kubernetes v1.23.3 安装 kube-prometheus-release-0.11

节点信息

[root@cloud-1 kube-prometheus-release-0.11]# kubectl get node -o wide
NAME      STATUS   ROLES                  AGE   VERSION   INTERNAL-IP   EXTERNAL-IP   OS-IMAGE                           KERNEL-VERSION                 CONTAINER-RUNTIME
cloud-1   Ready    control-plane,master   39h   v1.23.3   172.17.4.40   <none>        Rocky Linux 8.7 (Green Obsidian)   4.18.0-425.10.1.el8_7.x86_64   containerd://1.6.19

kube-prometheus-release-0.11 下载

https://github.com/prometheus-operator/kube-prometheus
相关版本依赖 可参考如下文档
https://github.com/prometheus-operator/kube-prometheus/blob/main/README.md

部署过程

kubectl apply --server-side -f manifests/setup
kubectl apply -f manifests/

查看相关pod状态
kubectl get pod -n monitoring

[root@cloud-1 kube-prometheus-release-0.11]# kubectl get pod -n monitoring
NAME                                  READY   STATUS              RESTARTS   AGE
alertmanager-main-0                   2/2     Running             0          15h
alertmanager-main-1                   2/2     Running             0          15h
alertmanager-main-2                   2/2     Running             0          15h
blackbox-exporter-746c64fd88-hb99r    3/3     Running             0          16h
grafana-5fc7f9f55d-977cj              1/1     Running             0          16h
kube-state-metrics-6c8846558c-hwvd2   2/3     ImagePullBackOff    0          16h
node-exporter-bqb7b                   2/2     Running             0          16h
prometheus-adapter-6455646bdc-9zncj   0/1     Running             0          16h
prometheus-adapter-b4f7dc9b6-p5m9x    0/1     ErrImageNeverPull   0          2m52s
prometheus-adapter-b4f7dc9b6-zmw6t    0/1     ErrImageNeverPull   0          2m51s
prometheus-k8s-0                      2/2     Running             0          15h
prometheus-k8s-1                      2/2     Running             0          15h
prometheus-operator-f59c8b954-lg9sm   2/2     Running             0          16h

kubectl  -n monitoring describe pod prometheus-adapter-b4f7dc9b6-p5m9x
kubectl  -n monitoring describe pod kube-state-metrics-6c8846558c-hwvd2
prometheus-adapter  kube-state-metrics  获取镜像失败


kubectl  -n monitoring describe pod kube-state-metrics-6c8846558c-hwvd2

Events:
  Type     Reason   Age                     From     Message
  ----     ------   ----                    ----     -------
  Warning  Failed   54m (x38 over 15h)      kubelet  Failed to pull image "k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.5.0": rpc error: code = Unknown desc = failed to pull and unpack image "k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.5.0": failed to resolve reference "k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.5.0": failed to do request: Head "https://k8s.gcr.io/v2/kube-state-metrics/kube-state-metrics/manifests/v2.5.0": dial tcp 64.233.188.82:443: i/o timeout
  Normal   Pulling  9m34s (x175 over 16h)   kubelet  Pulling image "k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.5.0"
  Normal   BackOff  4m35s (x3858 over 16h)  kubelet  Back-off pulling image "k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.5.0"




上传无法直接下载的镜像
链接：https://pan.baidu.com/s/1cKeDTc7hc0ozIKkhEmYSig 
提取码：opxf 
导入镜像
ctr -n=k8s.io image import /root/kube-state-metricsv2.5.0
ctr -n=k8s.io image import /root/prometheus-adapterv0.9.1


[root@cloud-1 kube-prometheus-release-0.11]# kubectl get pod -n monitoring
NAME                                  READY   STATUS    RESTARTS   AGE
alertmanager-main-0                   2/2     Running   0          16h
alertmanager-main-1                   2/2     Running   0          16h
alertmanager-main-2                   2/2     Running   0          16h
blackbox-exporter-746c64fd88-hb99r    3/3     Running   0          16h
grafana-5fc7f9f55d-977cj              1/1     Running   0          16h
kube-state-metrics-59c8b66df6-dg76g   3/3     Running   0          21m
node-exporter-bqb7b                   2/2     Running   0          16h
prometheus-adapter-b4f7dc9b6-p5m9x    1/1     Running   0          35m
prometheus-adapter-b4f7dc9b6-zmw6t    1/1     Running   0          35m
prometheus-k8s-0                      2/2     Running   0          16h
prometheus-k8s-1                      2/2     Running   0          16h
prometheus-operator-f59c8b954-lg9sm   2/2     Running   0          16h

修改svc type

kubectl -n monitoring edit svc grafana
kubectl -n monitoring edit svc prometheus-k8s
将  type修改为NodePort
  type: NodePort

放通网络策略

cat network-policy-allow-all-ingress.yaml
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
  namespace: monitoring
  name: allow-all-ingress
spec:
  podSelector: {}
  ingress:
  - {}
  policyTypes:
  - Ingress

kubectl apply -f network-policy-allow-all-ingress.yaml