[PATCH v11 39/40] btrfs: serialize log transaction on ZONED mode

From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, dsterba@suse.com
Cc: hare@suse.com, linux-fsdevel@vger.kernel.org,
	Jens Axboe <axboe@kernel.dk>,
	Christoph Hellwig <hch@infradead.org>,
	"Darrick J. Wong" <darrick.wong@oracle.com>,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v11 39/40] btrfs: serialize log transaction on ZONED mode
Date: Tue, 22 Dec 2020 12:49:32 +0900	[thread overview]
Message-ID: <39b1c016d74422b9dcac01ba6e33d3ccd8000889.1608608848.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <06add214bc16ef08214de1594ecdfcc4cdcdbd78.1608608848.git.naohiro.aota@wdc.com>

This is the 2/3 patch to enable tree-log on ZONED mode.

Since we can start more than one log transactions per subvolume
simultaneously, nodes from multiple transactions can be allocated
interleaved. Such mixed allocation results in non-sequential writes at the
time of log transaction commit. The nodes of the global log root tree
(fs_info->log_root_tree), also have the same mixed allocation problem.

This patch serializes log transactions by waiting for a committing
transaction when someone tries to start a new transaction, to avoid the
mixed allocation problem. We must also wait for running log transactions
from another subvolume, but there is no easy way to detect which subvolume
root is running a log transaction. So, this patch forbids starting a new
log transaction when other subvolumes already allocated the global log root
tree.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/tree-log.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 930e752686b4..d269c9ea8706 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -105,6 +105,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *log,
 				       struct btrfs_path *path,
 				       u64 dirid, int del_all);
+static void wait_log_commit(struct btrfs_root *root, int transid);
 
 /*
  * tree logging is a special write ahead log used to make sure that
@@ -140,6 +141,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *tree_root = fs_info->tree_root;
+	const bool zoned = btrfs_is_zoned(fs_info);
 	int ret = 0;
 
 	/*
@@ -160,12 +162,20 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&root->log_mutex);
 
+again:
 	if (root->log_root) {
+		int index = (root->log_transid + 1) % 2;
+
 		if (btrfs_need_log_full_commit(trans)) {
 			ret = -EAGAIN;
 			goto out;
 		}
 
+		if (zoned && atomic_read(&root->log_commit[index])) {
+			wait_log_commit(root, root->log_transid - 1);
+			goto again;
+		}
+
 		if (!root->log_start_pid) {
 			clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 			root->log_start_pid = current->pid;
@@ -173,6 +183,15 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 			set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		}
 	} else {
+		mutex_lock(&fs_info->tree_log_mutex);
+		if (zoned && fs_info->log_root_tree)
+			ret = -EAGAIN;
+		else if (!fs_info->log_root_tree)
+			ret = btrfs_init_log_root_tree(trans, fs_info);
+		mutex_unlock(&fs_info->tree_log_mutex);
+		if (ret)
+			goto out;
+
 		ret = btrfs_add_log_tree(trans, root);
 		if (ret)
 			goto out;
@@ -201,14 +220,22 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
  */
 static int join_running_log_trans(struct btrfs_root *root)
 {
+	const bool zoned = btrfs_is_zoned(root->fs_info);
 	int ret = -ENOENT;
 
 	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state))
 		return ret;
 
 	mutex_lock(&root->log_mutex);
+again:
 	if (root->log_root) {
+		int index = (root->log_transid + 1) % 2;
+
 		ret = 0;
+		if (zoned && atomic_read(&root->log_commit[index])) {
+			wait_log_commit(root, root->log_transid - 1);
+			goto again;
+		}
 		atomic_inc(&root->log_writers);
 	}
 	mutex_unlock(&root->log_mutex);
-- 
2.27.0

