Remove useless warning alerts

pica-metrologie/vmalert-rules.yml

@@ -2,32 +2,14 @@ groups:
   # The name of the group. Must be unique within a file.
 - name: disk
   rules:
-  - record: instance:node_fs:space_used
-    expr: 100 - ((node_filesystem_avail_bytes{fstype=~"ext.|xfs"} / node_filesystem_size_bytes{fstype=~"ext.|xfs"}) * 100)
-  - record: instance:node_disk:temperature
-    expr: avg(smartmon_temperature_celsius_raw_value) by (instance, disk)
     # The name of the alert. Must be a valid metric name.
   - alert: DiskFull
-    # The PromQL expression to evaluate
-    expr: instance:node_fs:space_used > 80
-    # Alerts are considered firing once they have been returned for this long.
-    # Alerts which have not yet fired for long enough are considered pending.
-    # If param is omitted or set to 0 then alerts will be immediately considered
-    # as firing once they return.
+    expr: (100 - ((node_filesystem_avail_bytes{fstype=~"ext.|xfs"} / node_filesystem_size_bytes{fstype=~"ext.|xfs"}) * 100)) > 90
     for: "10m"
     labels:
       severity: warning
     annotations:
-      summary: Disk 80% full on {{ $labels.instance }}
-      description: Device {{ $labels.device }} mounted on {{ $labels.mountpoint }} is {{ printf "%.0f" $value }}% full
-      dashboard: https://grafana.picasoft.net/d/VIb73SGWa/server-overview?var-node={{ $labels.instance }}
-  - alert: DiskFull
-    expr: instance:node_fs:space_used > 95
-    for: "10m"
-    labels:
-      severity: critical
-    annotations:
-      summary: Disk 95% full on {{ $labels.instance }}
+      summary: Disk 90% full on {{ $labels.instance }}
       description: Device {{ $labels.device }} mounted on {{ $labels.mountpoint }} is {{ printf "%.0f" $value }}% full
       dashboard: https://grafana.picasoft.net/d/VIb73SGWa/server-overview?var-node={{ $labels.instance }}
   - alert: VMBackupFull
@@ -84,16 +66,7 @@ groups:
       description: "Degraded RAID array {{ $labels.device }} on {{ $labels.instance }} : {{ $value }} disks failed"
       dashboard: https://grafana.picasoft.net/d/iwR8rQBZk/raid-state?var-node={{ $labels.instance }}
   - alert: DiskHighTemperature
-    expr: instance:node_disk:temperature > 50
-    for: "5m"
-    labels:
-      severity: warning
-    annotations:
-      summary: Disk temperature > 50°C
-      description: Disk {{ $labels.disk }} on {{ $labels.instance }} at {{ printf "%.0f" $value }}°C for more than 5 minutes
-      dashboard: https://grafana.picasoft.net/d/moX2wwfZk/temperatures?var-node={{ $labels.instance }}
-  - alert: DiskHighTemperature
-    expr: instance:node_disk:temperature > 60
+    expr: (avg(smartmon_temperature_celsius_raw_value) by (instance, disk)) > 60
     for: "5m"
     labels:
       severity: critical
@@ -135,15 +108,6 @@ groups:
       summary: CPU usage over 90%
       description: CPU use percent is {{ printf "%.0f" $value }}% on {{ $labels.instance }} for the past 30 minutes
       dashboard: https://grafana.picasoft.net/d/VIb73SGWa/server-overview?var-node={{ $labels.instance }}
-  - alert: HighCPUTemperature
-    expr: instance:node_cpu_temperature > 60
-    for: "5m"
-    labels:
-      severity: warning
-    annotations:
-      summary: CPU temperature over 60°C
-      description: CPU temperature averaged over cores is {{ printf "%.0f" $value }}°C on {{ $labels.instance }}
-      dashboard: https://grafana.picasoft.net/d/VIb73SGWa/server-overview?var-node={{ $labels.instance }}
   - alert: HighCPUTemperature
     expr: instance:node_cpu_temperature > 80
     for: "5m"
@@ -156,24 +120,13 @@ groups:
 
 - name: ram
   rules:
-  - record: instance:node_memory
-    expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
   - alert: HighRAMUse
-    expr: instance:node_memory < 20
+    expr: ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100) < 10
     for: "10m"
     labels:
       severity: warning
     annotations:
-      summary: More than 80% of RAM is used
-      description: Available RAM on {{ $labels.instance }} is {{ printf "%.0f" $value }}%.
-      dashboard: https://grafana.picasoft.net/d/moX2wwfZk/temperatures?var-node={{ $labels.instance }}
-  - alert: HighRAMUse
-    expr: instance:node_memory < 5
-    for: "10m"
-    labels:
-      severity: critical
-    annotations:
-      summary: More than 95% of RAM is used
+      summary: More than 90% of RAM is used
       description: Available RAM on {{ $labels.instance }} is {{ printf "%.0f" $value }}%.
       dashboard: https://grafana.picasoft.net/d/moX2wwfZk/temperatures?var-node={{ $labels.instance }}