From 558732df2122092259ab4ef85594bee11dbb9104 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sun, 13 Feb 2022 15:42:33 +0800 Subject: btrfs: reduce extent threshold for autodefrag There is a big gap between inode_should_defrag() and autodefrag extent size threshold. For inode_should_defrag() it has a flexible @small_write value. For compressed extent is 16K, and for non-compressed extent it's 64K. However for autodefrag extent size threshold, it's always fixed to the default value (256K). This means, the following write sequence will trigger autodefrag to defrag ranges which didn't trigger autodefrag: pwrite 0 8k sync pwrite 8k 128K sync The latter 128K write will also be considered as a defrag target (if other conditions are met). While only that 8K write is really triggering autodefrag. Such behavior can cause extra IO for autodefrag. Close the gap, by copying the @small_write value into inode_defrag, so that later autodefrag can use the same @small_write value which triggered autodefrag. With the existing transid value, this allows autodefrag really to scan the ranges which triggered autodefrag. Although this behavior change is mostly reducing the extent_thresh value for autodefrag, I believe in the future we should allow users to specify the autodefrag extent threshold through mount options, but that's an other problem to consider in the future. CC: stable@vger.kernel.org # 5.16+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/file.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 36a81368ed46..a0179cc62913 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -49,6 +49,15 @@ struct inode_defrag { /* root objectid */ u64 root; + + /* + * The extent size threshold for autodefrag. + * + * This value is different for compressed/non-compressed extents, + * thus needs to be passed from higher layer. + * (aka, inode_should_defrag()) + */ + u32 extent_thresh; }; static int __compare_inode_defrag(struct inode_defrag *defrag1, @@ -101,6 +110,8 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, */ if (defrag->transid < entry->transid) entry->transid = defrag->transid; + entry->extent_thresh = min(defrag->extent_thresh, + entry->extent_thresh); return -EEXIST; } } @@ -126,7 +137,7 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) * enabled */ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) + struct btrfs_inode *inode, u32 extent_thresh) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; @@ -152,6 +163,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, defrag->ino = btrfs_ino(inode); defrag->transid = transid; defrag->root = root->root_key.objectid; + defrag->extent_thresh = extent_thresh; spin_lock(&fs_info->defrag_inodes_lock); if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) { @@ -275,6 +287,7 @@ again: memset(&range, 0, sizeof(range)); range.len = (u64)-1; range.start = cur; + range.extent_thresh = defrag->extent_thresh; sb_start_write(fs_info->sb); ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid, -- cgit