perf(plugins): stop rewriting a plugin's metrics file on every call

src/plugin_system/resource_monitor.py

@@ -49,6 +49,20 @@ def update_average_execution_time(self):
             self.total_execution_time = self.total_execution_time / self.call_count
 
 
+#: How often a plugin's metrics are written to the cache, in seconds.
+#:
+#: Persisting on every call meant a small file rewritten roughly nine times a
+#: minute per plugin. On a rig with fourteen active plugins that was ~126
+#: writes a minute for metrics alone, and since each ~350-byte file costs a
+#: 4KB block plus an ext4 journal entry, it dominated the device's write
+#: volume -- on an SD card, which wears out.
+#:
+#: The in-memory copy stays authoritative and exact; only the cross-process
+#: snapshot the web UI reads is delayed, and telemetry up to half a minute old
+#: is still a fair description of a long-running plugin.
+_METRICS_PERSIST_INTERVAL = 30.0
+
+
 class PluginResourceMonitor:
     """
     Monitors resource usage for plugins.
@@ -75,6 +89,10 @@ def __init__(self, cache_manager, enable_monitoring: bool = True):
         # Resource metrics per plugin
         self._metrics: Dict[str, ResourceMetrics] = {}
         self._limits: Dict[str, ResourceLimits] = {}
+        # When each plugin's metrics last reached the cache. Metrics change on
+        # every call, so they cannot be de-duplicated the way health state can;
+        # they are rate-limited instead. See _METRICS_PERSIST_INTERVAL.
+        self._metrics_persisted_at: Dict[str, float] = {}
 
         # Thread-local storage for execution tracking
         self._local = threading.local()
@@ -232,18 +250,8 @@ def monitor_call(self, plugin_id: str, func: Callable, *args, **kwargs) -> Any:
                     # CPU is harder to measure per-call, so we track it separately
                     metrics.cpu_percent = self._get_process_cpu_percent()
 
-                # Persist metrics
-                cache_key = self._get_metrics_key(plugin_id)
-                self.cache_manager.set(cache_key, {
-                    'memory_mb': metrics.memory_mb,
-                    'cpu_percent': metrics.cpu_percent,
-                    'execution_time': metrics.execution_time,
-                    'call_count': metrics.call_count,
-                    'total_execution_time': metrics.total_execution_time,
-                    'max_execution_time': metrics.max_execution_time,
-                    'min_execution_time': metrics.min_execution_time if metrics.min_execution_time != float('inf') else 0.0,
-                    'last_update_time': metrics.last_update_time
-                })
+                # Persist metrics, at most once per interval per plugin.
+                self._persist_metrics(plugin_id, metrics)
 
             # Check limits
             if limits:
@@ -363,11 +371,45 @@ def get_all_metrics_summaries(self) -> Dict[str, Dict[str, Any]]:
             summaries[plugin_id] = self.get_metrics_summary(plugin_id)
         return summaries
 
+    def _persist_metrics(self, plugin_id: str, metrics: ResourceMetrics,
+                         force: bool = False) -> None:
+        """Write a plugin's metrics to the cache, at most once per interval.
+
+        Caller must hold ``self._lock``.
+        """
+        # Monotonic, not wall clock: these devices have no RTC, so the clock
+        # jumps by however far off boot-time was the moment NTP first syncs.
+        # A forward jump would allow an early write, a backward one would
+        # stall the snapshot well past the interval.
+        now = time.monotonic()
+        if not force and now - self._metrics_persisted_at.get(plugin_id, 0.0) \
+                < _METRICS_PERSIST_INTERVAL:
+            return
+        cache_key = self._get_metrics_key(plugin_id)
+        self.cache_manager.set(cache_key, {
+            'memory_mb': metrics.memory_mb,
+            'cpu_percent': metrics.cpu_percent,
+            'execution_time': metrics.execution_time,
+            'call_count': metrics.call_count,
+            'total_execution_time': metrics.total_execution_time,
+            'max_execution_time': metrics.max_execution_time,
+            'min_execution_time': (metrics.min_execution_time
+                                   if metrics.min_execution_time != float('inf')
+                                   else 0.0),
+            'last_update_time': metrics.last_update_time,
+        })
+        # Only after the write lands. Marking it first would mean a failed
+        # set() bought the next interval's silence without leaving a snapshot.
+        self._metrics_persisted_at[plugin_id] = now
+
     def reset_metrics(self, plugin_id: str) -> None:
         """Reset metrics for a plugin."""
         with self._lock:
             if plugin_id in self._metrics:
                 self._metrics[plugin_id] = ResourceMetrics()
                 cache_key = self._get_metrics_key(plugin_id)
                 self.cache_manager.delete(cache_key)
+                # Let the next call persist immediately rather than leaving the
+                # deleted key absent for the rest of the interval.
+                self._metrics_persisted_at.pop(plugin_id, None)
 

test/test_resource_monitor.py

@@ -127,3 +127,67 @@ def cache_get(key, max_age=None, memory_ttl=None):
         fresh = mon.get_metrics_summary("p", force_reload=True)
         assert fresh["call_count"] == 7
         assert any(c.kwargs.get("memory_ttl") == 0 for c in cache.get.call_args_list)
+
+
+class TestMetricsPersistenceChurn:
+    """Metrics are telemetry; writing them on every call wore the SD card.
+
+    Each write is a ~350-byte file, which on ext4 costs a 4KB block plus a
+    journal entry. At roughly nine calls a minute per plugin across fourteen
+    plugins it dominated the device's write volume.
+    """
+
+    def test_repeated_calls_persist_once_per_interval(self):
+        cache = _cache()
+        mon = PluginResourceMonitor(cache, enable_monitoring=False)
+        for _ in range(50):
+            mon.monitor_call("p", lambda: None)
+        writes = [c for c in cache.set.call_args_list
+                  if c.args and str(c.args[0]).startswith("plugin_metrics:")]
+        assert len(writes) == 1, (
+            f"50 calls produced {len(writes)} metric writes; expected 1")
+
+    def test_the_interval_elapsing_allows_the_next_write(self, monkeypatch):
+        import src.plugin_system.resource_monitor as rm
+        cache = _cache()
+        mon = PluginResourceMonitor(cache, enable_monitoring=False)
+        mon.monitor_call("p", lambda: None)
+        # pretend the interval has passed
+        mon._metrics_persisted_at["p"] -= rm._METRICS_PERSIST_INTERVAL + 1
+        mon.monitor_call("p", lambda: None)
+        writes = [c for c in cache.set.call_args_list
+                  if c.args and str(c.args[0]).startswith("plugin_metrics:")]
+        assert len(writes) == 2
+
+    def test_in_memory_metrics_stay_exact_while_writes_are_skipped(self):
+        mon = PluginResourceMonitor(_cache(), enable_monitoring=False)
+        for _ in range(20):
+            mon.monitor_call("p", lambda: None)
+        assert mon.get_metrics("p").call_count == 20
+
+    def test_reset_lets_the_next_call_persist_immediately(self):
+        cache = _cache()
+        mon = PluginResourceMonitor(cache, enable_monitoring=False)
+        mon.monitor_call("p", lambda: None)
+        mon.reset_metrics("p")
+        mon.monitor_call("p", lambda: None)
+        writes = [c for c in cache.set.call_args_list
+                  if c.args and str(c.args[0]).startswith("plugin_metrics:")]
+        assert len(writes) == 2, "reset should clear the throttle timestamp"
+
+    def test_a_failed_write_does_not_buy_the_next_interval_of_silence(self):
+        """A set() that raises must not count as having persisted.
+
+        Marking the timestamp before the write would leave no snapshot in the
+        cache and still suppress the next 30 seconds of attempts.
+        """
+        cache = _cache()
+        cache.set.side_effect = [OSError("disk full"), None]
+        mon = PluginResourceMonitor(cache, enable_monitoring=False)
+        with pytest.raises(OSError):
+            mon.monitor_call("p", lambda: None)
+        # the very next call must try again rather than skip the interval
+        mon.monitor_call("p", lambda: None)
+        writes = [c for c in cache.set.call_args_list
+                  if c.args and str(c.args[0]).startswith("plugin_metrics:")]
+        assert len(writes) == 2, "a failed write should be retried, not skipped"