Files
apfstests/tests/generic/475
T
Darrick J. Wong ce02f1b2f8 generic: test error shutdown while stressing filesystem
Test log recovery with repeated (simulated) disk failures.  We kick
off fsstress on the scratch fs, then switch out the underlying
device with dm-error to see what happens when the disk goes down.
Having taken down the fs in this manner, remount it and repeat.
This test is a Good Enough (tm) simulation of our internal multipath
failure testing efforts.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eryu Guan <eguan@redhat.com>
Signed-off-by: Eryu Guan <eguan@redhat.com>
2018-01-02 17:35:45 +08:00

98 lines
2.8 KiB
Bash
Executable File

#! /bin/bash
# FS QA Test No. 475
#
# Test log recovery with repeated (simulated) disk failures. We kick
# off fsstress on the scratch fs, then switch out the underlying device
# with dm-error to see what happens when the disk goes down. Having
# taken down the fs in this manner, remount it and repeat. This test
# is a Good Enough (tm) simulation of our internal multipath failure
# testing efforts.
#
#-----------------------------------------------------------------------
# Copyright (c) 2017 Oracle, Inc. All Rights Reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it would be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write the Free Software Foundation,
# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#-----------------------------------------------------------------------
#
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.*
$KILLALL_PROG -9 fsstress > /dev/null 2>&1
_dmerror_unmount
_dmerror_cleanup
}
# get standard environment, filters and checks
. ./common/rc
. ./common/dmerror
# Modify as appropriate.
_supported_fs generic
_supported_os Linux
_require_scratch
_require_dm_target error
_require_command "$KILLALL_PROG" "killall"
rm -f $seqres.full
echo "Silence is golden."
_scratch_mkfs >> $seqres.full 2>&1
_require_metadata_journaling $SCRATCH_DEV
_dmerror_init
_dmerror_mount
for i in $(seq 1 $((50 * TIME_FACTOR)) ); do
($FSSTRESS_PROG $FSSTRESS_AVOID -d $SCRATCH_MNT -n 999999 -p $((LOAD_FACTOR * 4)) >> $seqres.full &) \
> /dev/null 2>&1
# purposely include 0 second sleeps to test shutdown immediately after
# recovery
sleep $((RANDOM % 3))
# Loading error table without "--nolockfs" option. Because "--nolockfs"
# won't freeze fs, then some running I/Os may cause XFS to shutdown
# prematurely. That's not what we want to test.
_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
# Mount again to replay log after loading working table, so we have a
# consistent XFS after test.
_dmerror_unmount || _fail "unmount failed"
_dmerror_load_working_table
_dmerror_mount || _fail "mount failed"
done
# success, all done
status=0
exit