prometheus.yaml

kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: prometheus
rules:
- apiGroups: [""]
  resources: ["nodes", "nodes/proxy", "pods"]
  verbs: ["get", "list", "watch"]
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: default
---
kind: ServiceAccount
apiVersion: v1
metadata:
  name: prometheus
  namespace: default
---
kind: ConfigMap
apiVersion: v1
metadata:
  name: prometheus-config
  namespace: default
data:
  prometheus.yml: |-
    global:
      evaluation_interval: 10s
      scrape_interval: 10s
      scrape_timeout: 10s

    rule_files:
    - /etc/prometheus/*_rules.yml
    - /etc/prometheus/*_rules.yaml

    remote_write:
    - url: http://cortex-service.default.svc.cluster.local:9009/api/prom/push

    scrape_configs:
    - job_name: 'prometheus'
      static_configs:
      - targets: ['localhost:9090']

    - job_name: 'grafana'
      kubernetes_sd_configs:
      - role: pod
        namespaces:
          names: ['linkerd']
      relabel_configs:
      - source_labels:
        - __meta_kubernetes_pod_container_name
        action: keep
        regex: ^grafana$

    #  Required for: https://grafana.com/grafana/dashboards/315
    - job_name: 'kubernetes-nodes-cadvisor'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
      metric_relabel_configs:
      - source_labels: [__name__]
        regex: '(container|machine)_(cpu|memory|network|fs)_(.+)'
        action: keep
      - source_labels: [__name__]
        regex: 'container_memory_failures_total' # unneeded large metric
        action: drop

    - job_name: 'linkerd-controller'
      kubernetes_sd_configs:
      - role: pod
        namespaces:
          names: ['linkerd']
      relabel_configs:
      - source_labels:
        - __meta_kubernetes_pod_label_linkerd_io_control_plane_component
        - __meta_kubernetes_pod_container_port_name
        action: keep
        regex: (.*);admin-http$
      - source_labels: [__meta_kubernetes_pod_container_name]
        action: replace
        target_label: component

    - job_name: 'linkerd-service-mirror'
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels:
        - __meta_kubernetes_pod_label_linkerd_io_control_plane_component
        - __meta_kubernetes_pod_container_port_name
        action: keep
        regex: linkerd-service-mirror;admin-http$
      - source_labels: [__meta_kubernetes_pod_container_name]
        action: replace
        target_label: component

    - job_name: 'linkerd-proxy'
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - source_labels:
        - __meta_kubernetes_pod_container_name
        - __meta_kubernetes_pod_container_port_name
        - __meta_kubernetes_pod_label_linkerd_io_control_plane_ns
        action: keep
        regex: ^linkerd-proxy;linkerd-admin;linkerd$
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: pod
      # special case k8s' "job" label, to not interfere with prometheus' "job"
      # label
      # __meta_kubernetes_pod_label_linkerd_io_proxy_job=foo =>
      # k8s_job=foo
      - source_labels: [__meta_kubernetes_pod_label_linkerd_io_proxy_job]
        action: replace
        target_label: k8s_job
      # drop __meta_kubernetes_pod_label_linkerd_io_proxy_job
      - action: labeldrop
        regex: __meta_kubernetes_pod_label_linkerd_io_proxy_job
      # __meta_kubernetes_pod_label_linkerd_io_proxy_deployment=foo =>
      # deployment=foo
      - action: labelmap
        regex: __meta_kubernetes_pod_label_linkerd_io_proxy_(.+)
      # drop all labels that we just made copies of in the previous labelmap
      - action: labeldrop
        regex: __meta_kubernetes_pod_label_linkerd_io_proxy_(.+)
      # __meta_kubernetes_pod_label_linkerd_io_foo=bar =>
      # foo=bar
      - action: labelmap
        regex: __meta_kubernetes_pod_label_linkerd_io_(.+)
      # Copy all pod labels to tmp labels
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
        replacement: __tmp_pod_label_$1
      # Take `linkerd_io_` prefixed labels and copy them without the prefix
      - action: labelmap
        regex: __tmp_pod_label_linkerd_io_(.+)
        replacement:  __tmp_pod_label_$1
      # Drop the `linkerd_io_` originals
      - action: labeldrop
        regex: __tmp_pod_label_linkerd_io_(.+)
      # Copy tmp labels into real labels
      - action: labelmap
        regex: __tmp_pod_label_(.+)
---
kind: Service
apiVersion: v1
metadata:
  name: prometheus
  namespace: default
spec:
  type: ClusterIP
  selector:
    app: prometheus
  ports:
  - name: admin-http
    port: 9090
    targetPort: 9090
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      nodeSelector:
        beta.kubernetes.io/os: linux
      securityContext:
        fsGroup: 65534
      containers:
      - args:
        - --config.file=/etc/prometheus/prometheus.yml
        - --log.level=info
        - --storage.tsdb.path=/data
        - --storage.tsdb.retention.time=6h
        image: prom/prometheus:v2.19.3
        imagePullPolicy: IfNotPresent
        livenessProbe:
          httpGet:
            path: /-/healthy
            port: 9090
          initialDelaySeconds: 30
          timeoutSeconds: 30
        name: prometheus
        ports:
        - containerPort: 9090
          name: admin-http
        readinessProbe:
          httpGet:
            path: /-/ready
            port: 9090
          initialDelaySeconds: 30
          timeoutSeconds: 30
        securityContext:
          runAsNonRoot: true
          runAsUser: 65534
          runAsGroup: 65534
        volumeMounts:
        - mountPath: /data
          name: data
        - mountPath: /etc/prometheus/prometheus.yml
          name: prometheus-config
          subPath: prometheus.yml
          readOnly: true
      serviceAccountName: prometheus
      volumes:
      - name: data
        emptyDir: {}
      - configMap:
          name: prometheus-config
        name: prometheus-config