apiVersion: monitoring.coreos.com/v1
kind: Probe
metadata:
  name: nodes-proxmox
spec:
  targets:
    staticConfig:
      static:
        - nas.mgmt.k-space.ee:9100
        - pve1.proxmox.infra.k-space.ee:9100
        - pve8.proxmox.infra.k-space.ee:9100
        - pve9.proxmox.infra.k-space.ee:9100
      relabelingConfigs:
      - sourceLabels: [__param_target]
        targetLabel: instance
      - sourceLabels: [__param_target]
        targetLabel: __address__
  prober:
    url: localhost
    path: /metrics
  metricRelabelings:
  - sourceLabels: [__address__]
    targetLabel: target
---
apiVersion: monitoring.coreos.com/v1
kind: Probe
metadata:
  name: nodes-misc
spec:
  targets:
    staticConfig:
      static:
          - sprucecone.infra.k-space.ee:9100
          - cedarcone.infra.k-space.ee:9100
      relabelingConfigs:
      - sourceLabels: [__param_target]
        targetLabel: instance
      - sourceLabels: [__param_target]
        targetLabel: __address__
  prober:
    url: localhost
    path: /metrics
  metricRelabelings:
  - sourceLabels: [__address__]
    targetLabel: target
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: node-exporter
spec:
  groups:
  - name: node-exporter
    rules:
    - alert: ZfsOfflinePool
      expr: node_zfs_zpool_state{state!="online"} > 0
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: ZFS offline pool (instance {{ $labels.instance }})
        description: "A ZFS zpool is in a unexpected state: {{ $labels.state }}.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    - alert: HostHighLoad
      expr: sum(node_load1{}) by (instance) / count(node_cpu_seconds_total{mode="user"}) by (instance) > 2.5
      for: 15m
      labels:
        severity: warning
      annotations:
        summary: Host under high load
        description: Many processes are queued up for execution
    - alert: HostOutOfMemory
      expr: (node_memory_Cached_bytes + node_memory_Buffers_bytes + node_memory_MemFree_bytes ) / node_memory_MemTotal_bytes * 100 < 20
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: Host out of memory (instance {{ $labels.instance }})
        description: Node memory is filling up (< 10% left)
    - 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
    - alert: HostUnusualNetworkThroughputIn
      expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) > 160e+06
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Host unusual network throughput in (instance {{ $labels.instance }})
        description: Host network interfaces are probably receiving too much data (> 160 MB/s)
    - alert: HostUnusualNetworkThroughputOut
      expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) > 160e+06
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Host unusual network throughput out (instance {{ $labels.instance }})
        description: Host network interfaces are probably sending too much data (> 160 MB/s)
    - alert: HostUnusualDiskReadRate
      expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) > 50000000
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Host unusual disk read rate (instance {{ $labels.instance }})
        description: Disk is probably reading too much data (> 50 MB/s)
    - alert: HostUnusualDiskWriteRate
      expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) > 50000000
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Host unusual disk write rate (instance {{ $labels.instance }})
        description: Disk is probably writing too much data (> 50 MB/s)
    # Please add ignored mountpoints in node_exporter parameters like
    # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
    # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
    - alert: HostOutOfDiskSpace
      expr: (node_filesystem_avail_bytes * 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 {{ $labels.instance }})
        description: Disk is almost full (< 10% left)
    # Please add ignored mountpoints in node_exporter parameters like
    # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
    # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
    - alert: 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
    - alert: HostOutOfInodes
      expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 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)
    - alert: HostInodesWillFillIn24Hours
      expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 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
    - 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)
    - 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)
    - 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.
    # 1000 context switches is an arbitrary number.
    # Alert threshold depends on nature of application.
    # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
    - alert: HostContextSwitching
      expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 50000
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Host context switching (instance {{ $labels.instance }})
        description: Context switching is growing on node (> 50000 / s)
    - alert: HostSwapIsEnabled
      expr: node_memory_SwapTotal_bytes > 0
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Swap is discouraged nowadays
    - alert: HostPhysicalComponentTooHot
      expr: node_hwmon_temp_celsius > 75
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Host physical component too hot (instance {{ $labels.instance }})
        description: Physical hardware component too hot
    - alert: HostNodeOvertemperatureAlarm
      expr: node_hwmon_temp_alarm == 1
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Host node overtemperature alarm (instance {{ $labels.instance }})
        description: Physical node temperature alarm triggered
    - 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.
    - 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
    - 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
    - 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: {{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.
    - 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: {{ $labels.instance }} has had {{ printf "%.0f" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.
    - 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: {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last five minutes.
    - 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: {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last five minutes.
    - alert: HostNetworkInterfaceSaturated
      expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8
      for: 1m
      labels:
        severity: warning
      annotations:
        summary: Host Network Interface Saturated (instance {{ $labels.instance }})
        description: The network interface "{{ $labels.interface }}" on "{{ $labels.instance }}" is getting overloaded.
    - alert: HostNetworkBondDegraded
      expr: node_bonding_active != node_bonding_slaves {master=~"bond.*"}
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: Host Network Bond Degraded
    - 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 approching limit
    - 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.
    - 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.
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: smart
spec:
  groups:
    - name: smart
      rules:
      - alert: SmartSSDWriteRateTooHigh
        expr: rate(smartmon_total_lbas_written_raw_value[72h]) * 512 > 10000000
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: SSD write rate exceeds 10MB/s
          description: At this rate the SSD will be worn out before warranty period expires
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: temperatures
spec:
  groups:
    - name: temperatures
      rules:
      - alert: HighDiskTemperature
        expr: smartmon_airflow_temperature_cel_raw_value > 45 or smartmon_temperature_celsius_raw_value > 45
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: High HDD/SSD temperature indicates high ambient temperature
      - alert: HighChipsetTemperature
        expr: node_hwmon_temp_celsius > 65
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: High chipset (CPU, NB) temperature indicates insufficient or failing fans
      - alert: LowDiskTemperature
        expr: smartmon_airflow_temperature_cel_raw_value < 10 or smartmon_temperature_celsius_raw_value < 10
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: Low HDD/SSD temperature indicates low ambient temperature and stuck server room exhaust fan relay
---
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
  name: node-exporter
spec:
  selector:
    matchLabels:
      app: node-exporter
  podMetricsEndpoints:
    - port: web
      scrapeTimeout: 30s
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: node-exporter
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    app: node-exporter
  name: node-exporter
  annotations:
    keel.sh/policy: force
    keel.sh/trigger: poll
    keel.sh/pollSchedule: "@midnight"
spec:
  selector:
    matchLabels:
      app: node-exporter
  template:
    metadata:
      labels:
        app: node-exporter
    spec:
      containers:
      - name: node-exporter
        args:
        - --web.listen-address=0.0.0.0:9101
        - --path.sysfs=/host/sys
        - --path.rootfs=/host/root
        - --no-collector.wifi
        - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
        - --collector.netclass.ignored-devices=^(veth.*|[a-f0-9]{15})$
        - --collector.netdev.device-exclude=^(veth.*|[a-f0-9]{15})$
        image: prom/node-exporter:v1.3.1
        resources:
          limits:
            cpu: 50m
            memory: 180Mi
          requests:
            cpu: 5m
            memory: 20Mi
        volumeMounts:
        - mountPath: /host/sys
          mountPropagation: HostToContainer
          name: sys
          readOnly: true
        - mountPath: /host/root
          mountPropagation: HostToContainer
          name: root
          readOnly: true
        ports:
        - containerPort: 9101
          name: web
        securityContext:
          runAsGroup: 65532
          runAsNonRoot: true
          runAsUser: 65532
          readOnlyRootFilesystem: true
      hostNetwork: true
      hostPID: true
      securityContext:
        runAsNonRoot: true
        runAsUser: 65534
      serviceAccountName: node-exporter
      tolerations:
      - operator: Exists
      volumes:
      - hostPath:
          path: /sys
        name: sys
      - hostPath:
          path: /
        name: root