@@ -108,6 +108,7 @@ 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
@@ -142,16 +143,25 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
struct btrfs_log_ctx *ctx)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ bool zoned = btrfs_fs_incompat(fs_info, ZONED);
int ret = 0;
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;
@@ -160,8 +170,13 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
}
} else {
mutex_lock(&fs_info->tree_log_mutex);
- if (!fs_info->log_root_tree)
+ if (zoned && fs_info->log_root_tree) {
+ ret = -EAGAIN;
+ mutex_unlock(&fs_info->tree_log_mutex);
+ goto out;
+ } 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;
@@ -195,14 +210,22 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
*/
static int join_running_log_trans(struct btrfs_root *root)
{
+ bool zoned = btrfs_fs_incompat(root->fs_info, ZONED);
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);
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 | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-)