Kubernetes 之 Prometheus 监控 - cAdvisor （二）

配置文件

ctr images pull registry.cn-hangzhou.aliyuncs.com/zhangshijie/cadvisor-amd64:v0.39.3

[root@xksmaster1 case]# cat case1-daemonset-deploy-cadvisor.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: cadvisor
  namespace: monitoring
spec:
  selector:
    matchLabels:
      app: cAdvisor
  template:
    metadata:
      labels:
        app: cAdvisor
    spec:
      tolerations:    #污点容忍,忽略master的NoSchedule
        - effect: NoSchedule
          key: node-role.kubernetes.io/master
      hostNetwork: true
      restartPolicy: Always   # 重启策略
      containers:
      - name: cadvisor
        image: registry.cn-hangzhou.aliyuncs.com/zhangshijie/cadvisor-amd64:v0.39.3
        imagePullPolicy: IfNotPresent  # 镜像策略
        ports:
        - containerPort: 8080
        volumeMounts:
          - name: root
            mountPath: /rootfs
          - name: run
            mountPath: /var/run
          - name: sys
            mountPath: /sys
          - name: docker
            mountPath: /var/lib/docker
          - name: containerd
            mountPath: /var/lib/containerd
      volumes:
      - name: root
        hostPath:
          path: /
      - name: run
        hostPath:
          path: /var/run
      - name: sys
        hostPath:
          path: /sys
      - name: docker
        hostPath:
          path: /var/lib/docker
      - name: containerd
        hostPath:
          path: /var/lib/containerd

访问地址http://192.168.19.181:8080/containers/

Prometheus配置静态手动发现

[root@xksmaster1 case]# cat /apps/prometheus/prometheus.yml
# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["localhost:9090"]

  - job_name: "prometheus-node-xks"
    static_configs:
      - targets: ["192.168.19.180:9100","192.168.19.181:9100","192.168.19.182:9100"]

  - job_name: "prometheus-node-cAdvisor"
    static_configs:
      - targets: ["192.168.19.181:8080","192.168.19.182:8080"]


[root@xksmaster1 case]# systemctl restart prometheus

 应用14282模板