Btrfs: avoid tree log commit when there are no changes
rpm has a habit of running fdatasync when the file hasn't
changed. We already detect if a file hasn't been changed
in the current transaction but it might have been sent to
the tree-log in this transaction and not changed since
the last call to fsync.
In this case, we want to avoid a tree log sync, which includes
a number of synchronous writes and barriers. This commit
extends the existing tracking of the last transaction to change
a file to also track the last sub-transaction.
The end result is that rpm -ivh and -Uvh are roughly twice as fast,
and on par with ext3.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 6d9ec28..0a1bde2 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1980,6 +1980,7 @@
int ret;
struct btrfs_root *log = root->log_root;
struct btrfs_root *log_root_tree = root->fs_info->log_root_tree;
+ u64 log_transid = 0;
mutex_lock(&root->log_mutex);
index1 = root->log_transid % 2;
@@ -2018,6 +2019,7 @@
btrfs_set_root_node(&log->root_item, log->node);
root->log_batch = 0;
+ log_transid = root->log_transid;
root->log_transid++;
log->log_transid = root->log_transid;
root->log_start_pid = 0;
@@ -2095,6 +2097,11 @@
write_ctree_super(trans, root->fs_info->tree_root, 1);
ret = 0;
+ mutex_lock(&root->log_mutex);
+ if (root->last_log_commit < log_transid)
+ root->last_log_commit = log_transid;
+ mutex_unlock(&root->log_mutex);
+
out_wake_log_root:
atomic_set(&log_root_tree->log_commit[index2], 0);
smp_mb();
@@ -2862,6 +2869,21 @@
return ret;
}
+static int inode_in_log(struct btrfs_trans_handle *trans,
+ struct inode *inode)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ int ret = 0;
+
+ mutex_lock(&root->log_mutex);
+ if (BTRFS_I(inode)->logged_trans == trans->transid &&
+ BTRFS_I(inode)->last_sub_trans <= root->last_log_commit)
+ ret = 1;
+ mutex_unlock(&root->log_mutex);
+ return ret;
+}
+
+
/*
* helper function around btrfs_log_inode to make sure newly created
* parent directories also end up in the log. A minimal inode and backref
@@ -2901,6 +2923,11 @@
if (ret)
goto end_no_trans;
+ if (inode_in_log(trans, inode)) {
+ ret = BTRFS_NO_LOG_SYNC;
+ goto end_no_trans;
+ }
+
start_log_trans(trans, root);
ret = btrfs_log_inode(trans, root, inode, inode_only);
