feat: generic threshold matching for nagios_runner with {check_name} display support
_find_threshold() now returns the stripped prefix ("check_name") alongside
the ThresholdConfig, enabling a single generic entry (e.g. nagios_runner.status_code)
to cover all per-command metrics (check_disk_root_status_code, check_load_status_code,
…). The prefix is threaded through to _format_display() as {check_name}, with
{metric_name} also available in display templates. purge_stale_alerts() updated
to use generic matching so it does not incorrectly drop alerts on generic-matched
metrics. README updated with Display Format Templates and Generic Threshold
Matching sections.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -181,7 +181,8 @@ thresholds:
|
||||
warning: 80.0 # Warn when CPU > 80%
|
||||
critical: 90.0 # Critical when CPU > 90%
|
||||
operator: ">"
|
||||
hysteresis: 0.1 # 10% hysteresis to prevent flapping
|
||||
hysteresis: 0.02 # 2% hysteresis to prevent flapping
|
||||
display: "(threshold: {op_symbol} {threshold_value}%)" # optional
|
||||
|
||||
memory_monitor:
|
||||
percent:
|
||||
@@ -274,7 +275,59 @@ All plugin metrics can be thresholded:
|
||||
- **Memory**: percent, available_mb, swap_percent
|
||||
- **Disk**: Per-partition percent, free_gb, free_mb
|
||||
- **Network**: errors_total, dropped packets, connection counts
|
||||
- **Nagios**: exit_code mapping (0=OK, 1=WARNING, 2=CRITICAL)
|
||||
- **Nagios**: Any field emitted by `nagios_runner` (status_code, exit_code, performance data, …)
|
||||
|
||||
### Display Format Templates
|
||||
|
||||
Each threshold entry accepts an optional `display` field — a Python format string shown in notifications and on the Alerts dashboard:
|
||||
|
||||
```yaml
|
||||
nagios_runner:
|
||||
status_code:
|
||||
warning: 1
|
||||
critical: 2
|
||||
operator: ">="
|
||||
display: "{check_name}: exit {value} (expected < {threshold_value})"
|
||||
```
|
||||
|
||||
Available variables:
|
||||
|
||||
| Variable | Description |
|
||||
|---|---|
|
||||
| `{value}` | Current metric value |
|
||||
| `{threshold_value}` | Threshold that was crossed |
|
||||
| `{op_symbol}` | Comparison operator (`>`, `<`, `>=`, …) |
|
||||
| `{check_name}` | Prefix stripped by generic matching (see below) |
|
||||
| `{metric_name}` | Full field name within the plugin data |
|
||||
| any plugin field | Any other field present in the plugin's data |
|
||||
|
||||
### Generic Threshold Matching
|
||||
|
||||
When a metric name has no exact threshold entry, the server progressively strips leading underscore-separated segments and re-tries the lookup. This lets a single generic entry cover an entire family of metrics.
|
||||
|
||||
The classic use case is `nagios_runner`, which names each metric after the command that produced it:
|
||||
|
||||
```
|
||||
nagios_runner.check_disk_root_status_code → no exact match
|
||||
nagios_runner.disk_root_status_code → no match
|
||||
nagios_runner.root_status_code → no match
|
||||
nagios_runner.status_code → matched ✓
|
||||
```
|
||||
|
||||
Configure the generic threshold once:
|
||||
|
||||
```yaml
|
||||
nagios_runner:
|
||||
status_code:
|
||||
warning: 1
|
||||
critical: 2
|
||||
operator: ">="
|
||||
display: "{check_name}: exit {value}"
|
||||
```
|
||||
|
||||
The stripped prefix (`check_disk_root` in the example above) is available as `{check_name}` in the display template, so you can identify which check triggered the alert without writing a separate threshold entry per command.
|
||||
|
||||
Exact matches always take priority. A generic entry only applies when no specific one is defined.
|
||||
|
||||
### Per-Host Threshold Profiles
|
||||
|
||||
|
||||
+72
-35
@@ -823,26 +823,33 @@ class ThresholdChecker:
|
||||
return None
|
||||
def _find_threshold(
|
||||
self, thresholds: Dict[str, "ThresholdConfig"], metric_path: str
|
||||
) -> Optional["ThresholdConfig"]:
|
||||
"""Return the threshold for *metric_path*, falling back to suffix matches.
|
||||
) -> Tuple[Optional["ThresholdConfig"], Optional[str]]:
|
||||
"""Return (threshold, check_name) for *metric_path*, falling back to suffix matches.
|
||||
|
||||
Allows generic thresholds like ``ping_monitor.rtt_avg`` to match
|
||||
fully-qualified paths like ``ping_monitor.8_8_8_8_rtt_avg``.
|
||||
Allows generic thresholds like ``nagios_runner.status_code`` to match
|
||||
fully-qualified paths like ``nagios_runner.check_disk_root_status_code``.
|
||||
The exact match is always tried first; then successive leading
|
||||
underscore-delimited segments are stripped from the field name until
|
||||
a match is found or no segments remain.
|
||||
|
||||
Returns:
|
||||
(ThresholdConfig, None) for an exact match.
|
||||
(ThresholdConfig, "check_disk_root") for a suffix match — the second
|
||||
element is the stripped prefix, available as ``{check_name}`` in
|
||||
display format templates.
|
||||
(None, None) when no threshold is found.
|
||||
"""
|
||||
if metric_path in thresholds:
|
||||
return thresholds[metric_path]
|
||||
return thresholds[metric_path], None
|
||||
plugin, sep, field = metric_path.partition(".")
|
||||
if not sep:
|
||||
return None
|
||||
return None, None
|
||||
parts = field.split("_")
|
||||
for i in range(1, len(parts)):
|
||||
candidate = plugin + "." + "_".join(parts[i:])
|
||||
if candidate in thresholds:
|
||||
return thresholds[candidate]
|
||||
return None
|
||||
return thresholds[candidate], "_".join(parts[:i])
|
||||
return None, None
|
||||
|
||||
def check_plugin_data(
|
||||
self,
|
||||
@@ -871,23 +878,23 @@ class ThresholdChecker:
|
||||
# Check flat metrics
|
||||
for metric_name, value in data.items():
|
||||
metric_path = f"{plugin_name}.{metric_name}"
|
||||
|
||||
threshold = self._find_threshold(thresholds, metric_path)
|
||||
|
||||
threshold, check_name = self._find_threshold(thresholds, metric_path)
|
||||
if threshold is None:
|
||||
continue
|
||||
|
||||
|
||||
# Get or create alert state
|
||||
if metric_path not in alert_states:
|
||||
alert_states[metric_path] = AlertState(metric_path)
|
||||
|
||||
|
||||
alert_state = alert_states[metric_path]
|
||||
|
||||
|
||||
# Evaluate threshold with hysteresis
|
||||
new_level = threshold.evaluate_with_hysteresis(
|
||||
value,
|
||||
alert_state.level
|
||||
)
|
||||
|
||||
|
||||
# Determine which threshold was exceeded
|
||||
threshold_value = None
|
||||
if new_level == AlertLevel.CRITICAL and threshold.critical is not None:
|
||||
@@ -901,9 +908,9 @@ class ThresholdChecker:
|
||||
old_level = alert_state.level
|
||||
if alert_state.update(new_level, value, threshold_value, threshold.operator.value):
|
||||
state_changes.append((metric_path, old_level, new_level, value))
|
||||
self._apply_grace(host_name, alert_state, metric_path, old_level, new_level, value, threshold, data)
|
||||
self._apply_grace(host_name, alert_state, metric_path, old_level, new_level, value, threshold, data, check_name=check_name, metric_name=metric_name)
|
||||
elif new_level != AlertLevel.OK:
|
||||
self._check_pending_or_renotify(host_name, alert_state, metric_path, value, threshold, data)
|
||||
self._check_pending_or_renotify(host_name, alert_state, metric_path, value, threshold, data, check_name=check_name, metric_name=metric_name)
|
||||
|
||||
# Check nested metrics (e.g., partition data in disk_monitor)
|
||||
self._check_nested_metrics(
|
||||
@@ -981,6 +988,8 @@ class ThresholdChecker:
|
||||
value: Any,
|
||||
threshold: ThresholdConfig,
|
||||
plugin_data: Optional[Dict[str, Any]] = None,
|
||||
check_name: Optional[str] = None,
|
||||
metric_name: Optional[str] = None,
|
||||
):
|
||||
"""Trigger a notification for an alert state change.
|
||||
|
||||
@@ -1019,7 +1028,9 @@ class ThresholdChecker:
|
||||
value=display_value,
|
||||
threshold_value=threshold_value,
|
||||
op_symbol=op_symbol,
|
||||
plugin_data=plugin_data
|
||||
plugin_data=plugin_data,
|
||||
check_name=check_name,
|
||||
metric_name=metric_name,
|
||||
)
|
||||
message = f"{metric_path} = {display_value} {threshold_info}"
|
||||
else:
|
||||
@@ -1032,7 +1043,9 @@ class ThresholdChecker:
|
||||
value=display_value,
|
||||
threshold_value=threshold_value,
|
||||
op_symbol=op_symbol,
|
||||
plugin_data=plugin_data
|
||||
plugin_data=plugin_data,
|
||||
check_name=check_name,
|
||||
metric_name=metric_name,
|
||||
)
|
||||
message = f"{metric_path} = {display_value} {threshold_info}"
|
||||
else:
|
||||
@@ -1040,7 +1053,7 @@ class ThresholdChecker:
|
||||
else:
|
||||
lvl = "UNKNOWN"
|
||||
message = f"{metric_path} = {display_value}"
|
||||
|
||||
|
||||
# Return the formatted threshold info for storing in AlertState
|
||||
formatted_threshold_msg = None
|
||||
if threshold_value is not None and new_level != AlertLevel.OK:
|
||||
@@ -1049,9 +1062,11 @@ class ThresholdChecker:
|
||||
value=display_value,
|
||||
threshold_value=threshold_value,
|
||||
op_symbol=op_symbol,
|
||||
plugin_data=plugin_data
|
||||
plugin_data=plugin_data,
|
||||
check_name=check_name,
|
||||
metric_name=metric_name,
|
||||
)
|
||||
|
||||
|
||||
return lvl, message, formatted_threshold_msg
|
||||
|
||||
def _send_notification(
|
||||
@@ -1102,16 +1117,22 @@ class ThresholdChecker:
|
||||
threshold_value: float,
|
||||
op_symbol: str,
|
||||
plugin_data: Optional[Dict[str, Any]] = None,
|
||||
check_name: Optional[str] = None,
|
||||
metric_name: Optional[str] = None,
|
||||
) -> str:
|
||||
"""Format the display string using available data.
|
||||
|
||||
Args:
|
||||
display_format: Format string from threshold config
|
||||
value: Current metric value
|
||||
threshold_value: Threshold value that was exceeded
|
||||
op_symbol: Comparison operator symbol
|
||||
plugin_data: Optional dictionary of plugin data fields
|
||||
|
||||
|
||||
Available template variables:
|
||||
{value} - current metric value
|
||||
{threshold_value} - threshold that was exceeded
|
||||
{op_symbol} - comparison operator (>, <, >=, <=, ==, !=)
|
||||
{check_name} - prefix stripped for generic threshold match
|
||||
(e.g. "check_disk_root" when metric
|
||||
"check_disk_root_status_code" matched generic
|
||||
threshold "status_code")
|
||||
{metric_name} - field name within the plugin data dict
|
||||
Any key from plugin_data is also available.
|
||||
|
||||
Returns:
|
||||
Formatted display string
|
||||
"""
|
||||
@@ -1121,7 +1142,13 @@ class ThresholdChecker:
|
||||
'threshold_value': threshold_value,
|
||||
'op_symbol': op_symbol,
|
||||
}
|
||||
|
||||
|
||||
# Add generic-match context variables when available
|
||||
if check_name is not None:
|
||||
format_context['check_name'] = check_name
|
||||
if metric_name is not None:
|
||||
format_context['metric_name'] = metric_name
|
||||
|
||||
# Add all plugin data fields if available
|
||||
if plugin_data:
|
||||
format_context.update(plugin_data)
|
||||
@@ -1155,6 +1182,8 @@ class ThresholdChecker:
|
||||
value: Any,
|
||||
threshold: ThresholdConfig,
|
||||
plugin_data: Optional[Dict[str, Any]],
|
||||
check_name: Optional[str] = None,
|
||||
metric_name: Optional[str] = None,
|
||||
) -> None:
|
||||
"""Handle a state-change transition with grace-period logic.
|
||||
|
||||
@@ -1167,7 +1196,8 @@ class ThresholdChecker:
|
||||
- Past grace: fires the RECOVER notification normally.
|
||||
"""
|
||||
lvl, message, formatted_msg = self._trigger_notification(
|
||||
host_name, metric_path, old_level, new_level, value, threshold, plugin_data
|
||||
host_name, metric_path, old_level, new_level, value, threshold, plugin_data,
|
||||
check_name=check_name, metric_name=metric_name,
|
||||
)
|
||||
alert_state.formatted_message = formatted_msg
|
||||
|
||||
@@ -1203,6 +1233,8 @@ class ThresholdChecker:
|
||||
value: Any,
|
||||
threshold: ThresholdConfig,
|
||||
plugin_data: Optional[Dict[str, Any]],
|
||||
check_name: Optional[str] = None,
|
||||
metric_name: Optional[str] = None,
|
||||
) -> None:
|
||||
"""Called when alert level is unchanged and non-OK.
|
||||
|
||||
@@ -1212,7 +1244,8 @@ class ThresholdChecker:
|
||||
if alert_state.pending_since is not None:
|
||||
if time.time() - alert_state.pending_since >= self.grace_seconds:
|
||||
lvl, message, formatted_msg = self._trigger_notification(
|
||||
host_name, metric_path, AlertLevel.OK, alert_state.level, value, threshold, plugin_data
|
||||
host_name, metric_path, AlertLevel.OK, alert_state.level, value, threshold, plugin_data,
|
||||
check_name=check_name, metric_name=metric_name,
|
||||
)
|
||||
alert_state.formatted_message = formatted_msg
|
||||
self._send_notification(
|
||||
@@ -1221,7 +1254,7 @@ class ThresholdChecker:
|
||||
alert_state.pending_since = None
|
||||
# else: still within grace window, do nothing
|
||||
else:
|
||||
self._check_renotify(host_name, alert_state, metric_path, value, threshold, plugin_data)
|
||||
self._check_renotify(host_name, alert_state, metric_path, value, threshold, plugin_data, check_name=check_name, metric_name=metric_name)
|
||||
|
||||
def _check_renotify(
|
||||
self,
|
||||
@@ -1231,6 +1264,8 @@ class ThresholdChecker:
|
||||
value: Any,
|
||||
threshold: ThresholdConfig,
|
||||
plugin_data: Optional[Dict[str, Any]] = None,
|
||||
check_name: Optional[str] = None,
|
||||
metric_name: Optional[str] = None,
|
||||
):
|
||||
"""Check if we should send a repeat notification.
|
||||
|
||||
@@ -1277,7 +1312,9 @@ class ThresholdChecker:
|
||||
value=value,
|
||||
threshold_value=threshold_value,
|
||||
op_symbol=op_symbol,
|
||||
plugin_data=plugin_data
|
||||
plugin_data=plugin_data,
|
||||
check_name=check_name,
|
||||
metric_name=metric_name,
|
||||
)
|
||||
message = f"REMINDER ({alert_state.level.name}): {host_name} - {metric_path} = {value} {threshold_info}, ongoing for {int(now - alert_state.since)}s"
|
||||
else:
|
||||
@@ -1310,7 +1347,7 @@ class ThresholdChecker:
|
||||
if not host.alert_states:
|
||||
continue
|
||||
configured = self.get_thresholds_for_host(hostname)
|
||||
stale = [mp for mp in host.alert_states if mp not in configured]
|
||||
stale = [mp for mp in host.alert_states if self._find_threshold(configured, mp)[0] is None]
|
||||
for mp in stale:
|
||||
logger.info(
|
||||
"Purging stale alert state for %s / %s (no threshold configured)",
|
||||
|
||||
Reference in New Issue
Block a user