mirror of
https://github.com/torvalds/linux
synced 2024-10-17 00:39:37 +00:00
dc2872247e
After the first time we log a directory in the current transaction, for
each directory item in a changed leaf of the subvolume tree, we have to
check if we previously logged the item, in order to overwrite it in case
its data changed or skip it in case its data hasn't changed.
Checking if we have logged each item before not only wastes times, but it
also adds lock contention on the log tree. So in order to minimize the
number of times we do such checks, keep track of the offset of the last
key we logged for a directory and, on the next time we log the directory,
skip the checks for any new keys that have an offset greater than the
offset we have previously saved. This is specially effective for index
keys, because the offset for these keys comes from a monotonically
increasing counter.
This patch is part of a patchset comprised of the following 5 patches:
btrfs: remove root argument from btrfs_log_inode() and its callees
btrfs: remove redundant log root assignment from log_dir_items()
btrfs: factor out the copying loop of dir items from log_dir_items()
btrfs: insert items in batches when logging a directory when possible
btrfs: keep track of the last logged keys when logging a directory
This is patch 5/5.
The following test was used on a non-debug kernel to measure the impact
it has on a directory fsync:
$ cat test-dir-fsync.sh
#!/bin/bash
DEV=/dev/nvme0n1
MNT=/mnt/nvme0n1
NUM_NEW_FILES=100000
NUM_FILE_DELETES=1000
mkfs.btrfs -f $DEV
mount -o ssd $DEV $MNT
mkdir $MNT/testdir
for ((i = 1; i <= $NUM_NEW_FILES; i++)); do
echo -n > $MNT/testdir/file_$i
done
# fsync the directory, this will log the new dir items and the inodes
# they point to, because these are new inodes.
start=$(date +%s%N)
xfs_io -c "fsync" $MNT/testdir
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "dir fsync took $dur ms after adding $NUM_NEW_FILES files"
# sync to force transaction commit and wipeout the log.
sync
del_inc=$(( $NUM_NEW_FILES / $NUM_FILE_DELETES ))
for ((i = 1; i <= $NUM_NEW_FILES; i += $del_inc)); do
rm -f $MNT/testdir/file_$i
done
# fsync the directory, this will only log dir items, there are no
# dentries pointing to new inodes.
start=$(date +%s%N)
xfs_io -c "fsync" $MNT/testdir
end=$(date +%s%N)
dur=$(( (end - start) / 1000000 ))
echo "dir fsync took $dur ms after deleting $NUM_FILE_DELETES files"
umount $MNT
Test results with NUM_NEW_FILES set to 100 000 and 1 000 000:
**** before patchset, 100 000 files, 1000 deletes ****
dir fsync took 848 ms after adding 100000 files
dir fsync took 175 ms after deleting 1000 files
**** after patchset, 100 000 files, 1000 deletes ****
dir fsync took 758 ms after adding 100000 files (-11.2%)
dir fsync took 63 ms after deleting 1000 files (-94.1%)
**** before patchset, 1 000 000 files, 1000 deletes ****
dir fsync took 9945 ms after adding 1000000 files
dir fsync took 473 ms after deleting 1000 files
**** after patchset, 1 000 000 files, 1000 deletes ****
dir fsync took 8677 ms after adding 1000000 files (-13.6%)
dir fsync took 146 ms after deleting 1000 files (-105.6%)
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
93 lines
2.9 KiB
C
93 lines
2.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_TREE_LOG_H
|
|
#define BTRFS_TREE_LOG_H
|
|
|
|
#include "ctree.h"
|
|
#include "transaction.h"
|
|
|
|
/* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
|
|
#define BTRFS_NO_LOG_SYNC 256
|
|
|
|
struct btrfs_log_ctx {
|
|
int log_ret;
|
|
int log_transid;
|
|
bool log_new_dentries;
|
|
bool logging_new_name;
|
|
/* Tracks the last logged dir item/index key offset. */
|
|
u64 last_dir_item_offset;
|
|
struct inode *inode;
|
|
struct list_head list;
|
|
/* Only used for fast fsyncs. */
|
|
struct list_head ordered_extents;
|
|
};
|
|
|
|
static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
|
|
struct inode *inode)
|
|
{
|
|
ctx->log_ret = 0;
|
|
ctx->log_transid = 0;
|
|
ctx->log_new_dentries = false;
|
|
ctx->logging_new_name = false;
|
|
ctx->inode = inode;
|
|
INIT_LIST_HEAD(&ctx->list);
|
|
INIT_LIST_HEAD(&ctx->ordered_extents);
|
|
}
|
|
|
|
static inline void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
|
|
{
|
|
struct btrfs_ordered_extent *ordered;
|
|
struct btrfs_ordered_extent *tmp;
|
|
|
|
ASSERT(inode_is_locked(ctx->inode));
|
|
|
|
list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
|
|
list_del_init(&ordered->log_list);
|
|
btrfs_put_ordered_extent(ordered);
|
|
}
|
|
}
|
|
|
|
static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans)
|
|
{
|
|
WRITE_ONCE(trans->fs_info->last_trans_log_full_commit, trans->transid);
|
|
}
|
|
|
|
static inline int btrfs_need_log_full_commit(struct btrfs_trans_handle *trans)
|
|
{
|
|
return READ_ONCE(trans->fs_info->last_trans_log_full_commit) ==
|
|
trans->transid;
|
|
}
|
|
|
|
int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root, struct btrfs_log_ctx *ctx);
|
|
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
|
|
int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info);
|
|
int btrfs_recover_log_trees(struct btrfs_root *tree_root);
|
|
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
|
|
struct dentry *dentry,
|
|
struct btrfs_log_ctx *ctx);
|
|
int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *dir, u64 index);
|
|
int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *inode, u64 dirid);
|
|
void btrfs_end_log_trans(struct btrfs_root *root);
|
|
void btrfs_pin_log_trans(struct btrfs_root *root);
|
|
void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir, struct btrfs_inode *inode,
|
|
int for_rename);
|
|
void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir);
|
|
void btrfs_log_new_name(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *inode, struct btrfs_inode *old_dir,
|
|
struct dentry *parent);
|
|
|
|
#endif
|