From: Darrick J. Wong <djwong@xxxxxxxxxx>
If we're stress-testing scrub on a realtime filesystem, make sure that
we run fsstress on separate directory trees for data and realtime
workouts.
Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
common/fuzzy | 66 +++++++++++++++++++++++++++++++++++++++++++---------------
1 file changed, 49 insertions(+), 17 deletions(-)
diff --git a/common/fuzzy b/common/fuzzy
index 73e5cd2a544455..ceb547669b51cd 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -998,13 +998,37 @@ __stress_scrub_fsx_loop() {
rm -f "$runningfile"
}
+# Run fsstress with a timeout, and touch $tmp.killstress if dead
+__run_timed_fsstress() {
+ timeout -s TERM "$remount_period" $FSSTRESS_PROG $* >> $seqres.full
+ res=$?
+ echo "$mode fsstress $* exits with $res at $(date)" >> $seqres.full
+ if [ "$res" -ne 0 ] && [ "$res" -ne 124 ]; then
+ # Stop if fsstress returns error. Mask off the magic code 124
+ # because that is how the timeout(1) program communicates that
+ # we ran out of time.
+ touch "$tmp.killstress"
+ fi
+}
+
+# Run fsstress and record outcome
+__run_fsstress() {
+ $FSSTRESS_PROG $* >> $seqres.full
+ echo "fsstress $* exits with $? at $(date)" >> $seqres.full
+}
+
# Run fsstress while we're testing online fsck.
__stress_scrub_fsstress_loop() {
local end="$1"
local runningfile="$2"
local remount_period="$3"
local stress_tgt="$4"
- local focus=()
+ local focus=(-p 4 -n 2000000)
+ local scale_args=()
+ local has_rt
+
+ test $FSTYP = "xfs" && _xfs_has_feature "$SCRATCH_MNT" realtime && \
+ has_rt=1
case "$stress_tgt" in
"parent")
@@ -1096,28 +1120,35 @@ __stress_scrub_fsstress_loop() {
# As of March 2022, 2 million fsstress ops should be enough to keep
# any filesystem busy for a couple of hours.
- local args=$(_scale_fsstress_args -p 4 -d $SCRATCH_MNT -n 2000000 "${focus[@]}" $FSSTRESS_AVOID)
- echo "Running $FSSTRESS_PROG $args" >> $seqres.full
+ local args
+ if [ -n "$has_rt" ]; then
+ mkdir -p $SCRATCH_MNT/rt $SCRATCH_MNT/data
+ $XFS_IO_PROG -c 'chattr +rt' $SCRATCH_MNT/rt
+ $XFS_IO_PROG -c 'chattr -rt' $SCRATCH_MNT/data
+
+ rt_args=$(_scale_fsstress_args -d $SCRATCH_MNT/rt "${focus[@]}" $FSSTRESS_AVOID)
+ args=$(_scale_fsstress_args -d $SCRATCH_MNT/data "${focus[@]}" $FSSTRESS_AVOID)
+ echo "Running $FSSTRESS_PROG $args" >> $seqres.full
+ echo "Running $FSSTRESS_PROG $rt_args" >> $seqres.full
+ else
+ args=$(_scale_fsstress_args -d $SCRATCH_MNT "${focus[@]}" $FSSTRESS_AVOID)
+ echo "Running $FSSTRESS_PROG $args" >> $seqres.full
+ fi
if [ -n "$remount_period" ]; then
local mode="rw"
local rw_arg=""
+
+ rm -f "$tmp.killstress"
while __stress_scrub_running "$end" "$runningfile"; do
# Need to recheck running conditions if we cleared
# anything.
test "$mode" = "rw" && __stress_scrub_clean_scratch && continue
- timeout -s TERM "$remount_period" $FSSTRESS_PROG \
- $args $rw_arg >> $seqres.full
- res=$?
- echo "$mode fsstress exits with $res at $(date)" >> $seqres.full
- if [ "$res" -ne 0 ] && [ "$res" -ne 124 ]; then
- # Stop if fsstress returns error. Mask off
- # the magic code 124 because that is how the
- # timeout(1) program communicates that we ran
- # out of time.
- break;
- fi
+ __run_timed_fsstress $args $rw_arg &
+ test -n "$has_rt" && __run_timed_fsstress $rt_args $rw_arg &
+ wait
+ test -e "$tmp.killstress" && break
if [ "$mode" = "rw" ]; then
mode="ro"
rw_arg="-R"
@@ -1132,15 +1163,16 @@ __stress_scrub_fsstress_loop() {
sleep 0.2
done
done
- rm -f "$runningfile"
+ rm -f "$runningfile" "$tmp.killstress"
return 0
fi
while __stress_scrub_running "$end" "$runningfile"; do
# Need to recheck running conditions if we cleared anything
__stress_scrub_clean_scratch && continue
- $FSSTRESS_PROG $args >> $seqres.full
- echo "fsstress exits with $? at $(date)" >> $seqres.full
+ __run_fsstress $args &
+ test -n "$has_rt" && __run_fsstress $rt_args &
+ wait
done
rm -f "$runningfile"
}
