groups:
  - name: node-alerts
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} is down"
          description: "Prometheus target {{ $labels.job }} on {{ $labels.instance }} is unreachable for >1 minute."

      - alert: HostOutOfMemory
        expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < .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[5m]) > 1000)
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host memory under memory pressure (instance {{ $labels.instance }})
          description: "The node is under heavy memory pressure. High rate of loading memory pages from disk.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: HostUnusualNetworkThroughputIn
        expr: ((rate(node_network_receive_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host unusual network throughput in (instance {{ $labels.instance }})
          description: "Host receive bandwidth is high (>80%).\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: HostUnusualNetworkThroughputOut
        expr: ((rate(node_network_transmit_bytes_total[5m]) / on(instance, device) node_network_speed_bytes) > .80)
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host unusual network throughput out (instance {{ $labels.instance }})
          description: "Host transmit bandwidth is high (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: HostUnusualDiskReadRate
        expr: (rate(node_disk_io_time_seconds_total[5m]) > .80)
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk read rate (instance {{ $labels.instance }})
          description: "Disk is too busy (IO wait > 80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      # Please add ignored mountpoints in node_exporter parameters like
      # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
      # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
      - alert: HostOutOfDiskSpace
        expr: (node_filesystem_avail_bytes{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} / node_filesystem_size_bytes < .10 and on (instance, device, mountpoint) node_filesystem_readonly == 0)
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: Host out of disk space (instance {{ $labels.instance }})
          description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: HostOutOfInodes
        expr: (node_filesystem_files_free / node_filesystem_files < .10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0)
        for: 2m
        labels:
          severity: critical
        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: HostFilesystemDeviceError
        expr: node_filesystem_device_error{fstype!~"^(fuse.*|tmpfs|cifs|nfs)"} == 1
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: Host filesystem device error (instance {{ $labels.instance }})
          description: "Error stat-ing the {{ $labels.mountpoint }} filesystem\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: 1 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m]))) > .80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: Host high CPU load (instance {{ $labels.instance }})
          description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: HostUnusualDiskIo
        expr: rate(node_disk_io_time_seconds_total[5m]) > 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: Host unusual disk IO (instance {{ $labels.instance }})
          description: "Disk usage >80%. Check storage for issues or increase IOPS capabilities. Check storage for issues.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      # x2 context switches is an arbitrary number.
      # The alert threshold depends on the nature of the application.
      # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
      - alert: HostContextSwitchingHigh
        expr: (rate(node_context_switches_total[15m])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) / (rate(node_context_switches_total[1d])/count without(mode,cpu) (node_cpu_seconds_total{mode="idle"})) > 2
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: Host context switching high (instance {{ $labels.instance }})
          description: "Context switching is growing on the node (twice the daily average during the last 15m)\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: 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: 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: 10m
        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 }}"

      # docker container alerts
      - alert: ContainerHighCpuUtilization
        expr: (sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) > 80
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: Container High CPU utilization (instance {{ $labels.instance }})
          description: "Container CPU utilization is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

      - alert: ContainerHighMemoryUsage
        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 High Memory usage (instance {{ $labels.instance }})
          description: "Container Memory usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"