Question

我正在尝试使用RKE和2个使用RKE的节点设置一个小的Kubernetes集群。这两个节点是在VirtualBox中运行的Ubuntu服务器VM，两者均具有桥接连接。

虚拟机1的IP：xx.xx.xx.61

虚拟机2的IP：xx.xx.xx.67

当我使用rke up启动集群时，出现以下错误：

FATA[0212] [etcd] Failed to bring up Etcd Plane: [etcd] Etcd Cluster is not healthy

当我随后运行kubectl命令（例如kubectl --kubeconfig kube_config_cluster.yml版本）时，出现以下错误：

Client Version: version.Info{Major:"1", Minor:"15", GitVersion:"v1.15.1", GitCommit:"4485c6f18cee9a5d3c3b4e523bd27972b1b53892", GitTreeState:"clean", BuildDate:"2019-07-18T09:18:22Z", GoVersion:"go1.12.5", Compiler:"gc", Platform:"linux/amd64"}
The connection to the server xx.xx.xx.67:6443 was refused - did you specify the right host or port?

不确定这些错误是否是由同一基本问题引起的。

是什么原因引起的，或者如何解决此问题。我是否可以查看任何特定的日志文件？

cluster.yml是这样的：

# If you intened to deploy Kubernetes in an air-gapped environment,
# please consult the documentation on how to configure custom RKE images.
nodes:
- address: xx.xx.xx.61
  port: "22"
  internal_address: ""
  role:
  - controlplane
  - worker
  - etcd
  hostname_override: ""
  user: rke
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
- address: xx.xx.xx.67
  port: "22"
  internal_address: ""
  role:
  - controlplane
  - worker
  - etcd
  hostname_override: ""
  user: rke
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
services:
  etcd:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    external_urls: []
    ca_cert: ""
    cert: ""
    key: ""
    path: ""
    snapshot: null
    retention: ""
    creation: ""
    backup_config: null
  kube-api:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    service_cluster_ip_range: 10.43.0.0/16
    service_node_port_range: ""
    pod_security_policy: false
    always_pull_images: false
  kube-controller:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    cluster_cidr: 10.42.0.0/16
    service_cluster_ip_range: 10.43.0.0/16
  scheduler:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
  kubelet:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    cluster_domain: cluster.local
    infra_container_image: ""
    cluster_dns_server: 10.43.0.10
    fail_swap_on: false
  kubeproxy:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
network:
  plugin: canal
  options: {}
authentication:
  strategy: x509
  sans: []
  webhook: null
addons: ""
addons_include:
- https://raw.githubusercontent.com/kubernetes/dashboard/master/src/deploy/recommended/kubernetes-dashboard.yaml
- https://gist.githubusercontent.com/superseb/499f2caa2637c404af41cfb7e5f4a938/raw/930841ac00653fdff8beca61dab9a20bb8983782/k8s-dashboard-user.yml
system_images:
  etcd: rancher/coreos-etcd:v3.3.10-rancher1
  alpine: rancher/rke-tools:v0.1.34
  nginx_proxy: rancher/rke-tools:v0.1.34
  cert_downloader: rancher/rke-tools:v0.1.34
  kubernetes_services_sidecar: rancher/rke-tools:v0.1.34
  kubedns: rancher/k8s-dns-kube-dns:1.15.0
  dnsmasq: rancher/k8s-dns-dnsmasq-nanny:1.15.0
  kubedns_sidecar: rancher/k8s-dns-sidecar:1.15.0
  kubedns_autoscaler: rancher/cluster-proportional-autoscaler:1.3.0
  coredns: rancher/coredns-coredns:1.3.1
  coredns_autoscaler: rancher/cluster-proportional-autoscaler:1.3.0
  kubernetes: rancher/hyperkube:v1.14.3-rancher1
  flannel: rancher/coreos-flannel:v0.10.0-rancher1
  flannel_cni: rancher/flannel-cni:v0.3.0-rancher1
  calico_node: rancher/calico-node:v3.4.0
  calico_cni: rancher/calico-cni:v3.4.0
  calico_controllers: ""
  calico_ctl: rancher/calico-ctl:v2.0.0
  canal_node: rancher/calico-node:v3.4.0
  canal_cni: rancher/calico-cni:v3.4.0
  canal_flannel: rancher/coreos-flannel:v0.10.0
  weave_node: weaveworks/weave-kube:2.5.0
  weave_cni: weaveworks/weave-npc:2.5.0
  pod_infra_container: rancher/pause:3.1
  ingress: rancher/nginx-ingress-controller:0.21.0-rancher3
  ingress_backend: rancher/nginx-ingress-controller-defaultbackend:1.5-rancher1
  metrics_server: rancher/metrics-server:v0.3.1
ssh_key_path: ~/.ssh/id_rsa
ssh_cert_path: ""
ssh_agent_auth: false
authorization:
  mode: rbac
  options: {}
ignore_docker_version: false
kubernetes_version: ""
private_registries: []
ingress:
  provider: ""
  options: {}
  node_selector: {}
  extra_args: {}
cluster_name: ""
cloud_provider:
  name: ""
prefix_path: ""
addon_job_timeout: 0
bastion_host:
  address: ""
  port: ""
  user: ""
  ssh_key: ""
  ssh_key_path: ""
  ssh_cert: ""
  ssh_cert_path: ""
monitoring:
  provider: ""
  options: {}
restore:
  restore: false
  snapshot_name: ""
dns: null

Answer 1

etcd部署的规模通常为奇数（1、3、5 ...）。我看到您已经选择了两个具有etcd角色的节点。这可能导致仲裁问题。您可以仅在其中一个节点上使用etcd角色，然后再次运行rke up吗？

（RKE）FATA [0212] [etcd]无法启动Etcd平面：[etcd] Etcd群集不健康

1 个答案: