fix(delivery): wait for HTTPS readiness during startup

This commit is contained in:
2026-10-29 15:29:50 +08:00
parent 4e5f491952
commit 6e20b53013
6 changed files with 230 additions and 3 deletions
+43
View File
@@ -22,6 +22,7 @@ from . import (
operation_proof,
operator_units,
preflight,
proxy_health,
proxy_install,
proxy_service,
service_install,
@@ -372,6 +373,8 @@ class Maintenance:
values = self.unit(name)
if operation == "start" and values["ActiveState"] == "active":
node_health.inspect_unit(name, self.selected)
if name == "proxy":
self._wait_for_proxy(time.monotonic() + 130)
return
if operation == "stop" and values["ActiveState"] == "inactive" and values["MainPID"] == "0":
self.empty_cgroup(name)
@@ -396,6 +399,8 @@ class Maintenance:
and values["SubState"] == "running"
):
node_health.inspect_unit(name, self.selected)
if name == "proxy":
self._wait_for_proxy(deadline)
break
if (
operation == "stop"
@@ -410,6 +415,40 @@ class Maintenance:
self.record["events"][-1]["confirmed"] = True
self.save(operation + "_confirmed")
def _wait_for_proxy(self, deadline: float) -> None:
"""Type=exec is process startup; confirm actual HTTPS before admission."""
while True:
if time.monotonic() >= deadline:
raise DeliveryError("bounded HTTPS startup unconfirmed")
if install.selection(check_configuration=False) != self.selected:
raise DeliveryError("selected binding changed during maintenance")
# Invalid selected TLS/configuration is fatal, never a retry reason.
proxy_install.check_binding(
self.selected["release_id"], self.selected["configuration_id"]
)
remaining = deadline - time.monotonic()
if remaining <= 0:
raise DeliveryError("bounded HTTPS startup unconfirmed")
try:
ready = proxy_health.observe(self.selected, timeout=min(5.0, remaining))
except proxy_health.HTTPSNotReady as error:
remaining = deadline - time.monotonic()
if remaining <= 0:
raise DeliveryError("bounded HTTPS startup unconfirmed") from error
time.sleep(min(0.5, remaining))
continue
if time.monotonic() >= deadline:
raise DeliveryError("bounded HTTPS startup unconfirmed")
if install.selection(check_configuration=False) != self.selected:
raise DeliveryError("selected binding changed during maintenance")
if ready != {
"reachable": True,
"pinned_certificate_and_hostname_verified": True,
"public_browser_trust_verified": False,
}:
raise DeliveryError("HTTPS startup proof differs")
return
def start_group(self, names: tuple[str, ...]) -> None:
"""Dispatch one fixed dependency stage; confirm each real unit separately."""
if names not in START_GROUPS:
@@ -424,6 +463,8 @@ class Maintenance:
values = self.unit(name)
if values["ActiveState"] == "active":
node_health.inspect_unit(name, self.selected)
if name == "proxy":
self._wait_for_proxy(time.monotonic() + 130)
else:
inactive.append(name)
pending = {}
@@ -448,6 +489,8 @@ class Maintenance:
raise DeliveryError("bounded lifecycle operation unconfirmed")
if values["ActiveState"] == "active" and values["SubState"] == "running":
node_health.inspect_unit(name, self.selected)
if name == "proxy":
self._wait_for_proxy(deadline)
event["confirmed"] = True
self.save("start_confirmed")
del pending[name]