On Fri, Dec 30, 2022 at 02:12:57PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <djwong@xxxxxxxxxx>
>
> Add a couple of new online fsck stress tests that race fsx against
> online fsck.
>
> Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx>
> ---
> common/fuzzy | 39 ++++++++++++++++++++++++++++++++++++---
> tests/xfs/847 | 38 ++++++++++++++++++++++++++++++++++++++
> tests/xfs/847.out | 2 ++
> tests/xfs/848 | 38 ++++++++++++++++++++++++++++++++++++++
> tests/xfs/848.out | 2 ++
> 5 files changed, 116 insertions(+), 3 deletions(-)
> create mode 100755 tests/xfs/847
> create mode 100644 tests/xfs/847.out
> create mode 100755 tests/xfs/848
> create mode 100644 tests/xfs/848.out
>
>
> diff --git a/common/fuzzy b/common/fuzzy
> index 1df51a6dd8..3512e95e02 100644
> --- a/common/fuzzy
> +++ b/common/fuzzy
> @@ -408,6 +408,30 @@ __stress_scrub_clean_scratch() {
> return 0
> }
>
> +# Run fsx while we're testing online fsck.
> +__stress_scrub_fsx_loop() {
> + local end="$1"
> + local runningfile="$2"
> + local focus=(-q -X) # quiet, validate file contents
> +
> + # As of November 2022, 2 million fsx ops should be enough to keep
> + # any filesystem busy for a couple of hours.
> + focus+=(-N 2000000)
> + focus+=(-o $((128000 * LOAD_FACTOR)) )
> + focus+=(-l $((600000 * LOAD_FACTOR)) )
> +
> + local args="$FSX_AVOID ${focus[@]} ${SCRATCH_MNT}/fsx.$seq"
> + echo "Running $here/ltp/fsx $args" >> $seqres.full
> +
> + while __stress_scrub_running "$end" "$runningfile"; do
> + # Need to recheck running conditions if we cleared anything
> + __stress_scrub_clean_scratch && continue
> + $here/ltp/fsx $args >> $seqres.full
> + echo "fsx exits with $? at $(date)" >> $seqres.full
> + done
> + rm -f "$runningfile"
> +}
> +
> # Run fsstress while we're testing online fsck.
> __stress_scrub_fsstress_loop() {
> local end="$1"
> @@ -454,7 +478,7 @@ _scratch_xfs_stress_scrub_cleanup() {
> # Send SIGINT so that bash won't print a 'Terminated' message that
> # distorts the golden output.
> echo "Killing stressor processes at $(date)" >> $seqres.full
> - $KILLALL_PROG -INT xfs_io fsstress >> $seqres.full 2>&1
> + $KILLALL_PROG -INT xfs_io fsstress fsx >> $seqres.full 2>&1
>
> # Tests are not allowed to exit with the scratch fs frozen. If we
> # started a fs freeze/thaw background loop, wait for that loop to exit
> @@ -522,30 +546,39 @@ __stress_scrub_check_commands() {
> # -w Delay the start of the scrub/repair loop by this number of seconds.
> # Defaults to no delay unless XFS_SCRUB_STRESS_DELAY is set. This value
> # will be clamped to ten seconds before the end time.
> +# -X Run this program to exercise the filesystem. Currently supported
> +# options are 'fsx' and 'fsstress'. The default is 'fsstress'.
> _scratch_xfs_stress_scrub() {
> local one_scrub_args=()
> local scrub_tgt="$SCRATCH_MNT"
> local runningfile="$tmp.fsstress"
> local freeze="${XFS_SCRUB_STRESS_FREEZE}"
> local scrub_delay="${XFS_SCRUB_STRESS_DELAY:--1}"
> + local exerciser="fsstress"
>
> __SCRUB_STRESS_FREEZE_PID=""
> rm -f "$runningfile"
> touch "$runningfile"
>
> OPTIND=1
> - while getopts "fs:t:w:" c; do
> + while getopts "fs:t:w:X:" c; do
> case "$c" in
> f) freeze=yes;;
> s) one_scrub_args+=("$OPTARG");;
> t) scrub_tgt="$OPTARG";;
> w) scrub_delay="$OPTARG";;
> + X) exerciser="$OPTARG";;
> *) return 1; ;;
> esac
> done
>
> __stress_scrub_check_commands "$scrub_tgt" "${one_scrub_args[@]}"
>
> + if ! command -v "__stress_scrub_${exerciser}_loop" &>/dev/null; then
> + echo "${exerciser}: Unknown fs exercise program."
> + return 1
> + fi
> +
> local start="$(date +%s)"
> local end="$((start + (30 * TIME_FACTOR) ))"
> local scrub_startat="$((start + scrub_delay))"
> @@ -555,7 +588,7 @@ _scratch_xfs_stress_scrub() {
> echo "Loop started at $(date --date="@${start}")," \
> "ending at $(date --date="@${end}")" >> $seqres.full
>
> - __stress_scrub_fsstress_loop "$end" "$runningfile" &
> + "__stress_scrub_${exerciser}_loop" "$end" "$runningfile" &
>
> if [ -n "$freeze" ]; then
> __stress_scrub_freeze_loop "$end" "$runningfile" &
> diff --git a/tests/xfs/847 b/tests/xfs/847
> new file mode 100755
> index 0000000000..856e9a6c26
> --- /dev/null
> +++ b/tests/xfs/847
> @@ -0,0 +1,38 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (c) 2022 Oracle, Inc. All Rights Reserved.
> +#
> +# FS QA Test No. 847
> +#
> +# Race fsx and xfs_scrub in read-only mode for a while to see if we crash
> +# or livelock.
> +#
> +. ./common/preamble
> +_begin_fstest scrub dangerous_fsstress_scrub
Hi Darrick,
Such huge patchsets :) I'll try to review them one by one (patchset).
Now I'm trying to review "[NYE DELUGE 1/4]", but I can't find the
"dangerous_fsstress_scrub" group in the whole patchsets. Is there any
prepositive patch(set)? Or you'd like to use "dangerous_fsstress_repair"?
P.S: More cases use "dangerous_fsstress_scrub" in your new patchsets.
Thanks,
Zorro
> +
> +_cleanup() {
> + cd /
> + _scratch_xfs_stress_scrub_cleanup &> /dev/null
> + rm -r -f $tmp.*
> +}
> +_register_cleanup "_cleanup" BUS
> +
> +# Import common functions.
> +. ./common/filter
> +. ./common/fuzzy
> +. ./common/inject
> +. ./common/xfs
> +
> +# real QA test starts here
> +_supported_fs xfs
> +_require_scratch
> +_require_xfs_stress_scrub
> +
> +_scratch_mkfs > "$seqres.full" 2>&1
> +_scratch_mount
> +_scratch_xfs_stress_scrub -S '-n' -X 'fsx'
> +
> +# success, all done
> +echo Silence is golden
> +status=0
> +exit
> diff --git a/tests/xfs/847.out b/tests/xfs/847.out
> new file mode 100644
> index 0000000000..b7041db159
> --- /dev/null
> +++ b/tests/xfs/847.out
> @@ -0,0 +1,2 @@
> +QA output created by 847
> +Silence is golden
> diff --git a/tests/xfs/848 b/tests/xfs/848
> new file mode 100755
> index 0000000000..ab32020624
> --- /dev/null
> +++ b/tests/xfs/848
> @@ -0,0 +1,38 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (c) 2022 Oracle, Inc. All Rights Reserved.
> +#
> +# FS QA Test No. 848
> +#
> +# Race fsx and xfs_scrub in force-repair mode for a while to see if we
> +# crash or livelock.
> +#
> +. ./common/preamble
> +_begin_fstest online_repair dangerous_fsstress_repair
> +
> +_cleanup() {
> + cd /
> + _scratch_xfs_stress_scrub_cleanup &> /dev/null
> + rm -r -f $tmp.*
> +}
> +_register_cleanup "_cleanup" BUS
> +
> +# Import common functions.
> +. ./common/filter
> +. ./common/fuzzy
> +. ./common/inject
> +. ./common/xfs
> +
> +# real QA test starts here
> +_supported_fs xfs
> +_require_scratch
> +_require_xfs_stress_online_repair
> +
> +_scratch_mkfs > "$seqres.full" 2>&1
> +_scratch_mount
> +_scratch_xfs_stress_online_repair -S '-k' -X 'fsx'
> +
> +# success, all done
> +echo Silence is golden
> +status=0
> +exit
> diff --git a/tests/xfs/848.out b/tests/xfs/848.out
> new file mode 100644
> index 0000000000..23f674045c
> --- /dev/null
> +++ b/tests/xfs/848.out
> @@ -0,0 +1,2 @@
> +QA output created by 848
> +Silence is golden
>
