btrfs: send: skip resolution of our own backref when finding clone source

When doing backref walking to determine a source range to clone from, it
is worthless to collect and resolve our own data backref, as we can't
obviously use it as a clone source and it represents the range we want to
clone into. Collecting the backref implies doing the extra work to resolve
it, doing the search for a file extent item in a subvolume tree, etc.
Skipping the data backref is valid as long as we only have the send root
as the single clone root, otherwise the leaf with the file extent item may
be accessible from another clone root due to shared subtrees created by
snapshots, and therefore we have to collect the backref and resolve it.

So add a callback to the backref walking code to guide it to skip data
backrefs.

This change is part of a patchset comprised of the following patches:

  01/17 btrfs: fix inode list leak during backref walking at resolve_indirect_refs()
  02/17 btrfs: fix inode list leak during backref walking at find_parent_nodes()
  03/17 btrfs: fix ulist leaks in error paths of qgroup self tests
  04/17 btrfs: remove pointless and double ulist frees in error paths of qgroup tests
  05/17 btrfs: send: avoid unnecessary path allocations when finding extent clone
  06/17 btrfs: send: update comment at find_extent_clone()
  07/17 btrfs: send: drop unnecessary backref context field initializations
  08/17 btrfs: send: avoid unnecessary backref lookups when finding clone source
  09/17 btrfs: send: optimize clone detection to increase extent sharing
  10/17 btrfs: use a single argument for extent offset in backref walking functions
  11/17 btrfs: use a structure to pass arguments to backref walking functions
  12/17 btrfs: reuse roots ulist on each leaf iteration for iterate_extent_inodes()
  13/17 btrfs: constify ulist parameter of ulist_next()
  14/17 btrfs: send: cache leaf to roots mapping during backref walking
  15/17 btrfs: send: skip unnecessary backref iterations
  16/17 btrfs: send: avoid double extent tree search when finding clone source
  17/17 btrfs: send: skip resolution of our own backref when finding clone source

The following test was run on non-debug kernel (Debian's default kernel
config) before and after applying the patchset:

   $ cat test-send-many-shared-extents.sh
   #!/bin/bash

   DEV=/dev/sdh
   MNT=/mnt/sdh

   umount $DEV &> /dev/null
   mkfs.btrfs -f $DEV
   mount $DEV $MNT

   num_files=50000
   num_clones_per_file=50

   for ((i = 1; i <= $num_files; i++)); do
       xfs_io -f -c "pwrite 0 64K" $MNT/file_$i > /dev/null
       echo -ne "\r$i files created..."
   done
   echo

   btrfs subvolume snapshot -r $MNT $MNT/snap1

   cloned=0
   for ((i = 1; i <= $num_clones_per_file; i++)); do
       for ((j = 1; j <= $num_files; j++)); do
           cp --reflink=always $MNT/file_$j $MNT/file_${j}_clone_${i}
           cloned=$((cloned + 1))
           echo -ne "\r$cloned / $((num_files * num_clones_per_file)) clone operations"
       done
   done
   echo

   btrfs subvolume snapshot -r $MNT $MNT/snap2

   # Unmount and mount again to clear all cached metadata (and data).
   umount $DEV
   mount $DEV $MNT

   start=$(date +%s%N)
   btrfs send $MNT/snap2 > /dev/null
   end=$(date +%s%N)

   dur=$(( (end - start) / 1000000000 ))
   echo -e "\nFull send took $dur seconds"

   # Unmount and mount again to clear all cached metadata (and data).
   umount $DEV
   mount $DEV $MNT

   start=$(date +%s%N)
   btrfs send -p $MNT/snap1 $MNT/snap2 > /dev/null
   end=$(date +%s%N)

   dur=$(( (end - start) / 1000000000 ))
   echo -e "\nIncremental send took $dur seconds"

   umount $MNT

Before applying the patchset:

   (...)
   Full send took 1108 seconds
   (...)
   Incremental send took 1135 seconds

After applying the whole patchset:

   (...)
   Full send took 268 seconds            (-75.8%)
   (...)
   Incremental send took 316 seconds     (-72.2%)

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 21 insertions, 14 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 33056c4c0528..430974cf3b96 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1111,10 +1111,12 @@ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx,
 
 			root = btrfs_extent_data_ref_root(leaf, dref);
 
-			ret = add_indirect_ref(ctx->fs_info, preftrees, root,
-					       &key, 0, ctx->bytenr, count,
-					       sc, GFP_NOFS);
-
+			if (!ctx->skip_data_ref ||
+			    !ctx->skip_data_ref(root, key.objectid, key.offset,
+						ctx->user_ctx))
+				ret = add_indirect_ref(ctx->fs_info, preftrees,
+						       root, &key, 0, ctx->bytenr,
+						       count, sc, GFP_NOFS);
 			break;
 		}
 		default:
@@ -1133,8 +1135,9 @@ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx,
  *
  * Returns 0 on success, <0 on error, or BACKREF_FOUND_SHARED.
  */
-static int add_keyed_refs(struct btrfs_root *extent_root,
-			  struct btrfs_path *path, u64 bytenr,
+static int add_keyed_refs(struct btrfs_backref_walk_ctx *ctx,
+			  struct btrfs_root *extent_root,
+			  struct btrfs_path *path,
 			  int info_level, struct preftrees *preftrees,
 			  struct share_check *sc)
 {
@@ -1157,7 +1160,7 @@ static int add_keyed_refs(struct btrfs_root *extent_root,
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, slot);
 
-		if (key.objectid != bytenr)
+		if (key.objectid != ctx->bytenr)
 			break;
 		if (key.type < BTRFS_TREE_BLOCK_REF_KEY)
 			continue;
@@ -1169,7 +1172,7 @@ static int add_keyed_refs(struct btrfs_root *extent_root,
 			/* SHARED DIRECT METADATA backref */
 			ret = add_direct_ref(fs_info, preftrees,
 					     info_level + 1, key.offset,
-					     bytenr, 1, NULL, GFP_NOFS);
+					     ctx->bytenr, 1, NULL, GFP_NOFS);
 			break;
 		case BTRFS_SHARED_DATA_REF_KEY: {
 			/* SHARED DIRECT FULL backref */
@@ -1180,14 +1183,14 @@ static int add_keyed_refs(struct btrfs_root *extent_root,
 					      struct btrfs_shared_data_ref);
 			count = btrfs_shared_data_ref_count(leaf, sdref);
 			ret = add_direct_ref(fs_info, preftrees, 0,
-					     key.offset, bytenr, count,
+					     key.offset, ctx->bytenr, count,
 					     sc, GFP_NOFS);
 			break;
 		}
 		case BTRFS_TREE_BLOCK_REF_KEY:
 			/* NORMAL INDIRECT METADATA backref */
 			ret = add_indirect_ref(fs_info, preftrees, key.offset,
-					       NULL, info_level + 1, bytenr,
+					       NULL, info_level + 1, ctx->bytenr,
 					       1, NULL, GFP_NOFS);
 			break;
 		case BTRFS_EXTENT_DATA_REF_KEY: {
@@ -1211,9 +1214,13 @@ static int add_keyed_refs(struct btrfs_root *extent_root,
 			}
 
 			root = btrfs_extent_data_ref_root(leaf, dref);
-			ret = add_indirect_ref(fs_info, preftrees, root,
-					       &key, 0, bytenr, count,
-					       sc, GFP_NOFS);
+
+			if (!ctx->skip_data_ref ||
+			    !ctx->skip_data_ref(root, key.objectid, key.offset,
+						ctx->user_ctx))
+				ret = add_indirect_ref(fs_info, preftrees, root,
+						       &key, 0, ctx->bytenr,
+						       count, sc, GFP_NOFS);
 			break;
 		}
 		default:
@@ -1466,7 +1473,7 @@ again:
 					      &preftrees, sc);
 			if (ret)
 				goto out;
-			ret = add_keyed_refs(root, path, ctx->bytenr, info_level,
+			ret = add_keyed_refs(ctx, root, path, info_level,
 					     &preftrees, sc);
 			if (ret)
 				goto out;