Publish

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

@@ -94,6 +94,15 @@ groups:
         summary: Host out of inodes (instance {{ $labels.instance }})
         description: "Disk is almost running out of available inodes (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
+    - alert: HostFilesystemDeviceError
+      expr: 'node_filesystem_device_error == 1'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Host filesystem device error (instance {{ $labels.instance }})
+        description: "{{ $labels.instance }}: Device error with the {{ $labels.mountpoint }} filesystem\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
     - alert: HostInodesWillFillIn24Hours
       expr: '(node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
       for: 2m

dist/rules/loki/embedded-exporter.yml

@@ -5,7 +5,7 @@ groups:
   rules:
 
     - alert: LokiProcessTooManyRestarts
-      expr: 'changes(process_start_time_seconds{job=~"loki"}[15m]) > 2'
+      expr: 'changes(process_start_time_seconds{job=~".*loki.*"}[15m]) > 2'
       for: 0m
       labels:
         severity: warning

dist/rules/patroni/embedded-exporter-patroni.yml

@@ -0,0 +1,14 @@
+groups:
+
+- name: EmbeddedExporterPatroni
+
+  rules:
+
+    - alert: PatroniHasNoLeader
+      expr: '(max by (scope) (patroni_master) < 1) and (max by (scope) (patroni_standby_leader) < 1)'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Patroni has no Leader (instance {{ $labels.instance }})
+        description: "A leader node (neither primary nor standby) cannot be found inside the cluster {{ $labels.scope }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

dist/rules/postgresql/postgres-exporter.yml

@@ -50,7 +50,7 @@ groups:
         description: "Table {{ $labels.relname }} has not been auto analyzed for 10 days\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: PostgresqlTooManyConnections
-      expr: 'sum by (instance, job, server) (pg_stat_activity_count) > min by (instance, job, server) (pg_settings_max_connections * 0.8)'
+      expr: ''
       for: 2m
       labels:
         severity: warning

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

@@ -247,11 +247,11 @@ groups:
         summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
         description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
-    - alert: PrometheusTimeserieCardinality
+    - alert: PrometheusTimeseriesCardinality
       expr: 'label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000'
       for: 0m
       labels:
         severity: warning
       annotations:
-        summary: Prometheus timeserie cardinality (instance {{ $labels.instance }})
-        description: "The \"{{ $labels.name }}\" timeserie cardinality is getting very high: {{ $value }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        summary: Prometheus timeseries cardinality (instance {{ $labels.instance }})
+        description: "The \"{{ $labels.name }}\" timeseries cardinality is getting very high: {{ $value }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

dist/rules/redis/oliver006-redis-exporter.yml

@@ -32,7 +32,7 @@ groups:
         description: "Redis cluster has too many nodes marked as master.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: RedisDisconnectedSlaves
-      expr: 'count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 1'
+      expr: 'count without (instance, job) (redis_connected_slaves) - sum without (instance, job) (redis_connected_slaves) - 1 > 0'
       for: 0m
       labels:
         severity: critical