First commit

templates/0-namespace.yaml

@@ -0,0 +1,6 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  labels:
+    name: monitoring

templates/config.yaml

@@ -0,0 +1,253 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+  namespace: monitoring
+data:
+  prometheus.yaml: |-
+    # Global config
+    global:
+      scrape_interval: 15s
+
+    # AlertManager
+    alerting:
+      alertmanagers:
+      - static_configs:
+        - targets:
+          - alertmanager:9093
+
+    # Scrape configs for running Prometheus on a Kubernetes cluster.
+    # This uses separate scrape configs for cluster components (i.e. API server, node)
+    # and services to allow each to use different authentication configs.
+    #
+    # Kubernetes labels will be added as Prometheus labels on metrics via the
+    # `labelmap` relabeling action.
+    scrape_configs:
+
+    # Scrape config for API servers.
+    #
+    # Kubernetes exposes API servers as endpoints to the default/kubernetes
+    # service so this uses `endpoints` role and uses relabelling to only keep
+    # the endpoints associated with the default/kubernetes service using the
+    # default named port `https`. This works for single API server deployments as
+    # well as HA API server deployments.
+    - job_name: 'kubernetes-apiservers'
+      kubernetes_sd_configs:
+      - role: endpoints
+      
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        # Using endpoints to discover kube-apiserver targets finds the pod IP
+        # (host IP since apiserver uses host network) which is not used in
+        # the server certificate.
+        insecure_skip_verify: true
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      # Keep only the default/kubernetes service endpoints for the https port. This
+      # will add targets for each API server which Kubernetes adds an endpoint to
+      # the default/kubernetes service.
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: default;kubernetes;https
+      - replacement: apiserver
+        action: replace
+        target_label: job
+
+      metric_relabel_configs:
+      - source_labels: [__name__]
+        action: drop
+        regex: etcd_(debugging|disk|request|server).*
+      - source_labels: [__name__]
+        action: drop
+        regex: apiserver_admission_controller_admission_latencies_seconds_.*
+      - source_labels: [__name__]
+        action: drop
+        regex: apiserver_admission_step_admission_latencies_seconds_.*
+      - source_labels: [__name__, group]
+        regex: apiserver_request_duration_seconds_bucket;.+
+        action: drop
+
+    # Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
+    # metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
+    - job_name: 'kubelet'
+      kubernetes_sd_configs:
+      - role: node
+      
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        # Kubelet certs don't have any fixed IP SANs
+        insecure_skip_verify: true
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_name
+
+    # Scrape config for Kubelet cAdvisor. Explore metrics from a node by
+    # scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
+    - job_name: 'kubernetes-cadvisor'
+      kubernetes_sd_configs:
+      - role: node
+
+      scheme: https
+      metrics_path: /metrics/cadvisor
+      tls_config:
+        # Kubelet certs don't have any fixed IP SANs
+        insecure_skip_verify: true
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_name
+      metric_relabel_configs:
+      - source_labels: [__name__, image]
+        action: drop
+        regex: container_([a-z_]+);
+      - source_labels: [__name__]
+        action: drop
+        regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
+
+
+    # Scrap etcd metrics from controllers via listen-metrics-urls
+    - job_name: 'etcd'
+      kubernetes_sd_configs:
+      - role: node
+      scheme: http
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
+        action: keep
+        regex: 'true'
+      - action: labelmap
+        regex: __meta_kubernetes_node_name
+      - source_labels: [__meta_kubernetes_node_address_InternalIP]
+        action: replace
+        target_label: __address__
+        replacement: '${1}:2381'
+    
+    # Scrape config for service endpoints.
+    #
+    # The relabeling allows the actual service scrape endpoint to be configured
+    # via the following annotations:
+    #
+    # * `prometheus.io/scrape`: Only scrape services that have a value of `true`
+    # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need
+    # to set this to `https` & most likely set the `tls_config` of the scrape config.
+    # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
+    # * `prometheus.io/port`: If the metrics are exposed on a different port to the
+    # service then set this appropriately.
+    - job_name: 'kubernetes-service-endpoints'
+      kubernetes_sd_configs:
+      - role: endpoints
+
+      honor_labels: true
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+        action: replace
+        target_label: __scheme__
+        regex: (https?)
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+        action: replace
+        target_label: __address__
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+      - action: labelmap
+        regex: __meta_kubernetes_service_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: pod
+      - source_labels: [__meta_kubernetes_service_name]
+        action: replace
+        target_label: job
+      
+      metric_relabel_configs:
+      - source_labels: [__name__]
+        action: drop
+        regex: etcd_(debugging|disk|request|server).*
+
+    # Example scrape config for probing services via the Blackbox Exporter.
+    #
+    # The relabeling allows the actual service scrape endpoint to be configured
+    # via the following annotations:
+    #
+    # * `prometheus.io/probe`: Only probe services that have a value of `true`
+    - job_name: 'kubernetes-services'
+
+      metrics_path: /probe
+      params:
+        module: [http_2xx]
+
+      kubernetes_sd_configs:
+      - role: service
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
+        action: keep
+        regex: true
+      - source_labels: [__address__]
+        target_label: __param_target
+      - target_label: __address__
+        replacement: blackbox
+      - source_labels: [__param_target]
+        target_label: instance
+      - action: labelmap
+        regex: __meta_kubernetes_service_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        target_label: namespace
+      - source_labels: [__meta_kubernetes_service_name]
+        target_label: job
+
+    # Example scrape config for pods
+    #
+    # The relabeling allows the actual pod scrape endpoint to be configured via the
+    # following annotations:
+    #
+    # * `prometheus.io/scrape`: Only scrape pods that have a value of `true`
+    # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
+    # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the
+    # pod's declared ports (default is a port-free target if none are declared).
+    - job_name: 'kubernetes-pods'
+
+      kubernetes_sd_configs:
+      - role: pod
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: kubernetes_pod_name
+
+    # Rule files
+    rule_files:
+      - "/etc/prometheus/rules/*.rules"
+      - "/etc/prometheus/rules/*.yaml"
+      - "/etc/prometheus/rules/*.yml"

templates/deployment.yaml

@@ -0,0 +1,63 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      name: prometheus
+      phase: prod
+  template:
+    metadata:
+      labels:
+        name: prometheus
+        phase: prod
+      annotations:
+        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
+    spec:
+      serviceAccountName: prometheus
+      containers:
+        - name: prometheus
+          image: quay.io/prometheus/prometheus:v2.15.2
+          args:
+            - --web.listen-address=0.0.0.0:9090
+            - --config.file=/etc/prometheus/prometheus.yaml
+            - --storage.tsdb.path=/var/lib/prometheus
+          ports:
+            - name: web
+              containerPort: 9090
+          resources:
+            requests:
+              cpu: 100m
+              memory: 200Mi
+          volumeMounts:
+            - name: config
+              mountPath: /etc/prometheus
+            - name: rules
+              mountPath: /etc/prometheus/rules
+            - name: data
+              mountPath: /var/lib/prometheus
+          livenessProbe:
+            httpGet:
+              path: /-/healthy
+              port: 9090
+            initialDelaySeconds: 10
+            timeoutSeconds: 10
+          readinessProbe:
+            httpGet:
+              path: /-/ready
+              port: 9090
+            initialDelaySeconds: 10
+            timeoutSeconds: 10
+      terminationGracePeriodSeconds: 30
+      volumes:
+        - name: config
+          configMap:
+            name: prometheus-config
+        - name: rules
+          configMap:
+            name: prometheus-rules
+        - name: data
+          emptyDir: {}

templates/discovery/kube-controller-manager.yaml

@@ -0,0 +1,18 @@
+# Allow Prometheus to scrape service endpoints
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-controller-manager
+  namespace: kube-system
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  clusterIP: None
+  selector:
+    k8s-app: kube-controller-manager
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 10252
+      targetPort: 10252

templates/discovery/kube-proxy.yaml

@@ -0,0 +1,19 @@
+# Allow Prometheus to scrape service endpoints
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-proxy
+  namespace: kube-system
+  annotations:
+    prometheus.io/scrape: 'true'
+    prometheus.io/port: '10249'
+spec:
+  type: ClusterIP
+  clusterIP: None
+  selector:
+    k8s-app: kube-proxy
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 10249
+      targetPort: 10249

templates/discovery/kube-scheduler.yaml

@@ -0,0 +1,18 @@
+# Allow Prometheus to scrape service endpoints
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-scheduler
+  namespace: kube-system
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  clusterIP: None
+  selector:
+    k8s-app: kube-scheduler
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 10251
+      targetPort: 10251

templates/exporters/kube-state-metrics/cluster-role-binding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1
+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

templates/exporters/kube-state-metrics/cluster-role.yaml

@@ -0,0 +1,103 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: kube-state-metrics
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - configmaps
+  - secrets
+  - nodes
+  - pods
+  - services
+  - resourcequotas
+  - replicationcontrollers
+  - limitranges
+  - persistentvolumeclaims
+  - persistentvolumes
+  - namespaces
+  - endpoints
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - extensions
+  resources:
+  - daemonsets
+  - deployments
+  - replicasets
+  - ingresses
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - apps
+  resources:
+  - statefulsets
+  - daemonsets
+  - deployments
+  - replicasets
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - batch
+  resources:
+  - cronjobs
+  - jobs
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - autoscaling
+  resources:
+  - horizontalpodautoscalers
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - policy
+  resources:
+  - poddisruptionbudgets
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - certificates.k8s.io
+  resources:
+  - certificatesigningrequests
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - storage.k8s.io
+  resources:
+  - storageclasses
+  - volumeattachments
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - autoscaling.k8s.io
+  resources:
+  - verticalpodautoscalers
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - admissionregistration.k8s.io
+  resources:
+  - mutatingwebhookconfigurations
+  - validatingwebhookconfigurations
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - networking.k8s.io
+  resources:
+  - networkpolicies
+  verbs:
+  - list
+  - watch
+

templates/exporters/kube-state-metrics/deployment.yaml

@@ -0,0 +1,42 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  replicas: 1
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  selector:
+    matchLabels:
+      name: kube-state-metrics
+      phase: prod
+  template:
+    metadata:
+      labels:
+        name: kube-state-metrics
+        phase: prod
+      annotations:
+        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
+    spec:
+      serviceAccountName: kube-state-metrics
+      containers:
+      - name: kube-state-metrics
+        image: quay.io/coreos/kube-state-metrics:v1.9.3
+        ports:
+          - name: metrics
+            containerPort: 8080
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 8081
+          initialDelaySeconds: 5
+          timeoutSeconds: 5

templates/exporters/kube-state-metrics/service-account.yaml

@@ -0,0 +1,5 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring

templates/exporters/kube-state-metrics/service.yaml

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  # service is created to allow prometheus to scape endpoints
+  clusterIP: None
+  selector:
+    name: kube-state-metrics
+    phase: prod
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 8080
+      targetPort: 8080

templates/exporters/node-exporter/daemonset.yaml

@@ -0,0 +1,73 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+spec:
+  updateStrategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  selector:
+    matchLabels:
+      name: node-exporter
+      phase: prod
+  template:
+    metadata:
+      labels:
+        name: node-exporter
+        phase: prod
+      annotations:
+        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
+    spec:
+      serviceAccountName: node-exporter
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65534
+      hostNetwork: true
+      hostPID: true
+      containers:
+      - name: node-exporter
+        image: quay.io/prometheus/node-exporter:v0.18.1
+        args:
+          - --path.procfs=/host/proc
+          - --path.sysfs=/host/sys
+          - --path.rootfs=/host/root
+          - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/)
+          - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
+        ports:
+          - name: metrics
+            containerPort: 9100
+            hostPort: 9100
+        resources:
+          requests:
+            cpu: 100m
+            memory: 50Mi
+          limits:
+            cpu: 200m
+            memory: 100Mi
+        volumeMounts:
+          - name: proc
+            mountPath: /host/proc
+            readOnly:  true
+          - name: sys
+            mountPath: /host/sys
+            readOnly: true
+          - name: root
+            mountPath: /host/root
+            readOnly: true
+      tolerations:
+        - key: node-role.kubernetes.io/master
+          operator: Exists
+        - key: node.kubernetes.io/not-ready
+          operator: Exists
+      volumes:
+        - name: proc
+          hostPath:
+            path: /proc
+        - name: sys
+          hostPath:
+            path: /sys
+        - name: root
+          hostPath:
+            path: /

templates/exporters/node-exporter/service-account.yaml

@@ -0,0 +1,5 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: node-exporter
+  namespace: monitoring

templates/exporters/node-exporter/service.yaml

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  # service is created to allow prometheus to scape endpoints
+  clusterIP: None
+  selector:
+    name: node-exporter
+    phase: prod
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 80
+      targetPort: 9100

templates/network-policy.yaml

@@ -0,0 +1,28 @@
+# Allow Grafana access and in-cluster Prometheus scraping
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  podSelector:
+    matchLabels:
+      name: prometheus
+  ingress:
+    - ports:
+        - protocol: TCP
+          port: 9090
+      from:
+        - namespaceSelector:
+            matchLabels:
+              name: monitoring
+          podSelector:
+            matchLabels:
+              name: grafana
+        - namespaceSelector:
+            matchLabels:
+              name: monitoring
+          podSelector:
+            matchLabels:
+              name: prometheus
+

templates/rbac/cluster-role-binding.yaml

@@ -0,0 +1,12 @@
+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
+  namespace: monitoring

templates/rbac/cluster-role.yaml

@@ -0,0 +1,15 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: prometheus
+rules:
+- apiGroups: [""]
+  resources:
+  - nodes
+  - nodes/metrics
+  - services
+  - endpoints
+  - pods
+  verbs: ["get", "list", "watch"]
+- nonResourceURLs: ["/metrics"]
+  verbs: ["get"]

templates/service-account.yaml

@@ -0,0 +1,5 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: monitoring

templates/service.yaml

@@ -0,0 +1,18 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+  annotations:
+    prometheus.io/scrape: 'true'
+    prometheus.io/port: '9090'
+spec:
+  type: ClusterIP
+  selector:
+    name: prometheus
+    phase: prod
+  ports:
+    - name: web
+      protocol: TCP
+      port: 80
+      targetPort: 9090