xfs: stress test for shrinking free space in the last AG

This adds a stress testcase to shrink free space as much as
possible in the last AG with background fsstress workload.

The expectation is that no crash happens with expected output.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>

tests/xfs/168

@@ -0,0 +1,122 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2020-2021 Red Hat, Inc.  All Rights Reserved.
+#
+# FS QA Test No. 168
+#
+# XFS online shrinkfs stress test
+#
+# This test attempts to shrink unused space as much as possible with
+# background fsstress workload. It will decrease the shrink size if
+# larger size fails. And totally repeat 2 * TIME_FACTOR times.
+#
+seq=`basename $0`
+seqres=$RESULT_DIR/$seq
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1	# failure is the default!
+trap "rm -f $tmp.*; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+
+create_scratch()
+{
+	_scratch_mkfs_xfs $@ | tee -a $seqres.full | \
+		_filter_mkfs 2>$tmp.mkfs >/dev/null
+	. $tmp.mkfs
+
+	_scratch_mount
+	# fix the reserve block pool to a known size so that the enospc
+	# calculations work out correctly.
+	_scratch_resvblks 1024 > /dev/null 2>&1
+}
+
+fill_scratch()
+{
+	$XFS_IO_PROG -f -c "falloc 0 $1" $SCRATCH_MNT/resvfile
+}
+
+stress_scratch()
+{
+	local procs=3
+	local nops=1000
+	# -w ensures that the only ops are ones which cause write I/O
+	local FSSTRESS_ARGS=`_scale_fsstress_args -d $SCRATCH_MNT -w \
+		-p $procs -n $nops $FSSTRESS_AVOID`
+	$FSSTRESS_PROG $FSSTRESS_ARGS >> $seqres.full 2>&1
+}
+
+# real QA test starts here
+_supported_fs xfs
+_require_scratch_xfs_shrink
+_require_xfs_io_command "falloc"
+
+rm -f $seqres.full
+_scratch_mkfs_xfs | tee -a $seqres.full | _filter_mkfs 2>$tmp.mkfs >/dev/null
+. $tmp.mkfs	# extract blocksize and data size for scratch device
+
+endsize=`expr 125 \* 1048576`	# stop after shrinking this big
+[ `expr $endsize / $dbsize` -lt $dblocks ] || _notrun "Scratch device too small"
+
+nags=2
+totalcount=$((2 * TIME_FACTOR))
+
+while [ $totalcount -gt 0 ]; do
+	size=`expr 1010 \* 1048576`	# 1010 megabytes initially
+	logblks=$(_scratch_find_xfs_min_logblocks -dsize=${size} -dagcount=${nags})
+
+	create_scratch -lsize=${logblks}b -dsize=${size} -dagcount=${nags}
+
+	for i in `seq 125 -1 90`; do
+		fillsize=`expr $i \* 1048576`
+		out="$(fill_scratch $fillsize 2>&1)"
+		echo "$out" | grep -q 'No space left on device' && continue
+		test -n "${out}" && echo "$out"
+		break
+	done
+
+	# shrink in chunks of this size at most
+	decsize=`expr  41 \* 1048576 + 1 + $RANDOM \* $RANDOM % 1048576`
+
+	while [ $size -gt $endsize ]; do
+		stress_scratch &
+		sleep 1
+
+		decb=`expr $decsize / $dbsize`    # in data blocks
+		while [ $decb -gt 0 ]; do
+			sizeb=`expr $size / $dbsize - $decb`
+
+			$XFS_GROWFS_PROG -D ${sizeb} $SCRATCH_MNT \
+				>> $seqres.full 2>&1 && break
+
+			[ $decb -gt 100 ] && decb=`expr $decb + $RANDOM % 10`
+			decb=`expr $decb / 2`
+		done
+
+		wait
+		[ $decb -eq 0 ] && break
+
+		# get latest dblocks
+		$XFS_INFO_PROG $SCRATCH_MNT 2>&1 | _filter_mkfs 2>$tmp.growfs >/dev/null
+		. $tmp.growfs
+
+		size=`expr $dblocks \* $dbsize`
+		_scratch_unmount
+		_scratch_xfs_repair -n >> $seqres.full 2>&1 || \
+			_fail "xfs_repair failed with shrinking $sizeb"
+		_scratch_mount
+	done
+
+	_scratch_unmount
+	_scratch_xfs_repair -n >> $seqres.full 2>&1 || \
+		_fail "xfs_repair failed with shrinking $sizeb"
+	totalcount=`expr $totalcount - 1`
+done
+
+echo "Silence is golden"
+status=0
+exit

tests/xfs/168.out

@@ -0,0 +1,2 @@
+QA output created by 168
+Silence is golden

tests/xfs/group

@@ -165,6 +165,7 @@
 165 rw pattern auto prealloc quick
 166 rw metadata auto quick
 167 rw metadata auto stress
+168 auto growfs shrinkfs ioctl prealloc stress
 169 auto clone
 170 rw filestreams auto quick
 171 rw filestreams