Kubernets集群排错之-scheduler&controller-manager组件不健康

scheduler&controller-manager status Unhealthy

使用"kubectl get cs"查看集群状态，发现scheduler&controller-manager组件的状态都是 Unhealthy的，且提示"Get “http://127.0.0.1:10251/healthz”: dial tcp 127.0.0.1:10251: connect: connection refused"

分析问题

查看相应的yaml文件，发现是kube-controller-manager.yaml和kube-scheduler.yaml设置的默认端口是0。

[root@master1 ~]# cd /etc/kubernetes/manifests/
[root@master1 manifests]# ll
total 16
-rw------- 1 root root 2109 Sep  6 16:27 etcd.yaml
-rw------- 1 root root 3171 Sep  6 16:27 kube-apiserver.yaml
-rw------- 1 root root 2859 Sep  7 14:02 kube-controller-manager.yaml
-rw------- 1 root root 1414 Sep  7 14:03 kube-scheduler.yaml

[root@master1 manifests]# vim kube-controller-manager.yaml
apiVersion: v1
kind: Pod
metadata:
  creationTimestamp: null
  labels:
    component: kube-controller-manager
    tier: control-plane
  name: kube-controller-manager
  namespace: kube-system
spec:
  containers:
  - command:
    - kube-controller-manager
    - --allocate-node-cidrs=true
    - --authentication-kubeconfig=/etc/kubernetes/controller-manager.conf
    - --authorization-kubeconfig=/etc/kubernetes/controller-manager.conf
    - --bind-address=127.0.0.1
    - --client-ca-file=/etc/kubernetes/pki/ca.crt
    - --cluster-cidr=172.10.0.0/16
    - --cluster-name=kubernetes
    - --cluster-signing-cert-file=/etc/kubernetes/pki/ca.crt
    - --cluster-signing-key-file=/etc/kubernetes