[PATCH] generic: test for deduplication between different files

[fdmanana@kernel.org]

From: Filipe Manana <fdmanana@suse.com>

Test that deduplication of an entire file that has a size that is not
aligned to the filesystem's block size into a different file does not
corrupt the destination's file data.

This test is motivated by a bug found in Btrfs which is fixed by the
following patch for the linux kernel:

  "Btrfs: fix data corruption when deduplicating between different files"

XFS also fails this test, at least as of linux kernel 4.18-rc7, exactly
with the same corruption as in Btrfs - some bytes of a block get replaced
with zeroes after the deduplication.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 tests/generic/505     | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
 tests/generic/505.out | 33 ++++++++++++++++++++
 tests/generic/group   |  1 +
 3 files changed, 118 insertions(+)
 create mode 100755 tests/generic/505
 create mode 100644 tests/generic/505.out

diff --git a/tests/generic/505 b/tests/generic/505
new file mode 100755
index 00000000..5ee232a2
--- /dev/null
+++ b/tests/generic/505
@@ -0,0 +1,84 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2018 SUSE Linux Products GmbH. All Rights Reserved.
+#
+# FS QA Test No. 505
+#
+# Test that deduplication of an entire file that has a size that is not aligned
+# to the filesystem's block size into a different file does not corrupt the
+# destination's file data.
+#
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+tmp=/tmp/$$
+status=1	# failure is the default!
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+_cleanup()
+{
+	cd /
+	rm -f $tmp.*
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+. ./common/reflink
+
+# real QA test starts here
+_supported_fs generic
+_supported_os Linux
+_require_scratch_dedupe
+
+rm -f $seqres.full
+
+_scratch_mkfs >>$seqres.full 2>&1
+_scratch_mount
+
+# The first byte with a value of 0xae starts at an offset (2518890) which is not
+# a multiple of the block size.
+$XFS_IO_PROG -f \
+	-c "pwrite -S 0x6b 0 2518890" \
+	-c "pwrite -S 0xae 2518890 102398" \
+	$SCRATCH_MNT/foo | _filter_xfs_io
+
+# Create a second file with a length not aligned to the block size, whose bytes
+# all have the value 0x6b, so that its extent(s) can be deduplicated with the
+# first file.
+$XFS_IO_PROG -f -c "pwrite -S 0x6b 0 557771" $SCRATCH_MNT/bar | _filter_xfs_io
+
+# The file is filled with bytes having the value 0x6b from offset 0 to offset
+# 2518889 and with the value 0xae from offset 2518890 to offset 2621287.
+echo "File content before deduplication:"
+od -t x1 $SCRATCH_MNT/foo
+
+# Now deduplicate the entire second file into a range of the first file that
+# also has all bytes with the value 0x6b. The destination range's end offset
+# must not be aligned to the block size and must be less then the offset of
+# the first byte with the value 0xae (byte at offset 2518890).
+$XFS_IO_PROG -c "dedupe $SCRATCH_MNT/bar 0 1957888 557771" $SCRATCH_MNT/foo \
+	| _filter_xfs_io
+
+# The bytes in the range starting at offset 2515659 (end of the deduplication
+# range) and ending at offset 2519040 (start offset rounded up to the block
+# size) must all have the value 0xae (and not replaced with 0x00 values).
+# In other words, we should have exactly the same data we had before we asked
+# for deduplication.
+echo "File content after deduplication and before unmounting:"
+od -t x1 $SCRATCH_MNT/foo
+
+# Unmount the filesystem and mount it again. This guarantees any file data in
+# the page cache is dropped.
+_scratch_cycle_mount
+
+# The bytes in the range starting at offset 2515659 (end of the deduplication
+# range) and ending at offset 2519040 (start offset rounded up to the block
+# size) must all have the value 0xae (and not replaced with 0x00 values).
+# In other words, we should have exactly the same data we had before we asked
+# for deduplication.
+echo "File content after unmounting:"
+od -t x1 $SCRATCH_MNT/foo
+
+status=0
+exit
diff --git a/tests/generic/505.out b/tests/generic/505.out
new file mode 100644
index 00000000..7556b9fb
--- /dev/null
+++ b/tests/generic/505.out
@@ -0,0 +1,33 @@
+QA output created by 505
+wrote 2518890/2518890 bytes at offset 0
+XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 102398/102398 bytes at offset 2518890
+XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 557771/557771 bytes at offset 0
+XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+File content before deduplication:
+0000000 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b
+*
+11467540 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b ae ae ae ae ae ae
+11467560 ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae
+*
+11777540 ae ae ae ae ae ae ae ae
+11777550
+deduped 557771/557771 bytes at offset 1957888
+XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+File content after deduplication and before unmounting:
+0000000 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b
+*
+11467540 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b ae ae ae ae ae ae
+11467560 ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae
+*
+11777540 ae ae ae ae ae ae ae ae
+11777550
+File content after unmounting:
+0000000 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b
+*
+11467540 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b ae ae ae ae ae ae
+11467560 ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae ae
+*
+11777540 ae ae ae ae ae ae ae ae
+11777550
diff --git a/tests/generic/group b/tests/generic/group
index 55155de8..2ff1bd7e 100644
--- a/tests/generic/group
+++ b/tests/generic/group
@@ -507,3 +507,4 @@
 502 auto quick log
 503 auto quick dax punch collapse zero
 504 auto quick locks
+505 auto quick clone dedupe
-- 
2.11.0