Merge branch 'samber:master' into master

_data/rules.yml

@@ -2089,6 +2089,30 @@ groups:
                 query: 'node_zfs_zpool_state{state!="online"} > 0'
                 severity: critical
                 for: 1m
+          - name: ZFS exporter
+            slug: zfs_exporter
+            doc_url: https://github.com/pdf/zfs_exporter
+            rules:
+              - name: ZFS pool out of space
+                description: Disk is almost full (< 10% left)
+                query: 'zfs_pool_free_bytes * 100 / zfs_pool_size_bytes < 10 and ON (instance, device, mountpoint) zfs_pool_readonly == 0'
+                severity: warning
+              - name: ZFS pool unhealthy
+                description: ZFS pool state is {{ $value }}. See comments for more information.
+                query: 'zfs_pool_health > 0'
+                severity: critical
+                comments: |
+                  0: ONLINE
+                  1: DEGRADED
+                  2: FAULTED
+                  3: OFFLINE
+                  4: UNAVAIL
+                  5: REMOVED
+                  6: SUSPENDED
+              - name: ZFS collector failed
+                description: ZFS collector for {{ $labels.instance }} has failed to collect information
+                query: 'zfs_scrape_collector_success != 1'
+                severity: warning
 
       - name: OpenEBS
         exporters:
@@ -2362,3 +2386,35 @@ groups:
                   * FAILURE   2 false - The build had a fatal error.
                   * NOT_BUILT 3 false - The module was not built.
                   * ABORTED   4 false - The build was manually aborted.
+
+      - name: APC UPS
+        exporters:
+          - name: mdlayher/apcupsd_exporter
+            slug: apcupsd_exporter
+            doc_url: https://github.com/mdlayher/apcupsd_exporter
+            rules:
+              - name: APC UPS Battery nearly empty
+                description: Battery is almost empty (< 10% left)
+                query: 'apcupsd_battery_charge_percent < 10'
+                severity: critical
+              - name: APC UPS Less than 15 Minutes of battery time remaining
+                description: Battery is almost empty (< 15 Minutes remaining)
+                query: 'apcupsd_battery_time_left_seconds < 900'
+                severity: critical
+              - name: APC UPS AC input outage
+                description: UPS now running on battery (since {{$value | humanizeDuration}})
+                query: 'apcupsd_battery_time_on_seconds > 0'
+                severity: warning
+              - name: APC UPS low battery voltage
+                description: Battery voltage is lower than nominal (< 95%)
+                query: '(apcupsd_battery_volts / apcupsd_battery_nominal_volts) < 0.95'
+                severity: warning
+              - name: APC UPS high temperature
+                description: Internal temperature is high ({{$value}}°C)
+                query: 'apcupsd_internal_temperature_celsius >= 40'
+                severity: warning
+                for: 2m
+              - name: APC UPS high load
+                description: UPS load is > 80%
+                query: 'apcupsd_ups_load_percent > 80'
+                severity: warning

dist/rules/apc-ups/apcupsd_exporter.yml

@@ -0,0 +1,59 @@
+groups:
+
+- name: Apcupsd_exporter
+
+  rules:
+
+    - alert: ApcUpsBatteryNearlyEmpty
+      expr: 'apcupsd_battery_charge_percent < 10'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: APC UPS Battery nearly empty (instance {{ $labels.instance }})
+        description: "Battery is almost empty (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ApcUpsLessThan15MinutesOfBatteryTimeRemaining
+      expr: 'apcupsd_battery_time_left_seconds < 900'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: APC UPS Less than 15 Minutes of battery time remaining (instance {{ $labels.instance }})
+        description: "Battery is almost empty (< 15 Minutes remaining)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ApcUpsAcInputOutage
+      expr: 'apcupsd_battery_time_on_seconds > 0'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: APC UPS AC input outage (instance {{ $labels.instance }})
+        description: "UPS now running on battery (since {{$value | humanizeDuration}})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ApcUpsLowBatteryVoltage
+      expr: '(apcupsd_battery_volts / apcupsd_battery_nominal_volts) < 0.95'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: APC UPS low battery voltage (instance {{ $labels.instance }})
+        description: "Battery voltage is lower than nominal (< 95%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ApcUpsHighTemperature
+      expr: 'apcupsd_internal_temperature_celsius >= 40'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: APC UPS high temperature (instance {{ $labels.instance }})
+        description: "Internal temperature is high ({{$value}}°C)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ApcUpsHighLoad
+      expr: 'apcupsd_ups_load_percent > 80'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: APC UPS high load (instance {{ $labels.instance }})
+        description: "UPS load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

dist/rules/zfs/zfs_exporter.yml

@@ -0,0 +1,32 @@
+groups:
+
+- name: Zfs_exporter
+
+  rules:
+
+    - alert: ZfsPoolOutOfSpace
+      expr: 'zfs_pool_free_bytes * 100 / zfs_pool_size_bytes < 10 and ON (instance, device, mountpoint) zfs_pool_readonly == 0'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: ZFS pool out of space (instance {{ $labels.instance }})
+        description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ZfsPoolUnhealthy
+      expr: 'zfs_pool_health > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: ZFS pool unhealthy (instance {{ $labels.instance }})
+        description: "ZFS pool state is {{ $value }}. See comments for more information.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: ZfsCollectorFailed
+      expr: 'zfs_scrape_collector_success != 1'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: ZFS collector failed (instance {{ $labels.instance }})
+        description: "ZFS collector for {{ $labels.instance }} has failed to collect information\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"