tests/btrfs/192

#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (C) 2019 SUSE Linux Products GmbH. All Rights Reserved.
#
# FS QA Test 192
#
# Test btrfs consistency after each FUA for a workload with snapshot creation
# and removal
#
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 /
	kill -q $pid1 &> /dev/null
	kill -q $pid2 &> /dev/null
	"$KILLALL_PROG" -q $FSSTRESS_PROG &> /dev/null
	wait
	_log_writes_cleanup &> /dev/null
	rm -f $tmp.*
}

# get standard environment, filters and checks
. ./common/rc
. ./common/filter
. ./common/attr
. ./common/dmlogwrites

# remove previous $seqres.full before test
rm -f $seqres.full

# real QA test starts here

# Modify as appropriate.
_supported_fs btrfs

_require_command "$KILLALL_PROG" killall
_require_command "$BLKDISCARD_PROG" blkdiscard
_require_btrfs_fs_feature "no_holes"
_require_btrfs_mkfs_feature "no-holes"
_require_log_writes
_require_scratch
_require_attrs

# We require a 4K nodesize to ensure the test isn't too slow
if [ $(get_page_size) -ne 4096 ]; then
	_notrun "This test doesn't support non-4K page size yet"
fi

runtime=30
nr_cpus=$("$here/src/feature" -o)
# cap nr_cpus to 8 to avoid spending too much time on hosts with many cpus
if [ $nr_cpus -gt 8 ]; then
	nr_cpus=8
fi
fsstress_args=$(_scale_fsstress_args -w -d $SCRATCH_MNT -n 99999 -p $nr_cpus \
		$FSSTRESS_AVOID)
_log_writes_init $SCRATCH_DEV

# Discard the whole devices so when some tree pointer is wrong, it won't point
# to some older valid tree blocks, so we can detect it.
$BLKDISCARD_PROG $LOGWRITES_DMDEV > /dev/null 2>&1

# Use no-holes to avoid warnings of missing file extent items (expected
# for holes due to mix of buffered and direct IO writes).
# And use 4K nodesize to bump tree height.
_log_writes_mkfs -O no-holes -n 4k >> $seqres.full
_log_writes_mount

$BTRFS_UTIL_PROG subvolume create $SCRATCH_MNT/src > /dev/null
mkdir -p $SCRATCH_MNT/snapshots
mkdir -p $SCRATCH_MNT/src/padding

random_file()
{
	local basedir=$1
	echo "$basedir/$(ls $basedir | sort -R | tail -1)"
}

snapshot_workload()
{
	trap "wait; exit" SIGTERM

	local i=0
	while true; do
		$BTRFS_UTIL_PROG subvolume snapshot \
			$SCRATCH_MNT/src $SCRATCH_MNT/snapshots/$i \
			> /dev/null
		# Do something small to make snapshots different
		rm -f "$(random_file $SCRATCH_MNT/src/padding)"
		rm -f "$(random_file $SCRATCH_MNT/src/padding)"
		touch "$(random_file $SCRATCH_MNT/src/padding)"
		touch "$SCRATCH_MNT/src/padding/random_$RANDOM"

		i=$(($i + 1))
		sleep 1
	done
}

delete_workload()
{
	trap "wait; exit" SIGTERM

	while true; do
		sleep 2
		$BTRFS_UTIL_PROG subvolume delete \
			"$(random_file $SCRATCH_MNT/snapshots)" \
			> /dev/null 2>&1
	done
}

# Replay and check each fua/flush (specified by $2) point.
#
# Since dm-log-writes records bio sequentially, even just replaying a range
# still needs to iterate all records before the end point.
# When number of records grows, it will be unacceptably slow, thus we need
# to use relay-log itself to trigger fsck, avoid unnecessary seek.
log_writes_fast_replay_check()
{
	local check_point=$1
	local blkdev=$2
	local fsck_command="$BTRFS_UTIL_PROG check $blkdev"
	local ret

	[ -z "$check_point" -o -z "$blkdev" ] && _fail \
	"check_point and blkdev must be specified for log_writes_fast_replay_check"

	$here/src/log-writes/replay-log --log $LOGWRITES_DEV \
		--replay $blkdev --check $check_point --fsck "$fsck_command" \
		&> $tmp.full_fsck
	ret=$?
	tail -n 150 $tmp.full_fsck > $seqres.full
	[ $ret -ne 0 ] && _fail "fsck failed during replay"
}

xattr_value=$(printf '%0.sX' $(seq 1 3800))

# Bumping tree height to level 2.
for ((i = 0; i < 64; i++)); do
	touch "$SCRATCH_MNT/src/padding/$i"
	$SETFATTR_PROG -n 'user.x1' -v $xattr_value "$SCRATCH_MNT/src/padding/$i"
done

_log_writes_mark prepare

snapshot_workload &
pid1=$!
delete_workload &
pid2=$!

"$FSSTRESS_PROG" $fsstress_args > /dev/null &
sleep $runtime

"$KILLALL_PROG" -q "$FSSTRESS_PROG" &> /dev/null
kill $pid1 &> /dev/null
kill $pid2 &> /dev/null
wait
_log_writes_unmount
_log_writes_remove

log_writes_fast_replay_check fua "$SCRATCH_DEV"

echo "Silence is golden"

# success, all done
status=0
exit