Re: [PATCH 2/2] xfs/438: fail metadata writes with the buf_ioerror error tag

[Brian Foster <bfoster@redhat.com>]

On Thu, Nov 12, 2026 at 10:37:18AM +0900, Daejun Park via B4 Relay wrote:
> From: Daejun Park <daejun7.park@samsung.com>
> 
> xfs/438 needs metadata writes to fail while the log keeps working.
> With a write cache, dm-flakey also fails the flushes that dm sends it
> with REQ_PREFLUSH log writes. The internal log survives only because
> dm drops that error. The dm patch "dm: fail a REQ_PREFLUSH bio with
> data when its preflush fails" fixes that. With an external log, the
> flakey table fails the log device too.
> 
> Use the buf_ioerror error tag. It fails async metadata buffer writes
> and leaves log writes alone. The test now needs XFS_DEBUG.
> 
> Signed-off-by: Daejun Park <daejun7.park@samsung.com>
> ---
> On v7.4-rc2 and on v7.4-rc2 with the dm patch, the test passes with
> an internal log (3 of 3) and an external log (1 of 1). The failed
> dquot write is retried until the unmount. On the TEST ONLY kernel of
> patch 1 the unmount hangs with both logs (1 of 1 each).
> ---

Nice simplification.

Reviewed-by: Brian Foster <bfoster@redhat.com>

>  tests/xfs/438 | 76 ++++++-----------------------------------------------------
>  1 file changed, 7 insertions(+), 69 deletions(-)
> 
> diff --git a/tests/xfs/438 b/tests/xfs/438
> index e4850ff..5c228e4 100755
> --- a/tests/xfs/438
> +++ b/tests/xfs/438
> @@ -14,9 +14,9 @@
>  # 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.
> +# This test emulates the write error with the buf_ioerror error tag,
> +# which fails async metadata buffer writes. Log writes are not buffer
> +# writes, so the XFS will not be shutdown prematurely.
>  #
>  # Fixed by upstream commit 373b058 ("xfs: Properly retry failed dquot
>  # items in case of error during buffer writeback")
> @@ -33,85 +33,27 @@ _cleanup()
>  	cd /
>  	rm -f $tmp.*
>  	_scratch_unmount >/dev/null 2>&1
> -	_cleanup_flakey > /dev/null 2>&1
> -}
> -
> -# inject IO write error for the XFS filesystem except its log section
> -make_xfs_scratch_flakey_table()
> -{
> -	local tgt=flakey
> -	local opt="0 1 1 error_writes"
> -	local dev=${SCRATCH_DEV}
> -	local dev_sz=$(blockdev --getsz $dev)
> -
> -	# If using an external log device, just making the writing of
> -	# entire data/metadata area fail forever.
> -	if [ "${USE_EXTERNAL}" = "yes" -a ! -z "$SCRATCH_LOGDEV" ]; then
> -		echo "0 ${dev_sz} $tgt $dev 0 $opt"
> -		return
> -	fi
> -
> -	local blk_sz=$(_scratch_xfs_get_sb_field blocksize)
> -	local log_ofs=$(_scratch_xfs_get_sb_field logstart)
> -	local log_sz=$(_scratch_xfs_get_sb_field logblocks)
> -	local table=""
> -	local ofs=0
> -	local sz
> -
> -	log_ofs=$(_scratch_xfs_db -r -c "convert fsb ${log_ofs} bb" | \
> -			  $AWK_PROG '{gsub("[()]", "", $2); print $2}')
> -	let "log_sz *= blk_sz / 512"
> -
> -	# Add a flakey target for the area before the log section
> -	# to make the data/metadata write fail forever
> -	if [ "$ofs" -lt "${log_ofs}" ]; then
> -		let "sz = log_ofs - ofs"
> -		table="$ofs $sz $tgt $dev $ofs $opt"
> -	fi
> -
> -	# Add a linear target for the log section, so the log write
> -	# will work normally
> -	table="$table\n${log_ofs} ${log_sz} linear $dev ${log_ofs}"
> -
> -	# Add a flakey target for the area after the log section
> -	# to make the data/metadata write fail forever
> -	let "ofs = log_ofs + log_sz"
> -	if [ "$ofs" -lt "${dev_sz}" ]; then
> -		let "sz = dev_sz - ofs"
> -		table="$table\n$ofs $sz $tgt $dev $ofs $opt"
> -	fi
> -
> -	echo -e $table
>  }
>  
>  # Import common functions.
> -. ./common/dmflakey
>  . ./common/quota
> +. ./common/inject
>  
>  
>  # 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
>  _require_test_sysfs_dev_attr error/fail_at_unmount
>  _require_test_sysfs_dev_attr error/metadata/EIO/max_retries
>  _require_test_sysfs_dev_attr error/metadata/EIO/retry_timeout_seconds
> +_require_xfs_io_error_injection buf_ioerror
>  
>  echo "Silence is golden"
>  
>  _scratch_mkfs > $seqres.full 2>&1
>  
> -# this needs to happen after mkfs, but before _init_flakey overrides SCRATCH_DEV
> -FLAKEY_TABLE_NON_LOG_ERROR=$(make_xfs_scratch_flakey_table)
> -
> -# no error will be injected
> -_init_flakey
> -FLAKEY_TABLE_ERROR=${FLAKEY_TABLE_NON_LOG_ERROR}
> -$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
> @@ -139,10 +81,8 @@ $XFS_QUOTA_PROG -x -c "report -ih" $SCRATCH_MNT >> $seqres.full
>  xfs_freeze -f $SCRATCH_MNT
>  xfs_freeze -u $SCRATCH_MNT
>  
> -# inject write IO error
> -_load_flakey_table ${FLAKEY_ERROR_WRITES}
> -$DMSETUP_PROG info >> $seqres.full
> -$DMSETUP_PROG table >> $seqres.full
> +# fail every async metadata buffer write from now on
> +_scratch_inject_error buf_ioerror 1
>  
>  # update the dquota buffer
>  $XFS_QUOTA_PROG -x -c "limit -u isoft=400 $qa_user" $SCRATCH_MNT
> @@ -160,8 +100,6 @@ stat $SCRATCH_MNT > /dev/null
>  
>  _scratch_unmount
>  
> -_cleanup_flakey
> -
>  # success, all done
>  status=0
>  exit
> 
> -- 
> 2.43.0
> 
>