manifests-all.yaml

# Derived from ./manifests
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
  - kind: ServiceAccount
    name: prometheus-k8s
    namespace: monitoring
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
  - apiGroups: [""]
    resources:
      - nodes
      - nodes/proxy
      - services
      - endpoints
      - pods
    verbs: ["get", "list", "watch"]
  - apiGroups: [""]
    resources:
      - configmaps
    verbs: ["get"]
  - nonResourceURLs: ["/metrics"]
    verbs: ["get"]
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus-k8s
  namespace: monitoring
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager
  namespace: monitoring
data:
  config.yml: |-
    global:
      # ResolveTimeout is the time after which an alert is declared resolved
      # if it has not been updated.
      resolve_timeout: 5m

      # The smarthost and SMTP sender used for mail notifications.
      smtp_smarthost: 'smtp.gmail.com:587'
      smtp_from: 'foo@bar.com'
      smtp_auth_username: 'foo@bar.com'
      smtp_auth_password: 'barfoo'

      # The API URL to use for Slack notifications.
      slack_api_url: 'https://hooks.slack.com/services/some/api/token'

    # # The directory from which notification templates are read.
    templates:
    - '/etc/alertmanager-templates/*.tmpl'

    # The root route on which each incoming alert enters.
    route:

      # The labels by which incoming alerts are grouped together. For example,
      # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
      # be batched into a single group.

      group_by: ['alertname', 'cluster', 'service']

      # When a new group of alerts is created by an incoming alert, wait at
      # least 'group_wait' to send the initial notification.
      # This way ensures that you get multiple alerts for the same group that start
      # firing shortly after another are batched together on the first
      # notification.

      group_wait: 30s

      # When the first notification was sent, wait 'group_interval' to send a batch
      # of new alerts that started firing for that group.

      group_interval: 5m

      # If an alert has successfully been sent, wait 'repeat_interval' to
      # resend them.

      #repeat_interval: 1m
      repeat_interval: 15m

      # A default receiver

      # If an alert isn't caught by a route, send it to default.
      receiver: default

      # All the above attributes are inherited by all child routes and can
      # overwritten on each.

      # The child route trees.
      routes:
      # Send severity=slack alerts to slack.
      - match:
          severity: slack
        receiver: slack_alert
      # - match:
      #     severity: email
      #   receiver: email_alert

    receivers:
    - name: 'default'
      slack_configs:
      - channel: '#alertmanager-test'
        text: '<!channel>{{ template "slack.devops.text" . }}'
        send_resolved: true

    - name: 'slack_alert'
      slack_configs:
      - channel: '#alertmanager-test'
        send_resolved: true
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: alertmanager
  namespace: monitoring
  labels: 
    app: alertmanager
spec:
  replicas: 1
  selector:
    matchLabels:
      app: alertmanager
  template:
    metadata:
      name: alertmanager
      labels:
        app: alertmanager
    spec:
      containers:
        - name: alertmanager
          image: quay.io/prometheus/alertmanager:v0.7.1
          args:
            - "-config.file=/etc/alertmanager/config.yml"
            - "-storage.path=/alertmanager"
          ports:
            - name: alertmanager
              containerPort: 9093
          volumeMounts:
            - name: config-volume
              mountPath: /etc/alertmanager
            - name: templates-volume
              mountPath: /etc/alertmanager-templates
            - name: alertmanager
              mountPath: /alertmanager
      volumes:
        - name: config-volume
          configMap:
            name: alertmanager
        - name: templates-volume
          configMap:
            name: alertmanager-templates
        - name: alertmanager
          emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: "true"
    prometheus.io/path: "/metrics"
  labels:
    name: alertmanager
  name: alertmanager
  namespace: monitoring
spec:
  selector:
    app: alertmanager
  type: NodePort
  ports:
    - name: alertmanager
      protocol: TCP
      port: 9093
      targetPort: 9093
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-core
  namespace: monitoring
  labels:
    app: grafana
    component: core
spec:
  replicas: 1
  selector:
    matchLabels:
      app: grafana
      component: core
  template:
    metadata:
      labels:
        app: grafana
        component: core
    spec:
      containers:
        - image: grafana/grafana:latest
          name: grafana-core
          imagePullPolicy: Always
          # env:
          resources:
            # keep request = limit to keep this container in guaranteed class
            limits:
              cpu: 100m
              memory: 100Mi
            requests:
              cpu: 100m
              memory: 100Mi
          env:
            # The following env variables set up basic auth twith the default admin user and admin password.
            - name: GF_AUTH_BASIC_ENABLED
              value: "true"
            - name: GF_AUTH_ANONYMOUS_ENABLED
              value: "false"
            - name: GF_SECURITY_ADMIN_USER
              valueFrom:
                secretKeyRef:
                  name: monitoring
                  key: admin-username
            - name: GF_SECURITY_ADMIN_PASSWORD
              valueFrom:
                secretKeyRef:
                  name: monitoring
                  key: admin-password
            - name: GF_SMTP_HOST
              valueFrom:
                secretKeyRef:
                  name: monitoring
                  key: smtp-host
            - name: GF_SMTP_USER
              valueFrom:
                secretKeyRef:
                  name: monitoring
                  key: smtp-username
            - name: GF_SMTP_PASSWORD
              valueFrom:
                secretKeyRef:
                  name: monitoring
                  key: smtp-password
            # - name: GF_AUTH_ANONYMOUS_ORG_ROLE
            #   value: Admin
            # does not really work, because of template variables in exported dashboards:
            # - name: GF_DASHBOARDS_JSON_ENABLED
            #   value: "true"
          readinessProbe:
            httpGet:
              path: /login
              port: 3000
            # initialDelaySeconds: 30
            # timeoutSeconds: 1
          volumeMounts:
            - name: grafana-persistent-storage
              mountPath: /var/lib/grafana
      volumes:
        - name: grafana-persistent-storage
          emptyDir: {}
---
# apiVersion: extensions/v1beta1
# kind: Ingress
# metadata:
#   name: grafana
#   namespace: monitoring
# spec:
#   rules:
#   - host: <yourchoice>.<cluster-id>.k8s.gigantic.io
#     http:
#       paths:
#       - path: /
#         backend:
#          serviceName: grafana
#          servicePort: 3000
---
apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: monitoring
  labels:
    app: grafana
    component: core
spec:
  type: NodePort
  ports:
    - port: 3000
  selector:
    app: grafana
    component: core
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-core
  namespace: monitoring
  labels:
    app: prometheus
    component: core
spec:
  selector:
    matchLabels:
      app: prometheus
      component: core
  replicas: 1
  template:
    metadata:
      name: prometheus-main
      labels:
        app: prometheus
        component: core
    spec:
      serviceAccountName: prometheus-k8s
      containers:
        - name: prometheus
          image: prom/prometheus:v1.7.0
          args:
            - "-storage.local.retention=12h"
            - "-storage.local.memory-chunks=500000"
            - "-config.file=/etc/prometheus/prometheus.yaml"
            - "-alertmanager.url=http://alertmanager:9093/"
          ports:
            - name: webui
              containerPort: 9090
          resources:
            requests:
              cpu: 500m
              memory: 500M
            limits:
              cpu: 500m
              memory: 500M
          volumeMounts:
            - name: config-volume
              mountPath: /etc/prometheus
            - name: rules-volume
              mountPath: /etc/prometheus-rules
      volumes:
        - name: config-volume
          configMap:
            name: prometheus-core
        - name: rules-volume
          configMap:
            name: prometheus-rules
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kube-state-metrics
  namespace: monitoring
  labels:
    app: kube-state-metrics
spec:
  selector:
    matchLabels:
      app: kube-state-metrics
  replicas: 1
  template:
    metadata:
      labels:
        app: kube-state-metrics
    spec:
      serviceAccountName: kube-state-metrics
      containers:
        - name: kube-state-metrics
          image: gcr.io/google_containers/kube-state-metrics:v0.5.0
          ports:
            - containerPort: 8080
---
# ---
## apiVersion: rbac.authorization.k8s.io/v1beta1
## kind: ClusterRoleBinding
## metadata:
##   name: kube-state-metrics
## roleRef:
##   apiGroup: rbac.authorization.k8s.io
##   kind: ClusterRole
##   name: kube-state-metrics
## subjects:
## - kind: ServiceAccount
##   name: kube-state-metrics
##   namespace: monitoring
## ---
## apiVersion: rbac.authorization.k8s.io/v1beta1
## kind: ClusterRole
## metadata:
##   name: kube-state-metrics
## rules:
## - apiGroups: [""]
##   resources:
##   - nodes
##   - pods
##   - services
##   - resourcequotas
##   - replicationcontrollers
##   - limitranges
##   verbs: ["list", "watch"]
## - apiGroups: ["extensions"]
##   resources:
##   - daemonsets
##   - deployments
##   - replicasets
##   verbs: ["list", "watch"]
## ---
#apiVersion: v1
#kind: ServiceAccount
#metadata:
#  name: kube-state-metrics
#  namespace: monitoring
#---
#apiVersion: v1
#kind: Service
#metadata:
#  annotations:
#    prometheus.io/scrape: "true"
#  name: kube-state-metrics
#  namespace: monitoring
#  labels:
#    app: kube-state-metrics
#spec:
#  ports:
#    - name: kube-state-metrics
#      port: 8080
#      protocol: TCP
#  selector:
#    app: kube-state-metrics
#
#---
#apiVersion: apps/v1
#kind: DaemonSet
#metadata:
#  name: node-directory-size-metrics
#  namespace: monitoring
#  labels:
#    prom: disk
#  annotations:
#    description: |
#      This `DaemonSet` provides metrics in Prometheus format about disk usage on the nodes.
#      The container `read-du` reads in sizes of all directories below /mnt and writes that to `/tmp/metrics`. It only reports directories larger then `100M` for now.
#      The other container `caddy` just hands out the contents of that file on request via `http` on `/metrics` at port `9102` which are the defaults for Prometheus.
#      These are scheduled on every node in the Kubernetes cluster.
#      To choose directories from the node to check, just mount them on the `read-du` container below `/mnt`.
#spec:
#  selector:
#    matchLabels:
#      prom: disk
#  template:
#    metadata:
#      labels:
#        app: node-directory-size-metrics
#      annotations:
#        prometheus.io/scrape: "true"
#        prometheus.io/port: "9102"
#        description: |
#          This `Pod` provides metrics in Prometheus format about disk usage on the node.
#          The container `read-du` reads in sizes of all directories below /mnt and writes that to `/tmp/metrics`. It only reports directories larger then `100M` for now.
#          The other container `caddy` just hands out the contents of that file on request on `/metrics` at port `9102` which are the defaults for Prometheus.
#          This `Pod` is scheduled on every node in the Kubernetes cluster.
#          To choose directories from the node to check just mount them on `read-du` below `/mnt`.
#    spec:
#      containers:
#        - name: read-du
#          image: giantswarm/tiny-tools
#          imagePullPolicy: Always
#          # FIXME threshold via env var
#          # The
#          command:
#            - fish
#            - --command
#            - |
#              touch /tmp/metrics-temp
#              while true
#                for directory in (du --bytes --separate-dirs --threshold=100M /mnt)
#                  echo $directory | read size path
#                  echo "node_directory_size_bytes{path=\"$path\"} $size" \
#                    >> /tmp/metrics-temp
#                end
#                mv /tmp/metrics-temp /tmp/metrics
#                sleep 300
#              end
#          volumeMounts:
#            - name: host-fs-var
#              mountPath: /mnt/var
#              readOnly: true
#            - name: metrics
#              mountPath: /tmp
#        - name: caddy
#          image: dockermuenster/caddy:0.9.3
#          command:
#            - "caddy"
#            - "-port=9102"
#            - "-root=/var/www"
#          ports:
#            - containerPort: 9102
#          volumeMounts:
#            - name: metrics
#              mountPath: /var/www
#      volumes:
#        - name: host-fs-var
#          hostPath:
#            path: /var
#        - name: metrics
#          emptyDir:
#            medium: Memory
#---
#apiVersion: apps/v1
#kind: DaemonSet
#metadata:
#  name: prometheus-node-exporter
#  namespace: monitoring
#  labels:
#    app: prometheus
#    component: node-exporter
#spec:
#  selector:
#    matchLabels:
#      app: prometheus
#      component: node-exporter
#  template:
#    metadata:
#      name: prometheus-node-exporter
#      labels:
#        app: prometheus
#        component: node-exporter
#    spec:
#      containers:
#        - image: prom/node-exporter:v0.14.0
#          name: prometheus-node-exporter
#          ports:
#            - name: prom-node-exp
#              #^ must be an IANA_SVC_NAME (at most 15 characters, ..)
#              containerPort: 9100
#              hostPort: 9100
#      hostNetwork: true
#      hostPID: true
#---
#apiVersion: v1
#kind: Service
#metadata:
#  annotations:
#    prometheus.io/scrape: "true"
#  name: prometheus-node-exporter
#  namespace: monitoring
#  labels:
#    app: prometheus
#    component: node-exporter
#spec:
#  clusterIP: None
#  ports:
#    - name: prometheus-node-exporter
#      port: 9100
#      protocol: TCP
#  selector:
#    app: prometheus
#    component: node-exporter
#  type: ClusterIP
#---
#apiVersion: v1
#kind: Service
#metadata:
#  name: prometheus
#  namespace: monitoring
#  labels:
#    app: prometheus
#    component: core
#  annotations:
#    prometheus.io/scrape: "true"
#spec:
#  type: NodePort
#  ports:
#    - port: 9090
#      protocol: TCP
#      name: webui
#  selector:
#    app: prometheus
#    component: core