summaryrefslogtreecommitdiff
path: root/fs/btrfs/extent-tree.c
diff options
context:
space:
mode:
authorFilipe Manana <fdmanana@suse.com>2014-10-29 11:57:59 +0000
committerChris Mason <clm@fb.com>2014-11-25 07:41:23 -0800
commit9ea24bbe17a29f937e7f48e4b15fd52e89e9d386 (patch)
tree283655f8865c6d4adc6f080151ceb5f951f56b23 /fs/btrfs/extent-tree.c
parente5fa8f865b3324aebd055e4054bf479cbab37e5a (diff)
Btrfs: fix snapshot inconsistency after a file write followed by truncate
If right after starting the snapshot creation ioctl we perform a write against a file followed by a truncate, with both operations increasing the file's size, we can get a snapshot tree that reflects a state of the source subvolume's tree where the file truncation happened but the write operation didn't. This leaves a gap between 2 file extent items of the inode, which makes btrfs' fsck complain about it. For example, if we perform the following file operations: $ mkfs.btrfs -f /dev/vdd $ mount /dev/vdd /mnt $ xfs_io -f \ -c "pwrite -S 0xaa -b 32K 0 32K" \ -c "fsync" \ -c "pwrite -S 0xbb -b 32770 16K 32770" \ -c "truncate 90123" \ /mnt/foobar and the snapshot creation ioctl was just called before the second write, we often can get the following inode items in the snapshot's btree: item 120 key (257 INODE_ITEM 0) itemoff 7987 itemsize 160 inode generation 146 transid 7 size 90123 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 flags 0x0 item 121 key (257 INODE_REF 256) itemoff 7967 itemsize 20 inode ref index 282 namelen 10 name: foobar item 122 key (257 EXTENT_DATA 0) itemoff 7914 itemsize 53 extent data disk byte 1104855040 nr 32768 extent data offset 0 nr 32768 ram 32768 extent compression 0 item 123 key (257 EXTENT_DATA 53248) itemoff 7861 itemsize 53 extent data disk byte 0 nr 0 extent data offset 0 nr 40960 ram 40960 extent compression 0 There's a file range, corresponding to the interval [32K; ALIGN(16K + 32770, 4096)[ for which there's no file extent item covering it. This is because the file write and file truncate operations happened both right after the snapshot creation ioctl called btrfs_start_delalloc_inodes(), which means we didn't start and wait for the ordered extent that matches the write and, in btrfs_setsize(), we were able to call btrfs_cont_expand() before being able to commit the current transaction in the snapshot creation ioctl. So this made it possibe to insert the hole file extent item in the source subvolume (which represents the region added by the truncate) right before the transaction commit from the snapshot creation ioctl. Btrfs' fsck tool complains about such cases with a message like the following: "root 331 inode 257 errors 100, file extent discount" >From a user perspective, the expectation when a snapshot is created while those file operations are being performed is that the snapshot will have a file that either: 1) is empty 2) only the first write was captured 3) only the 2 writes were captured 4) both writes and the truncation were captured But never capture a state where only the first write and the truncation were captured (since the second write was performed before the truncation). A test case for xfstests follows. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/extent-tree.c')
-rw-r--r--fs/btrfs/extent-tree.c16
1 files changed, 9 insertions, 7 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5e81e3694d92..b4e3ab115f5f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9656,12 +9656,14 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
}
/*
- * btrfs_{start,end}_write() is similar to mnt_{want, drop}_write(),
- * they are used to prevent the some tasks writing data into the page cache
- * by nocow before the subvolume is snapshoted, but flush the data into
- * the disk after the snapshot creation.
+ * btrfs_{start,end}_write_no_snapshoting() are similar to
+ * mnt_{want,drop}_write(), they are used to prevent some tasks from writing
+ * data into the page cache through nocow before the subvolume is snapshoted,
+ * but flush the data into disk after the snapshot creation, or to prevent
+ * operations while snapshoting is ongoing and that cause the snapshot to be
+ * inconsistent (writes followed by expanding truncates for example).
*/
-void btrfs_end_nocow_write(struct btrfs_root *root)
+void btrfs_end_write_no_snapshoting(struct btrfs_root *root)
{
percpu_counter_dec(&root->subv_writers->counter);
/*
@@ -9673,7 +9675,7 @@ void btrfs_end_nocow_write(struct btrfs_root *root)
wake_up(&root->subv_writers->wait);
}
-int btrfs_start_nocow_write(struct btrfs_root *root)
+int btrfs_start_write_no_snapshoting(struct btrfs_root *root)
{
if (atomic_read(&root->will_be_snapshoted))
return 0;
@@ -9684,7 +9686,7 @@ int btrfs_start_nocow_write(struct btrfs_root *root)
*/
smp_mb();
if (atomic_read(&root->will_be_snapshoted)) {
- btrfs_end_nocow_write(root);
+ btrfs_end_write_no_snapshoting(root);
return 0;
}
return 1;