btrfs: implement delayed inode items operation

Changelog V5 -> V6:
- Fix oom when the memory load is high, by storing the delayed nodes into the
  root's radix tree, and letting btrfs inodes go.

Changelog V4 -> V5:
- Fix the race on adding the delayed node to the inode, which is spotted by
  Chris Mason.
- Merge Chris Mason's incremental patch into this patch.
- Fix deadlock between readdir() and memory fault, which is reported by
  Itaru Kitayama.

Changelog V3 -> V4:
- Fix nested lock, which is reported by Itaru Kitayama, by updating space cache
  inode in time.

Changelog V2 -> V3:
- Fix the race between the delayed worker and the task which does delayed items
  balance, which is reported by Tsutomu Itoh.
- Modify the patch address David Sterba's comment.
- Fix the bug of the cpu recursion spinlock, reported by Chris Mason

Changelog V1 -> V2:
- break up the global rb-tree, use a list to manage the delayed nodes,
  which is created for every directory and file, and used to manage the
  delayed directory name index items and the delayed inode item.
- introduce a worker to deal with the delayed nodes.

Compare with Ext3/4, the performance of file creation and deletion on btrfs
is very poor. the reason is that btrfs must do a lot of b+ tree insertions,
such as inode item, directory name item, directory name index and so on.

If we can do some delayed b+ tree insertion or deletion, we can improve the
performance, so we made this patch which implemented delayed directory name
index insertion/deletion and delayed inode update.

Implementation:
- introduce a delayed root object into the filesystem, that use two lists to
  manage the delayed nodes which are created for every file/directory.
  One is used to manage all the delayed nodes that have delayed items. And the
  other is used to manage the delayed nodes which is waiting to be dealt with
  by the work thread.
- Every delayed node has two rb-tree, one is used to manage the directory name
  index which is going to be inserted into b+ tree, and the other is used to
  manage the directory name index which is going to be deleted from b+ tree.
- introduce a worker to deal with the delayed operation. This worker is used
  to deal with the works of the delayed directory name index items insertion
  and deletion and the delayed inode update.
  When the delayed items is beyond the lower limit, we create works for some
  delayed nodes and insert them into the work queue of the worker, and then
  go back.
  When the delayed items is beyond the upper bound, we create works for all
  the delayed nodes that haven't been dealt with, and insert them into the work
  queue of the worker, and then wait for that the untreated items is below some
  threshold value.
- When we want to insert a directory name index into b+ tree, we just add the
  information into the delayed inserting rb-tree.
  And then we check the number of the delayed items and do delayed items
  balance. (The balance policy is above.)
- When we want to delete a directory name index from the b+ tree, we search it
  in the inserting rb-tree at first. If we look it up, just drop it. If not,
  add the key of it into the delayed deleting rb-tree.
  Similar to the delayed inserting rb-tree, we also check the number of the
  delayed items and do delayed items balance.
  (The same to inserting manipulation)
- When we want to update the metadata of some inode, we cached the data of the
  inode into the delayed node. the worker will flush it into the b+ tree after
  dealing with the delayed insertion and deletion.
- We will move the delayed node to the tail of the list after we access the
  delayed node, By this way, we can cache more delayed items and merge more
  inode updates.
- If we want to commit transaction, we will deal with all the delayed node.
- the delayed node will be freed when we free the btrfs inode.
- Before we log the inode items, we commit all the directory name index items
  and the delayed inode update.

I did a quick test by the benchmark tool[1] and found we can improve the
performance of file creation by ~15%, and file deletion by ~20%.

Before applying this patch:
Create files:
        Total files: 50000
        Total time: 1.096108
        Average time: 0.000022
Delete files:
        Total files: 50000
        Total time: 1.510403
        Average time: 0.000030

After applying this patch:
Create files:
        Total files: 50000
        Total time: 0.932899
        Average time: 0.000019
Delete files:
        Total files: 50000
        Total time: 1.215732
        Average time: 0.000024

[1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3

Many thanks for Kitayama-san's help!

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: David Sterba <dave@jikos.cz>
Tested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Tested-by: Itaru Kitayama <kitayama@cl.bb4u.ne.jp>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit is contained in:
Miao Xie 2011-04-22 18:12:22 +08:00 коммит произвёл Chris Mason
Родитель 61c4f2c81c
Коммит 16cdcec736
16 изменённых файлов: 2075 добавлений и 92 удалений

Просмотреть файл

@ -7,4 +7,4 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
compression.o delayed-ref.o relocation.o
compression.o delayed-ref.o relocation.o delayed-inode.o

Просмотреть файл

@ -22,6 +22,7 @@
#include "extent_map.h"
#include "extent_io.h"
#include "ordered-data.h"
#include "delayed-inode.h"
/* in memory btrfs inode */
struct btrfs_inode {
@ -158,9 +159,13 @@ struct btrfs_inode {
*/
unsigned force_compress:4;
struct btrfs_delayed_node *delayed_node;
struct inode vfs_inode;
};
extern unsigned char btrfs_filetype_table[];
static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
{
return container_of(inode, struct btrfs_inode, vfs_inode);

Просмотреть файл

@ -38,11 +38,6 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
struct extent_buffer *src_buf);
static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int level, int slot);
static int setup_items_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr);
struct btrfs_path *btrfs_alloc_path(void)
{
@ -3559,11 +3554,10 @@ out:
* to save stack depth by doing the bulk of the work in a function
* that doesn't call btrfs_search_slot
*/
static noinline_for_stack int
setup_items_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr)
int setup_items_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr)
{
struct btrfs_item *item;
int i;

Просмотреть файл

@ -869,6 +869,7 @@ struct btrfs_block_group_cache {
struct reloc_control;
struct btrfs_device;
struct btrfs_fs_devices;
struct btrfs_delayed_root;
struct btrfs_fs_info {
u8 fsid[BTRFS_FSID_SIZE];
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@ -895,7 +896,10 @@ struct btrfs_fs_info {
/* logical->physical extent mapping */
struct btrfs_mapping_tree mapping_tree;
/* block reservation for extent, checksum and root tree */
/*
* block reservation for extent, checksum, root tree and
* delayed dir index item
*/
struct btrfs_block_rsv global_block_rsv;
/* block reservation for delay allocation */
struct btrfs_block_rsv delalloc_block_rsv;
@ -1022,6 +1026,7 @@ struct btrfs_fs_info {
* for the sys_munmap function call path
*/
struct btrfs_workers fixup_workers;
struct btrfs_workers delayed_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
int thread_pool_size;
@ -1079,6 +1084,8 @@ struct btrfs_fs_info {
/* filesystem state */
u64 fs_state;
struct btrfs_delayed_root *delayed_root;
};
/*
@ -1161,6 +1168,11 @@ struct btrfs_root {
/* red-black tree that keeps track of in-memory inodes */
struct rb_root inode_tree;
/*
* radix tree that keeps track of delayed nodes of every inode,
* protected by inode_lock
*/
struct radix_tree_root delayed_nodes_tree;
/*
* right now this just gets used so that a root has its own devid
* for stat. It may be used for more later
@ -2099,6 +2111,13 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
}
/* extent-tree.c */
static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
int num_items)
{
return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
3 * num_items;
}
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
@ -2294,6 +2313,8 @@ void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
void btrfs_clear_path_blocking(struct btrfs_path *p,
struct extent_buffer *held);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@ -2305,6 +2326,10 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
return btrfs_del_items(trans, root, path, path->slots[0], 1);
}
int setup_items_for_insert(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr);
int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_key *key, void *data, u32 data_size);
int btrfs_insert_some_items(struct btrfs_trans_handle *trans,
@ -2368,7 +2393,7 @@ void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
/* dir-item.c */
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root, const char *name,
int name_len, u64 dir,
int name_len, struct inode *dir,
struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,

1694
fs/btrfs/delayed-inode.c Normal file

Разница между файлами не показана из-за своего большого размера Загрузить разницу

141
fs/btrfs/delayed-inode.h Normal file
Просмотреть файл

@ -0,0 +1,141 @@
/*
* Copyright (C) 2011 Fujitsu. All rights reserved.
* Written by Miao Xie <miaox@cn.fujitsu.com>
*
* 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 __DELAYED_TREE_OPERATION_H
#define __DELAYED_TREE_OPERATION_H
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <asm/atomic.h>
#include "ctree.h"
/* types of the delayed item */
#define BTRFS_DELAYED_INSERTION_ITEM 1
#define BTRFS_DELAYED_DELETION_ITEM 2
struct btrfs_delayed_root {
spinlock_t lock;
struct list_head node_list;
/*
* Used for delayed nodes which is waiting to be dealt with by the
* worker. If the delayed node is inserted into the work queue, we
* drop it from this list.
*/
struct list_head prepare_list;
atomic_t items; /* for delayed items */
int nodes; /* for delayed nodes */
wait_queue_head_t wait;
};
struct btrfs_delayed_node {
u64 inode_id;
u64 bytes_reserved;
struct btrfs_root *root;
/* Used to add the node into the delayed root's node list. */
struct list_head n_list;
/*
* Used to add the node into the prepare list, the nodes in this list
* is waiting to be dealt with by the async worker.
*/
struct list_head p_list;
struct rb_root ins_root;
struct rb_root del_root;
struct mutex mutex;
struct btrfs_inode_item inode_item;
atomic_t refs;
u64 index_cnt;
bool in_list;
bool inode_dirty;
int count;
};
struct btrfs_delayed_item {
struct rb_node rb_node;
struct btrfs_key key;
struct list_head tree_list; /* used for batch insert/delete items */
struct list_head readdir_list; /* used for readdir items */
u64 bytes_reserved;
struct btrfs_block_rsv *block_rsv;
struct btrfs_delayed_node *delayed_node;
atomic_t refs;
int ins_or_del;
u32 data_len;
char data[0];
};
static inline void btrfs_init_delayed_root(
struct btrfs_delayed_root *delayed_root)
{
atomic_set(&delayed_root->items, 0);
delayed_root->nodes = 0;
spin_lock_init(&delayed_root->lock);
init_waitqueue_head(&delayed_root->wait);
INIT_LIST_HEAD(&delayed_root->node_list);
INIT_LIST_HEAD(&delayed_root->prepare_list);
}
int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
struct btrfs_root *root, const char *name,
int name_len, struct inode *dir,
struct btrfs_disk_key *disk_key, u8 type,
u64 index);
int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *dir,
u64 index);
int btrfs_inode_delayed_dir_index_count(struct inode *inode);
int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_balance_delayed_items(struct btrfs_root *root);
int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
struct inode *inode);
/* Used for evicting the inode. */
void btrfs_remove_delayed_node(struct inode *inode);
void btrfs_kill_delayed_inode_items(struct inode *inode);
int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode);
/* Used for drop dead root */
void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
/* Used for readdir() */
void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
struct list_head *del_list);
void btrfs_put_delayed_items(struct list_head *ins_list,
struct list_head *del_list);
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index);
int btrfs_readdir_delayed_dir_index(struct file *filp, void *dirent,
filldir_t filldir,
struct list_head *ins_list);
/* for init */
int __init btrfs_delayed_inode_init(void);
void btrfs_delayed_inode_exit(void);
#endif

Просмотреть файл

@ -124,8 +124,9 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
* to use for the second index (if one is created).
*/
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
*root, const char *name, int name_len, u64 dir,
struct btrfs_key *location, u8 type, u64 index)
*root, const char *name, int name_len,
struct inode *dir, struct btrfs_key *location,
u8 type, u64 index)
{
int ret = 0;
int ret2 = 0;
@ -137,13 +138,17 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
struct btrfs_disk_key disk_key;
u32 data_size;
key.objectid = dir;
key.objectid = dir->i_ino;
btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
key.offset = btrfs_name_hash(name, name_len);
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->leave_spinning = 1;
btrfs_cpu_key_to_disk(&disk_key, location);
data_size = sizeof(*dir_item) + name_len;
dir_item = insert_with_overflow(trans, root, path, &key, data_size,
name, name_len);
@ -155,7 +160,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
}
leaf = path->nodes[0];
btrfs_cpu_key_to_disk(&disk_key, location);
btrfs_set_dir_item_key(leaf, dir_item, &disk_key);
btrfs_set_dir_type(leaf, dir_item, type);
btrfs_set_dir_data_len(leaf, dir_item, 0);
@ -174,27 +178,9 @@ second_insert:
}
btrfs_release_path(root, path);
btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
key.offset = index;
dir_item = insert_with_overflow(trans, root, path, &key, data_size,
name, name_len);
if (IS_ERR(dir_item)) {
ret2 = PTR_ERR(dir_item);
goto out_free;
}
leaf = path->nodes[0];
btrfs_cpu_key_to_disk(&disk_key, location);
btrfs_set_dir_item_key(leaf, dir_item, &disk_key);
btrfs_set_dir_type(leaf, dir_item, type);
btrfs_set_dir_data_len(leaf, dir_item, 0);
btrfs_set_dir_name_len(leaf, dir_item, name_len);
btrfs_set_dir_transid(leaf, dir_item, trans->transid);
name_ptr = (unsigned long)(dir_item + 1);
write_extent_buffer(leaf, name, name_ptr, name_len);
btrfs_mark_buffer_dirty(leaf);
ret2 = btrfs_insert_delayed_dir_index(trans, root, name, name_len, dir,
&disk_key, type, index);
out_free:
btrfs_free_path(path);
if (ret)
return ret;

Просмотреть файл

@ -1058,6 +1058,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
root->name = NULL;
root->in_sysfs = 0;
root->inode_tree = RB_ROOT;
INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
root->block_rsv = NULL;
root->orphan_block_rsv = NULL;
@ -1693,6 +1694,13 @@ struct btrfs_root *open_ctree(struct super_block *sb,
INIT_LIST_HEAD(&fs_info->ordered_extents);
spin_lock_init(&fs_info->ordered_extent_lock);
fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
GFP_NOFS);
if (!fs_info->delayed_root) {
err = -ENOMEM;
goto fail_iput;
}
btrfs_init_delayed_root(fs_info->delayed_root);
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
@ -1760,7 +1768,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
bh = btrfs_read_dev_super(fs_devices->latest_bdev);
if (!bh) {
err = -EINVAL;
goto fail_iput;
goto fail_alloc;
}
memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy));
@ -1772,7 +1780,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
disk_super = &fs_info->super_copy;
if (!btrfs_super_root(disk_super))
goto fail_iput;
goto fail_alloc;
/* check FS state, whether FS is broken. */
fs_info->fs_state |= btrfs_super_flags(disk_super);
@ -1788,7 +1796,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
ret = btrfs_parse_options(tree_root, options);
if (ret) {
err = ret;
goto fail_iput;
goto fail_alloc;
}
features = btrfs_super_incompat_flags(disk_super) &
@ -1798,7 +1806,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
"unsupported optional features (%Lx).\n",
(unsigned long long)features);
err = -EINVAL;
goto fail_iput;
goto fail_alloc;
}
features = btrfs_super_incompat_flags(disk_super);
@ -1814,7 +1822,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
"unsupported option features (%Lx).\n",
(unsigned long long)features);
err = -EINVAL;
goto fail_iput;
goto fail_alloc;
}
btrfs_init_workers(&fs_info->generic_worker,
@ -1861,6 +1869,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write",
1, &fs_info->generic_worker);
btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
fs_info->thread_pool_size,
&fs_info->generic_worker);
/*
* endios are largely parallel and should have a very
@ -1882,6 +1893,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
btrfs_start_workers(&fs_info->endio_write_workers, 1);
btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
btrfs_start_workers(&fs_info->delayed_workers, 1);
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@ -2138,6 +2150,9 @@ fail_sb_buffer:
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->endio_freespace_worker);
btrfs_stop_workers(&fs_info->submit_workers);
btrfs_stop_workers(&fs_info->delayed_workers);
fail_alloc:
kfree(fs_info->delayed_root);
fail_iput:
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
iput(fs_info->btree_inode);
@ -2578,6 +2593,7 @@ int close_ctree(struct btrfs_root *root)
del_fs_roots(fs_info);
iput(fs_info->btree_inode);
kfree(fs_info->delayed_root);
btrfs_stop_workers(&fs_info->generic_worker);
btrfs_stop_workers(&fs_info->fixup_workers);
@ -2589,6 +2605,7 @@ int close_ctree(struct btrfs_root *root)
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->endio_freespace_worker);
btrfs_stop_workers(&fs_info->submit_workers);
btrfs_stop_workers(&fs_info->delayed_workers);
btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
@ -2662,6 +2679,29 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
u64 num_dirty;
unsigned long thresh = 32 * 1024 * 1024;
if (current->flags & PF_MEMALLOC)
return;
btrfs_balance_delayed_items(root);
num_dirty = root->fs_info->dirty_metadata_bytes;
if (num_dirty > thresh) {
balance_dirty_pages_ratelimited_nr(
root->fs_info->btree_inode->i_mapping, 1);
}
return;
}
void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr)
{
/*
* looks as though older kernels can get into trouble with
* this code, they end up stuck in balance_dirty_pages forever
*/
u64 num_dirty;
unsigned long thresh = 32 * 1024 * 1024;
if (current->flags & PF_MEMALLOC)
return;

Просмотреть файл

@ -71,6 +71,7 @@ int btrfs_insert_dev_radix(struct btrfs_root *root,
u64 block_start,
u64 num_blocks);
void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr);
int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root);
void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
void btrfs_mark_buffer_dirty_nonblocking(struct extent_buffer *buf);

Просмотреть файл

@ -3973,12 +3973,6 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
}
static u64 calc_trans_metadata_size(struct btrfs_root *root, int num_items)
{
return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
3 * num_items;
}
int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
int num_items)
@ -3989,7 +3983,7 @@ int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
if (num_items == 0 || root->fs_info->chunk_root == root)
return 0;
num_bytes = calc_trans_metadata_size(root, num_items);
num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
ret = btrfs_block_rsv_add(trans, root, &root->fs_info->trans_block_rsv,
num_bytes);
if (!ret) {
@ -4028,14 +4022,14 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
* If all of the metadata space is used, we can commit
* transaction and use space it freed.
*/
u64 num_bytes = calc_trans_metadata_size(root, 4);
u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
}
void btrfs_orphan_release_metadata(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 num_bytes = calc_trans_metadata_size(root, 4);
u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
}
@ -4049,7 +4043,7 @@ int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
* two for root back/forward refs, two for directory entries
* and one for root of the snapshot.
*/
u64 num_bytes = calc_trans_metadata_size(root, 5);
u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
dst_rsv->space_info = src_rsv->space_info;
return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
}
@ -4078,7 +4072,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
if (nr_extents > reserved_extents) {
nr_extents -= reserved_extents;
to_reserve = calc_trans_metadata_size(root, nr_extents);
to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
} else {
nr_extents = 0;
to_reserve = 0;
@ -4132,7 +4126,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
to_free = calc_csum_metadata_size(inode, num_bytes);
if (nr_extents > 0)
to_free += calc_trans_metadata_size(root, nr_extents);
to_free += btrfs_calc_trans_metadata_size(root, nr_extents);
btrfs_block_rsv_release(root, &root->fs_info->delalloc_block_rsv,
to_free);

Просмотреть файл

@ -2647,11 +2647,26 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
struct extent_buffer *leaf;
int ret;
/*
* If root is tree root, it means this inode is used to
* store free space information. And these inodes are updated
* when committing the transaction, so they needn't delaye to
* be updated, or deadlock will occured.
*/
if (likely(root != root->fs_info->tree_root)) {
ret = btrfs_delayed_update_inode(trans, root, inode);
if (!ret)
btrfs_set_inode_last_trans(trans, inode);
return ret;
}
path = btrfs_alloc_path();
BUG_ON(!path);
if (!path)
return -ENOMEM;
path->leave_spinning = 1;
ret = btrfs_lookup_inode(trans, root, path,
&BTRFS_I(inode)->location, 1);
ret = btrfs_lookup_inode(trans, root, path, &BTRFS_I(inode)->location,
1);
if (ret) {
if (ret > 0)
ret = -ENOENT;
@ -2661,7 +2676,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
btrfs_unlock_up_safe(path, 1);
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
struct btrfs_inode_item);
fill_inode_item(trans, leaf, inode_item, inode);
btrfs_mark_buffer_dirty(leaf);
@ -2672,7 +2687,6 @@ failed:
return ret;
}
/*
* unlink helper that gets used here in inode.c and in the tree logging
* recovery code. It remove a link in a directory with a given name, and
@ -2724,18 +2738,9 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
goto err;
}
di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
index, name, name_len, -1);
if (IS_ERR(di)) {
ret = PTR_ERR(di);
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
if (ret)
goto err;
}
if (!di) {
ret = -ENOENT;
goto err;
}
ret = btrfs_delete_one_dir_name(trans, root, path, di);
btrfs_release_path(root, path);
ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
inode, dir->i_ino);
@ -2924,6 +2929,14 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
index = btrfs_inode_ref_index(path->nodes[0], ref);
btrfs_release_path(root, path);
/*
* This is a commit root search, if we can lookup inode item and other
* relative items in the commit root, it means the transaction of
* dir/file creation has been committed, and the dir index item that we
* delay to insert has also been inserted into the commit root. So
* we needn't worry about the delayed insertion of the dir index item
* here.
*/
di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino, index,
dentry->d_name.name, dentry->d_name.len, 0);
if (IS_ERR(di)) {
@ -3029,24 +3042,16 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
btrfs_release_path(root, path);
index = key.offset;
}
di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
index, name, name_len, -1);
BUG_ON(!di || IS_ERR(di));
leaf = path->nodes[0];
btrfs_dir_item_key_to_cpu(leaf, di, &key);
WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
ret = btrfs_delete_one_dir_name(trans, root, path, di);
BUG_ON(ret);
btrfs_release_path(root, path);
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
BUG_ON(ret);
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, dir);
BUG_ON(ret);
btrfs_free_path(path);
return 0;
}
@ -3306,6 +3311,15 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
if (root->ref_cows || root == root->fs_info->tree_root)
btrfs_drop_extent_cache(inode, new_size & (~mask), (u64)-1, 0);
/*
* This function is also used to drop the items in the log tree before
* we relog the inode, so if root != BTRFS_I(inode)->root, it means
* it is used to drop the loged items. So we shouldn't kill the delayed
* items.
*/
if (min_type == 0 && root == BTRFS_I(inode)->root)
btrfs_kill_delayed_inode_items(inode);
path = btrfs_alloc_path();
BUG_ON(!path);
path->reada = -1;
@ -4208,7 +4222,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
return d_splice_alias(inode, dentry);
}
static unsigned char btrfs_filetype_table[] = {
unsigned char btrfs_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
@ -4222,6 +4236,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
struct btrfs_key key;
struct btrfs_key found_key;
struct btrfs_path *path;
struct list_head ins_list;
struct list_head del_list;
int ret;
struct extent_buffer *leaf;
int slot;
@ -4234,6 +4250,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
char tmp_name[32];
char *name_ptr;
int name_len;
int is_curr = 0; /* filp->f_pos points to the current index? */
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@ -4258,8 +4275,16 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
filp->f_pos = 2;
}
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->reada = 2;
if (key_type == BTRFS_DIR_INDEX_KEY) {
INIT_LIST_HEAD(&ins_list);
INIT_LIST_HEAD(&del_list);
btrfs_get_delayed_items(inode, &ins_list, &del_list);
}
btrfs_set_key_type(&key, key_type);
key.offset = filp->f_pos;
key.objectid = inode->i_ino;
@ -4289,8 +4314,13 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
break;
if (found_key.offset < filp->f_pos)
goto next;
if (key_type == BTRFS_DIR_INDEX_KEY &&
btrfs_should_delete_dir_index(&del_list,
found_key.offset))
goto next;
filp->f_pos = found_key.offset;
is_curr = 1;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
di_cur = 0;
@ -4345,6 +4375,15 @@ next:
path->slots[0]++;
}
if (key_type == BTRFS_DIR_INDEX_KEY) {
if (is_curr)
filp->f_pos++;
ret = btrfs_readdir_delayed_dir_index(filp, dirent, filldir,
&ins_list);
if (ret)
goto nopos;
}
/* Reached end of directory/root. Bump pos past the last item. */
if (key_type == BTRFS_DIR_INDEX_KEY)
/*
@ -4357,6 +4396,8 @@ next:
nopos:
ret = 0;
err:
if (key_type == BTRFS_DIR_INDEX_KEY)
btrfs_put_delayed_items(&ins_list, &del_list);
btrfs_free_path(path);
return ret;
}
@ -4434,6 +4475,8 @@ void btrfs_dirty_inode(struct inode *inode)
}
}
btrfs_end_transaction(trans, root);
if (BTRFS_I(inode)->delayed_node)
btrfs_balance_delayed_items(root);
}
/*
@ -4502,9 +4545,12 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index)
int ret = 0;
if (BTRFS_I(dir)->index_cnt == (u64)-1) {
ret = btrfs_set_inode_index_count(dir);
if (ret)
return ret;
ret = btrfs_inode_delayed_dir_index_count(dir);
if (ret) {
ret = btrfs_set_inode_index_count(dir);
if (ret)
return ret;
}
}
*index = BTRFS_I(dir)->index_cnt;
@ -4671,7 +4717,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
if (ret == 0) {
ret = btrfs_insert_dir_item(trans, root, name, name_len,
parent_inode->i_ino, &key,
parent_inode, &key,
btrfs_inode_type(inode), index);
BUG_ON(ret);
@ -6784,6 +6830,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->dummy_inode = 0;
ei->force_compress = BTRFS_COMPRESS_NONE;
ei->delayed_node = NULL;
inode = &ei->vfs_inode;
extent_map_tree_init(&ei->extent_tree, GFP_NOFS);
extent_io_tree_init(&ei->io_tree, &inode->i_data, GFP_NOFS);
@ -6874,6 +6922,7 @@ void btrfs_destroy_inode(struct inode *inode)
inode_tree_del(inode);
btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
free:
btrfs_remove_delayed_node(inode);
call_rcu(&inode->i_rcu, btrfs_i_callback);
}

Просмотреть файл

@ -422,7 +422,7 @@ static noinline int create_subvol(struct btrfs_root *root,
BUG_ON(ret);
ret = btrfs_insert_dir_item(trans, root,
name, namelen, dir->i_ino, &key,
name, namelen, dir, &key,
BTRFS_FT_DIR, index);
if (ret)
goto fail;

Просмотреть файл

@ -40,6 +40,7 @@
#include <linux/magic.h>
#include <linux/slab.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@ -1206,10 +1207,14 @@ static int __init init_btrfs_fs(void)
if (err)
goto free_extent_io;
err = btrfs_interface_init();
err = btrfs_delayed_inode_init();
if (err)
goto free_extent_map;
err = btrfs_interface_init();
if (err)
goto free_delayed_inode;
err = register_filesystem(&btrfs_fs_type);
if (err)
goto unregister_ioctl;
@ -1219,6 +1224,8 @@ static int __init init_btrfs_fs(void)
unregister_ioctl:
btrfs_interface_exit();
free_delayed_inode:
btrfs_delayed_inode_exit();
free_extent_map:
extent_map_exit();
free_extent_io:
@ -1235,6 +1242,7 @@ free_sysfs:
static void __exit exit_btrfs_fs(void)
{
btrfs_destroy_cachep();
btrfs_delayed_inode_exit();
extent_map_exit();
extent_io_exit();
btrfs_interface_exit();

Просмотреть файл

@ -487,19 +487,40 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
int btrfs_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
return __btrfs_end_transaction(trans, root, 0, 1);
int ret;
ret = __btrfs_end_transaction(trans, root, 0, 1);
if (ret)
return ret;
return 0;
}
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
return __btrfs_end_transaction(trans, root, 1, 1);
int ret;
ret = __btrfs_end_transaction(trans, root, 1, 1);
if (ret)
return ret;
return 0;
}
int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
return __btrfs_end_transaction(trans, root, 0, 0);
int ret;
ret = __btrfs_end_transaction(trans, root, 0, 0);
if (ret)
return ret;
return 0;
}
int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
return __btrfs_end_transaction(trans, root, 1, 1);
}
/*
@ -967,7 +988,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
BUG_ON(ret);
ret = btrfs_insert_dir_item(trans, parent_root,
dentry->d_name.name, dentry->d_name.len,
parent_inode->i_ino, &key,
parent_inode, &key,
BTRFS_FT_DIR, index);
BUG_ON(ret);
@ -1037,6 +1058,14 @@ static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans,
int ret;
list_for_each_entry(pending, head, list) {
/*
* We must deal with the delayed items before creating
* snapshots, or we will create a snapthot with inconsistent
* information.
*/
ret = btrfs_run_delayed_items(trans, fs_info->fs_root);
BUG_ON(ret);
ret = create_pending_snapshot(trans, fs_info, pending);
BUG_ON(ret);
}
@ -1290,6 +1319,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
BUG_ON(ret);
}
ret = btrfs_run_delayed_items(trans, root);
BUG_ON(ret);
/*
* rename don't use btrfs_join_transaction, so, once we
* set the transaction to blocked above, we aren't going
@ -1316,6 +1348,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
ret = create_pending_snapshots(trans, root->fs_info);
BUG_ON(ret);
ret = btrfs_run_delayed_items(trans, root);
BUG_ON(ret);
ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
BUG_ON(ret);
@ -1432,6 +1467,8 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
root = list_entry(list.next, struct btrfs_root, root_list);
list_del(&root->root_list);
btrfs_kill_all_delayed_nodes(root);
if (btrfs_header_backref_rev(root->node) <
BTRFS_MIXED_BACKREF_REV)
btrfs_drop_snapshot(root, NULL, 0);

Просмотреть файл

@ -115,6 +115,8 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
int wait_for_unblock);
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_throttle(struct btrfs_root *root);

Просмотреть файл

@ -2773,6 +2773,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
max_key.type = (u8)-1;
max_key.offset = (u64)-1;
ret = btrfs_commit_inode_delayed_items(trans, inode);
if (ret) {
btrfs_free_path(path);
btrfs_free_path(dst_path);
return ret;
}
mutex_lock(&BTRFS_I(inode)->log_mutex);
/*