linux/fs/btrfs/tree-log.h
Filipe Manana 30b80f3ce0 btrfs: use delayed items when logging a directory
When logging a directory we start by flushing all its delayed items.
That results in adding dir index items to the subvolume btree, for new
dentries, and removing dir index items from the subvolume btree for any
dentries that were deleted.

This makes it straightforward to log a directory simply by iterating over
all the modified subvolume btree leaves, especially when we used to log
both dir index keys and dir item keys (before commit 339d035424
("btrfs: only copy dir index keys when logging a directory") and when we
used to copy old dir index entries for leaves modified in the current
transaction (before commit 732d591a5d ("btrfs: stop copying old dir
items when logging a directory")).

From an efficiency point of view this has a couple of drawbacks:

1) Adds extra latency, due to copying delayed items to the subvolume btree
   and deleting dir index items from the btree.

   Further if there are other tasks accessing the btree, which is common
   (syscalls like creat, mkdir, rename, link, unlink, truncate, reflinks,
   etc, finishing an ordered extent, etc), lock contention can cause
   further delays, both to the task logging a directory and to the other
   tasks accessing the btree;

2) More time spent overall flushing delayed items, if after logging the
   directory further changes are done to the directory in the same
   transaction.

   For example, if we add 10 dentries to a directory, fsync it, add more
   10 dentries, fsync it again, then add more 10 dentries and fsync it
   again, then we end up inserting 3 batches of 10 items to the subvolume
   btree. With the changes from this patch, we flush all the delayed items
   to the btree only once - a single batch of 30 items, and outside the
   logging code (transaction commit or when delayed items are flushed
   asynchronously).

This change simply skips the flushing of delayed items every time we log a
directory. Instead we copy the delayed insertion items directly to the log
tree and delete delayed deletion items directly from the log tree.
Therefore avoiding changing first the subvolume btree and then scanning it
for new items to copy from it to the log tree and detecting deletions
by observing gaps in consecutive dir index keys in subvolume btree leaves.

Running the following tests on a non-debug kernel (Debian's default kernel
config), on a box with a NVMe device, a 12 cores Intel CPU and 64G of ram,
produced the results below.

The results compare a branch without this patch and all the other patches
it depends on versus the same branch with the patchset applied.

The patchset is comprised of the following patches:

  btrfs: don't drop dir index range items when logging a directory
  btrfs: remove the root argument from log_new_dir_dentries()
  btrfs: update stale comment for log_new_dir_dentries()
  btrfs: free list element sooner at log_new_dir_dentries()
  btrfs: avoid memory allocation at log_new_dir_dentries() for common case
  btrfs: remove root argument from btrfs_delayed_item_reserve_metadata()
  btrfs: store index number instead of key in struct btrfs_delayed_item
  btrfs: remove unused logic when looking up delayed items
  btrfs: shrink the size of struct btrfs_delayed_item
  btrfs: search for last logged dir index if it's not cached in the inode
  btrfs: move need_log_inode() to above log_conflicting_inodes()
  btrfs: move log_new_dir_dentries() above btrfs_log_inode()
  btrfs: log conflicting inodes without holding log mutex of the initial inode
  btrfs: skip logging parent dir when conflicting inode is not a dir
  btrfs: use delayed items when logging a directory

Custom test script for testing time spent at btrfs_log_inode():

   #!/bin/bash

   DEV=/dev/nvme0n1
   MNT=/mnt/nvme0n1

   # Total number of files to create in the test directory.
   NUM_FILES=10000
   # Fsync after creating or renaming N files.
   FSYNC_AFTER=100

   umount $DEV &> /dev/null
   mkfs.btrfs -f $DEV
   mount -o ssd $DEV $MNT

   TEST_DIR=$MNT/testdir
   mkdir $TEST_DIR

   echo "Creating files..."
   for ((i = 1; i <= $NUM_FILES; i++)); do
           echo -n > $TEST_DIR/file_$i
           if (( ($i % $FSYNC_AFTER) == 0 )); then
                   xfs_io -c "fsync" $TEST_DIR
           fi
   done

   sync

   echo "Renaming files..."
   for ((i = 1; i <= $NUM_FILES; i++)); do
           mv $TEST_DIR/file_$i $TEST_DIR/file_$i.renamed
           if (( ($i % $FSYNC_AFTER) == 0 )); then
                   xfs_io -c "fsync" $TEST_DIR
           fi
   done

   umount $MNT

And using the following bpftrace script to capture the total time that is
spent at btrfs_log_inode():

   #!/usr/bin/bpftrace

   k:btrfs_log_inode
   {
           @start_log_inode[tid] = nsecs;
   }

   kr:btrfs_log_inode
   /@start_log_inode[tid]/
   {
           $dur = (nsecs - @start_log_inode[tid]) / 1000;
           @btrfs_log_inode_total_time = sum($dur);
           delete(@start_log_inode[tid]);
   }

   END
   {
           clear(@start_log_inode);
   }

Result before applying patchset:

   @btrfs_log_inode_total_time: 622642

Result after applying patchset:

   @btrfs_log_inode_total_time: 354134    (-43.1% time spent)

The following dbench script was also used for testing:

   #!/bin/bash

   NUM_JOBS=$(nproc --all)

   DEV=/dev/nvme0n1
   MNT=/mnt/nvme0n1
   MOUNT_OPTIONS="-o ssd"
   MKFS_OPTIONS="-O no-holes -R free-space-tree"

   echo "performance" | \
       tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor

   umount $DEV &> /dev/null
   mkfs.btrfs -f $MKFS_OPTIONS $DEV
   mount $MOUNT_OPTIONS $DEV $MNT

   dbench -D $MNT --skip-cleanup -t 120 -S $NUM_JOBS

   umount $MNT

Before patchset:

 Operation      Count    AvgLat    MaxLat
 ----------------------------------------
 NTCreateX    3322265     0.034    21.032
 Close        2440562     0.002     0.994
 Rename        140664     1.150   269.633
 Unlink        670796     1.093   269.678
 Deltree           96     5.481    15.510
 Mkdir             48     0.004     0.052
 Qpathinfo    3010924     0.014     8.127
 Qfileinfo     528055     0.001     0.518
 Qfsinfo       552113     0.003     0.372
 Sfileinfo     270575     0.005     0.688
 Find         1164176     0.052    13.931
 WriteX       1658537     0.019     5.918
 ReadX        5207412     0.003     1.034
 LockX          10818     0.003     0.079
 UnlockX        10818     0.002     0.313
 Flush         232811     1.027   269.735

Throughput 869.867 MB/sec (sync dirs)  12 clients  12 procs  max_latency=269.741 ms

After patchset:

 Operation      Count    AvgLat    MaxLat
 ----------------------------------------
 NTCreateX    4152738     0.029    20.863
 Close        3050770     0.002     1.119
 Rename        175829     0.871   211.741
 Unlink        838447     0.845   211.724
 Deltree          120     4.798    14.162
 Mkdir             60     0.003     0.005
 Qpathinfo    3763807     0.011     4.673
 Qfileinfo     660111     0.001     0.400
 Qfsinfo       690141     0.003     0.429
 Sfileinfo     338260     0.005     0.725
 Find         1455273     0.046     6.787
 WriteX       2073307     0.017     5.690
 ReadX        6509193     0.003     1.171
 LockX          13522     0.003     0.077
 UnlockX        13522     0.002     0.125
 Flush         291044     0.811   211.631

Throughput 1089.27 MB/sec (sync dirs)  12 clients  12 procs  max_latency=211.750 ms

(+25.2% throughput, -21.5% max latency)

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2022-09-26 12:27:57 +02:00

107 lines
3.4 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
/* We can't use the tree log for whatever reason, force a transaction commit */
#define BTRFS_LOG_FORCE_COMMIT (1)
struct btrfs_log_ctx {
int log_ret;
int log_transid;
bool log_new_dentries;
bool logging_new_name;
bool logging_new_delayed_dentries;
/* Indicate if the inode being logged was logged before. */
bool logged_before;
/* 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;
struct list_head conflict_inodes;
int num_conflict_inodes;
bool logging_conflict_inodes;
};
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->logging_new_delayed_dentries = false;
ctx->logged_before = false;
ctx->inode = inode;
INIT_LIST_HEAD(&ctx->list);
INIT_LIST_HEAD(&ctx->ordered_extents);
INIT_LIST_HEAD(&ctx->conflict_inodes);
ctx->num_conflict_inodes = 0;
ctx->logging_conflict_inodes = false;
}
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);
void 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);
void 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 dentry *old_dentry, struct btrfs_inode *old_dir,
u64 old_dir_index, struct dentry *parent);
#endif