marko10_000
/
btrfs-progs
forked from Mirrors/btrfs-progs
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

btrfs-progs: Wire up delayed refs 

This commit enables the delayed refs infrastructures. This entails doing
the following:

1. Replacing existing calls of btrfs_extent_post_op (which is the
   equivalent of delayed refs) with the proper btrfs_run_delayed_refs.
   As well as eliminating open-coded calls to finish_current_insert and
   del_pending_extents which execute the delayed ops.

2. Wiring up the addition of delayed refs when freeing extents
   (btrfs_free_extent) and when adding new extents (alloc_tree_block).

3. Adding calls to btrfs_run_delayed refs in the transaction commit
   path alongside comments why every call is needed, since it's not
   always obvious (those call sites were derived empirically by running
   and debugging existing tests)

4. Correctly flagging the transaction in which we are reinitialising
   the extent tree.

5. Moving btrfs_write_dirty_block_groups to
   btrfs_write_dirty_block_groups since blockgroups should be written to
   disk after the last delayed refs have been run.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
master
Nikolay Borisov 2018-06-08 15:47:57 +03:00 committed by David Sterba
parent d8a5e756be
commit 909357e867
3 changed files with 112 additions and 83 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
check/main.c
View File

@ -8718,7 +8718,7 @@ again:
fprintf(stderr, "Error adding block group\n");
return ret;
}
btrfs_extent_post_op(trans);
btrfs_run_delayed_refs(trans, -1);
}
ret = reset_balance(trans, fs_info);
@ -9775,6 +9775,7 @@ int cmd_check(int argc, char **argv)
goto close_out;
}
trans->reinit_extent_tree = true;
if (init_extent_tree) {
printf("Creating a new extent tree\n");
ret = reinit_extent_tree(trans, info,

164
extent-tree.c
View File

@ -1418,8 +1418,6 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
err = ret;
out:
btrfs_free_path(path);
finish_current_insert(trans);
del_pending_extents(trans);
BUG_ON(err);
return err;
}
@ -1602,8 +1600,6 @@ again:
btrfs_set_extent_flags(l, item, flags);
out:
btrfs_free_path(path);
finish_current_insert(trans);
del_pending_extents(trans);
return ret;
}
@ -1701,7 +1697,6 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *cache)
{
int ret;
int pending_ret;
struct btrfs_root *extent_root = trans->fs_info->extent_root;
unsigned long bi;
struct extent_buffer *leaf;
@ -1717,12 +1712,8 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
fail:
finish_current_insert(trans);
pending_ret = del_pending_extents(trans);
if (ret)
return ret;
if (pending_ret)
return pending_ret;
return 0;
}
@ -2049,6 +2040,7 @@ static int finish_current_insert(struct btrfs_trans_handle *trans)
int skinny_metadata =
btrfs_fs_incompat(extent_root->fs_info, SKINNY_METADATA);
while(1) {
ret = find_first_extent_bit(&info->extent_ins, 0, &start,
&end, EXTENT_LOCKED);
@ -2080,6 +2072,8 @@ static int finish_current_insert(struct btrfs_trans_handle *trans)
BUG_ON(1);
}
printf("shouldn't be executed\n");
clear_extent_bits(&info->extent_ins, start, end, EXTENT_LOCKED);
kfree(extent_op);
}
@ -2379,7 +2373,6 @@ static int __free_extent(struct btrfs_trans_handle *trans,
}
fail:
btrfs_free_path(path);
finish_current_insert(trans);
return ret;
}
@ -2462,33 +2455,30 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, u64 parent,
u64 root_objectid, u64 owner, u64 offset)
{
struct btrfs_root *extent_root = root->fs_info->extent_root;
int pending_ret;
int ret;
WARN_ON(num_bytes < root->fs_info->sectorsize);
if (root == extent_root) {
struct pending_extent_op *extent_op;
extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
BUG_ON(!extent_op);
extent_op->type = PENDING_EXTENT_DELETE;
extent_op->bytenr = bytenr;
extent_op->num_bytes = num_bytes;
extent_op->level = (int)owner;
set_extent_bits(&root->fs_info->pending_del,
bytenr, bytenr + num_bytes - 1,
EXTENT_LOCKED);
set_state_private(&root->fs_info->pending_del,
bytenr, (unsigned long)extent_op);
return 0;
/*
* tree log blocks never actually go into the extent allocation
* tree, just update pinning info and exit early.
*/
if (root_objectid == BTRFS_TREE_LOG_OBJECTID) {
printf("PINNING EXTENTS IN LOG TREE\n");
WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID);
btrfs_pin_extent(trans->fs_info, bytenr, num_bytes);
ret = 0;
} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
BUG_ON(offset);
ret = btrfs_add_delayed_tree_ref(trans->fs_info, trans,
bytenr, num_bytes, parent,
root_objectid, (int)owner,
BTRFS_DROP_DELAYED_REF,
NULL, NULL, NULL);
} else {
ret = __free_extent(trans, bytenr, num_bytes, parent,
root_objectid, owner, offset, 1);
}
ret = __free_extent(trans, bytenr, num_bytes, parent,
root_objectid, owner, offset, 1);
pending_ret = del_pending_extents(trans);
return ret ? ret : pending_ret;
return ret;
}
static u64 stripe_align(struct btrfs_root *root, u64 val)
@ -2694,6 +2684,8 @@ static int alloc_reserved_tree_block2(struct btrfs_trans_handle *trans,
struct btrfs_delayed_tree_ref *ref = btrfs_delayed_node_to_tree_ref(node);
struct btrfs_key ins;
bool skinny_metadata = btrfs_fs_incompat(trans->fs_info, SKINNY_METADATA);
int ret;
u64 start, end;
ins.objectid = node->bytenr;
if (skinny_metadata) {
@ -2704,10 +2696,25 @@ static int alloc_reserved_tree_block2(struct btrfs_trans_handle *trans,
ins.type = BTRFS_EXTENT_ITEM_KEY;
}
return alloc_reserved_tree_block(trans, ref->root, trans->transid,
extent_op->flags_to_set,
&extent_op->key, ref->level, &ins);
if (ref->root == BTRFS_EXTENT_TREE_OBJECTID) {
ret = find_first_extent_bit(&trans->fs_info->extent_ins,
node->bytenr, &start, &end,
EXTENT_LOCKED);
ASSERT(!ret);
ASSERT(start == node->bytenr);
ASSERT(end == node->bytenr + node->num_bytes - 1);
}
ret = alloc_reserved_tree_block(trans, ref->root, trans->transid,
extent_op->flags_to_set,
&extent_op->key, ref->level, &ins);
if (ref->root == BTRFS_EXTENT_TREE_OBJECTID) {
clear_extent_bits(&trans->fs_info->extent_ins, start, end,
EXTENT_LOCKED);
}
return ret;
}
static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
@ -2772,40 +2779,51 @@ static int alloc_tree_block(struct btrfs_trans_handle *trans,
u64 search_end, struct btrfs_key *ins)
{
int ret;
u64 extent_size;
struct btrfs_delayed_extent_op *extent_op;
bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
SKINNY_METADATA);
extent_op = btrfs_alloc_delayed_extent_op();
if (!extent_op)
return -ENOMEM;
ret = btrfs_reserve_extent(trans, root, num_bytes, empty_size,
hint_byte, search_end, ins, 0);
if (ret < 0)
return ret;
if (root_objectid == BTRFS_EXTENT_TREE_OBJECTID) {
struct pending_extent_op *extent_op;
if (key)
memcpy(&extent_op->key, key, sizeof(extent_op->key));
else
memset(&extent_op->key, 0, sizeof(extent_op->key));
extent_op->flags_to_set = flags;
extent_op->update_key = skinny_metadata ? false : true;
extent_op->update_flags = true;
extent_op->is_data = false;
extent_op->level = level;
extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
BUG_ON(!extent_op);
extent_size = ins->offset;
extent_op->type = PENDING_EXTENT_INSERT;
extent_op->bytenr = ins->objectid;
extent_op->num_bytes = ins->offset;
extent_op->level = level;
extent_op->flags = flags;
memcpy(&extent_op->key, key, sizeof(*key));
set_extent_bits(&root->fs_info->extent_ins, ins->objectid,
ins->objectid + ins->offset - 1,
EXTENT_LOCKED);
set_state_private(&root->fs_info->extent_ins,
ins->objectid, (unsigned long)extent_op);
} else {
if (btrfs_fs_incompat(root->fs_info, SKINNY_METADATA)) {
ins->offset = level;
ins->type = BTRFS_METADATA_ITEM_KEY;
}
ret = alloc_reserved_tree_block(trans, root_objectid,
generation, flags,
key, level, ins);
finish_current_insert(trans);
del_pending_extents(trans);
if (btrfs_fs_incompat(root->fs_info, SKINNY_METADATA)) {
ins->offset = level;
ins->type = BTRFS_METADATA_ITEM_KEY;
}
/* Ensure this reserved extent is not found by the allocator */
if (root_objectid == BTRFS_EXTENT_TREE_OBJECTID) {
ret = set_extent_bits(&trans->fs_info->extent_ins,
ins->objectid,
ins->objectid + extent_size - 1,
EXTENT_LOCKED);
BUG_ON(ret);
}
ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, ins->objectid,
extent_size, 0, root_objectid,
level, BTRFS_ADD_DELAYED_EXTENT,
extent_op, NULL, NULL);
return ret;
}
@ -3330,11 +3348,6 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
sizeof(cache->item));
BUG_ON(ret);
ret = finish_current_insert(trans);
BUG_ON(ret);
ret = del_pending_extents(trans);
BUG_ON(ret);
return 0;
}
@ -3430,10 +3443,6 @@ int btrfs_make_block_groups(struct btrfs_trans_handle *trans,
sizeof(cache->item));
BUG_ON(ret);
finish_current_insert(trans);
ret = del_pending_extents(trans);
BUG_ON(ret);
cur_start = cache->key.objectid + cache->key.offset;
}
return 0;
@ -3815,14 +3824,9 @@ int btrfs_fix_block_accounting(struct btrfs_trans_handle *trans)
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root = fs_info->extent_root;
while(extent_root_pending_ops(fs_info)) {
ret = finish_current_insert(trans);
if (ret)
return ret;
ret = del_pending_extents(trans);
if (ret)
return ret;
}
ret = btrfs_run_delayed_refs(trans, -1);
if (ret)
return ret;
while(1) {
cache = btrfs_lookup_first_block_group(fs_info, start);
@ -4027,7 +4031,7 @@ static int __btrfs_record_file_extent(struct btrfs_trans_handle *trans,
} else if (ret != -EEXIST) {
goto fail;
}
btrfs_extent_post_op(trans);
btrfs_run_delayed_refs(trans, -1);
extent_bytenr = disk_bytenr;
extent_num_bytes = num_bytes;
extent_offset = 0;

28
transaction.c
View File

@ -61,7 +61,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
u64 old_root_bytenr;
struct btrfs_root *tree_root = root->fs_info->tree_root;
btrfs_write_dirty_block_groups(trans);
while(1) {
old_root_bytenr = btrfs_root_bytenr(&root->root_item);
if (old_root_bytenr == root->node->start)
@ -99,6 +98,17 @@ int commit_tree_roots(struct btrfs_trans_handle *trans,
if (ret)
return ret;
/*
* If the above CoW is the first one to dirty the current tree_root,
* delayed refs for it won't be run until after this function has
* finished executing, meaning we won't process the extent tree root,
* which will have been added to ->dirty_cowonly_roots. So run
* delayed refs here as well.
*/
ret = btrfs_run_delayed_refs(trans, -1);
if (ret)
return ret;
while(!list_empty(&fs_info->dirty_cowonly_roots)) {
next = fs_info->dirty_cowonly_roots.next;
list_del_init(next);
@ -150,6 +160,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
if (trans->fs_info->transaction_aborted)
return -EROFS;
/*
* Flush all accumulated delayed refs so that root-tree updates are
* consistent
*/
ret = btrfs_run_delayed_refs(trans, -1);
BUG_ON(ret);
if (root->commit_root == root->node)
goto commit_tree;
@ -167,10 +183,18 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
ret = btrfs_update_root(trans, root->fs_info->tree_root,
&root->root_key, &root->root_item);
BUG_ON(ret);
commit_tree:
ret = commit_tree_roots(trans, fs_info);
BUG_ON(ret);
ret = __commit_transaction(trans, root);
/*
* Ensure that all comitted roots are properly accounted in the
* extent tree
*/
ret = btrfs_run_delayed_refs(trans, -1);
BUG_ON(ret);
btrfs_write_dirty_block_groups(trans);
__commit_transaction(trans, root);
if (ret < 0)
goto out;
write_ctree_super(trans);