[v11,40/40] btrfs: reorder log node allocation

Commit Message

Naohiro Aota Dec. 22, 2020, 3:49 a.m. UTC

This is the 3/3 patch to enable tree-log on ZONED mode.

The allocation order of nodes of "fs_info->log_root_tree" and nodes of
"root->log_root" is not the same as the writing order of them. So, the
writing causes unaligned write errors.

This patch reorders the allocation of them by delaying allocation of the
root node of "fs_info->log_root_tree," so that the node buffers can go out
sequentially to devices.

Reviewed-by: Josef Bacik <[e-mail]>
Signed-off-by: Johannes Thumshirn <[e-mail]>
Signed-off-by: Naohiro Aota <[e-mail]>
---
 fs/btrfs/disk-io.c  |  7 -------
 fs/btrfs/tree-log.c | 24 ++++++++++++++++++------
 2 files changed, 18 insertions(+), 13 deletions(-)

Patch

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 12c23cb410fd..0b403affa59c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1241,18 +1241,11 @@  int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *log_root;
-	int ret;
 
 	log_root = alloc_log_tree(trans, fs_info);
 	if (IS_ERR(log_root))
 		return PTR_ERR(log_root);
 
-	ret = btrfs_alloc_log_tree_node(trans, log_root);
-	if (ret) {
-		btrfs_put_root(log_root);
-		return ret;
-	}
-
 	WARN_ON(fs_info->log_root_tree);
 	fs_info->log_root_tree = log_root;
 	return 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d269c9ea8706..8f917cb91151 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3157,6 +3157,16 @@  int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
 	root_log_ctx.log_transid = log_root_tree->log_transid;
 
+	mutex_lock(&fs_info->tree_log_mutex);
+	if (!log_root_tree->node) {
+		ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
+		if (ret) {
+			mutex_unlock(&fs_info->tree_log_mutex);
+			goto out;
+		}
+	}
+	mutex_unlock(&fs_info->tree_log_mutex);
+
 	/*
 	 * Now we are safe to update the log_root_tree because we're under the
 	 * log_mutex, and we're a current writer so we're holding the commit
@@ -3315,12 +3325,14 @@  static void free_log_tree(struct btrfs_trans_handle *trans,
 		.process_func = process_one_buffer
 	};
 
-	ret = walk_log_tree(trans, log, &wc);
-	if (ret) {
-		if (trans)
-			btrfs_abort_transaction(trans, ret);
-		else
-			btrfs_handle_fs_error(log->fs_info, ret, NULL);
+	if (log->node) {
+		ret = walk_log_tree(trans, log, &wc);
+		if (ret) {
+			if (trans)
+				btrfs_abort_transaction(trans, ret);
+			else
+				btrfs_handle_fs_error(log->fs_info, ret, NULL);
+		}
 	}
 
 	clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,