prometheus

--name space  생성
root@k8s-master-00:~# kubectl create ns monitoring
namespace/monitoring created

root@k8s-master-00:~# vim prometheus-cluster-role.yaml
apiVersion: rbac.authorization.k8s.io/v1    
kind: ClusterRole
metadata:
  name: prometheus
  namespace: monitoring
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:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: default
  namespace: monitoring
  
root@k8s-master-00:~# kubectl apply -f prometheus-cluster-role.yaml
clusterrole.rbac.authorization.k8s.io/prometheus created
clusterrolebinding.rbac.authorization.k8s.io/prometheus created

root@k8s-master-00:~# vim prometheus-config-map.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-server-conf
  labels:
    name: prometheus-server-conf
  namespace: monitoring
data:
  prometheus.rules: |-    
    groups:
    - name: container memory alert
      rules:
      - alert: container memory usage rate is very high( > 55%)
        expr: sum(container_memory_working_set_bytes{pod!="", name=""})/ sum (kube_node_status_allocatable_memory_bytes) * 100 > 55
        for: 1m
        labels:
          severity: fatal
        annotations:
          summary: High Memory Usage on
          identifier: ""
          description: " Memory Usage: "
    - name: container CPU alert
      rules:
      - alert: container CPU usage rate is very high( > 10%)
        expr: sum (rate (container_cpu_usage_seconds_total{pod!=""}[1m])) / sum (machine_cpu_cores) * 100 > 10
        for: 1m
        labels:
          severity: fatal
        annotations:
          summary: High Cpu 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: 'kubernetes-apiservers'
        kubernetes_sd_configs:
        - role: endpoints
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: default;kubernetes;https
      - job_name: 'kubernetes-nodes'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        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
      - 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:$2
          target_label: __address__
        - action: labelmap
          regex: __meta_kubernetes_pod_label_(.+)
        - source_labels: [__meta_kubernetes_namespace]
          action: replace
          target_label: kubernetes_namespace
        - source_labels: [__meta_kubernetes_pod_name]
          action: replace
          target_label: kubernetes_pod_name
      - job_name: 'kube-state-metrics'
        static_configs:
          - targets: ['kube-state-metrics.kube-system.svc.cluster.local:8080']
      - job_name: 'kubernetes-cadvisor'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - target_label: __address__
          replacement: kubernetes.default.svc:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
      - job_name: 'kubernetes-service-endpoints'
        kubernetes_sd_configs:
        - role: endpoints
        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: kubernetes_namespace
        - source_labels: [__meta_kubernetes_service_name]
          action: replace
          target_label: kubernetes_name
          
root@k8s-master-00:~# kubectl apply -f prometheus-config-map.yaml
configmap/prometheus-server-conf created

--디플로이먼트 를 적용 하여 파드 생성
root@k8s-master-00:~# vim prometheus-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-deployment
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus-server
  template:
    metadata:
      labels:
        app: prometheus-server
    spec:
      containers:
        - name: prometheus
          image: prom/prometheus:latest   
          args:
            - "--config.file=/etc/prometheus/prometheus.yml"
            - "--storage.tsdb.path=/prometheus/"
          ports:
            - containerPort: 9090
          volumeMounts:    
            - name: prometheus-config-volume
              mountPath: /etc/prometheus/
            - name: prometheus-storage-volume
              mountPath: /prometheus/
      volumes:
        - name: prometheus-config-volume
          configMap:
            defaultMode: 420
            name: prometheus-server-conf
        - name: prometheus-storage-volume
          emptyDir: {}
root@k8s-master-00:~# kubectl apply -f prometheus-deployment.yaml
deployment.apps/prometheus-deployment created

-- 디플로이먼트 확인
root@k8s-master-00:~# kubectl get deployment -n monitoring
NAME                    READY   UP-TO-DATE   AVAILABLE   AGE
prometheus-deployment   1/1     1            1           51s

-- 파드 확인 
root@k8s-master-00:~# kubectl get pod -n monitoring
NAME                                     READY   STATUS    RESTARTS   AGE
prometheus-deployment-568f7f568f-r6wzz   1/1     Running   0          59s

--동작 상태
root@k8s-master-00:~# kubectl get pod -n monitoring -o wide
NAME                                     READY   STATUS    RESTARTS   AGE    IP                NODE            NOMINATED NODE   READINESS GATES
prometheus-deployment-568f7f568f-r6wzz   1/1     Running   0          112s   192.168.118.116   k8s-worker-02   <none>           <none>

--데몬셋을 이용한 node exporter : 각 노드에 정보를 수집할 파드를 배치
root@k8s-master-00:~# vim prometheus-node-exporter.yaml
apiVersion: apps/v1
kind: DaemonSet    
metadata:
  name: node-exporter
  namespace: monitoring
  labels:
    k8s-app: node-exporter
spec:
  selector:
    matchLabels:
      k8s-app: node-exporter
  template:
    metadata:
      labels:
        k8s-app: node-exporter
    spec:
      containers:
      - image: prom/node-exporter
        name: node-exporter
        ports:
        - containerPort: 9100
          protocol: TCP
          name: http
---
apiVersion: v1
kind: Service
metadata:
  labels:
    k8s-app: node-exporter
  name: node-exporter
  namespace: kube-system
spec:
  ports:
  - name: http
    port: 9100
    nodePort: 31672
    protocol: TCP
  type: NodePort
  selector:
    k8s-app: node-exporter
    
root@k8s-master-00:~# kubectl apply -f prometheus-node-exporter.yaml
daemonset.apps/node-exporter created
service/node-exporter created

root@k8s-master-00:~# kubectl get daemonset -n monitoring
NAME            DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE   NODE SELECTOR   AGE
node-exporter   2         2         2       2            2           <none>          39s

root@k8s-master-00:~# vim prometheus-svc.yaml
apiVersion: v1
kind: Service
metadata:
  name: prometheus-service
  namespace: monitoring
  annotations:
      prometheus.io/scrape: 'true'
      prometheus.io/port:   '9090'
spec:
  selector:
    app: prometheus-server
  type: NodePort    
  ports:
    - port: 8080
      targetPort: 9090
      nodePort: 30001
      
root@k8s-master-00:~# kubectl apply -f prometheus-svc.yaml
service/prometheus-service created

root@k8s-master-00:~# kubectl get svc -n monitoring
NAME                 TYPE       CLUSTER-IP     EXTERNAL-IP   PORT(S)          AGE
prometheus-service   NodePort   10.98.48.221   <none>        8080:30001/TCP   2m50s

 

매트릭을 공급해주는 pod가 없어서 down상태임