Publish

dist/rules/host-and-hardware/node-exporter.yml

@@ -23,8 +23,8 @@ groups:
         description: "The node is under heavy memory pressure. High rate of loading memory pages from disk.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostMemoryIsUnderutilized
-      expr: '((avg_over_time(node_memory_MemFree_bytes[30m]) / node_memory_MemTotal_bytes) > .80)'
+      expr: 'min_over_time(node_memory_MemFree_bytes[1w]) > node_memory_MemTotal_bytes * .8'
-      for: 1w
+      for: 0m
       labels:
         severity: info
       annotations:
@@ -122,7 +122,7 @@ groups:
         description: "Disk latency is growing (write operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostHighCpuLoad
-      expr: '((avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80)'
+      expr: '(avg by (instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > .80'
       for: 10m
       labels:
         severity: warning
@@ -131,7 +131,7 @@ groups:
         description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostCpuIsUnderutilized
-      expr: '(avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > .80'
+      expr: '(min by (instance) (rate(node_cpu_seconds_total{mode="idle"}[1h]))) > 0.8'
       for: 1w
       labels:
         severity: info
@@ -194,7 +194,7 @@ groups:
         description: "systemd service crashed\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostPhysicalComponentTooHot
-      expr: 'node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75'
+      expr: 'node_hwmon_temp_celsius > node_hwmon_temp_max_celsius'
       for: 5m
       labels:
         severity: warning
@@ -203,7 +203,7 @@ groups:
         description: "Physical hardware component too hot\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostNodeOvertemperatureAlarm
-      expr: '(node_hwmon_temp_crit_alarm_celsius == 1)'
+      expr: 'node_hwmon_temp_crit_alarm_celsius == 1 or node_hwmon_temp_alarm == 1'
       for: 0m
       labels:
         severity: critical

dist/rules/postgresql/postgres-exporter.yml

@@ -86,7 +86,7 @@ groups:
         description: "Ratio of transactions being aborted compared to committed is > 2 %\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: PostgresqlCommitRateLow
-      expr: 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[1m]) < 5'
+      expr: 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[5m]) < 5'
       for: 5m
       labels:
         severity: critical

dist/rules/prometheus-self-monitoring/embedded-exporter.yml

@@ -248,7 +248,7 @@ groups:
         description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: PrometheusTimeseriesCardinality
-      expr: 'label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000'
+      expr: '(label_replace(count by (__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") unless on (__name__) ({__name__=~"node_cpu_seconds_total|node_systemd_unit_state"})) > 10000'
       for: 0m
       labels:
         severity: warning