andreas/heartbeat
Public Access
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases 44 Wiki Activity

threshold: synthesize health_ok server-side for older ZFS clients

Browse Source 
Older hbd clients send zfs_monitor data with a `health` string but no
`health_ok` numeric field (added in a recent plugin update). Without
health_ok in the data, the wildcard threshold check found nothing and
no CRITICAL alert was raised for DEGRADED/SUSPENDED pools.

Synthesize health_ok from the health string in the server's nested-
metric loop so alerts fire regardless of client version.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Andreas Wrede
2026-05-08 16:39:16 -04:00
parent c20245b0ab
commit 967e05ed74
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hbd/server/threshold.py
+7 -2
View File
@@ -1026,7 +1026,12 @@ class ThresholdChecker:
for pool_name, pool_metrics in pools.items(): for pool_name, pool_metrics in pools.items():
if not isinstance(pool_metrics, dict): if not isinstance(pool_metrics, dict):
continue continue
for metric_name, value in pool_metrics.items(): # Synthesize health_ok from health string for older clients
# that predate the health_ok field.
pool_metrics_effective = dict(pool_metrics)
if "health" in pool_metrics and "health_ok" not in pool_metrics:
pool_metrics_effective["health_ok"] = 1 if pool_metrics["health"] == "ONLINE" else 0
for metric_name, value in pool_metrics_effective.items():
# Try specific pool name first, then wildcard '*' # Try specific pool name first, then wildcard '*'
metric_path = f"{plugin_name}.{pool_name}.{metric_name}" metric_path = f"{plugin_name}.{pool_name}.{metric_name}"
wildcard_path = f"{plugin_name}.*.{metric_name}" wildcard_path = f"{plugin_name}.*.{metric_name}"
@@ -1043,7 +1048,7 @@ class ThresholdChecker:
elif new_level == AlertLevel.WARNING and threshold.warning is not None: elif new_level == AlertLevel.WARNING and threshold.warning is not None:
threshold_value = threshold.warning threshold_value = threshold.warning
alert_state.hysteresis = threshold.hysteresis if new_level != AlertLevel.OK else None alert_state.hysteresis = threshold.hysteresis if new_level != AlertLevel.OK else None
pool_context = dict(pool_metrics) pool_context = dict(pool_metrics_effective)
pool_context["pool_name"] = pool_name pool_context["pool_name"] = pool_name
old_level = alert_state.level old_level = alert_state.level
if alert_state.update(new_level, value, threshold_value, threshold.operator.value): if alert_state.update(new_level, value, threshold_value, threshold.operator.value):