shared: iterate dedupe integrity test

This case does dedupe on a dir, then copy the dir to next dir.
Dedupe the next dir again, then copy this dir to next again, and
dedupe again ... At the end, verify the data in the last dir is
still same with the first one.

Signed-off-by: Zorro Lang <zlang@redhat.com>
Reviewed-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>

tests/shared/009

@@ -0,0 +1,104 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Red Hat Inc.  All Rights Reserved.
+#
+# FS QA Test 009
+#
+# Iterate dedupe integrity test. Copy an original data0 several
+# times (d0 -> d1, d1 -> d2, ... dn-1 -> dn), dedupe dataN everytime
+# before copy. At last, verify dataN same with data0.
+#
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+
+here=`pwd`
+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
+
+# remove previous $seqres.full before test
+rm -f $seqres.full
+
+# real QA test starts here
+
+# duperemove only supports btrfs and xfs (with reflink feature).
+# Add other filesystems if it supports more later.
+_supported_fs xfs btrfs
+_supported_os Linux
+_require_scratch_dedupe
+_require_command "$DUPEREMOVE_PROG" duperemove
+
+_scratch_mkfs > $seqres.full 2>&1
+_scratch_mount >> $seqres.full 2>&1
+
+function iterate_dedup_verify()
+{
+	local src=$srcdir
+	local dest=$dupdir/1
+
+	for ((index = 1; index <= times; index++)); do
+		cp -a $src $dest
+		find $dest -type f -exec md5sum {} \; \
+			> $md5file$index
+		# Make some noise
+		$FSSTRESS_PROG $fsstress_opts -d $noisedir \
+			       -n 200 -p $((5 * LOAD_FACTOR)) >/dev/null 2>&1
+		# Too many output, so only save error output
+		$DUPEREMOVE_PROG -dr --dedupe-options=same $dupdir \
+			>/dev/null 2>$seqres.full
+		md5sum -c --quiet $md5file$index
+		src=$dest
+		dest=$dupdir/$((index + 1))
+	done
+}
+
+srcdir=$SCRATCH_MNT/src
+dupdir=$SCRATCH_MNT/dup
+noisedir=$dupdir/noise
+mkdir $srcdir $dupdir
+mkdir $dupdir/noise
+
+md5file=${tmp}.md5sum
+
+fsstress_opts="-w -r"
+# Create some files to be original data
+$FSSTRESS_PROG $fsstress_opts -d $srcdir \
+	       -n 500 -p $((5 * LOAD_FACTOR)) >/dev/null 2>&1
+
+# Calculate how many test cycles will be run
+src_size=`du -ks $srcdir | awk '{print $1}'`
+free_size=`df -kP $SCRATCH_MNT | grep -v Filesystem | awk '{print $4}'`
+times=$((free_size / src_size))
+if [ $times -gt $((4 * TIME_FACTOR)) ]; then
+	times=$((4 * TIME_FACTOR))
+fi
+
+echo "= Do dedup and verify ="
+iterate_dedup_verify
+
+# Use the last checksum file to verify the original data
+sed -e s#dup/$times#src#g $md5file$times > $md5file
+echo "= Backwords verify ="
+md5sum -c --quiet $md5file
+
+# read from the disk also doesn't show mutations.
+_scratch_cycle_mount
+echo "= Verify after cycle mount ="
+for ((index = 1; index <= times; index++)); do
+	md5sum -c --quiet $md5file$index
+done
+
+status=0
+exit

tests/shared/009.out

@@ -0,0 +1,4 @@
+QA output created by 009
+= Do dedup and verify =
+= Backwords verify =
+= Verify after cycle mount =

tests/shared/group

@@ -11,6 +11,7 @@
 006 auto enospc
 007 dangerous_fuzzers
 008 auto stress dedupe
+009 auto stress dedupe
 032 mkfs auto quick
 272 auto enospc rw
 289 auto quick