fix(reboot): enforce direct runner fail-closed guard [skip ci]

This commit is contained in:
Your Name
2026-06-28 09:16:43 +08:00
parent f8e2b39ab3
commit 8f402983ee
5 changed files with 186 additions and 4 deletions

View File

@@ -286,6 +286,20 @@ echo "ACTION_RUNNER_ENABLED_COUNT $(systemctl list-unit-files "actions.runner.*"
for u in $(systemctl list-units "actions.runner.*" --all --no-legend --plain 2>/dev/null | awk "{print \$1}"); do
systemctl show "$u" -p ActiveState -p SubState -p CPUQuotaPerSecUSec -p MemoryMax -p WatchdogUSec -p NRestarts | sed "s/^/RUNNER $u /"
done
for u in awoooi-direct-runner-open.service awoooi-direct-runner.service gitea-act-runner-host.service gitea-act-runner-awoooi-controlled.service gitea-awoooi-controlled-runner.service gitea-act-runner-awoooi-open.service; do
load=$(systemctl show "$u" -p LoadState --value 2>/dev/null || true)
unitfile=$(systemctl show "$u" -p UnitFileState --value 2>/dev/null || true)
active=$(systemctl show "$u" -p ActiveState --value 2>/dev/null || true)
mainpid=$(systemctl show "$u" -p MainPID --value 2>/dev/null || true)
echo "RUNNER_FAILCLOSED_UNIT $u load=$load unitfile=$unitfile active=$active mainpid=$mainpid"
done
direct_runner_count=$(pgrep -f "^/home/wooo/act-runner/act_runner|^/home/wooo/act-runner-controlled/act_runner|^/home/wooo/awoooi-controlled-runner/awoooi_controlled_runner" 2>/dev/null | wc -l | tr -d " ")
echo "RUNNER_DIRECT_PROCESS_COUNT $direct_runner_count"
for p in /home/wooo/act-runner/act_runner /home/wooo/act-runner/act_runner.real-20260628-runner-pressure-guard /home/wooo/act-runner-controlled/act_runner /home/wooo/awoooi-controlled-runner/awoooi_controlled_runner; do
kind=$(file -b "$p" 2>/dev/null || echo missing)
echo "RUNNER_FAILCLOSED_BINARY $p kind=$kind"
echo "$kind" | grep -qi "ELF" && echo "RUNNER_FAILCLOSED_BINARY_ELF $p"
done
docker ps --format "DOCKER {{.Names}}\t{{.Status}}" | head -120
' 2>&1); then
fail "ssh 110 read-only check"
@@ -309,6 +323,13 @@ docker ps --format "DOCKER {{.Names}}\t{{.Status}}" | head -120
else
warn "runner watchdog state not confirmed"
fi
if awk '$1 == "RUNNER_FAILCLOSED_UNIT" && ($3 != "load=masked" || $4 != "unitfile=masked") {bad=1} END {exit bad}' <<<"$out"; then
ok "110 direct/Gitea runner fail-closed units are masked"
else
fail "110 direct/Gitea runner fail-closed units are not all masked"
fi
grep -q "RUNNER_DIRECT_PROCESS_COUNT 0" <<<"$out" && ok "110 direct runner process count is zero" || fail "110 direct runner process detected"
grep -q "RUNNER_FAILCLOSED_BINARY_ELF" <<<"$out" && fail "110 runner fail-closed binary path restored to ELF" || ok "110 runner binary paths are fail-closed stubs or missing"
grep -q "sentry-self-hosted-clickhouse-1.*Restarting" <<<"$out" && warn "Sentry ClickHouse restarting" || ok "Sentry ClickHouse not visibly restarting"
}