ext4: fix block reservation for bigalloc filesystems
For bigalloc filesystems we have to check whether newly requested inode
block isn't already part of a cluster for which we already have delayed
allocation reservation. This check happens in ext4_ext_map_blocks() and
that function sets EXT4_MAP_FROM_CLUSTER if that's the case. However if
ext4_da_map_blocks() finds in extent cache information about the block,
we don't call into ext4_ext_map_blocks() and thus we always end up
getting new reservation even if the space for cluster is already
reserved. This results in overreservation and premature ENOSPC reports.
Fix the problem by checking for existing cluster reservation already in
ext4_da_map_blocks(). That simplifies the logic and actually allows us
to get rid of the EXT4_MAP_FROM_CLUSTER flag completely.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3356ab5..2315e45 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -416,11 +416,6 @@
}
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
up_read((&EXT4_I(inode)->i_data_sem));
- /*
- * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag
- * because it shouldn't be marked in es_map->m_flags.
- */
- map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY);
/*
* We don't check m_len because extent will be collpased in status
@@ -1434,19 +1429,9 @@
* file system block.
*/
down_read(&EXT4_I(inode)->i_data_sem);
- if (ext4_has_inline_data(inode)) {
- /*
- * We will soon create blocks for this page, and let
- * us pretend as if the blocks aren't allocated yet.
- * In case of clusters, we have to handle the work
- * of mapping from cluster so that the reserved space
- * is calculated properly.
- */
- if ((EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk))
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ if (ext4_has_inline_data(inode))
retval = 0;
- } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
retval = ext4_ext_map_blocks(NULL, inode, map,
EXT4_GET_BLOCKS_NO_PUT_HOLE);
else
@@ -1465,7 +1450,8 @@
* then we don't need to reserve it again. However we still need
* to reserve metadata for every block we're going to write.
*/
- if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio <= 1 ||
+ !ext4_find_delalloc_cluster(inode, map->m_lblk)) {
ret = ext4_da_reserve_space(inode, iblock);
if (ret) {
/* not enough space to reserve */
@@ -1481,11 +1467,6 @@
goto out_unlock;
}
- /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
- * and it should not appear on the bh->b_state.
- */
- map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
-
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);