在上一编文章部署kubernetes集群成功之后，接下来就是部署监控系统了，本编博客主要是基于coreos开源的prometheus-operator监控系统，该监控系统比较全面，主要是已经搞定了grafana的监控模版，废话不多说，接下来就进入正题:
下载v0.16.0.tar.gz release版本的prometheus-operator,然后解压(也可以下载源码自行编译)
wget https://github.com/coreos/prometheus-operator/archive/v0.16.0.tar.gz
tar -zvxf v0.16.0.tar.gz
[root@master-27 prometheus]# ls -l
total 5968
drwxrwxr-x 13 root root 4096 Jan 12 21:41 prometheus-operator-0.16.0
-rw-r--r-- 1 root root 2068 Jun 20 19:37 prometheus.yaml
-rwxr-xr-x 1 root root 6102555 Jun 20 20:03 v0.16.0.tar.gz
部署prometheus-operator的deployment
//用到的镜像是
- --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1
image: quay.io/coreos/prometheus-operator:v0.16.0
kubectl create -f bundle.yaml 部署成功查看
[root@master-27 prometheus-operator-0.16.0]# kubectl get deployment
NAME DESIRED CURRENT UP-TO-DATE AVAILABLE AGE
prometheus-operator 1 1 1 1 13h
[root@master-27 prometheus-operator-0.16.0]# kubectl get pod
NAME READY STATUS RESTARTS AGE
prometheus-operator-1084866340-sfpl3 1/1 Running 0 13h部署grafana alternanager kube-status-meric
[root@master-27 prometheus-operator-0.16.0]# cd contrib/kube-prometheus/
[root@master-27 kube-prometheus]# pwd
/root/prometheus/prometheus-operator-0.16.0/contrib/kube-prometheus
./hack/cluster-monitoring/deploy
[root@master-27 kube-prometheus]# ./hack/cluster-monitoring/deploy
namespace "monitoring" created
Warning: kubectl apply should be used on resource created by either kubectl create --save-config or kubectl apply
clusterrolebinding.rbac.authorization.k8s.io "prometheus-operator" configured
Warning: kubectl apply should be used on resource created by either kubectl create --save-config or kubectl apply
clusterrole.rbac.authorization.k8s.io "prometheus-operator" configured
serviceaccount "prometheus-operator" created
service "prometheus-operator" created
deployment.extensions "prometheus-operator" created
Waiting for Operator to register custom resource definitions...done!
daemonset.extensions "node-exporter" created
serviceaccount "node-exporter" created
service "node-exporter" created
unable to recognize "manifests/node-exporter/node-exporter-cluster-role-binding.yaml": no matches for kind "ClusterRoleBinding" in version "rbac.authorization.k8s.io/v1"
unable to recognize "manifests/node-exporter/node-exporter-cluster-role.yaml": no matches for kind "ClusterRole" in version "rbac.authorization.k8s.io/v1"
clusterrolebinding.rbac.authorization.k8s.io "kube-state-metrics" created
clusterrole.rbac.authorization.k8s.io "kube-state-metrics" created
deployment.extensions "kube-state-metrics" created
rolebinding.rbac.authorization.k8s.io "kube-state-metrics" created
role.rbac.authorization.k8s.io "kube-state-metrics-resizer" created
serviceaccount "kube-state-metrics" created
service "kube-state-metrics" created
secret "grafana-credentials" created
secret "grafana-credentials" unchanged
configmap "grafana-dashboards-0" created
deployment.apps "grafana" created
service "grafana" created
servicemonitor.monitoring.coreos.com "prometheus-operator" created
serviceaccount "prometheus-k8s" created
servicemonitor.monitoring.coreos.com "kube-controller-manager" created
servicemonitor.monitoring.coreos.com "node-exporter" created
servicemonitor.monitoring.coreos.com "prometheus" created
prometheus.monitoring.coreos.com "k8s" created
servicemonitor.monitoring.coreos.com "kube-state-metrics" created
servicemonitor.monitoring.coreos.com "alertmanager" created
servicemonitor.monitoring.coreos.com "kubelet" created
servicemonitor.monitoring.coreos.com "kube-scheduler" created
configmap "prometheus-k8s-rules" created
service "prometheus-k8s" created
servicemonitor.monitoring.coreos.com "kube-apiserver" created
role.rbac.authorization.k8s.io "prometheus-k8s" created
role.rbac.authorization.k8s.io "prometheus-k8s" created
role.rbac.authorization.k8s.io "prometheus-k8s" created
clusterrole.rbac.authorization.k8s.io "prometheus-k8s" created
rolebinding.rbac.authorization.k8s.io "prometheus-k8s" created
rolebinding.rbac.authorization.k8s.io "prometheus-k8s" created
rolebinding.rbac.authorization.k8s.io "prometheus-k8s" created
clusterrolebinding.rbac.authorization.k8s.io "prometheus-k8s" created
secret "alertmanager-main" created
service "alertmanager-main" created
alertmanager.monitoring.coreos.com "main" created用到的镜像好多,这里就不多说了，主要是有个镜像是谷歌的需要翻墙，可以自行翻墙下载，其他镜像都是quay.io/coreos，这个特别的镜像是
gcr.io/google_containers/addon-resizer:1.0查看结果
[root@master-27 kube-prometheus]# kubectl get deployment -n monitoring
NAME DESIRED CURRENT UP-TO-DATE AVAILABLE AGE
grafana 1 1 1 1 13h
kube-state-metrics 1 1 1 1 13h
prometheus-operator 1 1 1 1 13h
[root@master-27 kube-prometheus]# kubectl get pods -n monitoring
NAME READY STATUS RESTARTS AGE
alertmanager-main-0 2/2 Running 0 13h
alertmanager-main-1 2/2 Running 0 13h
alertmanager-main-2 2/2 Running 0 13h
grafana-2315080943-nzl62 2/2 Running 0 12h
kube-state-metrics-2381097451-06789 4/4 Running 0 40s
node-exporter-2s6bm 2/2 Running 0 13h
node-exporter-q79n2 2/2 Running 0 13h
node-exporter-r4dqt 2/2 Running 0 13h
prometheus-k8s-0 2/2 Running 0 13h
prometheus-k8s-1 2/2 Running 0 13h
prometheus-operator-1084866340-ljvfm 1/1 Running 0 13h[root@master-27 kube-prometheus]# kubectl get svc -n monitoring
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
alertmanager-main NodePort 10.12.192.98 <none> 9093:30903/TCP 13h
alertmanager-operated ClusterIP None <none> 9093/TCP,6783/TCP 13h
grafana NodePort 10.0.122.89 <none> 3000:30902/TCP 13h
kube-state-metrics ClusterIP None <none> 8443/TCP,9443/TCP 13h
node-exporter ClusterIP None <none> 9100/TCP 13h
prometheus-k8s NodePort 10.3.237.34 <none> 9090:30900/TCP 13h
prometheus-operated ClusterIP None <none> 9090/TCP 13h
prometheus-operator ClusterIP 10.10.228.57 <none> 8080/TCP 13h访问grafana的页面master-ip:/30902,
访问prometheus的页面master-ip:/30900
访问alertmanager 告警页面master-ip:/30903
到此为止，已经成功部署了k8s集群监控prometheus-operator