root@k8s-master1 \~# kubectl get cs
NAME STATUS MESSAGE ERROR
controller-manager Healthy ok
scheduler Healthy ok
etcd-1 Healthy {"health":"true"}
etcd-0 Healthy {"health":"true"}
etcd-2 Unhealthy HTTP probe failed with statuscode: 503
ETCDCTL_API=3 /opt/etcd/bin/etcdctl --cacert=/opt/etcd/ssl/ca.pem --cert=/opt/etcd/ssl/server.pem --key=/opt/etcd/ssl/server-key.pem --endpoints="https://192.168.233.91:2379,https://192.168.233.93:2379,https://192.168.233.94:2379" endpoint health --write-out=table
1.将有故障的etcd节点remove出集群:
ETCDCTL_API=3 /opt/etcd/bin/etcdctl --cacert=/opt/etcd/ssl/ca.pem --cert=/opt/etcd/ssl/server.pem --key=/opt/etcd/ssl/server-key.pem --endpoints="https://192.168.233.91:2379,https://192.168.233.93:2379,https://192.168.233.94:2379" --write-out=table member list
cf4f326398a30bd2
86ec40d44e54cf0a
/opt/etcd/bin/etcdctl --cacert=/opt/etcd/ssl/ca.pem --cert=/opt/etcd/ssl/server.pem --key=/opt/etcd/ssl/server-key.pem --endpoints="https://192.168.233.91:2379,https://192.168.233.93:2379,https://192.168.233.94:2379" member remove 故障节点的id
2、来到故障节点
rm -rf /var/lib/etcd/default.etcd/member/
修改etcd配置文件,将下面new修改为:
vim /opt/etcd/cfg/etcd
修改前:
ETCD_INITIAL_CLUSTER_STATE="new"
修改后:
ETCD_INITIAL_CLUSTER_STATE="existing"
3、重新加入etcd集群：
/opt/etcd/bin/etcdctl --cacert=/opt/etcd/ssl/ca.pem --cert=/opt/etcd/ssl/server.pem --key=/opt/etcd/ssl/server-key.pem --endpoints="https://192.168.233.91:2379,https://192.168.233.93:2379,https://192.168.233.94:2379" member add etcd-2 --peer-urls=https://192.168.233.94:2380
4、重启etcd故障节点