bd56b30205
Every transaction in btrfs creates a new snapshot, and then schedules the snapshot from the last transaction for deletion. Snapshot deletion works by walking down the btree and dropping the reference counts on each btree block during the walk. If if a given leaf or node has a reference count greater than one, the reference count is decremented and the subtree pointed to by that node is ignored. If the reference count is one, walking continues down into that node or leaf, and the references of everything it points to are decremented. The old code would try to work in small pieces, walking down the tree until it found the lowest leaf or node to free and then returning. This was very friendly to the rest of the FS because it didn't have a huge impact on other operations. But it wouldn't always keep up with the rate that new commits added new snapshots for deletion, and it wasn't very optimal for the extent allocation tree because it wasn't finding leaves that were close together on disk and processing them at the same time. This changes things to walk down to a level 1 node and then process it in bulk. All the leaf pointers are sorted and the leaves are dropped in order based on their extent number. The extent allocation tree and commit code are now fast enough for this kind of bulk processing to work without slowing the rest of the FS down. Overall it does less IO and is better able to keep up with snapshot deletions under high load. Signed-off-by: Chris Mason <chris.mason@oracle.com>
77 lines
2.2 KiB
C
77 lines
2.2 KiB
C
/*
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License v2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
#ifndef __REFCACHE__
|
|
#define __REFCACHE__
|
|
|
|
struct btrfs_extent_info {
|
|
/* bytenr and num_bytes find the extent in the extent allocation tree */
|
|
u64 bytenr;
|
|
u64 num_bytes;
|
|
|
|
/* objectid and offset find the back reference for the file */
|
|
u64 objectid;
|
|
u64 offset;
|
|
};
|
|
|
|
struct btrfs_leaf_ref {
|
|
struct rb_node rb_node;
|
|
struct btrfs_leaf_ref_tree *tree;
|
|
int in_tree;
|
|
atomic_t usage;
|
|
|
|
u64 root_gen;
|
|
u64 bytenr;
|
|
u64 owner;
|
|
u64 generation;
|
|
int nritems;
|
|
|
|
struct list_head list;
|
|
struct btrfs_extent_info extents[];
|
|
};
|
|
|
|
static inline size_t btrfs_leaf_ref_size(int nr_extents)
|
|
{
|
|
return sizeof(struct btrfs_leaf_ref) +
|
|
sizeof(struct btrfs_extent_info) * nr_extents;
|
|
}
|
|
|
|
static inline void btrfs_leaf_ref_tree_init(struct btrfs_leaf_ref_tree *tree)
|
|
{
|
|
tree->root.rb_node = NULL;
|
|
INIT_LIST_HEAD(&tree->list);
|
|
spin_lock_init(&tree->lock);
|
|
}
|
|
|
|
static inline int btrfs_leaf_ref_tree_empty(struct btrfs_leaf_ref_tree *tree)
|
|
{
|
|
return RB_EMPTY_ROOT(&tree->root);
|
|
}
|
|
|
|
void btrfs_leaf_ref_tree_init(struct btrfs_leaf_ref_tree *tree);
|
|
struct btrfs_leaf_ref *btrfs_alloc_leaf_ref(struct btrfs_root *root,
|
|
int nr_extents);
|
|
void btrfs_free_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref);
|
|
struct btrfs_leaf_ref *btrfs_lookup_leaf_ref(struct btrfs_root *root,
|
|
u64 bytenr);
|
|
int btrfs_add_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref,
|
|
int shared);
|
|
int btrfs_remove_leaf_refs(struct btrfs_root *root, u64 max_root_gen,
|
|
int shared);
|
|
int btrfs_remove_leaf_ref(struct btrfs_root *root, struct btrfs_leaf_ref *ref);
|
|
#endif
|