added some alerts

files/core_alerts.yml

+groups:
+- name: core
+  rules:
+# Prometheus Base Rules
+  - alert: PrometheusTargetMissing
+    expr: up == 0
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Prometheus target missing (instance {{ $labels.instance }})
+      description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: PrometheusConfigurationReloadFailure
+    expr: prometheus_config_last_reload_successful != 1
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
+      description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: PrometheusTooManyRestarts
+    expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Prometheus too many restarts (instance {{ $labels.instance }})
+      description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+# End Prometheus Base Rules
+  - alert: HostOutOfMemory
+    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host out of memory (instance {{ $labels.instance }})
+      description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostOutOfDiskSpace
+    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host out of disk space (instance {{ $labels.instance }})
+      description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}" 
+   - alert: HostDiskWillFillIn24Hours
+    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
+      description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostCpuHighIowait
+    expr: avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 5
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host CPU high iowait (instance {{ $labels.instance }})
+      description: "CPU iowait > 5%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+ - alert: HostNodeOvertemperatureAlarm
+    expr: node_hwmon_temp_crit_alarm_celsius == 1
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Host node overtemperature alarm (instance {{ $labels.instance }})
+      description: "Physical node temperature alarm triggered\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostRaidArrayGotInactive
+    expr: node_md_state{state="inactive"} > 0
+    for: 0m
+    labels:
+      severity: critical
+    annotations:
+      summary: Host RAID array got inactive (instance {{ $labels.instance }})
+      description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostRaidDiskFailure
+    expr: node_md_disks{state="failed"} > 0
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host RAID disk failure (instance {{ $labels.instance }})
+      description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostOomKillDetected
+    expr: increase(node_vmstat_oom_kill[1m]) > 0
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host OOM kill detected (instance {{ $labels.instance }})
+      description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostNetworkReceiveErrors
+    expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host Network Receive Errors (instance {{ $labels.instance }})
+      description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostNetworkTransmitErrors
+    expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host Network Transmit Errors (instance {{ $labels.instance }})
+      description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: HostClockNotSynchronising
+    expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Host clock not synchronising (instance {{ $labels.instance }})
+      description: "Clock not synchronising. Ensure NTP is configured on this host.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+  - alert: ContainerVolumeUsage
+    expr: (1 - (sum(container_fs_inodes_free{name!=""}) BY (instance) / sum(container_fs_inodes_total) BY (instance))) * 100 > 80
+    for: 2m
+    labels:
+      severity: warning
+    annotations:
+      summary: Container Volume usage (instance {{ $labels.instance }})
+      description: "Container Volume usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+
+
+
+

tasks/all.yml

@@ -40,3 +40,10 @@
     name: prometheus
     state: started
     enabled: yes
+
+
+- name: core alerts
+  copy:
+    src: core_alerts.yml
+    dest: /etc/prometheus/alerts/core.yml
+  tags: alerts