Refactor

coreos-config/plays/services/prometheus/.env

@@ -0,0 +1 @@
+COMPOSE_PROJECT_NAME=prometheus

coreos-config/plays/services/prometheus/alertmanager.yml

@@ -0,0 +1,50 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname']
+  group_wait: 5s
+  group_interval: 5m
+  repeat_interval: 1h
+  receiver: 'matrix-monitoring'
+  routes:
+    - receiver: 'hcio'
+      repeat_interval: 1h
+      matchers:
+        - alertname="PrometheusAlertmanagerE2eDeadManSwitch"
+    - receiver: 'email'
+      group_interval: 1m
+      matchers:
+        - job="matrix_synapse_1"
+    - receiver: 'matrix-monitoring'
+      group_wait: 30s
+      group_interval: 1h
+      matchers:
+        - alertname="PrometheusAllTargetsMissing"
+    - receiver: 'matrix-monitoring'
+      group_wait: 30s
+      group_interval: 1h
+      matchers:
+        - alertname="PrometheusTargetMissing"
+
+
+receivers:
+  - name: 'email'
+    email_configs:
+      - to: '{{ prometheus.alertmanager.smtp.target }}'
+        from: '"Alertmanager" <{{ prometheus.alertmanager.smtp.username }}>'
+        smarthost: 'mxe8cf.netcup.net:587'
+        auth_username: '{{ prometheus.alertmanager.smtp.username }}'
+        auth_identity: '{{ prometheus.alertmanager.smtp.username }}'
+        auth_password: '{{ prometheus.alertmanager.smtp.password }}'
+  - name: 'hcio'
+    email_configs:
+      - to: '{{ prometheus.alertmanager.hcio.mail }}'
+        from: '"Alertmanager" <{{ prometheus.alertmanager.smtp.username }}>'
+        smarthost: 'mxe8cf.netcup.net:587'
+        auth_username: '{{ prometheus.alertmanager.smtp.username }}'
+        auth_identity: '{{ prometheus.alertmanager.smtp.username }}'
+        auth_password: '{{ prometheus.alertmanager.smtp.password }}'
+  - name: 'matrix-monitoring'
+    webhook_configs:
+      - url: 'http://alertmanager-matrix:3000/alerts?secret={{ prometheus.alertmanager.matrix.alertmanager_token }}'

coreos-config/plays/services/prometheus/docker-compose.yaml

@@ -0,0 +1,161 @@
+version: "3.4"
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    restart: unless-stopped
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--web.external-url=https://prometheus.tobiasmanske.de'
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro,Z
+      - prom_data:/prometheus
+      - label_discovery:/label_discovery:ro
+      - ./rules:/rules:ro,Z
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.prometheus.rule=Host(`prometheus.tobiasmanske.de`)"
+      - "traefik.http.routers.prometheus.entryPoints=websecure"
+      - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
+      - "traefik.http.routers.prometheus.middlewares=oauth@file"
+    depends_on:
+      - prometheus-docker-sd
+      - cadvisor
+      - node-exporter
+    networks:
+      - gateway
+      - backend
+      - alertmanager
+
+  prometheus-docker-sd:
+    image: registry.tobiasmanske.de/prometheus-docker-sd:latest
+    restart: unless-stopped
+    privileged: true
+    networks:
+      - backend
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro,Z
+      - label_discovery:/prometheus-docker-sd:rw
+    logging: # this service generates a HUGE amout of logs.
+      driver: "none"
+
+  alertmanager:
+    image: prom/alertmanager:latest
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.alertmanager.rule=Host(`alertmanager.tobiasmanske.de`)"
+      - "traefik.http.routers.alertmanager.entryPoints=websecure"
+      - "traefik.http.services.alertmanager.loadbalancer.server.port=9093"
+      - "traefik.http.routers.alertmanager.middlewares=oauth@file"
+    volumes:
+      - ./alertmanager.yml:/etc/alertmanager/config.yml:ro,Z
+      - alertmanager_data:/data
+    networks:
+      - alertmanager
+      - gateway
+    restart: unless-stopped
+    command:
+      - '--config.file=/etc/alertmanager/config.yml'
+      - '--web.external-url=https://alertmanager.tobiasmanske.de'
+      - '--storage.path=/data'
+
+  alertmanager-matrix:
+    image: jaywink/matrix-alertmanager:latest
+    restart: unless-stopped
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.alertmanager-matrix.rule=Host(`alertmanager.tobiasmanske.de`) && PathPrefix(`/matrix/`)"
+      - "traefik.http.routers.alertmanager-matrix.middlewares=matrix-strip"
+      - "traefik.http.middlewares.matrix-strip.stripprefix.prefixes=/matrix"
+      - "traefik.http.middlewares.matrix-strip.stripprefix.forceslash=false"
+      - "traefik.http.routers.alertmanager-matrix.entryPoints=websecure"
+      - "traefik.http.services.alertmanager-matrix.loadbalancer.server.port=3000"
+    environment:
+      - APP_PORT=3000
+      - APP_ALERTMANAGER_SECRET={{ prometheus.alertmanager.matrix.alertmanager_token }}
+      - MATRIX_HOMESERVER_URL=http://pantalaimon:8008
+      - MATRIX_ROOMS={{ prometheus.alertmanager.matrix.rooms | join('|') }}
+      - MATRIX_TOKEN={{ prometheus.alertmanager.matrix.matrix_token }}
+      - MATRIX_USER=@alertmanager:{{ matrix.baseurl }}
+      - MENTION_ROOM=1
+    networks:
+      - alertmanager
+      - pantalaimon
+      - gateway
+
+
+  grafana:
+    image: grafana/grafana:latest
+    restart: unless-stopped
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.grafana.rule=Host(`grafana.tobiasmanske.de`)"
+      - "traefik.http.routers.grafana.entryPoints=websecure"
+      - "traefik.http.services.grafana.loadbalancer.server.port=3000"
+      - "traefik.http.routers.grafana.middlewares=oauth@file"
+    networks:
+      - gateway
+      - backend
+    environment:
+      - "GF_SECURITY_ADMIN_USER={{ grafana.admin.user }}"
+      - "GF_SECURITY_ADMIN_PASSWORD={{ grafana.admin.password }}"
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./grafana-ds.yml:/etc/grafana/provisioning/datasources/datasource.yml:ro,Z
+
+  node-exporter:
+    image: quay.io/prometheus/node-exporter:latest
+    container_name: host-nc-chaoswg-org-node-exporter
+    privileged: true
+    labels:
+      - "prometheus-scrape.enabled=true"
+      - "prometheus-scrape.port=9100"
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+      - /:/host:ro,rslave
+      - /run/dbus/system_bus_socket:/var/run/dbus/system_bus_socket:ro
+    command:
+      - '--path.rootfs=/host'
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - '--collector.filesystem.ignored-mount-points'
+      - "^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)"
+      - '--collector.systemd'
+    networks:
+      - backend
+    restart: unless-stopped
+
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:latest
+    privileged: true
+    labels:
+      - "prometheus-scrape.enabled=true"
+      - "prometheus-scrape.port=8080"
+    command:
+      - "-docker_only=true"
+      - "-housekeeping_interval=10s"
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+    networks:
+      - backend
+    restart: unless-stopped
+
+
+volumes:
+  prom_data:
+  grafana_data:
+  label_discovery:
+  alertmanager_data:
+networks:
+  gateway:
+    external: true
+  pantalaimon:
+    external: true
+  backend:
+    internal: true
+  alertmanager:
+    internal: true

coreos-config/plays/services/prometheus/grafana-ds.yml

@@ -0,0 +1,9 @@
+apiVersion: 1
+
+datasources:
+- name: Prometheus
+  type: prometheus
+  url: http://prometheus:9090
+  isDefault: true
+  access: proxy
+  editable: true

coreos-config/plays/services/prometheus/prometheus.yml

@@ -0,0 +1,54 @@
+global:
+  scrape_interval: 15s
+  scrape_timeout: 10s
+  evaluation_interval: 15s
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+      - targets: [ 'alertmanager:9093' ]
+  - static_configs:
+    - targets: []
+    scheme: http
+    timeout: 10s
+    api_version: v1
+rule_files:
+  - "/rules/*.yaml"
+scrape_configs:
+- job_name: prometheus
+  honor_timestamps: true
+  scrape_interval: 15s
+  scrape_timeout: 10s
+  metrics_path: /metrics
+  scheme: http
+  static_configs:
+  - targets:
+    - localhost:9090
+- job_name: 'service_discovery'
+  metric_relabel_configs:
+    - source_labels:
+        - "container_name"
+      target_label: "instance"
+      action: replace
+  file_sd_configs:
+    - files:
+      - /label_discovery/docker-targets.json
+- job_name: minio-job
+  bearer_token: "{{ prometheus.scrape.s3.bearer_token }}"
+  metrics_path: /minio/v2/metrics/cluster
+  scheme: https
+  static_configs:
+  - targets: [s3.tobiasmanske.de]
+- job_name: drone-job
+  bearer_token: "{{ prometheus.scrape.drone.bearer_token }}"
+  scheme: https
+  static_configs:
+  - targets: [drone.tobiasmanske.de]
+- job_name: 'uptime-kuma-job'
+  scrape_interval: 30s
+  scheme: https
+  static_configs:
+    - targets: [status.tobiasmanske.de]
+  basic_auth:
+    username: "{{ prometheus.scrape.kuma.user }}"
+    password: "{{ prometheus.scrape.kuma.password }}"

coreos-config/plays/services/prometheus/rules/cadvisor.yaml

@@ -0,0 +1,54 @@
+# {% raw %}
+
+groups:
+- name: GoogleCadvisor
+  rules:
+    # - alert: ContainerKilled
+    #   expr: 'time() - container_last_seen > 60'
+    #   for: 0m
+    #   labels:
+    #     severity: warning
+    #   annotations:
+    #     summary: Container killed (instance {{ $labels.instance }})
+    #     description: "A container has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    # - alert: ContainerAbsent
+    #   expr: 'absent(container_last_seen)'
+    #   for: 5m
+    #   labels:
+    #     severity: warning
+    #   annotations:
+    #     summary: Container absent (instance {{ $labels.instance }})
+    #     description: "A container is absent for 5 min\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: ContainerCpuUsage
+      expr: '(sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Container CPU usage (instance {{ $labels.instance }})
+        description: "Container CPU usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: ContainerMemoryUsage
+      expr: '(sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Container Memory usage (instance {{ $labels.instance }})
+        description: "Container Memory usage is above 80%\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 }}"
+    - alert: ContainerHighThrottleRate
+      expr: 'rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Container high throttle rate (instance {{ $labels.instance }})
+        description: "Container is being throttled\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+# {% endraw %}

coreos-config/plays/services/prometheus/rules/node.yaml

@@ -0,0 +1,303 @@
+# {% raw %}
+
+groups:
+- name: NodeExporter
+  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: HostMemoryUnderMemoryPressure
+      expr: 'rate(node_vmstat_pgmajfault[1m]) > 1000'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host memory under memory pressure (instance {{ $labels.instance }})
+        description: "The node is under heavy memory pressure. High rate of major page faults\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    # - alert: HostMemoryIsUnderUtilized
+    #   expr: '100 - (rate(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20'
+    #   for: 1w
+    #   labels:
+    #     severity: info
+    #   annotations:
+    #     summary: Host Memory is under utilized (instance {{ $labels.instance }})
+    #     description: "Node memory is < 20% for 1 week. Consider reducing memory space.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostUnusualNetworkThroughputIn
+      expr: 'sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host 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: HostUnusualNetworkThroughputOut
+      expr: 'sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host 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: HostUnusualDiskReadRate
+      expr: 'sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host 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: HostUnusualDiskWriteRate
+      expr: 'sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host 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: 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: HostOutOfInodes
+      expr: 'node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        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: 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'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
+        description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostUnusualDiskReadLatency
+      expr: 'rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk read latency (instance {{ $labels.instance }})
+        description: "Disk latency is growing (read operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostUnusualDiskWriteLatency
+      expr: 'rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk write latency (instance {{ $labels.instance }})
+        description: "Disk latency is growing (write operations > 100ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostHighCpuLoad
+      expr: '(100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100)) > 80'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host high CPU load (instance {{ $labels.instance }})
+        description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    # - alert: HostCpuIsUnderUtilized
+    #   expr: '100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20'
+    #   for: 1w
+    #   labels:
+    #     severity: info
+    #   annotations:
+    #     summary: Host CPU is under utilized (instance {{ $labels.instance }})
+    #     description: "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostCpuStealNoisyNeighbor
+      expr: 'avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
+        description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostCpuHighIowait
+      expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 15'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host CPU high iowait (instance {{ $labels.instance }})
+        description: "CPU iowait > 15%. A high iowait means that you are disk or network bound.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostUnusualDiskIo
+      expr: 'rate(node_disk_io_time_seconds_total[1m]) > 0.5'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host unusual disk IO (instance {{ $labels.instance }})
+        description: "Time spent in IO is too high on {{ $labels.instance }}. Check storage for issues.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    # - alert: HostContextSwitching
+    #   expr: '(rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 1000'
+    #   for: 0m
+    #   labels:
+    #     severity: warning
+    #   annotations:
+    #     summary: Host context switching (instance {{ $labels.instance }})
+    #     description: "Context switching is growing on node (> 1000 / s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostSwapIsFillingUp
+      expr: '(1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host swap is filling up (instance {{ $labels.instance }})
+        description: "Swap is filling up (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostSystemdServiceCrashed
+      expr: 'node_systemd_unit_state{state="failed"} == 1'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host systemd service crashed (instance {{ $labels.instance }})
+        description: "systemd service crashed\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostPhysicalComponentTooHot
+      expr: 'node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) node_hwmon_sensor_label{label!="tctl"} > 75'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host physical component too hot (instance {{ $labels.instance }})
+        description: "Physical hardware component too hot\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: HostKernelVersionDeviations
+      expr: 'count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1'
+      for: 6h
+      labels:
+        severity: warning
+      annotations:
+        summary: Host kernel version deviations (instance {{ $labels.instance }})
+        description: "Different kernel versions are running\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: HostEdacCorrectableErrorsDetected
+      expr: 'increase(node_edac_correctable_errors_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: info
+      annotations:
+        summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostEdacUncorrectableErrorsDetected
+      expr: 'node_edac_uncorrectable_errors_total > 0'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})
+        description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\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: HostNetworkInterfaceSaturated
+      expr: '(rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000'
+      for: 1m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Interface Saturated (instance {{ $labels.instance }})
+        description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostNetworkBondDegraded
+      expr: '(node_bonding_active - node_bonding_slaves) != 0'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host Network Bond Degraded (instance {{ $labels.instance }})
+        description: "Bond \"{{ $labels.device }}\" degraded on \"{{ $labels.instance }}\".\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostConntrackLimit
+      expr: 'node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host conntrack limit (instance {{ $labels.instance }})
+        description: "The number of conntrack is approaching limit\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: HostClockSkew
+      expr: '(node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)'
+      for: 2m
+      labels:
+        severity: warning
+      annotations:
+        summary: Host clock skew (instance {{ $labels.instance }})
+        description: "Clock skew detected. Clock is out of sync. Ensure NTP is configured correctly on this host.\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: HostRequiresReboot
+      expr: 'node_reboot_required > 0'
+      for: 4h
+      labels:
+        severity: info
+      annotations:
+        summary: Host requires reboot (instance {{ $labels.instance }})
+        description: "{{ $labels.instance }} requires a reboot.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+# {% endraw %}

coreos-config/plays/services/prometheus/rules/prometheus.yaml

@@ -0,0 +1,231 @@
+# {% raw %}
+
+groups:
+- name: EmbeddedExporter
+  rules:
+    - alert: PrometheusJobMissing
+      expr: 'absent(up{job="prometheus"})'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus job missing (instance {{ $labels.instance }})
+        description: "A Prometheus job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - 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: PrometheusAllTargetsMissing
+      expr: 'sum by (job) (up) == 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus all targets missing (instance {{ $labels.instance }})
+        description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTargetMissingWithWarmupTime
+      expr: 'sum by (instance, job) ((up == 0) * on (instance) group_right(job) (node_time_seconds - node_boot_time_seconds > 600))'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus target missing with warmup time (instance {{ $labels.instance }})
+        description: "Allow a job time to start up (10 minutes) before alerting that it's down.\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 }}"
+    # - alert: PrometheusAlertmanagerJobMissing
+    #   expr: 'absent(up{job="alertmanager"})'
+    #   for: 0m
+    #   labels:
+    #     severity: warning
+    #   annotations:
+    #     summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
+    #     description: "A Prometheus AlertManager job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusAlertmanagerConfigurationReloadFailure
+      expr: 'alertmanager_config_last_reload_successful != 1'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
+        description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusAlertmanagerConfigNotSynced
+      expr: 'count(count_values("config_hash", alertmanager_config_hash)) > 1'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
+        description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusAlertmanagerE2eDeadManSwitch
+      expr: 'vector(1)'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
+        description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusNotConnectedToAlertmanager
+      expr: 'prometheus_notifications_alertmanagers_discovered < 1'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
+        description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusRuleEvaluationFailures
+      expr: 'increase(prometheus_rule_evaluation_failures_total[3m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTemplateTextExpansionFailures
+      expr: 'increase(prometheus_template_text_expansion_failures_total[3m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} template text expansion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusRuleEvaluationSlow
+      expr: 'prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
+        description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusNotificationsBacklog
+      expr: 'min_over_time(prometheus_notifications_queue_length[10m]) > 0'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus notifications backlog (instance {{ $labels.instance }})
+        description: "The Prometheus notification queue has not been empty for 10 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusAlertmanagerNotificationFailing
+      expr: 'rate(alertmanager_notifications_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
+        description: "Alertmanager is failing sending notifications\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    # - alert: PrometheusTargetEmpty
+    #   expr: 'prometheus_sd_discovered_targets == 0'
+    #   for: 0m
+    #   labels:
+    #     severity: critical
+    #   annotations:
+    #     summary: Prometheus target empty (instance {{ $labels.instance }})
+    #     description: "Prometheus has no target in service discovery\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTargetScrapingSlow
+      expr: 'prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus target scraping slow (instance {{ $labels.instance }})
+        description: "Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusLargeScrape
+      expr: 'increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus large scrape (instance {{ $labels.instance }})
+        description: "Prometheus has many scrapes that exceed the sample limit\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTargetScrapeDuplicate
+      expr: 'increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
+        description: "Prometheus has many samples rejected due to duplicate timestamps but different values\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbCheckpointCreationFailures
+      expr: 'increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} checkpoint creation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbCheckpointDeletionFailures
+      expr: 'increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbCompactionsFailed
+      expr: 'increase(prometheus_tsdb_compactions_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} TSDB compactions failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbHeadTruncationsFailed
+      expr: 'increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbReloadFailures
+      expr: 'increase(prometheus_tsdb_reloads_failures_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} TSDB reload failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbWalCorruptions
+      expr: 'increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
+        description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+    - alert: PrometheusTsdbWalTruncationsFailed
+      expr: 'increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        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
+      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 }}"
+
+# {% endraw %}