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>
This commit is contained in:
parent
4722607db6
commit
257c62e1bc
|
@ -86,6 +86,12 @@ struct btrfs_inode {
|
|||
* transid of the trans_handle that last modified this inode
|
||||
*/
|
||||
u64 last_trans;
|
||||
|
||||
/*
|
||||
* log transid when this inode was last modified
|
||||
*/
|
||||
u64 last_sub_trans;
|
||||
|
||||
/*
|
||||
* transid that last logged this inode
|
||||
*/
|
||||
|
|
|
@ -1009,6 +1009,7 @@ struct btrfs_root {
|
|||
atomic_t log_writers;
|
||||
atomic_t log_commit[2];
|
||||
unsigned long log_transid;
|
||||
unsigned long last_log_commit;
|
||||
unsigned long log_batch;
|
||||
pid_t log_start_pid;
|
||||
bool log_multiple_pids;
|
||||
|
|
|
@ -919,6 +919,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
|
|||
atomic_set(&root->log_writers, 0);
|
||||
root->log_batch = 0;
|
||||
root->log_transid = 0;
|
||||
root->last_log_commit = 0;
|
||||
extent_io_tree_init(&root->dirty_log_pages,
|
||||
fs_info->btree_inode->i_mapping, GFP_NOFS);
|
||||
|
||||
|
@ -1089,6 +1090,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
|
|||
WARN_ON(root->log_root);
|
||||
root->log_root = log_root;
|
||||
root->log_transid = 0;
|
||||
root->last_log_commit = 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
@ -1087,8 +1087,10 @@ out_nolock:
|
|||
btrfs_end_transaction(trans, root);
|
||||
else
|
||||
btrfs_commit_transaction(trans, root);
|
||||
} else {
|
||||
} else if (ret != BTRFS_NO_LOG_SYNC) {
|
||||
btrfs_commit_transaction(trans, root);
|
||||
} else {
|
||||
btrfs_end_transaction(trans, root);
|
||||
}
|
||||
}
|
||||
if (file->f_flags & O_DIRECT) {
|
||||
|
@ -1138,6 +1140,13 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
|
|||
int ret = 0;
|
||||
struct btrfs_trans_handle *trans;
|
||||
|
||||
|
||||
/* we wait first, since the writeback may change the inode */
|
||||
root->log_batch++;
|
||||
/* the VFS called filemap_fdatawrite for us */
|
||||
btrfs_wait_ordered_range(inode, 0, (u64)-1);
|
||||
root->log_batch++;
|
||||
|
||||
/*
|
||||
* check the transaction that last modified this inode
|
||||
* and see if its already been committed
|
||||
|
@ -1145,6 +1154,11 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
|
|||
if (!BTRFS_I(inode)->last_trans)
|
||||
goto out;
|
||||
|
||||
/*
|
||||
* if the last transaction that changed this file was before
|
||||
* the current transaction, we can bail out now without any
|
||||
* syncing
|
||||
*/
|
||||
mutex_lock(&root->fs_info->trans_mutex);
|
||||
if (BTRFS_I(inode)->last_trans <=
|
||||
root->fs_info->last_trans_committed) {
|
||||
|
@ -1154,13 +1168,6 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
|
|||
}
|
||||
mutex_unlock(&root->fs_info->trans_mutex);
|
||||
|
||||
root->log_batch++;
|
||||
filemap_fdatawrite(inode->i_mapping);
|
||||
btrfs_wait_ordered_range(inode, 0, (u64)-1);
|
||||
root->log_batch++;
|
||||
|
||||
if (datasync && !(inode->i_state & I_DIRTY_PAGES))
|
||||
goto out;
|
||||
/*
|
||||
* ok we haven't committed the transaction yet, lets do a commit
|
||||
*/
|
||||
|
@ -1189,14 +1196,18 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync)
|
|||
*/
|
||||
mutex_unlock(&dentry->d_inode->i_mutex);
|
||||
|
||||
if (ret > 0) {
|
||||
ret = btrfs_commit_transaction(trans, root);
|
||||
} else {
|
||||
ret = btrfs_sync_log(trans, root);
|
||||
if (ret == 0)
|
||||
ret = btrfs_end_transaction(trans, root);
|
||||
else
|
||||
if (ret != BTRFS_NO_LOG_SYNC) {
|
||||
if (ret > 0) {
|
||||
ret = btrfs_commit_transaction(trans, root);
|
||||
} else {
|
||||
ret = btrfs_sync_log(trans, root);
|
||||
if (ret == 0)
|
||||
ret = btrfs_end_transaction(trans, root);
|
||||
else
|
||||
ret = btrfs_commit_transaction(trans, root);
|
||||
}
|
||||
} else {
|
||||
ret = btrfs_end_transaction(trans, root);
|
||||
}
|
||||
mutex_lock(&dentry->d_inode->i_mutex);
|
||||
out:
|
||||
|
|
|
@ -3480,6 +3480,7 @@ static noinline void init_btrfs_i(struct inode *inode)
|
|||
bi->generation = 0;
|
||||
bi->sequence = 0;
|
||||
bi->last_trans = 0;
|
||||
bi->last_sub_trans = 0;
|
||||
bi->logged_trans = 0;
|
||||
bi->delalloc_bytes = 0;
|
||||
bi->reserved_bytes = 0;
|
||||
|
@ -4980,7 +4981,9 @@ again:
|
|||
set_page_dirty(page);
|
||||
SetPageUptodate(page);
|
||||
|
||||
BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
|
||||
BTRFS_I(inode)->last_trans = root->fs_info->generation;
|
||||
BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
|
||||
|
||||
unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
|
||||
|
||||
out_unlock:
|
||||
|
@ -5100,6 +5103,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
|
|||
if (!ei)
|
||||
return NULL;
|
||||
ei->last_trans = 0;
|
||||
ei->last_sub_trans = 0;
|
||||
ei->logged_trans = 0;
|
||||
ei->outstanding_extents = 0;
|
||||
ei->reserved_extents = 0;
|
||||
|
|
|
@ -79,6 +79,7 @@ static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
|
|||
struct inode *inode)
|
||||
{
|
||||
BTRFS_I(inode)->last_trans = trans->transaction->transid;
|
||||
BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
|
||||
}
|
||||
|
||||
int btrfs_end_transaction(struct btrfs_trans_handle *trans,
|
||||
|
|
|
@ -1980,6 +1980,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|||
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 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|||
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 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|||
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 @@ out:
|
|||
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 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
|
|||
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);
|
||||
|
|
|
@ -19,6 +19,9 @@
|
|||
#ifndef __TREE_LOG_
|
||||
#define __TREE_LOG_
|
||||
|
||||
/* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
|
||||
#define BTRFS_NO_LOG_SYNC 256
|
||||
|
||||
int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
||||
struct btrfs_root *root);
|
||||
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
|
||||
|
|
Loading…
Reference in New Issue