diff options
author | Filipe Manana <fdmanana@suse.com> | 2017-11-04 00:16:59 +0000 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2017-11-15 17:27:46 +0100 |
commit | e3b8a4858566a6cc25422fbfdfdd760b13b79280 (patch) | |
tree | 96e5ff78992e66e6eb4e114ca84b2542a61d0bf0 /fs/btrfs/file.c | |
parent | f48bf66b662e7acd6a32dbc28c4fa38931f8f0a6 (diff) |
Btrfs: fix reported number of inode blocks after buffered append writes
The patch from commit a7e3b975a0f9 ("Btrfs: fix reported number of inode
blocks") introduced a regression where if we do a buffered write starting
at position equal to or greater than the file's size and then stat(2) the
file before writeback is triggered, the number of used blocks does not
change (unless there's a prealloc/unwritten extent). Example:
$ xfs_io -f -c "pwrite -S 0xab 0 64K" foobar
$ du -h foobar
0 foobar
$ sync
$ du -h foobar
64K foobar
The first version of that patch didn't had this regression and the second
version, which was the one committed, was made only to address some
performance regression detected by the intel test robots using fs_mark.
This fixes the regression by setting the new delaloc bit in the range, and
doing it at btrfs_dirty_pages() while setting the regular dealloc bit as
well, so that this way we set both bits at once avoiding navigation of the
inode's io tree twice. Doing it at btrfs_dirty_pages() is also the most
meaninful place, as we should set the new dellaloc bit when if we set the
delalloc bit, which happens only if we copied bytes into the pages at
__btrfs_buffered_write().
This was making some of LTP's du tests fail, which can be quickly run
using a command line like the following:
$ ./runltp -q -p -l /ltp.log -f commands -s du -d /mnt
Fixes: a7e3b975a0f9 ("Btrfs: fix reported number of inode blocks")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/file.c')
-rw-r--r-- | fs/btrfs/file.c | 43 |
1 files changed, 26 insertions, 17 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 47e6ebad78c3..2de7b4f4ca3c 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -538,14 +538,34 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, u64 end_of_last_block; u64 end_pos = pos + write_bytes; loff_t isize = i_size_read(inode); + unsigned int extra_bits = 0; start_pos = pos & ~((u64) fs_info->sectorsize - 1); num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); end_of_last_block = start_pos + num_bytes - 1; + + if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (start_pos >= isize && + !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case + * so just set the delalloc new bit for the range + * directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode), + start_pos, + num_bytes, cached); + if (err) + return err; + } + } + err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, - cached, 0); + extra_bits, cached, 0); if (err) return err; @@ -1473,10 +1493,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, + round_up(pos + write_bytes - start_pos, fs_info->sectorsize) - 1; - if (start_pos < inode->vfs_inode.i_size || - (inode->flags & BTRFS_INODE_PREALLOC)) { + if (start_pos < inode->vfs_inode.i_size) { struct btrfs_ordered_extent *ordered; - unsigned int clear_bits; lock_extent_bits(&inode->io_tree, start_pos, last_pos, cached_state); @@ -1498,19 +1516,10 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } if (ordered) btrfs_put_ordered_extent(ordered); - ret = btrfs_find_new_delalloc_bytes(inode, start_pos, - last_pos - start_pos + 1, - cached_state); - clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG; - if (ret) - clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED; - clear_extent_bit(&inode->io_tree, start_pos, - last_pos, clear_bits, - (clear_bits & EXTENT_LOCKED) ? 1 : 0, - 0, cached_state, GFP_NOFS); - if (ret) - return ret; + clear_extent_bit(&inode->io_tree, start_pos, last_pos, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, + 0, 0, cached_state, GFP_NOFS); *lockstart = start_pos; *lockend = last_pos; ret = 1; |