Compare commits

..
Author SHA1 Message Date
ChuckBuilds 14abea2d24 perf(health): stop rewriting a health record on every healthy cycle
Every successful plugin update called record_success(), which persisted the
record unconditionally. In steady state the only fields that had changed were
total_successes and last_success_time -- a counter and a timestamp that
health_monitor surfaces for display and that nothing reads back after a
restart. Nothing alerts on the age of last_successful_update; it is carried in
the metrics dataclass and shown.

Measured on a rig running 24 plugins, all steady-state (0 consecutive
failures, circuit closed): a five-minute sample caught 22 health-file
rewrites, about 4.4 a minute or 6,300 a day. Each write is ~400 bytes through
cache_manager.set(), which writes a file per call, so each one costs a
filesystem block plus an ext4 journal write.

That lands on an SD card, where the unit of cost is an erase-block cycle
rather than the bytes involved, and where wear is what eventually kills the
card. Two cards have already failed on the other rig with the same
signature -- unreadable block device, EIO on exec, sshd unable to read its
host keys.

The circuit breaker still has to survive a restart, so the write is kept for
exactly the fields it is rebuilt from: consecutive_failures, circuit_state,
circuit_opened_time, half_open_start_time. A failure, a circuit opening and a
recovery are all still written the moment they happen. In-memory state is
updated every time either way, so the health API and web UI show what they
always did.

Tested: 100 healthy cycles now perform zero writes after the first, the
counters remain accurate in memory, and a failure, a recovery and a
half-open-to-closed transition each still reach disk. One test kills and
rebuilds the tracker from the cache to prove the breaker's state genuinely
survives what is no longer written.

Mutation-checked both ways: persisting unconditionally again fails the
steady-state test, and widening _DURABLE_FIELDS to include last_success_time
fails it too. The 46 existing health tests pass.
2026-08-19 20:35:02 -04:00
4 changed files with 137 additions and 188 deletions
+25 -4
View File
@@ -178,11 +178,21 @@ class PluginHealthTracker:
)
return self._health_state[plugin_id]
# Fields the circuit breaker is rebuilt from after a restart. Everything
# else in a health record is reporting, read only for display.
_DURABLE_FIELDS = ('consecutive_failures', 'circuit_state',
'circuit_opened_time', 'half_open_start_time')
def _durable(self, state: Dict[str, Any]) -> tuple:
"""The part of a health record whose loss would change behaviour."""
return tuple(state.get(field) for field in self._DURABLE_FIELDS)
def record_success(self, plugin_id: str) -> None:
"""Record a successful plugin execution."""
state = self.get_health_state(plugin_id)
current_time = time.time()
durable_before = self._durable(state)
# Reset consecutive failures
state['consecutive_failures'] = 0
state['total_successes'] = state.get('total_successes', 0) + 1
@@ -198,9 +208,20 @@ class PluginHealthTracker:
# Shouldn't happen, but handle it
state['circuit_state'] = CircuitState.CLOSED.value
state['circuit_opened_time'] = None
self._save_health_state(plugin_id, state)
# A healthy plugin reports success every cycle, and in that steady state
# the only fields changed above are a counter and a timestamp that
# nothing reads back after a restart. Persisting them anyway rewrites a
# small file per plugin per cycle: on a rig running 24 plugins, a
# five-minute sample measured 22 rewrites, about 4.4 a minute or 6,300 a
# day. Those land on an SD card, where the cost is an erase-block cycle
# rather than the 400 bytes involved, and where wear is what eventually
# kills the card.
# In-memory state is still updated every time, so the health API and web
# UI show exactly what they did before; only the write is skipped.
if self._durable(state) != durable_before:
self._save_health_state(plugin_id, state)
def record_failure(self, plugin_id: str, error: Optional[Exception] = None) -> None:
"""Record a failed plugin execution."""
state = self.get_health_state(plugin_id)
-143
View File
@@ -1,143 +0,0 @@
"""GET /config/main must not hand out credentials.
The endpoint returned the raw config to anyone who could reach the port, and
this web interface has no authentication of any kind. Measured against a live
rig, an unauthenticated request returned:
github.api_token 40 chars
incoming-packages.ha_token 183 chars
jellyfin-now-playing.api_key 32 chars
ledmatrix-weather.api_key 32 chars
on-air.mqtt_password 8 chars
youtube.api_key 20 chars
youtube-stats.api_key 39 chars
A GitHub token and a Home Assistant long-lived token among them.
The x-secret masking the plugin config endpoints use does not apply here: this
endpoint never consults a schema, and core keys such as github.api_token have
no schema to carry the marker. Several of those fields *are* tagged x-secret in
their plugin's schema and were still returned in full, which is what makes the
schema route the wrong one to rely on for this endpoint.
Matching on field name is blunt. For a whole-config dump it is the right
default: anything named like a credential should not leave the process, and a
new plugin that adds a differently-shaped secret is covered without anyone
remembering to tag it.
"""
import pytest
from web_interface.blueprints.api_v3 import (
_looks_like_a_credential,
_redact_credentials,
)
@pytest.mark.parametrize("name", [
"password", "mqtt_password", "opensky_password", "passwd",
"api_key", "apikey", "API_KEY", "flightaware_api_key",
"token", "ha_token", "api_token", "access_token",
"secret", "client_secret", "spotify_client_secret",
"access_key", "private_key",
])
def test_credential_names_are_recognised(name):
assert _looks_like_a_credential(name)
@pytest.mark.parametrize("name", [
"timezone", "city", "brightness", "enabled", "update_interval",
"favorite_teams", "display_duration", "keyword",
])
def test_ordinary_names_are_left_alone(name):
assert not _looks_like_a_credential(name)
def test_the_measured_leak_is_closed():
"""The exact shape taken off the rig."""
config = {
"github": {"api_token": "ghp_" + "x" * 36},
"incoming-packages": {"ha_token": "y" * 183, "enabled": True},
"jellyfin-now-playing": {"api_key": "z" * 32},
"on-air": {"mqtt_password": "hunter22"},
"youtube": {"api_key": "k" * 20},
"timezone": "America/New_York",
}
out = _redact_credentials(config)
assert out["github"]["api_token"] == ""
assert out["incoming-packages"]["ha_token"] == ""
assert out["jellyfin-now-playing"]["api_key"] == ""
assert out["on-air"]["mqtt_password"] == ""
assert out["youtube"]["api_key"] == ""
# Everything else survives, or the config editor breaks.
assert out["timezone"] == "America/New_York"
assert out["incoming-packages"]["enabled"] is True
def test_nested_and_listed_credentials_are_reached():
config = {"a": {"b": {"c": {"password": "p"}}},
"feeds": [{"name": "x", "api_key": "k"}, {"name": "y"}]}
out = _redact_credentials(config)
assert out["a"]["b"]["c"]["password"] == ""
assert out["feeds"][0]["api_key"] == ""
assert out["feeds"][0]["name"] == "x"
def test_the_original_is_not_mutated():
"""The caller holds the live config; redaction must not edit it in place."""
config = {"github": {"api_token": "keepme"}}
_redact_credentials(config)
assert config["github"]["api_token"] == "keepme"
def test_a_credential_shaped_container_is_still_walked():
"""`secrets: {...}` is a section name, not a value to blank."""
config = {"secrets": {"api_key": "k", "note": "keep"}}
out = _redact_credentials(config)
assert out["secrets"]["api_key"] == ""
assert out["secrets"]["note"] == "keep"
def test_non_dict_input_passes_through():
assert _redact_credentials("plain") == "plain"
assert _redact_credentials(7) == 7
assert _redact_credentials(None) is None
def test_the_endpoint_itself_redacts():
"""Through the view function, not the helper.
The helper tests above all passed with the route still returning
`config` -- reverting the one line that calls the redactor changed
nothing, because nothing exercised the route. A property asserted on a
helper is not a property asserted on the endpoint, and it is the endpoint
that is exposed to the network.
"""
import json as _json
from unittest.mock import MagicMock
import flask
from web_interface.blueprints import api_v3 as mod
raw = {"github": {"api_token": "ghp_secret_value"},
"timezone": "America/New_York"}
manager = MagicMock()
manager.load_config.return_value = raw
previous = getattr(mod.api_v3, "config_manager", None)
mod.api_v3.config_manager = manager
app = flask.Flask(__name__)
try:
with app.test_request_context("/config/main"):
response = mod.get_main_config()
payload = response.get_json() if hasattr(response, "get_json") else _json.loads(response[0].data)
finally:
mod.api_v3.config_manager = previous
data = payload["data"]
assert data["github"]["api_token"] == "", (
"the endpoint returned the token; the redactor is not wired in")
assert data["timezone"] == "America/New_York"
# And the config the manager handed over is untouched.
assert raw["github"]["api_token"] == "ghp_secret_value"
+110
View File
@@ -0,0 +1,110 @@
"""A healthy plugin must not rewrite its health record every cycle.
Every successful plugin update called record_success(), which persisted the
record unconditionally. In steady state the only fields that had changed were
total_successes and last_success_time -- a counter and a timestamp that
health_monitor reads for display and that nothing reads back after a restart.
Measured on a rig running 24 plugins: about 17 health-file rewrites a minute,
roughly 25,000 a day. Each is ~400 bytes, but they land on an SD card where
the unit of cost is an erase-block cycle, not the byte count, and where wear is
what eventually kills the card.
The circuit breaker still needs its own state to survive a restart, so the
write is kept for exactly the fields it is rebuilt from -- and a failure, a
circuit opening, or a recovery must still be written the moment it happens.
"""
import time
import pytest
from src.plugin_system.plugin_health import PluginHealthTracker, CircuitState
class _Cache:
"""Counts writes; serves back whatever was last written."""
def __init__(self):
self.store = {}
self.writes = 0
def set(self, key, data, ttl=None, **kwargs):
self.writes += 1
self.store[key] = data
def get(self, key, max_age=None, memory_ttl=None, **kwargs):
return self.store.get(key)
@pytest.fixture
def tracker():
cache = _Cache()
t = PluginHealthTracker(cache_manager=cache)
return t, cache
def test_steady_state_success_stops_writing(tracker):
"""The regression: 100 healthy cycles used to be 100 SD writes."""
t, cache = tracker
t.record_success("weather")
first = cache.writes
for _ in range(100):
t.record_success("weather")
assert cache.writes == first, (
f"{cache.writes - first} redundant writes across 100 healthy cycles"
)
def test_the_counters_are_still_accurate_in_memory(tracker):
"""Skipping the write must not skip the bookkeeping."""
t, _ = tracker
for _ in range(10):
t.record_success("weather")
state = t.get_health_state("weather")
assert state["total_successes"] == 10
assert state["last_success_time"] is not None
assert state["last_success_time"] <= time.time()
def test_a_failure_is_written_immediately(tracker):
t, cache = tracker
t.record_success("weather")
before = cache.writes
t.record_failure("weather", RuntimeError("boom"))
assert cache.writes > before, "a failure must reach disk"
def test_recovery_after_failure_is_written(tracker):
"""consecutive_failures returning to 0 is durable state changing."""
t, cache = tracker
t.record_failure("weather", RuntimeError("boom"))
before = cache.writes
t.record_success("weather")
assert cache.writes > before, "recovery must reach disk"
assert t.get_health_state("weather")["consecutive_failures"] == 0
def test_a_closing_circuit_is_written(tracker):
"""Success in half-open closes the circuit -- that must survive a restart."""
t, cache = tracker
state = t.get_health_state("weather")
state["circuit_state"] = CircuitState.HALF_OPEN.value
state["half_open_start_time"] = time.time()
before = cache.writes
t.record_success("weather")
assert cache.writes > before, "a circuit transition must reach disk"
assert t.get_health_state("weather")["circuit_state"] == CircuitState.CLOSED.value
def test_durable_state_survives_a_restart(tracker):
"""What is skipped must genuinely not matter to the breaker."""
t, cache = tracker
for _ in range(3):
t.record_failure("weather", RuntimeError("boom"))
for _ in range(50):
t.record_success("weather")
revived = PluginHealthTracker(cache_manager=cache)
state = revived.get_health_state("weather")
assert state["consecutive_failures"] == 0
assert state["circuit_state"] == CircuitState.CLOSED.value
+2 -41
View File
@@ -262,54 +262,15 @@ def _stop_display_service():
result['status'] = status
return result
#: Field names whose value is a credential. Matched by name because this
#: endpoint returns the whole config, core keys included, and core config has
#: no schema to carry x-secret markers.
_CREDENTIAL_NAME_PARTS = ("password", "passwd", "secret", "token", "api_key",
"apikey", "access_key", "private_key", "client_secret")
def _looks_like_a_credential(name: str) -> bool:
lowered = name.lower()
return any(part in lowered for part in _CREDENTIAL_NAME_PARTS)
def _redact_credentials(value):
"""A copy of `value` with credential-named fields blanked.
/config/main returned the raw config to anyone who could reach the port,
and this interface has no authentication. On one rig that meant a 40-char
GitHub token, a 183-char Home Assistant token and five API keys were
readable by anything on the LAN.
The x-secret masking used by the plugin config endpoints does not help
here: this endpoint never consults a schema, and core keys such as
github.api_token have no schema to mark. Matching on the field name is
blunt, but for a whole-config dump the right default is that anything
named like a credential does not leave the process.
Blanked rather than removed, and safe to blank: POST /config/main merges
into the loaded config and only writes the keys it was given, so a client
that round-trips this response cannot erase a secret it never saw.
"""
if isinstance(value, dict):
return {k: ("" if _looks_like_a_credential(k) and not isinstance(v, (dict, list))
else _redact_credentials(v))
for k, v in value.items()}
if isinstance(value, list):
return [_redact_credentials(item) for item in value]
return value
@api_v3.route('/config/main', methods=['GET'])
def get_main_config():
"""Get main configuration, with credentials redacted."""
"""Get main configuration"""
try:
if not api_v3.config_manager:
return jsonify({'status': 'error', 'message': 'Config manager not initialized'}), 500
config = api_v3.config_manager.load_config()
return jsonify({'status': 'success', 'data': _redact_credentials(config)})
return jsonify({'status': 'success', 'data': config})
except Exception as e:
logger.error('Unhandled exception', exc_info=True)
return jsonify({'status': 'error', 'message': 'An error occurred; see logs for details', 'details': describe_exception(e)}), 500