fix(cd): reopen controlled runtime deploy lane
Some checks failed
CD Pipeline / tests (push) Failing after 7s
CD Pipeline / build-and-deploy (push) Has been skipped
CD Pipeline / post-deploy-checks (push) Has been skipped
Code Review / ai-code-review (push) Successful in 17s

This commit is contained in:
Your Name
2026-06-28 11:09:42 +08:00
parent 95c825f242
commit e97b252475
11 changed files with 203 additions and 56 deletions

View File

@@ -193,12 +193,19 @@ RUNNER_DIR="/home/wooo/act-runner"
RUNNER_SERVICE="gitea-act-runner-host.service"
RUNNER_ENABLE_SENTINEL="/run/awoooi-runner-host-enabled"
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_GITEA_RUNNER_ON_BOOT="${AWOOOI_START_GITEA_RUNNER_ON_BOOT:-0}"
START_CONTROLLED_CD_LANE="${AWOOOI_START_CONTROLLED_CD_LANE:-0}"
START_GITEA_RUNNER_ALLOWED=0
START_CD_LANE_ALLOWED=0
RUNNER_FAIL_CLOSED_SERVICES=(
"awoooi-cd-lane.service"
"awoooi-cd-lane-drain.service"
"awoooi-direct-runner-open.service"
"awoooi-direct-runner.service"
"gitea-act-runner-host.service"
@@ -207,18 +214,19 @@ RUNNER_FAIL_CLOSED_SERVICES=(
"gitea-act-runner-awoooi-open.service"
)
RUNNER_FAIL_CLOSED_BINARY_PATHS=(
"/home/wooo/awoooi-cd-lane/awoooi_cd_lane"
"/home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled"
"/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"
)
# Host runner still needs both keys. The direct cd-lane stays fail-closed until
# it is migrated or hard-limited outside this production host pressure lane.
# Legacy host runner still needs both keys. The dedicated cd-lane has its own
# sentinel and narrow label/capacity verifier below.
if [ "$START_GITEA_RUNNER_ON_BOOT" = "1" ] && [ -e "$RUNNER_ENABLE_SENTINEL" ]; then
START_GITEA_RUNNER_ALLOWED=1
fi
if [ -e "$CD_LANE_ENABLE_SENTINEL" ] || [ "$START_CONTROLLED_CD_LANE" = "1" ]; then
START_CD_LANE_ALLOWED=1
fi
mask_runner_unit_file() {
local unit="$1"
@@ -271,17 +279,96 @@ EOF
install_cd_lane_fail_closed_unit() {
local unit_file="/etc/systemd/system/awoooi-cd-lane.service"
local tmp
local quarantine_stamp
quarantine_stamp="$(date +%Y%m%d%H%M%S)"
systemctl mask awoooi-cd-lane.service >/dev/null 2>&1 || true
if [ -e "$unit_file" ] || [ -L "$unit_file" ]; then
chattr -i "$unit_file" >/dev/null 2>&1 || true
if ! { [ -L "$unit_file" ] && [ "$(readlink "$unit_file" 2>/dev/null || true)" = "/dev/null" ]; }; then
if ! grep -q "AWOOOI direct CD lane fail-closed" "$unit_file" 2>/dev/null; then
mv "$unit_file" "${unit_file}.quarantined-runner-incident-${quarantine_stamp}" >/dev/null 2>&1 || true
fi
fi
ln -sfn /dev/null "$unit_file" >/dev/null 2>&1 || true
tmp="$(mktemp)"
cat >"$tmp" <<'EOF'
[Unit]
Description=AWOOOI direct CD lane fail-closed after 2026-06-28 pressure incident
ConditionPathExists=/run/awoooi-cd-lane-enabled
[Service]
Type=oneshot
ExecStart=/bin/false
EOF
install -o root -g root -m 0444 "$tmp" "$unit_file" >/dev/null 2>&1 || true
rm -f "$tmp"
chattr +i "$unit_file" >/dev/null 2>&1 || true
}
install_controlled_cd_lane_unit() {
local unit_file="/etc/systemd/system/$CD_LANE_SERVICE"
local tmp
chattr -i "$unit_file" "$CD_LANE_BINARY" >/dev/null 2>&1 || true
tmp="$(mktemp)"
cat >"$tmp" <<EOF
[Unit]
Description=AWOOOI controlled CD lane
After=network-online.target docker.service
Wants=network-online.target
Requires=docker.service
[Service]
Type=simple
User=wooo
WorkingDirectory=${CD_LANE_DIR}/data
Environment=HOME=/home/wooo
Environment=AWOOOI_CONTROLLED_RUNNER_OPEN=1
Environment=HOST_WEB_BUILD_PRESSURE_ATTEMPTS=1
Environment=HOST_WEB_BUILD_PRESSURE_SLEEP_SECONDS=1
ExecStart=${CD_LANE_BINARY} daemon --config ${CD_LANE_CONFIG}
Restart=always
RestartSec=10
KillSignal=SIGINT
TimeoutStopSec=3700
SuccessExitStatus=0 130 143
CPUQuota=250%
MemoryHigh=8G
MemoryMax=12G
TasksMax=512
[Install]
WantedBy=multi-user.target
EOF
install -o root -g root -m 0644 "$tmp" "$unit_file" >/dev/null 2>&1 || true
rm -f "$tmp"
}
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 "$CD_LANE_DRAIN_BINARY" 2>/dev/null | grep -qi "ELF" || return 1
return 0
}
quarantine_cd_lane_registration_fail_closed() {
@@ -316,6 +403,25 @@ quarantine_cd_lane_registration_fail_closed() {
apply_cd_lane_fail_closed_guard() {
local unit
if cd_lane_drain_is_controlled_open; then
log "✅ controlled cd-lane drain verifier passed; preserving drain lane and fail-closing regular lane only"
systemctl kill --signal=SIGKILL "$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
log "✅ controlled cd-lane verifier passed; keeping dedicated lane open"
install_controlled_cd_lane_unit
systemctl daemon-reload >/dev/null 2>&1 || true
systemctl enable --now "$CD_LANE_SERVICE" >/dev/null 2>&1 || true
return 0
fi
for unit in awoooi-cd-lane.service awoooi-cd-lane-drain.service; do
systemctl kill --signal=SIGKILL "$unit" >/dev/null 2>&1 || true
systemctl stop "$unit" >/dev/null 2>&1 || true
@@ -336,6 +442,26 @@ apply_cd_lane_fail_closed_guard() {
systemctl daemon-reload >/dev/null 2>&1 || true
}
ensure_cd_lane_fail_closed() {
apply_cd_lane_fail_closed_guard
}
ensure_controlled_cd_lane_open() {
if ! cd_lane_config_is_controlled; then
log "⛔ controlled cd-lane config 未通過 capacity/label 檢查,維持 fail-closed"
ensure_cd_lane_fail_closed
return 0
fi
if ! file "$CD_LANE_BINARY" 2>/dev/null | grep -qi "ELF"; then
log "⛔ controlled cd-lane binary 不是可執行 ELF維持 fail-closed"
ensure_cd_lane_fail_closed
return 0
fi
install_controlled_cd_lane_unit
systemctl daemon-reload >/dev/null 2>&1 || true
systemctl enable --now "$CD_LANE_SERVICE" >/dev/null 2>&1 || true
}
ensure_host_runner_fail_closed() {
local unit
local binary
@@ -365,8 +491,6 @@ ensure_host_runner_fail_closed() {
fi
pkill -KILL -f "^${RUNNER_DIR}/act_runner(\\.real-[^ ]*)? daemon" >/dev/null 2>&1 || true
pkill -KILL -f "^${CD_LANE_DIR}/awoooi_cd_lane daemon" >/dev/null 2>&1 || true
quarantine_cd_lane_registration_fail_closed
for binary in "${RUNNER_FAIL_CLOSED_BINARY_PATHS[@]}"; do
guard_runner_binary_fail_closed "$binary"
done
@@ -472,8 +596,13 @@ else
log "⚠️ 找不到 act-runner binary/config: $RUNNER_DIR"
fi
log "⏸️ direct cd-lane 維持 fail-closed需完成搬遷或硬限流後才可用獨立變更恢復"
apply_cd_lane_fail_closed_guard
if [ "$START_CD_LANE_ALLOWED" = "1" ]; then
log "✅ controlled cd-lane 具備 sentinel/env 授權,執行 capacity/label/binary verifier 後受控開啟"
ensure_controlled_cd_lane_open
else
log "⏸️ controlled cd-lane 未要求啟動;保留合格 drain laneregular lane 維持 fail-closed"
ensure_cd_lane_fail_closed
fi
# ──────────────────────────────────────────────
# STEP 7: SentryError Tracking

View File

@@ -286,7 +286,7 @@ 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 $u /"
done
for u in awoooi-cd-lane-drain.service awoooi-direct-runner-open.service awoooi-direct-runner.service gitea-act-runner-host.service gitea-act-runner-awoooi-controlled.service gitea-awoooi-controlled-runner.service gitea-act-runner-awoooi-open.service; do
for u in awoooi-direct-runner-open.service awoooi-direct-runner.service gitea-act-runner-host.service gitea-act-runner-awoooi-controlled.service gitea-awoooi-controlled-runner.service gitea-act-runner-awoooi-open.service; do
load=$(systemctl show "$u" -p LoadState --value 2>/dev/null || true)
unitfile=$(systemctl show "$u" -p UnitFileState --value 2>/dev/null || true)
active=$(systemctl show "$u" -p ActiveState --value 2>/dev/null || true)
@@ -294,8 +294,6 @@ for u in awoooi-cd-lane-drain.service awoooi-direct-runner-open.service awoooi-d
unit_ok=0
if [ "$load" = "masked" ] && [ "$unitfile" = "masked" ] && [ "$active" = "inactive" ]; then
unit_ok=1
elif [ "$u" = "awoooi-cd-lane-drain.service" ] && [ "$load" = "not-found" ] && [ "$active" != "active" ]; then
unit_ok=1
fi
echo "RUNNER_FAILCLOSED_UNIT $u load=$load unitfile=$unitfile active=$active mainpid=$mainpid ok=$unit_ok"
done
@@ -319,7 +317,7 @@ fi
cd_lane_binary_kind=$(file -b /home/wooo/awoooi-cd-lane/awoooi_cd_lane 2>/dev/null || echo missing)
cd_lane_binary_elf=0
echo "$cd_lane_binary_kind" | grep -qi "ELF" && cd_lane_binary_elf=1
cd_lane_process_count=$(pgrep -f "^/home/wooo/awoooi-cd-lane/awoooi_cd_lane|^/home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled" 2>/dev/null | wc -l | tr -d " ")
cd_lane_process_count=$(pgrep -f "^/home/wooo/awoooi-cd-lane/awoooi_cd_lane" 2>/dev/null | wc -l | tr -d " ")
cd_lane_ok=0
cd_lane_mode=blocked
if [ "$cd_lane_active" = "inactive" ] \
@@ -360,16 +358,22 @@ if [ "$cd_lane_drain_active" != "active" ] \
&& { [ "$cd_lane_drain_load" = "not-found" ] || { [ "$cd_lane_drain_load" = "masked" ] && [ "$cd_lane_drain_unitfile" = "masked" ]; }; }; then
cd_lane_drain_ok=1
cd_lane_drain_mode=failclosed
elif [ "$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=$cd_lane_drain_binary_elf process_count=$cd_lane_drain_process_count ok=$cd_lane_drain_ok"
cd_lane_guard_ok=0
if [ "$cd_lane_ok" = "1" ] && [ "$cd_lane_drain_ok" = "1" ]; then
if [ "$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 $direct_runner_count"
for p in /home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled /home/wooo/act-runner/act_runner /home/wooo/act-runner/act_runner.real-20260628-runner-pressure-guard /home/wooo/act-runner-controlled/act_runner /home/wooo/awoooi-controlled-runner/awoooi_controlled_runner; do
for p in /home/wooo/act-runner/act_runner /home/wooo/act-runner/act_runner.real-20260628-runner-pressure-guard /home/wooo/act-runner-controlled/act_runner /home/wooo/awoooi-controlled-runner/awoooi_controlled_runner; do
kind=$(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"

View File

@@ -306,15 +306,13 @@ check_runner_guardrails() {
local out bad
if ! out=$(ssh_cmd "wooo@192.168.0.110" '
bad=0
for u in awoooi-cd-lane-drain.service awoooi-direct-runner-open.service awoooi-direct-runner.service gitea-act-runner-host.service gitea-act-runner-awoooi-controlled.service gitea-awoooi-controlled-runner.service gitea-act-runner-awoooi-open.service; do
for u in awoooi-direct-runner-open.service awoooi-direct-runner.service gitea-act-runner-host.service gitea-act-runner-awoooi-controlled.service gitea-awoooi-controlled-runner.service gitea-act-runner-awoooi-open.service; do
load=$(systemctl show "$u" -p LoadState --value 2>/dev/null || true)
unitfile=$(systemctl show "$u" -p UnitFileState --value 2>/dev/null || true)
active=$(systemctl show "$u" -p ActiveState --value 2>/dev/null || true)
unit_ok=0
if [ "$load" = "masked" ] && [ "$unitfile" = "masked" ] && [ "$active" = "inactive" ]; then
unit_ok=1
elif [ "$u" = "awoooi-cd-lane-drain.service" ] && [ "$load" = "not-found" ] && [ "$active" != "active" ]; then
unit_ok=1
fi
echo "RUNNER_FAILCLOSED_UNIT $u load=$load unitfile=$unitfile active=$active ok=$unit_ok"
[ "$unit_ok" = "1" ] || bad=1
@@ -338,7 +336,7 @@ fi
cd_lane_binary_kind=$(file -b /home/wooo/awoooi-cd-lane/awoooi_cd_lane 2>/dev/null || echo missing)
cd_lane_binary_elf=0
echo "$cd_lane_binary_kind" | grep -qi "ELF" && cd_lane_binary_elf=1
cd_lane_process_count=$(pgrep -f "^/home/wooo/awoooi-cd-lane/awoooi_cd_lane|^/home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled" 2>/dev/null | wc -l | tr -d " ")
cd_lane_process_count=$(pgrep -f "^/home/wooo/awoooi-cd-lane/awoooi_cd_lane" 2>/dev/null | wc -l | tr -d " ")
cd_lane_ok=0
cd_lane_mode=blocked
if [ "$cd_lane_active" = "inactive" ] \
@@ -378,10 +376,16 @@ if [ "$cd_lane_drain_active" != "active" ] \
&& { [ "$cd_lane_drain_load" = "not-found" ] || { [ "$cd_lane_drain_load" = "masked" ] && [ "$cd_lane_drain_unitfile" = "masked" ]; }; }; then
cd_lane_drain_ok=1
cd_lane_drain_mode=failclosed
elif [ "$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 process_count=$cd_lane_drain_process_count ok=$cd_lane_drain_ok"
cd_lane_guard_ok=0
if [ "$cd_lane_ok" = "1" ] && [ "$cd_lane_drain_ok" = "1" ]; then
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"
@@ -389,7 +393,7 @@ 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 $direct_runner_count"
[ "$direct_runner_count" = "0" ] || bad=1
for p in /home/wooo/awoooi-cd-lane-drain/awoooi_cd_lane_controlled /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
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" && bad=1