Add alert settings.

cookbooks/prometheus/files/etc/prometheus.d/alerts/node_exporter.yml

@@ -0,0 +1,119 @@
+groups:
+- name: Node
+  rules:
+  - alert: OutOfMemory
+    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Out of memory (instance {{ $labels.instance }})"
+      description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualNetworkThroughputIn
+    expr: sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual network throughput in (instance {{ $labels.instance }})"
+      description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualNetworkThroughputOut
+    expr: sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual network throughput out (instance {{ $labels.instance }})"
+      description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualDiskReadRate
+    expr: sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual disk read rate (instance {{ $labels.instance }})"
+      description: "Disk is probably reading too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualDiskWriteRate
+    expr: sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual disk write rate (instance {{ $labels.instance }})"
+      description: "Disk is probably writing too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: OutOfDiskSpace
+    expr: node_filesystem_free_bytes{mountpoint ="/"} / node_filesystem_size_bytes{mountpoint ="/"} * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Out of disk space (instance {{ $labels.instance }})"
+      description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: OutOfInodes
+    expr: node_filesystem_files_free{mountpoint ="/"} / node_filesystem_files{mountpoint ="/"} * 100 < 10
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Out of inodes (instance {{ $labels.instance }})"
+      description: "Disk is almost running out of available inodes (< 10% left)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualDiskReadLatency
+    expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual disk read latency (instance {{ $labels.instance }})"
+      description: "Disk latency is growing (read operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: UnusualDiskWriteLatency
+    expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 100
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Unusual disk write latency (instance {{ $labels.instance }})"
+      description: "Disk latency is growing (write operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: HighCpuLoad
+    expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "High CPU load (instance {{ $labels.instance }})"
+      description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: SwapIsFillingUp
+    expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Swap is filling up (instance {{ $labels.instance }})"
+      description: "Swap is filling up (>80%)\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: InstanceDown
+    expr: up == 0
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Instance {{ $labels.instance }} down"
+      description: "{{ $labels.instance }} has been down for more than 5 minutes."
+
+  - alert: LoadAvg
+    expr: node_load1 > 2
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      description: 'High Load Avg (1min) detected for instance {{ $labels.instance }}, the utilisation is currently: {{ $value }}%'
+      summary: Load Average (1min) Alert

cookbooks/prometheus/files/etc/prometheus.d/alerts/prometheus.yml

@@ -0,0 +1,29 @@
+groups:
+- name: Prometheus
+  rules:
+  - alert: ExporterDown
+    expr: up == 0
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Instance {{ $labels.instance }} down"
+      description: "{{ $labels.instance }} has been down for more than 5 minutes."
+
+  - alert: PrometheusConfigurationReload
+    expr: prometheus_config_last_reload_successful != 1
+    for: 5m
+    labels:
+      severity: error
+    annotations:
+      summary: "Prometheus configuration reload (instance {{ $labels.instance }})"
+      description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+    
+  - alert: AlertmanagerConfigurationReload
+    expr: alertmanager_config_last_reload_successful != 1
+    for: 5m
+    labels:
+      severity: error
+    annotations:
+      summary: "AlertManager configuration reload (instance {{ $labels.instance }})"
+      description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"