leader election token

README.md

Since we have leader election true:

kubectl create -f datadog/dd-configmap.yaml

Ensure we have all the permissions we need (including for leader election):

kubectl create -f datadog/datadog-rbac.yaml

Set up a mock check integration (hhtp_check) so that logs are enabled (otherwise it shows logs as disabled)

kubectl create -f datadog/example-integration.yaml

Finally launch the agent

kubectl create -f datadog/datadog-agent.yaml 

Validate that dd-agent is running.

kubectl get daemonset

Run the some checks:

kubectl exec datadog-agent-.. agent status 
kubectl exec datadog-agent-.. agent configcheck 
kubectl exec datadog-agent-.. agent health 

Under "Checks" the status command outputs what metrics are currently being collected.

Run the kube state metrics

kubectl create -f datadog/kube-state-metrics.yaml 

datadog-agent.yaml

apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: datadog-agent
spec:
  template:
    metadata:
      labels:
        app: datadog-agent
      name: datadog-agent
    spec:
      serviceAccountName: datadog-agent
      containers:
      - image: datadog/agent:latest
        imagePullPolicy: Always
        name: datadog-agent
        ports:
          - containerPort: 8125
            name: dogstatsdport
            protocol: UDP
          - containerPort: 8126
            name: traceport
            protocol: TCP
        env:
          - name: DD_API_KEY
            value: ***
          - name: DD_COLLECT_KUBERNETES_EVENTS
            value: "true"
          - name: DD_LEADER_ELECTION
            value: "true"
          - name: KUBERNETES
            value: "yes"
          - name: DD_KUBERNETES_KUBELET_HOST
            valueFrom:
              fieldRef:
                fieldPath: status.hostIP
          - name: DD_LOGS_ENABLED
            value: "true"
        resources:
          requests:
            memory: "128Mi"
            cpu: "100m"
          limits:
            memory: "512Mi"
            cpu: "250m"
        volumeMounts:
          - name: dockersocket
            mountPath: /var/run/docker.sock
          - name: procdir
            mountPath: /host/proc
            readOnly: true
          - name: cgroups
            mountPath: /host/sys/fs/cgroup
            readOnly: true
          - name: pointerdir
            mountPath: /opt/datadog-agent/run
          - name: dd-agent-config
            mountPath: /conf.d
        livenessProbe:
          exec:
            command:
            - ./probe.sh
          initialDelaySeconds: 15
          periodSeconds: 5
      volumes:
        - hostPath:
            path: /var/run/docker.sock
          name: dockersocket
        - hostPath:
            path: /proc
          name: procdir
        - hostPath:
            path: /sys/fs/cgroup
          name: cgroups
        - hostPath:
            path: /opt/datadog-agent/run
          name: pointerdir
        - name: dd-agent-config
          configMap:
            name: dd-agent-config
            items:
              - key: http-config
                path: http_check.yaml

datadog-rbac.yaml

kind: ServiceAccount
apiVersion: v1
metadata:
  name: datadog-agent
  namespace: default
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: datadog-agent
rules:
- apiGroups:
  - ""
  resources:
  - services
  - events
  - endpoints
  - pods
  - nodes
  - componentstatuses
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  resourceNames:
  - datadogtoken
  verbs:
  - get
  - update
- apiGroups:
  - ""
  resources:
  - configmaps
  verbs:
  - get
  - update
  - create
# Kubelet connectivity
- apiGroups:
  - ""
  resources:
  - nodes/metrics
  - nodes/spec
  - nodes/proxy
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: datadog-agent
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: datadog-agent
subjects:
- kind: ServiceAccount
  name: datadog-agent
  namespace: default

dd-configmap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: datadogtoken
data:
  event.tokenKey: "0"

example-integration.yaml

kind: ConfigMap
apiVersion: v1
metadata:
  name: dd-agent-config
  namespace: default
data:
  # see https://docs.datadoghq.com/integrations/http_check/
  http-config: |-
    init_config:
    instances:
    - name: BrpxService
      url: https://brpx.com
      skip_event: true
      tags:
        - service:critical
    - name: Downer website
      url: https://down.brpx.com/
      skip_event: true
    logs:
      - type: docker
        service: docker
        source: kubernetes
---

kube-state-metrics.yaml

---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kube-state-metrics
  namespace: default
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use 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: default
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
  name: kube-state-metrics
rules:
- apiGroups: [""]
  resources:
  - nodes
  - pods
  - services
  - resourcequotas
  - replicationcontrollers
  - limitranges
  - persistentvolumeclaims
  - persistentvolumes
  - namespaces
  - endpoints
  verbs: ["list", "watch"]
- apiGroups: ["extensions"]
  resources:
  - daemonsets
  - deployments
  - replicasets
  verbs: ["list", "watch"]
- apiGroups: ["apps"]
  resources:
  - statefulsets
  verbs: ["list", "watch"]
- apiGroups: ["batch"]
  resources:
  - cronjobs
  - jobs
  verbs: ["list", "watch"]
- apiGroups: ["autoscaling"]
  resources:
  - horizontalpodautoscalers
  verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
kind: Role
metadata:
  namespace: default
  name: kube-state-metrics-resizer
rules:
- apiGroups: [""]
  resources:
  - pods
  verbs: ["get"]
- apiGroups: ["extensions"]
  resources:
  - deployments
  resourceNames: ["kube-state-metrics"]
  verbs: ["get", "update"]
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
kind: RoleBinding
metadata:
  name: kube-state-metrics
  namespace: default
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: kube-state-metrics-resizer
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: default
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: kube-state-metrics
spec:
  replicas: 1
  template:
    metadata:
      labels:
        app: kube-state-metrics
    spec:
      containers:
      - name: kube-state-metrics
        image: gcr.io/google_containers/kube-state-metrics:v1.2.0
        ports:
        - name: metrics
          containerPort: 8080
        resources:
          requests:
            memory: 30Mi
            cpu: 100m
          limits:
            memory: 50Mi
            cpu: 200m
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  labels:
    app: kube-state-metrics
  name: kube-state-metrics
spec:
  ports:
  - name: metrics
    port: 8080
    targetPort: metrics
    protocol: TCP
  selector:
    app: kube-state-metrics