Re: [PATCH v3 3/4] xfs: test for umount hang caused by the pending dquota log item in AIL

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Thu, Nov 09, 2017 at 03:32:51PM +0800, Hou Tao wrote:
> When the first writeback and the retried writeback of dquota buffer get
> the same IO error, XFS will let xfsaild to restart the writeback and
> xfs_qm_dqflush_done() will not be invoked. xfsaild will try to re-push
> the quota log item in AIL, the push will return early everytime after
> checking xfs_dqflock_nowait(), and xfsaild will try to push it again.
> 
> IOWs, AIL will never be empty, and the umount process will wait for the
> drain of AIL, so the umount process hangs.
> 
> Signed-off-by: Hou Tao <houtao1@huawei.com>
> ---
>  tests/xfs/999     | 171 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  tests/xfs/999.out |   2 +
>  tests/xfs/group   |   1 +
>  3 files changed, 174 insertions(+)
>  create mode 100755 tests/xfs/999
>  create mode 100644 tests/xfs/999.out
> 
> diff --git a/tests/xfs/999 b/tests/xfs/999
> new file mode 100755
> index 0000000..22f7ba3
> --- /dev/null
> +++ b/tests/xfs/999
> @@ -0,0 +1,171 @@
> +#! /bin/bash
> +# FS QA Test No. 999
> +#
> +# Test for XFS umount hang problem caused by the unceasing push
> +# of dquot log item in AIL. Because xfs_qm_dqflush_done() will
> +# not be invoked, so each time xfsaild initiates the push,
> +# the push will return early after checking xfs_dqflock_nowait().
> +#
> +# xfs_qm_dqflush_done() should be invoked by xfs_buf_do_callbacks().
> +# However after the first write and the retried write of dquota buffer
> +# get the same IO error, XFS will let xfsaild to restart the write and
> +# xfs_buf_do_callbacks() will not be inovked.
> +#
> +# This test emulates the write error by using dm-flakey. The log
> +# area of the XFS filesystem is excluded from the range covered by
> +# dm-flakey, so the XFS will not be shutdown prematurely.

Upstream commit is 373b0589dc8d58bc09c9a28d03611ae4fb216057 ("xfs:
Properly retry failed dquot items in case of error during buffer
writeback"), etc.

--D

> +#
> +#-----------------------------------------------------------------------
> +# Copyright (c) 2017 Huawei Technologies Co., Ltd. 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()
> +{
> +	[ -z "${interval}" ] || \
> +		sysctl -w fs.xfs.xfssyncd_centisecs=${interval} >/dev/null 2>&1
> +	cd /
> +	rm -f $tmp.*
> +	_unmount_flakey >/dev/null 2>&1
> +	_cleanup_flakey > /dev/null 2>&1
> +}
> +
> +get_xfs_scratch_sb_field()
> +{
> +	local field=$1
> +
> +	_scratch_xfs_db -r -c "sb 0" -c "print $field" | \
> +	awk -v field=$field '$0 ~ field {print $3}'
> +}
> +
> +# inject IO write error for the XFS filesystem except its log section
> +make_xfs_scratch_flakey_table()
> +{
> +	local tgt=flakey
> +	local opt="0 1 1 error_writes"
> +	local dev=${SCRATCH_DEV}
> +	local dev_sz=$(blockdev --getsz $dev)
> +
> +	if [ "${USE_EXTERNAL}" = "yes" -a ! -z "$SCRATCH_LOGDEV" ]; then
> +		echo "0 ${dev_sz} $tgt $dev 0 $opt"
> +		return
> +	fi
> +
> +	local blk_sz=$(get_xfs_scratch_sb_field blocksize)
> +	local log_ofs=$(get_xfs_scratch_sb_field logstart)
> +	local log_sz=$(get_xfs_scratch_sb_field logblocks)
> +	local table=""
> +	local ofs=0
> +	local sz
> +
> +	log_ofs=$(_scratch_xfs_db -r -c "convert fsb ${log_ofs} bb" | \
> +			awk '{gsub("[()]", "", $2); print $2}')
> +	let "log_sz *= blk_sz / 512"
> +
> +	if [ "$ofs" -lt "${log_ofs}" ]; then
> +		let "sz = log_ofs - ofs"
> +		table="$ofs $sz $tgt $dev $ofs $opt"
> +	fi
> +
> +	table="$table\n${log_ofs} ${log_sz} linear $dev ${log_ofs}"
> +
> +	let "ofs = log_ofs + log_sz"
> +	if [ "$ofs" -lt "${dev_sz}" ]; then
> +		let "sz = dev_sz - ofs"
> +		table="$table\n$ofs $sz $tgt $dev $ofs $opt"
> +	fi
> +
> +	echo -e $table
> +}
> +
> +# get standard environment, filters and checks
> +. ./common/rc
> +. ./common/dmflakey
> +. ./common/quota
> +
> +_supported_fs xfs
> +_supported_os Linux
> +
> +# due to the injection of write IO error, the fs will be inconsistent
> +_require_scratch_nocheck
> +_require_flakey_with_error_writes
> +_require_user
> +_require_xfs_quota
> +_require_freeze
> +
> +rm -f $seqres.full
> +
> +echo "Silence is golden"
> +
> +_scratch_mkfs_xfs > $seqres.full 2>&1
> +
> +# no error will be injected
> +_init_flakey
> +$DMSETUP_PROG info >> $seqres.full
> +$DMSETUP_PROG table >> $seqres.full
> +
> +# save the old value for _cleanup()
> +interval=$(sysctl -n fs.xfs.xfssyncd_centisecs 2>/dev/null)
> +# shorten the time waiting for the push of ail items
> +sysctl -w fs.xfs.xfssyncd_centisecs=100 >> $seqres.full 2>&1
> +
> +_qmount_option "usrquota"
> +_mount_flakey
> +
> +# We need to set the quota limitation twice, and inject the write error
> +# after the second setting. If we try to inject the write error after
> +# the first setting, the initialization of the dquota buffer will get
> +# IO error and also be retried, and during the umount process the
> +# write will be ended, and xfs_qm_dqflush_done() will be inovked, and
> +# the umount will exit normally.
> +$XFS_QUOTA_PROG -x -c "limit -u isoft=500 fsgqa" $SCRATCH_MNT
> +$XFS_QUOTA_PROG -x -c "report -ih" $SCRATCH_MNT >> $seqres.full
> +
> +# ensure the initialization of the dquota buffer is done
> +xfs_freeze -f $SCRATCH_MNT
> +xfs_freeze -u $SCRATCH_MNT
> +
> +# inject write IO error
> +FLAKEY_TABLE_ERROR=$(make_xfs_scratch_flakey_table)
> +_load_flakey_table ${FLAKEY_ERROR_WRITES}
> +$DMSETUP_PROG info >> $seqres.full
> +$DMSETUP_PROG table >> $seqres.full
> +
> +# update the dquota buffer
> +$XFS_QUOTA_PROG -x -c "limit -u isoft=400 fsgqa" $SCRATCH_MNT
> +$XFS_QUOTA_PROG -x -c "report -ih" $SCRATCH_MNT >> $seqres.full
> +
> +sync
> +
> +# wait for the push of the dquota log item in AIL and
> +# the completion of the retried write of dquota buffer
> +sleep 2
> +
> +_unmount_flakey
> +
> +_cleanup_flakey
> +
> +# success, all done
> +status=0
> +exit
> diff --git a/tests/xfs/999.out b/tests/xfs/999.out
> new file mode 100644
> index 0000000..3b276ca
> --- /dev/null
> +++ b/tests/xfs/999.out
> @@ -0,0 +1,2 @@
> +QA output created by 999
> +Silence is golden
> diff --git a/tests/xfs/group b/tests/xfs/group
> index b439842..127019a 100644
> --- a/tests/xfs/group
> +++ b/tests/xfs/group
> @@ -431,3 +431,4 @@
>  431 auto quick dangerous
>  432 auto quick dir metadata
>  433 auto quick attr
> +999 auto quick quota dangerous
> -- 
> 2.9.5
> 
> --
> To unsubscribe from this list: send the line "unsubscribe fstests" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html