *trans,
 		 * reservations if we do add more properties in the future.
 		 */
 		if (need_reserve) {
-			num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+			num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
 			ret = btrfs_block_rsv_add(root, trans->block_rsv,
 					num_bytes, BTRFS_RESERVE_NO_FLUSH);
 			if (ret)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 47733fb55df7..3b17b647d002 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -533,7 +533,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 			return ret;
 	}
 
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
+	num_bytes = btrfs_calc_insert_metadata_size(fs_info, items);
 	rsv->space_info = btrfs_find_space_info(fs_info,
 					    BTRFS_BLOCK_GROUP_METADATA);
 	ret = btrfs_block_rsv_add(root, rsv, num_bytes,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index c5939c24c963..a43f6287074b 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -348,7 +348,7 @@ static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
 	u64 bytes;
 	u64 nr;
 
-	bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+	bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
 	nr = div64_u64(to_reclaim, bytes);
 	if (!nr)
 		nr = 1;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2e3f6778bfa3..f21416d68c2c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -485,7 +485,7 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 		 * worth of delayed refs updates in this trans handle, and
 		 * refill that amount for whatever is missing in the reserve.
 		 */
-		num_bytes = btrfs_calc_trans_metadata_size(fs_info, num_items);
+		num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items);
 		if (delayed_refs_rsv->full == 0) {
 			delayed_refs_bytes = num_bytes;
 			num_bytes <<= 1;
@@ -636,7 +636,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 	if (IS_ERR(trans))
 		return trans;
 
-	num_bytes = btrfs_calc_trans_metadata_size(fs_info, num_items);
+	num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items);
 	ret = btrfs_cond_migrate_bytes(fs_info, &fs_info->trans_block_rsv,
 				       num_bytes, min_factor);
 	if (ret) {
-- 
2.21.0

[PATCH 2/2] btrfs: only reserve metadata_size for inodes

[Josef Bacik]

Historically we reserved worst case for every btree operation, and
generally speaking we want to do that in cases where it could be the
worst case.  However for updating inodes we know the inode items are
already in the tree, so it will only be an update operation and never an
insert operation.  This allows us to always reserve only the
metadata_size amount for inode updates rather than the
insert_metadata_size amount.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/delalloc-space.c | 21 +++++++++++++++++----
 fs/btrfs/delayed-inode.c  |  2 +-
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2412be4a3de2..d949d7d2abed 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -251,9 +251,16 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 
 	lockdep_assert_held(&inode->lock);
 	outstanding_extents = inode->outstanding_extents;
-	if (outstanding_extents)
+
+	/*
+	 * Insert size for the number of outstanding extents, 1 normal size for
+	 * updating the inode.
+	 */
+	if (outstanding_extents) {
 		reserve_size = btrfs_calc_insert_metadata_size(fs_info,
-						outstanding_extents + 1);
+						outstanding_extents);
+		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
+	}
 	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
 						 inode->csum_bytes);
 	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
@@ -278,10 +285,16 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 {
 	u64 nr_extents = count_max_extents(num_bytes);
 	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
+	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
-	/* We add one for the inode update at finish ordered time */
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
-						nr_extents + csum_leaves + 1);
+						nr_extents + csum_leaves);
+
+	/*
+	 * finish_ordered_io has to update the inode, so add the space required
+	 * for an inode update.
+	 */
+	*meta_reserve += inode_update;
 	*qgroup_reserve = nr_extents * fs_info->nodesize;
 }
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index de87ea7ce84d..9318cf761a07 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -612,7 +612,7 @@ static int btrfs_delayed_inode_reserve_metadata(
 	src_rsv = trans->block_rsv;
 	dst_rsv = &fs_info->delayed_block_rsv;
 
-	num_bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
+	num_bytes = btrfs_calc_metadata_size(fs_info, 1);
 
 	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
-- 
2.21.0

Re: [PATCH 0/2][v2] Rework the worst case calculations for space reservation

[David Sterba]

On Thu, Aug 22, 2019 at 03:14:32PM -0400, Josef Bacik wrote:
> v1->v2:
> - dropped "btrfs: global reserve fallback should use metadata_size", turns out
>   I was testing without my evict changes in place so we don't even need this in
>   the first place, but it is also wrong because we need to reserve space for the
>   orphan item which is an insert.

As the evict patches are in misc-next now and this patchset applies
cleanly I'll add it directly to misc-next. Thanks.