fix(runner): accept controlled cd lane drain readback

This commit is contained in:
Your Name
2026-06-28 10:42:35 +08:00
parent 9b9f1cf385
commit b7b475983f
5 changed files with 156 additions and 9 deletions

View File

@@ -198,6 +198,10 @@ CD_LANE_DIR="/home/wooo/awoooi-cd-lane"
CD_LANE_SERVICE="awoooi-cd-lane.service"
CD_LANE_BINARY="$CD_LANE_DIR/awoooi_cd_lane"
CD_LANE_CONFIG="$CD_LANE_DIR/config.yaml"
CD_LANE_DRAIN_DIR="/home/wooo/awoooi-cd-lane-drain"
CD_LANE_DRAIN_SERVICE="awoooi-cd-lane-drain.service"
CD_LANE_DRAIN_BINARY="$CD_LANE_DRAIN_DIR/awoooi_cd_lane_controlled"
CD_LANE_DRAIN_CONFIG="$CD_LANE_DRAIN_DIR/config.yaml"
CD_LANE_ENABLE_SENTINEL="/run/awoooi-cd-lane-enabled"
START_CONTROLLED_CD_LANE="${AWOOOI_START_CONTROLLED_CD_LANE:-0}"
START_CD_LANE_ALLOWED=0
@@ -300,18 +304,46 @@ EOF
chattr +i "$unit_file" >/dev/null 2>&1 || true
}
cd_lane_config_is_controlled() {
[ -f "$CD_LANE_CONFIG" ] || return 1
grep -Eq '^[[:space:]]+capacity:[[:space:]]*1[[:space:]]*$' "$CD_LANE_CONFIG" || return 1
grep -q 'awoooi-ubuntu:docker://192.168.0.110:5000/awoooi/ci-runner:act-22.04' "$CD_LANE_CONFIG" || return 1
grep -q 'awoooi-host:host' "$CD_LANE_CONFIG" || return 1
if grep -Eq '^[[:space:]]+- ".*(ubuntu-latest|stockplatform|headless|playwright)' "$CD_LANE_CONFIG"; then
cd_lane_config_path_is_controlled() {
local config_path="$1"
[ -f "$config_path" ] || return 1
grep -Eq '^[[:space:]]+capacity:[[:space:]]*1[[:space:]]*$' "$config_path" || return 1
grep -q 'awoooi-ubuntu:docker://192.168.0.110:5000/awoooi/ci-runner:act-22.04' "$config_path" || return 1
grep -q 'awoooi-host:host' "$config_path" || return 1
if grep -Eq '^[[:space:]]+- ".*(ubuntu-latest|stockplatform|headless|playwright)' "$config_path"; then
return 1
fi
return 0
}
cd_lane_config_is_controlled() {
cd_lane_config_path_is_controlled "$CD_LANE_CONFIG"
}
cd_lane_drain_config_is_controlled() {
cd_lane_config_path_is_controlled "$CD_LANE_DRAIN_CONFIG"
}
cd_lane_drain_is_controlled_open() {
local active
active="$(systemctl show "$CD_LANE_DRAIN_SERVICE" -p ActiveState --value 2>/dev/null || true)"
[ "$active" = "active" ] || return 1
cd_lane_drain_config_is_controlled || return 1
file "$CD_LANE_DRAIN_BINARY" 2>/dev/null | grep -qi "ELF" || return 1
return 0
}
ensure_cd_lane_fail_closed() {
if cd_lane_drain_is_controlled_open; then
log "✅ controlled cd-lane drain verifier passed; preserving drain lane and fail-closing regular lane only"
systemctl kill --signal=SIGKILL "$CD_LANE_SERVICE" >/dev/null 2>&1 || true
systemctl stop "$CD_LANE_SERVICE" >/dev/null 2>&1 || true
systemctl disable "$CD_LANE_SERVICE" >/dev/null 2>&1 || true
install_cd_lane_fail_closed_unit
pkill -KILL -f "^${CD_LANE_BINARY} daemon" >/dev/null 2>&1 || true
systemctl daemon-reload >/dev/null 2>&1 || true
return 0
fi
if { [ -e "$CD_LANE_ENABLE_SENTINEL" ] || [ -e "/run/awoooi-cd-lane-controlled-open" ] || [ "$START_CONTROLLED_CD_LANE" = "1" ]; } \
&& cd_lane_config_is_controlled \
&& file "$CD_LANE_BINARY" 2>/dev/null | grep -qi "ELF"; then

View File

@@ -327,6 +327,38 @@ elif [ "$cd_lane_sentinel" = "present" ] && [ "$cd_lane_active" = "active" ] &&
cd_lane_mode=controlled_open
fi
echo "CD_LANE_CONTROLLED mode=$cd_lane_mode load=$cd_lane_load unitfile=$cd_lane_unitfile active=$cd_lane_active mainpid=$cd_lane_mainpid sentinel=$cd_lane_sentinel capacity=$cd_lane_capacity_ok labels=$cd_lane_labels_ok binary_elf=$cd_lane_binary_elf ok=$cd_lane_ok"
cd_lane_drain_load=$(systemctl show awoooi-cd-lane-drain.service -p LoadState --value 2>/dev/null || true)
cd_lane_drain_unitfile=$(systemctl show awoooi-cd-lane-drain.service -p UnitFileState --value 2>/dev/null || true)
cd_lane_drain_active=$(systemctl show awoooi-cd-lane-drain.service -p ActiveState --value 2>/dev/null || true)
cd_lane_drain_mainpid=$(systemctl show awoooi-cd-lane-drain.service -p MainPID --value 2>/dev/null || true)
cd_lane_drain_capacity_ok=0
cd_lane_drain_labels_ok=0
if grep -Eq "^[[:space:]]+capacity:[[:space:]]*1[[:space:]]*$" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_capacity_ok=1
fi
if grep -q "awoooi-ubuntu:docker://192.168.0.110:5000/awoooi/ci-runner:act-22.04" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& grep -q "awoooi-host:host" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& ! grep -Eq "^[[:space:]]+- \".*(ubuntu-latest|stockplatform|headless|playwright)" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_labels_ok=1
fi
cd_lane_drain_binary_kind=$(file -b /home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled 2>/dev/null || echo missing)
cd_lane_drain_binary_elf=0
echo "$cd_lane_drain_binary_kind" | grep -qi "ELF" && cd_lane_drain_binary_elf=1
cd_lane_drain_ok=0
cd_lane_drain_mode=absent
if [ "$cd_lane_drain_load" = "loaded" ] || [ "$cd_lane_drain_unitfile" = "enabled" ] || [ "$cd_lane_drain_active" = "active" ]; then
cd_lane_drain_mode=blocked
fi
if [ "$cd_lane_drain_active" = "active" ] && [ "$cd_lane_drain_capacity_ok" = "1" ] && [ "$cd_lane_drain_labels_ok" = "1" ] && [ "$cd_lane_drain_binary_elf" = "1" ]; then
cd_lane_drain_ok=1
cd_lane_drain_mode=controlled_open
fi
echo "CD_LANE_DRAIN_CONTROLLED mode=$cd_lane_drain_mode load=$cd_lane_drain_load unitfile=$cd_lane_drain_unitfile active=$cd_lane_drain_active mainpid=$cd_lane_drain_mainpid capacity=$cd_lane_drain_capacity_ok labels=$cd_lane_drain_labels_ok binary_elf=$cd_lane_drain_binary_elf ok=$cd_lane_drain_ok"
cd_lane_guard_ok=0
if [ "$cd_lane_ok" = "1" ] || [ "$cd_lane_drain_ok" = "1" ]; then
cd_lane_guard_ok=1
fi
echo "CD_LANE_GUARDRAILS_OK $cd_lane_guard_ok"
direct_runner_count=$(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 $direct_runner_count"
for p in /home/wooo/act-runner/act_runner /home/wooo/act-runner/act_runner.real-20260628-runner-pressure-guard /home/wooo/act-runner-controlled/act_runner /home/wooo/awoooi-controlled-runner/awoooi_controlled_runner; do
@@ -362,7 +394,7 @@ docker ps --format "DOCKER {{.Names}}\t{{.Status}}" | head -120
else
fail "110 legacy direct/Gitea runner units are not fail-closed"
fi
grep -q "CD_LANE_CONTROLLED .*ok=1" <<<"$out" && ok "110 controlled cd-lane is safe or fail-closed" || fail "110 controlled cd-lane is neither safe-open nor fail-closed"
grep -q "CD_LANE_GUARDRAILS_OK 1" <<<"$out" && ok "110 controlled cd-lane is safe, drained, or fail-closed" || fail "110 controlled cd-lane is neither safe-open/drained nor fail-closed"
grep -q "RUNNER_DIRECT_PROCESS_COUNT 0" <<<"$out" && ok "110 legacy direct runner process count is zero" || fail "110 legacy 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"

View File

@@ -346,7 +346,38 @@ elif [ "$cd_lane_sentinel" = "present" ] && [ "$cd_lane_active" = "active" ] &&
cd_lane_mode=controlled_open
fi
echo "CD_LANE_CONTROLLED mode=$cd_lane_mode load=$cd_lane_load unitfile=$cd_lane_unitfile active=$cd_lane_active sentinel=$cd_lane_sentinel capacity=$cd_lane_capacity_ok labels=$cd_lane_labels_ok binary_elf=$cd_lane_binary_elf ok=$cd_lane_ok"
[ "$cd_lane_ok" = "1" ] || bad=1
cd_lane_drain_load=$(systemctl show awoooi-cd-lane-drain.service -p LoadState --value 2>/dev/null || true)
cd_lane_drain_unitfile=$(systemctl show awoooi-cd-lane-drain.service -p UnitFileState --value 2>/dev/null || true)
cd_lane_drain_active=$(systemctl show awoooi-cd-lane-drain.service -p ActiveState --value 2>/dev/null || true)
cd_lane_drain_capacity_ok=0
cd_lane_drain_labels_ok=0
if grep -Eq "^[[:space:]]+capacity:[[:space:]]*1[[:space:]]*$" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_capacity_ok=1
fi
if grep -q "awoooi-ubuntu:docker://192.168.0.110:5000/awoooi/ci-runner:act-22.04" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& grep -q "awoooi-host:host" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& ! grep -Eq "^[[:space:]]+- \".*(ubuntu-latest|stockplatform|headless|playwright)" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_labels_ok=1
fi
cd_lane_drain_binary_kind=$(file -b /home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled 2>/dev/null || echo missing)
cd_lane_drain_binary_elf=0
echo "$cd_lane_drain_binary_kind" | grep -qi "ELF" && cd_lane_drain_binary_elf=1
cd_lane_drain_ok=0
cd_lane_drain_mode=absent
if [ "$cd_lane_drain_load" = "loaded" ] || [ "$cd_lane_drain_unitfile" = "enabled" ] || [ "$cd_lane_drain_active" = "active" ]; then
cd_lane_drain_mode=blocked
fi
if [ "$cd_lane_drain_active" = "active" ] && [ "$cd_lane_drain_capacity_ok" = "1" ] && [ "$cd_lane_drain_labels_ok" = "1" ] && [ "$cd_lane_drain_binary_elf" = "1" ]; then
cd_lane_drain_ok=1
cd_lane_drain_mode=controlled_open
fi
echo "CD_LANE_DRAIN_CONTROLLED mode=$cd_lane_drain_mode load=$cd_lane_drain_load unitfile=$cd_lane_drain_unitfile active=$cd_lane_drain_active capacity=$cd_lane_drain_capacity_ok labels=$cd_lane_drain_labels_ok binary_elf=$cd_lane_drain_binary_elf ok=$cd_lane_drain_ok"
cd_lane_guard_ok=0
if [ "$cd_lane_ok" = "1" ] || [ "$cd_lane_drain_ok" = "1" ]; then
cd_lane_guard_ok=1
fi
echo "CD_LANE_GUARDRAILS_OK $cd_lane_guard_ok"
[ "$cd_lane_guard_ok" = "1" ] || bad=1
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 $direct_runner_count"
[ "$direct_runner_count" = "0" ] || bad=1

View File

@@ -579,6 +579,38 @@ elif [ "$cd_lane_sentinel" = "present" ] && [ "$cd_lane_active" = "active" ] &&
cd_lane_mode=controlled_open
fi
echo "CD_LANE_CONTROLLED mode=$cd_lane_mode load=$cd_lane_load unitfile=$cd_lane_unitfile active=$cd_lane_active mainpid=$cd_lane_mainpid sentinel=$cd_lane_sentinel capacity=$cd_lane_capacity_ok labels=$cd_lane_labels_ok binary_elf=$cd_lane_binary_elf ok=$cd_lane_ok"
cd_lane_drain_load=$(systemctl show awoooi-cd-lane-drain.service -p LoadState --value 2>/dev/null || true)
cd_lane_drain_unitfile=$(systemctl show awoooi-cd-lane-drain.service -p UnitFileState --value 2>/dev/null || true)
cd_lane_drain_active=$(systemctl show awoooi-cd-lane-drain.service -p ActiveState --value 2>/dev/null || true)
cd_lane_drain_mainpid=$(systemctl show awoooi-cd-lane-drain.service -p MainPID --value 2>/dev/null || true)
cd_lane_drain_capacity_ok=0
cd_lane_drain_labels_ok=0
if grep -Eq "^[[:space:]]+capacity:[[:space:]]*1[[:space:]]*$" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_capacity_ok=1
fi
if grep -q "awoooi-ubuntu:docker://192.168.0.110:5000/awoooi/ci-runner:act-22.04" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& grep -q "awoooi-host:host" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null \
&& ! grep -Eq "^[[:space:]]+- \".*(ubuntu-latest|stockplatform|headless|playwright)" /home/wooo/awoooi-cd-lane-drain/config.yaml 2>/dev/null; then
cd_lane_drain_labels_ok=1
fi
cd_lane_drain_binary_kind=$(file -b /home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled 2>/dev/null || echo missing)
cd_lane_drain_binary_elf=0
echo "$cd_lane_drain_binary_kind" | grep -qi "ELF" && cd_lane_drain_binary_elf=1
cd_lane_drain_ok=0
cd_lane_drain_mode=absent
if [ "$cd_lane_drain_load" = "loaded" ] || [ "$cd_lane_drain_unitfile" = "enabled" ] || [ "$cd_lane_drain_active" = "active" ]; then
cd_lane_drain_mode=blocked
fi
if [ "$cd_lane_drain_active" = "active" ] && [ "$cd_lane_drain_capacity_ok" = "1" ] && [ "$cd_lane_drain_labels_ok" = "1" ] && [ "$cd_lane_drain_binary_elf" = "1" ]; then
cd_lane_drain_ok=1
cd_lane_drain_mode=controlled_open
fi
echo "CD_LANE_DRAIN_CONTROLLED mode=$cd_lane_drain_mode load=$cd_lane_drain_load unitfile=$cd_lane_drain_unitfile active=$cd_lane_drain_active mainpid=$cd_lane_drain_mainpid capacity=$cd_lane_drain_capacity_ok labels=$cd_lane_drain_labels_ok binary_elf=$cd_lane_drain_binary_elf ok=$cd_lane_drain_ok"
cd_lane_guard_ok=0
if [ "$cd_lane_ok" = "1" ] || [ "$cd_lane_drain_ok" = "1" ]; then
cd_lane_guard_ok=1
fi
echo "CD_LANE_GUARDRAILS_OK $cd_lane_guard_ok"
direct_runner_count=$(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
@@ -599,7 +631,7 @@ if awk '$1 == "RUNNER_FAILCLOSED_UNIT" && $NF != "ok=1" {bad=1} END {exit bad}'
else
blocked "110 legacy direct/Gitea runner units are not fail-closed"
fi
grep -q "CD_LANE_CONTROLLED .*ok=1" "$runner_tmp" && ok "110 controlled cd-lane is safe or fail-closed" || blocked "110 controlled cd-lane is neither safe-open nor fail-closed"
grep -q "CD_LANE_GUARDRAILS_OK 1" "$runner_tmp" && ok "110 controlled cd-lane is safe, drained, or fail-closed" || blocked "110 controlled cd-lane is neither safe-open/drained nor fail-closed"
grep -q "RUNNER_DIRECT_PROCESS_COUNT 0" "$runner_tmp" && ok "110 legacy direct runner process count is zero" || blocked "110 legacy direct runner process detected"
grep -q "RUNNER_FAILCLOSED_BINARY_ELF" "$runner_tmp" && blocked "110 runner fail-closed binary path restored to ELF" || ok "110 runner binary paths are fail-closed stubs or missing"
grep -q "RUNNER_PRESSURE_GATE_RC 0" "$runner_tmp" && ok "110 host pressure gate returned 0" || blocked "110 host pressure gate is blocking"