On Tue, Jul 27, 2021 at 05:10:30PM -0700, Darrick J. Wong wrote:

It currently fails for me on btrfs, the loop mount failed in 2nd
iteration, seems like a bug in btrfs.

+#
+. ./common/preamble
+_begin_fstest shutdown auto log metadata eio
+
+_cleanup()
+{
+	cd /
+	$KILLALL_PROG -9 fsstress > /dev/null 2>&1
+	wait
+	if [ -n "$loopmnt" ]; then
+		umount $loopmnt 2>/dev/null

$UMOUNT_PROG

+		rm -r -f $loopmnt
+	fi
+	rm -f $tmp.*
+	_dmerror_unmount
+	_dmerror_cleanup
+}
+
+# Import common functions.
+. ./common/dmerror
+. ./common/reflink
+
+# Modify as appropriate.
+_supported_fs generic
+
+_require_scratch_reflink
+_require_cp_reflink
+_require_dm_target error
+_require_command "$KILLALL_PROG" "killall"
+
+echo "Silence is golden."
+
+_scratch_mkfs >> $seqres.full 2>&1
+_require_metadata_journaling $SCRATCH_DEV
+_dmerror_init
+_dmerror_mount
+
+# Create a fs image consuming 1/3 of the scratch fs
+scratch_freesp_bytes=$(stat -f -c '%a * %S' $SCRATCH_MNT | bc)

_get_available_space $SCRATCH_MNT ?

+loopimg_bytes=$((scratch_freesp_bytes / 3))
+
+loopimg=$SCRATCH_MNT/testfs
+truncate -s $loopimg_bytes $loopimg
+_mkfs_dev $loopimg
+
+loopmnt=$tmp.mount
+mkdir -p $loopmnt
+
+scratch_aliveflag=$tmp.runsnap
+snap_aliveflag=$tmp.snapping
+
+snap_loop_fs() {
+	touch "$snap_aliveflag"
+	while [ -e "$scratch_aliveflag" ]; do
+		rm -f $loopimg.a
+		_cp_reflink $loopimg $loopimg.a
+		sleep 1
+	done
+	rm -f "$snap_aliveflag"
+}
+
+fsstress=($FSSTRESS_PROG $FSSTRESS_AVOID -d "$loopmnt" -n 999999 -p "$((LOAD_FACTOR * 4))")
+
+for i in $(seq 1 $((25 * TIME_FACTOR)) ); do
+	touch $scratch_aliveflag
+	snap_loop_fs >> $seqres.full 2>&1 &
+
+	if ! _mount $loopimg $loopmnt -o loop; then
+		rm -f $scratch_aliveflag
+		_fail "loop mount failed"

I found it a bit easier to debug if print $i here.

+		break
+	fi
+
+	("${fsstress[@]}" >> $seqres.full &) > /dev/null 2>&1
+
+	# purposely include 0 second sleeps to test shutdown immediately after
+	# recovery
+	sleep $((RANDOM % (3 * TIME_FACTOR) ))
+	rm -f $scratch_aliveflag
+
+	# This test aims to simulate sudden disk failure, which means that we
+	# do not want to quiesce the filesystem or otherwise give it a chance
+	# to flush its logs.  Therefore we want to call dmsetup with the
+	# --nolockfs parameter; to make this happen we must call the load
+	# error table helper *without* 'lockfs'.
+	_dmerror_load_error_table
+
+	ps -e | grep fsstress > /dev/null 2>&1
+	while [ $? -eq 0 ]; do
+		$KILLALL_PROG -9 fsstress > /dev/null 2>&1
+		wait > /dev/null 2>&1
+		ps -e | grep fsstress > /dev/null 2>&1
+	done
+	for ((i = 0; i < 10; i++)); do
+		test -e "$snap_aliveflag" || break
+		sleep 1
+	done
+
+	# Mount again to replay log after loading working table, so we have a
+	# consistent XFS after test.

This is a generic test, fix the XFS specific comments?

+	$UMOUNT_PROG $loopmnt
+	_dmerror_unmount || _fail "unmount failed"
+	_dmerror_load_working_table
+	if ! _dmerror_mount; then
+		dmsetup table | tee -a /dev/ttyprintk
+		lsblk | tee -a /dev/ttyprintk
+		$XFS_METADUMP_PROG -a -g -o $DMERROR_DEV $seqres.dmfail.md

Above logs all should go to $seqres.full ?

And $XFS_METADUMP_PROG is not suitable for a generic test.

+		_fail "mount failed"
+	fi
+done
+
+# Make sure the fs image file is ok
+if [ -f "$loopimg" ]; then
+	if _mount $loopimg $loopmnt -o loop; then
+		$UMOUNT_PROG $loopmnt &> /dev/null
+	else
+		echo "final loop mount failed"
+	fi
+	_check_xfs_filesystem $loopimg none none

Same here, use _check_scratch_fs?

Thanks,
Eryu