From 16cdcec736cd214350cdb591bf1091f8beedefa0 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 22 Apr 2011 18:12:22 +0800 Subject: 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 Reviewed-by: David Sterba Tested-by: Tsutomu Itoh Tested-by: Itaru Kitayama Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c571734d5e5a..b83ed5e64a32 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -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); -- cgit v1.2.3