admin/gbrain
1
0
Fork 0
mirror of https://github.com/garrytan/gbrain.git synced 2026-08-14 08:53:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "fix(scripts): capture check/shard rc before watchdog teardown in no-timeout fallback (#2864)"

Browse Source 
This reverts commit e9a4fee97f.
This commit is contained in:
Garry Tan
2026-07-23 12:02:36 -07:00
parent 6388be2088
commit 35edd0e2d5
4 changed files with 4 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/run-unit-parallel.sh
+1 -12
View File
@@ -133,7 +133,6 @@ for i in $(seq 1 "$N"); do
env SHARD="$i/$N" \
bash scripts/run-unit-shard.sh --max-concurrency="$INTRA_CONC" \
> "$SHARD_LOG" 2>&1
rc=$?
else
env SHARD="$i/$N" \
bash scripts/run-unit-shard.sh --max-concurrency="$INTRA_CONC" \
@@ -143,20 +142,10 @@ for i in $(seq 1 "$N"); do
sleep 5 && kill -KILL "$pid" 2>/dev/null ) &
cap_pid=$!
wait "$pid" 2>/dev/null
# Capture the shard's exit code from ITS `wait`, before any watchdog
# teardown runs. The teardown commands below overwrite $? — the killed
# watchdog reports 143 — which used to get stamped into every shard's
# sentinel on machines with no gtimeout/timeout: every run "failed"
# with rc=143 summaries even when all tests passed.
rc=$?
# Reap the watchdog's `sleep` child too (pkill -P), then the watchdog.
# Killing only the subshell leaves the sleep orphaned until
# $SHARD_TIMEOUT elapses — same quirk the heartbeat cleanup below works
# around; CI's orphan-process sweep flags those.
pkill -P "$cap_pid" 2>/dev/null
kill "$cap_pid" 2>/dev/null
wait "$cap_pid" 2>/dev/null
fi
rc=$?
echo "$rc" > "$LOG_DIR/shard-$i.exit"
[ "$rc" = "124" ] && echo "WEDGED" > "$LOG_DIR/shard-$i.wedged"
) &
scripts/run-verify-parallel.sh
+1 -12
View File
@@ -126,7 +126,6 @@ for c in "${CHECKS[@]}"; do
(
if [ -n "$TIMEOUT_BIN" ]; then
"$TIMEOUT_BIN" "${TIMEOUT}s" bun run "$c" > "$LOG_FILE" 2>&1
rc=$?
else
bun run "$c" > "$LOG_FILE" 2>&1 &
pid=$!
@@ -134,20 +133,10 @@ for c in "${CHECKS[@]}"; do
sleep 5 && kill -KILL "$pid" 2>/dev/null ) &
cap_pid=$!
wait "$pid" 2>/dev/null
# Capture the check's exit code from ITS `wait`, before any watchdog
# teardown runs. The teardown commands below overwrite $? — the killed
# watchdog reports 143 — which used to get stamped into every sentinel
# on machines with no gtimeout/timeout: verify reported pass=0
# fail=<all> while every per-check log said OK.
rc=$?
# Reap the watchdog's `sleep` child too (pkill -P), then the watchdog.
# Killing only the subshell leaves the sleep orphaned until $TIMEOUT
# elapses — same quirk the heartbeat cleanup in run-unit-parallel.sh
# works around; CI's orphan-process sweep flags those.
pkill -P "$cap_pid" 2>/dev/null
kill "$cap_pid" 2>/dev/null
wait "$cap_pid" 2>/dev/null
fi
rc=$?
echo "$rc" > "$EXIT_FILE"
) &
PIDS+=($!)