apiVersion: v1 automountServiceAccountToken: false kind: ServiceAccount metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 name: kube-state-metrics namespace: kube-system --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 name: kube-state-metrics rules: - apiGroups: - "" resources: - configmaps - secrets - nodes - pods - services - resourcequotas - replicationcontrollers - limitranges - persistentvolumeclaims - persistentvolumes - namespaces - endpoints 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: - authentication.k8s.io resources: - tokenreviews verbs: - create - apiGroups: - authorization.k8s.io resources: - subjectaccessreviews verbs: - create - 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: - admissionregistration.k8s.io resources: - mutatingwebhookconfigurations - validatingwebhookconfigurations verbs: - list - watch - apiGroups: - networking.k8s.io resources: - networkpolicies - ingresses verbs: - list - watch - apiGroups: - coordination.k8s.io resources: - leases verbs: - list - watch --- 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: - extensions resources: - ingresses verbs: - get - list - watch - nonResourceURLs: - /metrics verbs: - get --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 name: kube-state-metrics roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: kube-state-metrics subjects: - kind: ServiceAccount name: kube-state-metrics namespace: kube-system --- 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: default namespace: monitoring --- apiVersion: v1 data: config.yml: |- global: templates: - '/etc/alertmanager/*.tmpl' route: receiver: alert-emailer group_by: ['alertname', 'priority'] group_wait: 10s repeat_interval: 30m routes: - receiver: slack_demo # Send severity=slack alerts to slack. match: severity: slack group_wait: 10s repeat_interval: 1m receivers: - name: alert-emailer email_configs: - to: demo@devopscube.com send_resolved: false from: from-email@email.com smarthost: smtp.eample.com:25 require_tls: false - name: slack_demo slack_configs: - api_url: https://hooks.slack.com/services/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sz4Qk channel: '#devopscube-demo' kind: ConfigMap metadata: name: alertmanager-config namespace: monitoring --- apiVersion: v1 data: default.tmpl: | {{ define "__alertmanager" }}AlertManager{{ end }} {{ define "__alertmanagerURL" }}{{ .ExternalURL }}/#/alerts?receiver={{ .Receiver }}{{ end }} {{ define "__subject" }}[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .GroupLabels.SortedPairs.Values | join " " }} {{ if gt (len .CommonLabels) (len .GroupLabels) }}({{ with .CommonLabels.Remove .GroupLabels.Names }}{{ .Values | join " " }}{{ end }}){{ end }}{{ end }} {{ define "__description" }}{{ end }} {{ define "__text_alert_list" }}{{ range . }}Labels: {{ range .Labels.SortedPairs }} - {{ .Name }} = {{ .Value }} {{ end }}Annotations: {{ range .Annotations.SortedPairs }} - {{ .Name }} = {{ .Value }} {{ end }}Source: {{ .GeneratorURL }} {{ end }}{{ end }} {{ define "slack.default.title" }}{{ template "__subject" . }}{{ end }} {{ define "slack.default.username" }}{{ template "__alertmanager" . }}{{ end }} {{ define "slack.default.fallback" }}{{ template "slack.default.title" . }} | {{ template "slack.default.titlelink" . }}{{ end }} {{ define "slack.default.pretext" }}{{ end }} {{ define "slack.default.titlelink" }}{{ template "__alertmanagerURL" . }}{{ end }} {{ define "slack.default.iconemoji" }}{{ end }} {{ define "slack.default.iconurl" }}{{ end }} {{ define "slack.default.text" }}{{ end }} {{ define "hipchat.default.from" }}{{ template "__alertmanager" . }}{{ end }} {{ define "hipchat.default.message" }}{{ template "__subject" . }}{{ end }} {{ define "pagerduty.default.description" }}{{ template "__subject" . }}{{ end }} {{ define "pagerduty.default.client" }}{{ template "__alertmanager" . }}{{ end }} {{ define "pagerduty.default.clientURL" }}{{ template "__alertmanagerURL" . }}{{ end }} {{ define "pagerduty.default.instances" }}{{ template "__text_alert_list" . }}{{ end }} {{ define "opsgenie.default.message" }}{{ template "__subject" . }}{{ end }} {{ define "opsgenie.default.description" }}{{ .CommonAnnotations.SortedPairs.Values | join " " }} {{ if gt (len .Alerts.Firing) 0 -}} Alerts Firing: {{ template "__text_alert_list" .Alerts.Firing }} {{- end }} {{ if gt (len .Alerts.Resolved) 0 -}} Alerts Resolved: {{ template "__text_alert_list" .Alerts.Resolved }} {{- end }} {{- end }} {{ define "opsgenie.default.source" }}{{ template "__alertmanagerURL" . }}{{ end }} {{ define "victorops.default.message" }}{{ template "__subject" . }} | {{ template "__alertmanagerURL" . }}{{ end }} {{ define "victorops.default.from" }}{{ template "__alertmanager" . }}{{ end }} {{ define "email.default.subject" }}{{ template "__subject" . }}{{ end }} {{ define "email.default.html" }} {{ template "__subject" . }}
{{ .Alerts | len }} alert{{ if gt (len .Alerts) 1 }}s{{ end }} for {{ range .GroupLabels.SortedPairs }} {{ .Name }}={{ .Value }} {{ end }}
{{ if gt (len .Alerts.Firing) 0 }} {{ end }} {{ range .Alerts.Firing }} {{ end }} {{ if gt (len .Alerts.Resolved) 0 }} {{ if gt (len .Alerts.Firing) 0 }} {{ end }} {{ end }} {{ range .Alerts.Resolved }} {{ end }}
View in {{ template "__alertmanager" . }}
[{{ .Alerts.Firing | len }}] Firing
Labels
{{ range .Labels.SortedPairs }}{{ .Name }} = {{ .Value }}
{{ end }} {{ if gt (len .Annotations) 0 }}Annotations
{{ end }} {{ range .Annotations.SortedPairs }}{{ .Name }} = {{ .Value }}
{{ end }} Source


[{{ .Alerts.Resolved | len }}] Resolved
Labels
{{ range .Labels.SortedPairs }}{{ .Name }} = {{ .Value }}
{{ end }} {{ if gt (len .Annotations) 0 }}Annotations
{{ end }} {{ range .Annotations.SortedPairs }}{{ .Name }} = {{ .Value }}
{{ end }} Source
{{ end }} {{ define "pushover.default.title" }}{{ template "__subject" . }}{{ end }} {{ define "pushover.default.message" }}{{ .CommonAnnotations.SortedPairs.Values | join " " }} {{ if gt (len .Alerts.Firing) 0 }} Alerts Firing: {{ template "__text_alert_list" .Alerts.Firing }} {{ end }} {{ if gt (len .Alerts.Resolved) 0 }} Alerts Resolved: {{ template "__text_alert_list" .Alerts.Resolved }} {{ end }} {{ end }} {{ define "pushover.default.url" }}{{ template "__alertmanagerURL" . }}{{ end }} slack.tmpl: | {{ define "slack.devops.text" }} {{range .Alerts}}{{.Annotations.DESCRIPTION}} {{end}} {{ end }} kind: ConfigMap metadata: creationTimestamp: null name: alertmanager-templates namespace: monitoring --- apiVersion: v1 data: prometheus.yaml: |- { "apiVersion": 1, "datasources": [ { "access":"proxy", "editable": true, "name": "prometheus", "orgId": 1, "type": "prometheus", "url": "http://prometheus-service.monitoring.svc:8080", "version": 1 } ] } kind: ConfigMap metadata: name: grafana-datasources namespace: monitoring --- apiVersion: v1 kind: ConfigMap metadata: labels: name: prometheus-server-conf name: prometheus-server-conf namespace: monitoring data: prometheus.rules: |- groups: - name: devopscube demo alert rules: - alert: High Pod Memory expr: sum(container_memory_usage_bytes) > 1 for: 1m labels: severity: slack annotations: summary: High Memory Usage prometheus.yml: |- global: scrape_interval: 5s evaluation_interval: 5s rule_files: - /etc/prometheus/prometheus.rules alerting: alertmanagers: - scheme: http static_configs: - targets: - "alertmanager.monitoring.svc:9093" scrape_configs: - job_name: "haproxy" scrape_interval: 5s static_configs: - targets: ['haproxy_exporter:9101'] - job_name: "rtmp-fra1" scrape_interval: 5s static_configs: - targets: ['fra1.edge.lol:32113'] - job_name: "rtmp-lon1" scrape_interval: 5s static_configs: - targets: ['lon1.edge.lol:32113'] - job_name: "rtmp-nyc1" scrape_interval: 5s static_configs: - targets: ['nyc1.edge.lol:32113'] --- apiVersion: v1 kind: Service metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 name: kube-state-metrics namespace: kube-system spec: clusterIP: None ports: - name: http-metrics port: 8080 targetPort: http-metrics - name: telemetry port: 8081 targetPort: telemetry selector: app.kubernetes.io/name: kube-state-metrics --- apiVersion: v1 kind: Service metadata: annotations: prometheus.io/port: "9093" prometheus.io/scrape: "true" name: alertmanager namespace: monitoring spec: ports: - nodePort: 31000 port: 9093 targetPort: 9093 selector: app: alertmanager type: NodePort --- apiVersion: v1 kind: Service metadata: annotations: prometheus.io/port: "3000" prometheus.io/scrape: "true" name: grafana namespace: monitoring spec: ports: - nodePort: 32000 port: 3000 targetPort: 3000 selector: app: grafana type: NodePort --- apiVersion: v1 kind: Service metadata: annotations: prometheus.io/port: "9100" prometheus.io/scrape: "true" name: node-exporter namespace: monitoring spec: ports: - name: node-exporter port: 9100 protocol: TCP targetPort: 9100 selector: app.kubernetes.io/component: exporter app.kubernetes.io/name: node-exporter --- apiVersion: v1 kind: Service metadata: annotations: prometheus.io/port: "9090" prometheus.io/scrape: "true" name: prometheus-service namespace: monitoring spec: ports: - nodePort: 30000 port: 8080 targetPort: 9090 selector: app: prometheus-server type: NodePort --- apiVersion: apps/v1 kind: Deployment metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 name: kube-state-metrics namespace: kube-system spec: replicas: 1 selector: matchLabels: app.kubernetes.io/name: kube-state-metrics template: metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: kube-state-metrics app.kubernetes.io/version: 2.3.0 spec: automountServiceAccountToken: true containers: - image: k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.3.0 livenessProbe: httpGet: path: /healthz port: 8080 initialDelaySeconds: 5 timeoutSeconds: 5 name: kube-state-metrics ports: - containerPort: 8080 name: http-metrics - containerPort: 8081 name: telemetry readinessProbe: httpGet: path: / port: 8081 initialDelaySeconds: 5 timeoutSeconds: 5 securityContext: allowPrivilegeEscalation: false readOnlyRootFilesystem: true runAsUser: 65534 nodeSelector: kubernetes.io/os: linux serviceAccountName: kube-state-metrics --- apiVersion: apps/v1 kind: Deployment metadata: name: alertmanager namespace: monitoring spec: replicas: 1 selector: matchLabels: app: alertmanager template: metadata: labels: app: alertmanager name: alertmanager spec: containers: - args: - --config.file=/etc/alertmanager/config.yml - --storage.path=/alertmanager image: prom/alertmanager:latest name: alertmanager ports: - containerPort: 9093 name: alertmanager resources: limits: cpu: 1 memory: 1Gi requests: cpu: 500m memory: 500M volumeMounts: - mountPath: /etc/alertmanager name: config-volume - mountPath: /etc/alertmanager-templates name: templates-volume - mountPath: /alertmanager name: alertmanager volumes: - configMap: name: alertmanager-config name: config-volume - configMap: name: alertmanager-templates name: templates-volume - emptyDir: {} name: alertmanager --- apiVersion: apps/v1 kind: Deployment metadata: name: grafana namespace: monitoring spec: replicas: 1 selector: matchLabels: app: grafana template: metadata: labels: app: grafana name: grafana spec: containers: - image: grafana/grafana:latest name: grafana ports: - containerPort: 3000 name: grafana resources: limits: cpu: 1000m memory: 1Gi requests: cpu: 500m memory: 500M volumeMounts: - mountPath: /var/lib/grafana name: grafana-storage - mountPath: /etc/grafana/provisioning/datasources name: grafana-datasources readOnly: false volumes: - emptyDir: {} name: grafana-storage - configMap: defaultMode: 420 name: grafana-datasources name: grafana-datasources --- apiVersion: apps/v1 kind: Deployment metadata: labels: app: prometheus-server name: prometheus-deployment namespace: monitoring spec: replicas: 1 selector: matchLabels: app: prometheus-server template: metadata: labels: app: prometheus-server spec: containers: - args: - --config.file=/etc/prometheus/prometheus.yml - --storage.tsdb.path=/prometheus/ image: prom/prometheus name: prometheus ports: - containerPort: 9090 volumeMounts: - mountPath: /etc/prometheus/ name: prometheus-config-volume - mountPath: /prometheus/ name: prometheus-storage-volume volumes: - configMap: defaultMode: 420 name: prometheus-server-conf name: prometheus-config-volume - emptyDir: {} name: prometheus-storage-volume --- apiVersion: apps/v1 kind: DaemonSet metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: node-exporter name: node-exporter namespace: monitoring spec: selector: matchLabels: app.kubernetes.io/component: exporter app.kubernetes.io/name: node-exporter template: metadata: labels: app.kubernetes.io/component: exporter app.kubernetes.io/name: node-exporter spec: containers: - args: - --path.sysfs=/host/sys - --path.rootfs=/host/root - --no-collector.wifi - --no-collector.hwmon - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/) - --collector.netclass.ignored-devices=^(veth.*)$ image: prom/node-exporter name: node-exporter ports: - containerPort: 9100 protocol: TCP resources: limits: cpu: 250m memory: 180Mi requests: cpu: 102m memory: 180Mi volumeMounts: - mountPath: /host/sys mountPropagation: HostToContainer name: sys readOnly: true - mountPath: /host/root mountPropagation: HostToContainer name: root readOnly: true volumes: - hostPath: path: /sys name: sys - hostPath: path: / name: root --- apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: grafana namespace: monitoring spec: ingressClassName: nginx rules: - host: grafana.box.oe74.net http: paths: - backend: service: name: grafana port: number: 32000 path: / pathType: Prefix