From 827463c49f29111efd22148d24c9ca44d648acfa Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 14 Jan 2014 20:31:51 +0800 Subject: [PATCH] Btrfs: don't mix the ordered extents of all files together during logging the inodes There was a problem in the old code: If we failed to log the csum, we would free all the ordered extents in the log list including those ordered extents that were logged successfully, it would make the log committer not to wait for the completion of the ordered extents. This patch doesn't insert the ordered extents that is about to be logged into a global list, instead, we insert them into a local list. If we log the ordered extents successfully, we splice them with the global list, or we will throw them away, then do full sync. It can also reduce the lock contention and the traverse time of list. Signed-off-by: Miao Xie Signed-off-by: Josef Bacik --- fs/btrfs/ordered-data.c | 37 +++++++++++++++++++++++++++++-------- fs/btrfs/ordered-data.h | 6 +++++- fs/btrfs/tree-log.c | 41 +++++++++++++++-------------------------- 3 files changed, 49 insertions(+), 35 deletions(-) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index b16450b840e7..138a7d7e9c90 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -424,27 +424,48 @@ int btrfs_dec_test_ordered_pending(struct inode *inode, } /* Needs to either be called under a log transaction or the log_mutex */ -void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode) +void btrfs_get_logged_extents(struct inode *inode, + struct list_head *logged_list) { struct btrfs_ordered_inode_tree *tree; struct btrfs_ordered_extent *ordered; struct rb_node *n; - int index = log->log_transid % 2; tree = &BTRFS_I(inode)->ordered_tree; spin_lock_irq(&tree->lock); for (n = rb_first(&tree->tree); n; n = rb_next(n)) { ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node); - spin_lock(&log->log_extents_lock[index]); - if (list_empty(&ordered->log_list)) { - list_add_tail(&ordered->log_list, &log->logged_list[index]); - atomic_inc(&ordered->refs); - } - spin_unlock(&log->log_extents_lock[index]); + if (!list_empty(&ordered->log_list)) + continue; + list_add_tail(&ordered->log_list, logged_list); + atomic_inc(&ordered->refs); } spin_unlock_irq(&tree->lock); } +void btrfs_put_logged_extents(struct list_head *logged_list) +{ + struct btrfs_ordered_extent *ordered; + + while (!list_empty(logged_list)) { + ordered = list_first_entry(logged_list, + struct btrfs_ordered_extent, + log_list); + list_del_init(&ordered->log_list); + btrfs_put_ordered_extent(ordered); + } +} + +void btrfs_submit_logged_extents(struct list_head *logged_list, + struct btrfs_root *log) +{ + int index = log->log_transid % 2; + + spin_lock_irq(&log->log_extents_lock[index]); + list_splice_tail(logged_list, &log->logged_list[index]); + spin_unlock_irq(&log->log_extents_lock[index]); +} + void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid) { struct btrfs_ordered_extent *ordered; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 9b0450f7ac20..246897058efb 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -197,7 +197,11 @@ void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr); void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr); -void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode); +void btrfs_get_logged_extents(struct inode *inode, + struct list_head *logged_list); +void btrfs_put_logged_extents(struct list_head *logged_list); +void btrfs_submit_logged_extents(struct list_head *logged_list, + struct btrfs_root *log); void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid); void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); int __init ordered_data_init(void); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 39d83da03e03..7c449c699bed 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3479,7 +3479,8 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b) static int log_one_extent(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_root *root, - struct extent_map *em, struct btrfs_path *path) + struct extent_map *em, struct btrfs_path *path, + struct list_head *logged_list) { struct btrfs_root *log = root->log_root; struct btrfs_file_extent_item *fi; @@ -3495,7 +3496,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans, u64 extent_offset = em->start - em->orig_start; u64 block_len; int ret; - int index = log->log_transid % 2; bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; int extent_inserted = 0; @@ -3579,17 +3579,12 @@ static int log_one_extent(struct btrfs_trans_handle *trans, * First check and see if our csums are on our outstanding ordered * extents. */ -again: - spin_lock_irq(&log->log_extents_lock[index]); - list_for_each_entry(ordered, &log->logged_list[index], log_list) { + list_for_each_entry(ordered, logged_list, log_list) { struct btrfs_ordered_sum *sum; if (!mod_len) break; - if (ordered->inode != inode) - continue; - if (ordered->file_offset + ordered->len <= mod_start || mod_start + mod_len <= ordered->file_offset) continue; @@ -3632,12 +3627,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans, if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM, &ordered->flags)) continue; - atomic_inc(&ordered->refs); - spin_unlock_irq(&log->log_extents_lock[index]); - /* - * we've dropped the lock, we must either break or - * start over after this. - */ if (ordered->csum_bytes_left) { btrfs_start_ordered_extent(inode, ordered, 0); @@ -3647,16 +3636,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans, list_for_each_entry(sum, &ordered->list, list) { ret = btrfs_csum_file_blocks(trans, log, sum); - if (ret) { - btrfs_put_ordered_extent(ordered); + if (ret) goto unlocked; - } } - btrfs_put_ordered_extent(ordered); - goto again; } - spin_unlock_irq(&log->log_extents_lock[index]); unlocked: if (!mod_len || ret) @@ -3694,7 +3678,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans, static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, - struct btrfs_path *path) + struct btrfs_path *path, + struct list_head *logged_list) { struct extent_map *em, *n; struct list_head extents; @@ -3752,7 +3737,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, write_unlock(&tree->lock); - ret = log_one_extent(trans, inode, root, em, path); + ret = log_one_extent(trans, inode, root, em, path, logged_list); write_lock(&tree->lock); clear_em_logging(tree, em); free_extent_map(em); @@ -3788,6 +3773,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_key max_key; struct btrfs_root *log = root->log_root; struct extent_buffer *src = NULL; + LIST_HEAD(logged_list); u64 last_extent = 0; int err = 0; int ret; @@ -3836,7 +3822,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&BTRFS_I(inode)->log_mutex); - btrfs_get_logged_extents(log, inode); + btrfs_get_logged_extents(inode, &logged_list); /* * a brute force approach to making sure we get the most uptodate @@ -3962,7 +3948,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, btrfs_release_path(path); btrfs_release_path(dst_path); if (fast_search) { - ret = btrfs_log_changed_extents(trans, root, inode, dst_path); + ret = btrfs_log_changed_extents(trans, root, inode, dst_path, + &logged_list); if (ret) { err = ret; goto out_unlock; @@ -3987,8 +3974,10 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, BTRFS_I(inode)->logged_trans = trans->transid; BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans; out_unlock: - if (err) - btrfs_free_logged_extents(log, log->log_transid); + if (unlikely(err)) + btrfs_put_logged_extents(&logged_list); + else + btrfs_submit_logged_extents(&logged_list, log); mutex_unlock(&BTRFS_I(inode)->log_mutex); btrfs_free_path(path); -- GitLab