Merge branch 'perf/runtime-observability' of https://github.com/ChuckBuilds/LEDMatrix into consolidate/perf

This commit is contained in:
ChuckBuilds
2026-08-20 17:45:20 -04:00
8 changed files with 436 additions and 64 deletions
+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
+101
View File
@@ -0,0 +1,101 @@
"""Log lines must reach the journal with their real severity.
Everything this process writes to stdout lands in the journal as PRIORITY=6,
whatever the Python level was, because journald has no other signal. Measured
on a live rig over 24 hours: 55 lines containing " - ERROR - " and 13
containing " - WARNING - ", every one of them recorded as informational. So
journalctl -p err -u ledmatrix
returned nothing while errors were being logged, and anyone triaging has to
grep the message text instead. That is slower and it is wrong: a search for
"oom" also matches the radar logging "zoom=9", which is exactly the false
positive it produced during this audit.
systemd reads a leading "<N>" on each stdout line and uses it as the priority
(sd-daemon(3)), so this needs no extra dependency -- and it must only be
applied when systemd is actually reading, or the prefixes become literal noise
in a terminal, the emulator, and test output.
"""
import logging
import os
from unittest.mock import patch
import pytest
from src.logging_config import JournalPriorityFormatter, _SYSLOG_PRIORITY, _under_systemd
class _Plain(logging.Formatter):
def format(self, record):
return record.getMessage()
def _record(level, msg="hello"):
return logging.LogRecord("t", level, "f.py", 1, msg, None, None)
@pytest.mark.parametrize("level,expected", [
(logging.CRITICAL, 2),
(logging.ERROR, 3),
(logging.WARNING, 4),
(logging.INFO, 6),
(logging.DEBUG, 7),
])
def test_each_level_maps_to_its_syslog_priority(level, expected):
out = JournalPriorityFormatter(_Plain()).format(_record(level))
assert out.startswith(f"<{expected}>"), out
assert _SYSLOG_PRIORITY[level] == expected
def test_error_and_info_are_distinguishable():
"""The whole point: journalctl -p err must be able to tell them apart."""
fmt = JournalPriorityFormatter(_Plain())
assert fmt.format(_record(logging.ERROR))[:3] != fmt.format(_record(logging.INFO))[:3]
def test_every_line_of_a_multiline_record_is_tagged():
"""The journal splits them, and an untagged continuation loses its level.
A traceback is the case that matters -- it is the most important thing in
the log and the longest.
"""
out = JournalPriorityFormatter(_Plain()).format(
_record(logging.ERROR, "Traceback:\nline one\nline two"))
lines = out.split("\n")
assert len(lines) == 3
assert all(line.startswith("<3>") for line in lines), lines
def test_the_message_survives_intact():
out = JournalPriorityFormatter(_Plain()).format(_record(logging.WARNING, "disk full"))
assert out == "<4>disk full"
def test_an_unknown_level_falls_back_to_info():
out = JournalPriorityFormatter(_Plain()).format(_record(25))
assert out.startswith("<6>")
def test_prefixing_is_off_outside_systemd():
"""Otherwise a terminal run, the emulator and pytest all show `<6>`."""
with patch.dict(os.environ, {}, clear=True):
assert not _under_systemd()
with patch.dict(os.environ, {"JOURNAL_STREAM": "8:12345"}):
assert _under_systemd()
def test_setup_uses_the_wrapper_only_under_systemd():
from src.logging_config import setup_logging
for env, expect_wrapped in (({}, False), ({"JOURNAL_STREAM": "8:1"}, True)):
with patch.dict(os.environ, env, clear=True):
setup_logging()
handlers = [h for h in logging.getLogger().handlers
if isinstance(h, logging.StreamHandler)]
assert handlers, "no stream handler installed"
wrapped = any(isinstance(h.formatter, JournalPriorityFormatter)
for h in handlers)
assert wrapped is expect_wrapped, (
f"JOURNAL_STREAM={env}: wrapped={wrapped}, expected {expect_wrapped}")
logging.getLogger().handlers.clear()
+16 -4
View File
@@ -183,15 +183,27 @@ class TestSetupLogging:
setup_logging()
assert len(logging.getLogger().handlers) == 1
@staticmethod
def _selected_formatter():
"""The formatter setup_logging() chose, past any journald wrapper.
Under systemd the console handler's formatter is wrapped so each line
carries its syslog priority. That wrapper is applied only when
JOURNAL_STREAM is set, which is true in CI and false in a terminal, so
asserting on the handler's formatter directly passes locally and fails
on the runner. These tests are about which formatter format_type
selects, so they look through the wrapper.
"""
formatter = logging.getLogger().handlers[0].formatter
return getattr(formatter, "inner", formatter)
def test_json_format_selects_structured_formatter(self):
setup_logging(format_type="json")
assert isinstance(
logging.getLogger().handlers[0].formatter, StructuredFormatter)
assert isinstance(self._selected_formatter(), StructuredFormatter)
def test_readable_format_selects_contextual_formatter(self):
setup_logging(format_type="readable")
assert isinstance(
logging.getLogger().handlers[0].formatter, ContextualFormatter)
assert isinstance(self._selected_formatter(), ContextualFormatter)
def test_log_file_adds_file_handler(self, tmp_path):
log_file = tmp_path / "test.log"
+63
View File
@@ -0,0 +1,63 @@
"""The Vegas content path must trace at DEBUG, not INFO.
plugin_adapter narrates every step of acquiring content from every plugin --
"Has get_vegas_content", "Native: calling get_vegas_content()", "Native content
returned None", "Has scroll_helper", the per-item sizes -- and it does that for
each plugin on each cycle.
Measured on a live rig: 13,408 log lines an hour, of which 13,366 were INFO and
35 were WARNING. plugin_adapter alone produced 2,457 of them. That is ~223
lines a minute of string formatting on a Pi that is also driving the panel, all
of it written through journald to the SD card, and it buries the 35 lines that
actually indicate a problem.
Nothing is lost by moving it to DEBUG: the 19 warning/error/exception calls in
the module are untouched, so real failures still surface at their own level.
One INFO call is deliberate and stays -- the padding-strip message chooses its
level at runtime (`logger.warning if (left and right) else logger.info`) and
test_vegas_plugin_adapter.py pins it.
"""
import ast
from pathlib import Path
import pytest
ADAPTER = (Path(__file__).resolve().parent.parent / "src" / "vegas_mode"
/ "plugin_adapter.py")
def _info_calls(path):
"""Direct logger.info(...) call sites in a module."""
tree = ast.parse(path.read_text(encoding="utf-8"))
found = []
for node in ast.walk(tree):
if (isinstance(node, ast.Call)
and isinstance(node.func, ast.Attribute)
and node.func.attr == "info"
and getattr(node.func.value, "id", None) == "logger"):
found.append(node.lineno)
return found
def test_the_content_path_does_not_trace_at_info():
calls = _info_calls(ADAPTER)
assert not calls, (
"plugin_adapter should trace at DEBUG; found logger.info at lines "
f"{calls}. This path runs per plugin per cycle and its output goes to "
"the SD card via journald."
)
def test_real_failures_still_have_a_level_of_their_own():
"""Demoting the trace must not have swept up the error reporting."""
source = ADAPTER.read_text(encoding="utf-8")
loud = sum(source.count(f"logger.{level}(")
for level in ("warning", "error", "exception"))
assert loud >= 15, f"only {loud} warning/error/exception calls remain"
def test_the_deliberate_runtime_chosen_level_survives():
"""The padding-strip message picks its level at runtime; leave it alone."""
source = ADAPTER.read_text(encoding="utf-8")
assert "logger.warning if (left and right) else logger.info" in source