btrfs: stop doing excessive space reservation for csum deletion

Currently when reserving space for deleting the csum items for a data
extent, when adding or updating a delayed ref head, we determine how
many leaves of csum items we can have and then pass that number to the
helper btrfs_calc_delayed_ref_bytes(). This helper is used for calculating
space for all tree modifications we need when running delayed references,
however the amount of space it computes is excessive for deleting csum
items because:

1) It uses btrfs_calc_insert_metadata_size() which is excessive because
   we only need to delete csum items from the csum tree, we don't need
   to insert any items, so btrfs_calc_metadata_size() is all we need (as
   it computes space needed to delete an item);

2) If the free space tree is enabled, it doubles the amount of space,
   which is pointless for csum deletion since we don't need to touch the
   free space tree or any other tree other than the csum tree.

So improve on this by tracking how many csum deletions we have and using
a new helper to calculate space for csum deletions (just a wrapper around
btrfs_calc_metadata_size() with a comment). This reduces the amount of
space we need to reserve for csum deletions by a factor of 4, and it helps
reduce the number of times we have to block space reservations and have
the reclaim task enter the space flushing algorithm (flush delayed items,
flush delayed refs, etc) in order to satisfy tickets.

For example this results in a total time decrease when unlinking (or
truncating) files with many extents, as we end up having to block on space
metadata reservations less often. Example test:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/nullb0
  MNT=/mnt/test

  umount $DEV &> /dev/null
  mkfs.btrfs -f $DEV
  # Use compression to quickly create files with a lot of extents
  # (each with a size of 128K).
  mount -o compress=lzo $DEV $MNT

  # 100G gives at least 983040 extents with a size of 128K.
  xfs_io -f -c "pwrite -S 0xab -b 1M 0 120G" $MNT/foobar

  # Flush all delalloc and clear all metadata from memory.
  umount $MNT
  mount -o compress=lzo $DEV $MNT

  start=$(date +%s%N)
  rm -f $MNT/foobar
  end=$(date +%s%N)
  dur=$(( (end - start) / 1000000 ))
  echo "rm took $dur milliseconds"

  umount $MNT

Before this change rm took: 7504 milliseconds
After this change rm took:  6574 milliseconds  (-12.4%)

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 20 insertions, 13 deletions

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e9758929c247..ecfbc2d3f11a 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -57,17 +57,21 @@ bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info)
  * Release a ref head's reservation.
  *
  * @fs_info:  the filesystem
- * @nr:       number of items to drop
+ * @nr_refs:  number of delayed refs to drop
+ * @nr_csums: number of csum items to drop
  *
  * Drops the delayed ref head's count from the delayed refs rsv and free any
  * excess reservation we had.
  */
-void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
+void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr_refs, int nr_csums)
 {
 	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
-	const u64 num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, nr);
+	u64 num_bytes;
 	u64 released;
 
+	num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, nr_refs);
+	num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
+
 	released = btrfs_block_rsv_release(fs_info, block_rsv, num_bytes, NULL);
 	if (released)
 		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
@@ -77,8 +81,9 @@ void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
 /*
  * Adjust the size of the delayed refs rsv.
  *
- * This is to be called anytime we may have adjusted trans->delayed_ref_updates,
- * it'll calculate the additional size and add it to the delayed_refs_rsv.
+ * This is to be called anytime we may have adjusted trans->delayed_ref_updates
+ * or trans->delayed_ref_csum_deletions, it'll calculate the additional size and
+ * add it to the delayed_refs_rsv.
  */
 void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
 {
@@ -86,17 +91,19 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
 	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
 	u64 num_bytes;
 
-	if (!trans->delayed_ref_updates)
-		return;
+	num_bytes = btrfs_calc_delayed_ref_bytes(fs_info, trans->delayed_ref_updates);
+	num_bytes += btrfs_calc_delayed_ref_csum_bytes(fs_info,
+						       trans->delayed_ref_csum_deletions);
 
-	num_bytes = btrfs_calc_delayed_ref_bytes(fs_info,
-						 trans->delayed_ref_updates);
+	if (num_bytes == 0)
+		return;
 
 	spin_lock(&delayed_rsv->lock);
 	delayed_rsv->size += num_bytes;
 	delayed_rsv->full = false;
 	spin_unlock(&delayed_rsv->lock);
 	trans->delayed_ref_updates = 0;
+	trans->delayed_ref_csum_deletions = 0;
 }
 
 /*
@@ -434,7 +441,7 @@ static inline void drop_delayed_ref(struct btrfs_fs_info *fs_info,
 		list_del(&ref->add_list);
 	btrfs_put_delayed_ref(ref);
 	atomic_dec(&delayed_refs->num_entries);
-	btrfs_delayed_refs_rsv_release(fs_info, 1);
+	btrfs_delayed_refs_rsv_release(fs_info, 1, 0);
 }
 
 static bool merge_ref(struct btrfs_fs_info *fs_info,
@@ -710,11 +717,11 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
 
 		if (existing->total_ref_mod >= 0 && old_ref_mod < 0) {
 			delayed_refs->pending_csums -= existing->num_bytes;
-			btrfs_delayed_refs_rsv_release(fs_info, csum_leaves);
+			btrfs_delayed_refs_rsv_release(fs_info, 0, csum_leaves);
 		}
 		if (existing->total_ref_mod < 0 && old_ref_mod >= 0) {
 			delayed_refs->pending_csums += existing->num_bytes;
-			trans->delayed_ref_updates += csum_leaves;
+			trans->delayed_ref_csum_deletions += csum_leaves;
 		}
 	}
 
@@ -834,7 +841,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		 */
 		if (head_ref->is_data && head_ref->ref_mod < 0) {
 			delayed_refs->pending_csums += head_ref->num_bytes;
-			trans->delayed_ref_updates +=
+			trans->delayed_ref_csum_deletions +=
 				btrfs_csum_bytes_to_leaves(trans->fs_info,
 							   head_ref->num_bytes);
 		}