From: Darrick J. Wong <djwong@xxxxxxxxxx>
Quite a while ago, I added --duration= arguments to fsx and fsstress,
and apparently I forgot to update the scrub stress loops to use them.
Replace the usage of timeout(1) for the remount_period versions of the
loop to clean up that code; and convert the non-remount loop so that
they don't run over time.
Signed-off-by: "Darrick J. Wong" <djwong@xxxxxxxxxx>
---
common/fuzzy | 47 +++++++++++++++++++++++++++++------------------
1 file changed, 29 insertions(+), 18 deletions(-)
diff --git a/common/fuzzy b/common/fuzzy
index 8afa4d35759f62..f676614d8343f7 100644
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -939,6 +939,22 @@ __stress_scrub_clean_scratch() {
return 0
}
+# Compute a --duration= interval for fsx and fsstress
+___stress_scrub_duration()
+{
+ local end="$1"
+ local remount_period="$2"
+ local now="$(date +%s)"
+ local delta="$((end - now))"
+
+ test "$delta" -lt 0 && delta=0
+
+ test -n "$remount_period" && test "$remount_period" -lt "$delta" && \
+ delta="$remount_period"
+
+ echo "--duration=$delta"
+}
+
# Run fsx while we're testing online fsck.
__stress_scrub_fsx_loop() {
local end="$1"
@@ -946,11 +962,9 @@ __stress_scrub_fsx_loop() {
local remount_period="$3"
local stress_tgt="$4" # ignored
local focus=(-q -X) # quiet, validate file contents
+ local duration
local res
- # 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 $((600000 * LOAD_FACTOR)) )
@@ -965,17 +979,12 @@ __stress_scrub_fsx_loop() {
# anything.
test "$mode" = "rw" && __stress_scrub_clean_scratch && continue
- timeout -s TERM "$remount_period" $here/ltp/fsx \
- $args $rw_arg >> $seqres.full
+ duration=$(___stress_scrub_duration "$end" "$remount_period")
+ $here/ltp/fsx $duration $args $rw_arg >> $seqres.full
res=$?
echo "$mode fsx exits with $res at $(date)" >> $seqres.full
- if [ "$res" -ne 0 ] && [ "$res" -ne 124 ]; then
- # Stop if fsx returns error. Mask off
- # the magic code 124 because that is how the
- # timeout(1) program communicates that we ran
- # out of time.
- break;
- fi
+ test "$res" -ne 0 && break
+
if [ "$mode" = "rw" ]; then
mode="ro"
rw_arg="-t 0 -w 0 -FHzCIJBE0"
@@ -997,7 +1006,8 @@ __stress_scrub_fsx_loop() {
while __stress_scrub_running "$end" "$runningfile"; do
# Need to recheck running conditions if we cleared anything
__stress_scrub_clean_scratch && continue
- $here/ltp/fsx $args >> $seqres.full
+ duration=$(___stress_scrub_duration "$end" "$remount_period")
+ $here/ltp/fsx $duration $args >> $seqres.full
res=$?
echo "fsx exits with $res at $(date)" >> $seqres.full
test "$res" -ne 0 && break
@@ -1013,6 +1023,7 @@ __stress_scrub_fsstress_loop() {
local stress_tgt="$4"
local focus=()
local res
+ local duration
case "$stress_tgt" in
"parent")
@@ -1102,9 +1113,7 @@ __stress_scrub_fsstress_loop() {
;;
esac
- # 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[@]}")
+ local args=$(_scale_fsstress_args -p 4 -d $SCRATCH_MNT "${focus[@]}")
echo "Running $FSSTRESS_PROG $args" >> $seqres.full
if [ -n "$remount_period" ]; then
@@ -1115,7 +1124,8 @@ __stress_scrub_fsstress_loop() {
# anything.
test "$mode" = "rw" && __stress_scrub_clean_scratch && continue
- _run_fsstress_bg $args $rw_arg >> $seqres.full
+ duration=$(___stress_scrub_duration "$end" "$remount_period")
+ _run_fsstress_bg $duration $args $rw_arg >> $seqres.full
sleep $remount_period
_kill_fsstress
res=$?
@@ -1143,7 +1153,8 @@ __stress_scrub_fsstress_loop() {
while __stress_scrub_running "$end" "$runningfile"; do
# Need to recheck running conditions if we cleared anything
__stress_scrub_clean_scratch && continue
- _run_fsstress $args >> $seqres.full
+ duration=$(___stress_scrub_duration "$end" "$remount_period")
+ _run_fsstress $duration $args >> $seqres.full
res=$?
echo "$mode fsstress exits with $res at $(date)" >> $seqres.full
[ "$res" -ne 0 ] && break;
