In multi-thread situations, writeback of a file may span across several sub transactions, and we need to introduce first_sub_trans to get sub_transid of teh first sub transaction recorded, so that log code can skip file extents which have been logged or committed onto disk.
Signed-off-by: Liu Bo <liubo2...@cn.fujitsu.com> --- fs/btrfs/btrfs_inode.h | 9 +++++++++ fs/btrfs/inode.c | 13 ++++++++++++- fs/btrfs/transaction.h | 17 ++++++++++++++++- 3 files changed, 37 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 52d7eca..8eca5de 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -80,6 +80,15 @@ struct btrfs_inode { /* sequence number for NFS changes */ u64 sequence; + /* used to avoid race of first_sub_trans */ + spinlock_t sub_trans_lock; + + /* + * sub transid of the trans that first modified this inode before + * a trans commit or a log sync + */ + u64 first_sub_trans; + /* * transid of the trans_handle that last modified this inode */ diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ff9d4d1..93c9d22 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6468,7 +6468,16 @@ again: set_page_dirty(page); SetPageUptodate(page); - BTRFS_I(inode)->last_trans = root->fs_info->generation; + spin_lock(&BTRFS_I(inode)->sub_trans_lock); + + if (BTRFS_I(inode)->first_sub_trans > root->fs_info->sub_generation || + BTRFS_I(inode)->last_trans <= BTRFS_I(inode)->logged_trans || + BTRFS_I(inode)->last_trans <= root->fs_info->last_trans_committed) + BTRFS_I(inode)->first_sub_trans = root->fs_info->sub_generation; + + spin_unlock(&BTRFS_I(inode)->sub_trans_lock); + + BTRFS_I(inode)->last_trans = root->fs_info->sub_generation; BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid; unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -6714,6 +6723,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->space_info = NULL; ei->generation = 0; ei->sequence = 0; + ei->first_sub_trans = 0; ei->last_trans = 0; ei->last_sub_trans = 0; ei->logged_trans = 0; @@ -6740,6 +6750,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) extent_io_tree_init(&ei->io_tree, &inode->i_data); extent_io_tree_init(&ei->io_failure_tree, &inode->i_data); mutex_init(&ei->log_mutex); + spin_lock_init(&ei->sub_trans_lock); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->i_orphan); INIT_LIST_HEAD(&ei->delalloc_inodes); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 45876b0..f5ca0fd 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -73,7 +73,22 @@ struct btrfs_pending_snapshot { static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans, struct inode *inode) { - BTRFS_I(inode)->last_trans = trans->transaction->transid; + spin_lock(&BTRFS_I(inode)->sub_trans_lock); + + /* + * We have joined in a transaction, so btrfs_commit_transaction will + * definitely wait for us and it does not need to add a extra + * trans_mutex lock here. + */ + if (BTRFS_I(inode)->first_sub_trans > trans->transid || + BTRFS_I(inode)->last_trans <= BTRFS_I(inode)->logged_trans || + BTRFS_I(inode)->last_trans <= + BTRFS_I(inode)->root->fs_info->last_trans_committed) + BTRFS_I(inode)->first_sub_trans = trans->transid; + + spin_unlock(&BTRFS_I(inode)->sub_trans_lock); + + BTRFS_I(inode)->last_trans = trans->transid; BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid; } -- 1.6.5.2 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html