homelab-codex-ws/services/control-plane/tests/test_supervisor_duty_cycle.py

238 lines
8.8 KiB
Python
Raw Normal View History

feat(supervisor): duty-cycle nodes — liveness transitions logged, not actioned solaria (powered off ~16 h/day by design) and lustro (nightly display power-off) generated node_offline/node_stale/node_online alerts on every daily cycle. Six of them have sat in actions/pending/ since 2026-06-17/18, unapproved. Because an unapproved pending action suppresses its own dedup ID indefinitely (recon D14, supervisor.py pending/approved/running check), those stale alerts also meant a *real* future outage on either node would generate nothing at all. Suppression is data-driven from inventory/topology.yaml, not a hardcoded node-name check: - topology.yaml: new `duty_cycle` (+ `duty_cycle_reason`) on solaria and lustro, mirroring the existing dormant/dormant_reason shape. vps and piha deliberately do not carry it — an offline 24/7 node is a real incident. - supervisor: _load_dormant_nodes() -> _load_node_policy(), loading both dormant_nodes and duty_cycle_nodes from one topology read. dormant behavior is byte-for-byte unchanged. - supervisor: one guard in _route_node_event. Duty-cycle liveness events are logged at INFO and return; no action is written. duty_cycle is deliberately NOT dormant. A duty-cycle node stays fully active: its services are still reconciled (missing_service -> redeploy), its disk pressure still generates disk_cleanup, and its ha_* events still route. Only the liveness alert is suppressed. Regression tests pin all three. Fail-loud: an unreadable topology leaves both sets empty, which disables suppression and lets alerts through. A broken topology must never silently mute the fleet. Accepted trade-off: a genuine permanent outage of solaria or lustro no longer alerts. It stays visible in the operator UI (which computes liveness independently at read time) and in the event feed. An "offline longer than the expected window" escalation is the natural follow-up and needs a schedule in the topology field rather than a bare marker. Tests: 169 passed in services/control-plane/tests (was 157; +12). Runtime deployment is deliberately NOT part of this commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-05 13:48:29 +02:00
"""Duty-cycle node handling (topology `duty_cycle`).
Contract: a node that powers down on a schedule BY DESIGN (solaria ~16 h/day,
lustro nightly) still emits node_offline/node_stale/node_online events, but the
supervisor LOGS them instead of generating an alert_only action.
`duty_cycle` is deliberately NOT `dormant`: a duty-cycle node stays fully
active its services are reconciled and its disk pressure is acted on exactly
like a 24/7 node. Only the liveness alerts are suppressed.
Why this exists: before it, six pending liveness alerts from 2026-06-17/18 sat
in the queue forever for solaria and lustro. An unapproved pending action
suppresses its own dedup ID indefinitely (recon D14), so those stale alerts
also meant a *real* future outage on those nodes would generate nothing.
"""
from __future__ import annotations
import json
import logging
import sys
from pathlib import Path
import pytest
import yaml
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
import supervisor as supervisor_module
from supervisor import Supervisor
REPO_ROOT_REAL = Path(__file__).parent.parent.parent.parent
# solaria: duty-cycled. vps: 24/7, no duty_cycle. oldnode: dormant, to prove
# the two policies load independently from the same file.
TOPOLOGY_YAML = (
"nodes:\n"
" solaria:\n"
" status: active\n"
" duty_cycle: nightly\n"
" duty_cycle_reason: \"powered off ~16 h/day\"\n"
" roles: [compute]\n"
" vps:\n"
" status: active\n"
" roles: [edge]\n"
" oldnode:\n"
" status: dormant\n"
" roles: [remote]\n"
)
@pytest.fixture
def sup(tmp_path, monkeypatch):
actions = tmp_path / "actions"
events = tmp_path / "events"
world = tmp_path / "world"
state = tmp_path / "state"
repo = tmp_path / "repo"
for d in (actions, events, world, state,
repo / "inventory", repo / "hosts" / "solaria"):
d.mkdir(parents=True, exist_ok=True)
(repo / "inventory" / "topology.yaml").write_text(TOPOLOGY_YAML)
(repo / "hosts" / "solaria" / "services.yaml").write_text(
"host: solaria\nservices:\n some-svc:\n role: x\n"
)
monkeypatch.setattr(supervisor_module, "ACTIONS_DIR", actions)
monkeypatch.setattr(supervisor_module, "EVENTS_DIR", events)
monkeypatch.setattr(supervisor_module, "WORLD_DIR", world)
monkeypatch.setattr(supervisor_module, "REPO_ROOT", repo)
return Supervisor()
def _node_event(node: str, etype: str) -> dict:
return {
"id": f"evt-{node}-1-{etype}-node",
"type": etype,
"node": node,
"service": None,
"source": "observer",
"message": f"Node {node} liveness {etype}",
"payload": {"affected_node": node, "from": "fresh", "to": "dead"},
}
def _write_event(tmp_path, event: dict) -> None:
(tmp_path / "events" / f"{event['id']}.json").write_text(json.dumps(event))
def _pending(tmp_path):
return list((tmp_path / "actions" / "pending").glob("*.json"))
def _write_world(tmp_path, nodes=None, services=None, incidents=None):
world = tmp_path / "world"
(world / "nodes.json").write_text(json.dumps(nodes or {}))
(world / "services.json").write_text(json.dumps(services or {}))
(world / "incidents.json").write_text(json.dumps(incidents or {}))
# ---------------------------------------------------------------------------
# 1. Policy load
# ---------------------------------------------------------------------------
def test_load_node_policy_populates_both_sets(sup):
"""duty_cycle and dormant are loaded independently from one topology read."""
sup._load_node_policy()
assert sup.duty_cycle_nodes == {"solaria"}
assert sup.dormant_nodes == {"oldnode"}
def test_load_node_policy_fails_loud_on_unreadable_topology(sup, tmp_path):
"""Unreadable topology => empty sets => suppression disabled, alerts flow.
Never fail-silent: a broken topology must not mute the fleet.
"""
(tmp_path / "repo" / "inventory" / "topology.yaml").write_text("{[ not yaml")
sup._load_node_policy()
assert sup.duty_cycle_nodes == set()
assert sup.dormant_nodes == set()
_write_event(tmp_path, _node_event("solaria", "node_offline"))
sup._process_ha_events()
assert (tmp_path / "actions" / "pending" / "alert-node-offline-solaria.json").exists()
# ---------------------------------------------------------------------------
# 2. Liveness events from a duty-cycle node are logged, not actioned
# ---------------------------------------------------------------------------
@pytest.mark.parametrize("etype", ["node_offline", "node_stale", "node_online"])
def test_duty_cycle_liveness_event_generates_no_action(sup, tmp_path, caplog, etype):
sup._load_node_policy()
_write_event(tmp_path, _node_event("solaria", etype))
with caplog.at_level(logging.INFO, logger="supervisor"):
sup._process_ha_events()
assert _pending(tmp_path) == []
assert any(
"Duty-cycle node solaria" in r.getMessage() and etype in r.getMessage()
for r in caplog.records
), f"expected an INFO suppression line for {etype}, got: " \
f"{[r.getMessage() for r in caplog.records]}"
# ---------------------------------------------------------------------------
# 3. Regression guard — a 24/7 node is unaffected
# ---------------------------------------------------------------------------
@pytest.mark.parametrize("etype", ["node_offline", "node_stale", "node_online"])
def test_non_duty_cycle_node_still_alerts(sup, tmp_path, etype):
"""An offline vps is still a real incident."""
sup._load_node_policy()
_write_event(tmp_path, _node_event("vps", etype))
sup._process_ha_events()
action_id = f"alert-{etype.replace('_', '-')}-vps"
path = tmp_path / "actions" / "pending" / f"{action_id}.json"
assert path.exists()
action = json.loads(path.read_text())
assert action["type"] == "alert_only"
assert action["node"] == "vps"
assert action["payload"]["reason"] == etype
# ---------------------------------------------------------------------------
# 4. Scope guard — duty_cycle is NOT dormant
# ---------------------------------------------------------------------------
def test_duty_cycle_node_missing_service_still_redeploys(sup, tmp_path):
"""The drift loop must be untouched: a missing desired service on a
duty-cycle node still produces a redeploy action."""
_write_world(tmp_path, nodes={}, services={}, incidents={})
sup.reconcile()
assert (tmp_path / "actions" / "pending" / "redeploy-solaria-some-svc.json").exists()
def test_duty_cycle_node_disk_pressure_still_cleans(sup, tmp_path):
"""disk_cleanup must be untouched for a duty-cycle node."""
_write_world(
tmp_path,
nodes={"solaria": {"status": "online", "disk_pressure": "high"}},
services={"solaria/some-svc": {"node": "solaria", "service": "some-svc",
"status": "healthy"}},
incidents={},
)
sup.reconcile()
assert (tmp_path / "actions" / "pending" / "disk-cleanup-solaria.json").exists()
# ---------------------------------------------------------------------------
# 5. HA event routing on a duty-cycle node is untouched
# ---------------------------------------------------------------------------
def test_duty_cycle_node_ha_event_still_routed(sup, tmp_path):
sup._load_node_policy()
event = {
"id": "evt-solaria-2-ha_update_available-homeassistant",
"type": "ha_update_available",
"node": "solaria",
"service": "homeassistant",
"message": "Update available: test",
"payload": {},
}
(tmp_path / "events" / f"{event['id']}.json").write_text(json.dumps(event))
sup._process_ha_events()
assert (tmp_path / "actions" / "pending"
/ "alert-ha-update-available-solaria.json").exists()
# ---------------------------------------------------------------------------
# 6. The real topology carries the field — removing it fails CI
# ---------------------------------------------------------------------------
def test_real_topology_declares_expected_duty_cycle_nodes():
"""Guards the data half of the change: if someone drops `duty_cycle` from
solaria or lustro, or adds it to a 24/7 node, this fails."""
topo = yaml.safe_load((REPO_ROOT_REAL / "inventory" / "topology.yaml").read_text())
duty_cycle = {
name for name, info in (topo.get("nodes") or {}).items()
if (info or {}).get("duty_cycle")
}
assert duty_cycle == {"solaria", "lustro"}
# The 24/7 nodes must stay alertable.
for name in ("vps", "piha"):
assert not (topo["nodes"][name] or {}).get("duty_cycle"), \
f"{name} is a 24/7 node and must not carry duty_cycle"
# duty_cycle nodes stay `active` — duty_cycle is not a way to spell dormant.
for name in ("solaria", "lustro"):
assert topo["nodes"][name]["status"] == "active"