Rke安装k8s报错

Rancher 2.x RKE
1

RKE 版本:
rke version v1.2.21
Docker 版本: (docker version,docker info)

Client: Docker Engine - Community
 Version:           20.10.21
 API version:       1.41
 Go version:        go1.18.7
 Git commit:        baeda1f
 Built:             Tue Oct 25 18:04:24 2022
 OS/Arch:           linux/amd64
 Context:           default
 Experimental:      true

Server: Docker Engine - Community
 Engine:
  Version:          20.10.21
  API version:      1.41 (minimum version 1.12)
  Go version:       go1.18.7
  Git commit:       3056208
  Built:            Tue Oct 25 18:02:38 2022
  OS/Arch:          linux/amd64
  Experimental:     false
 containerd:
  Version:          1.6.9
  GitCommit:        1c90a442489720eec95342e1789ee8a5e1b9536f
 runc:
  Version:          1.1.4
  GitCommit:        v1.1.4-0-g5fd4c4d
 docker-init:
  Version:          0.19.0
  GitCommit:        de40ad0

操作系统和内核: (cat /etc/os-release, uname -r)
5.4.224-1.el7.elrepo.x86_64
主机类型和供应商: (移动云)

nodes:
- address: 192.168.1.7
  port: "22"
  internal_address: ""
  role:
  - controlplane
  - worker
  - etcd
  hostname_override: ""
  user: kuser
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
  taints: []
- address: 192.168.1.16
  port: "22"
  internal_address: ""
  role:
  - controlplane
  - worker
  - etcd
  hostname_override: ""
  user: kuser
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
  taints: []
- address: 192.168.1.24
  port: "22"
  internal_address: ""
  role:
  - controlplane
  - worker
  - etcd
  hostname_override: ""
  user: kuser
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
  taints: []
services:
  etcd:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    win_extra_args: {}
    win_extra_binds: []
    win_extra_env: []
    external_urls: []
    ca_cert: ""
    cert: ""
    key: ""
    path: ""
    uid: 0
    gid: 0
    snapshot: null
    retention: ""
    creation: ""
    backup_config: null
  kube-api:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    win_extra_args: {}
    win_extra_binds: []
    win_extra_env: []
    service_cluster_ip_range: 10.43.0.0/16
    service_node_port_range: ""
    pod_security_policy: false
    always_pull_images: false
    secrets_encryption_config: null
    audit_log: null
    admission_configuration: null
    event_rate_limit: null
  kube-controller:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    win_extra_args: {}
    win_extra_binds: []
    win_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: []
    win_extra_args: {}
    win_extra_binds: []
    win_extra_env: []
  kubelet:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    win_extra_args: {}
    win_extra_binds: []
    win_extra_env: []
    cluster_domain: cluster.local
    infra_container_image: ""
    cluster_dns_server: 10.43.0.10
    fail_swap_on: false
    generate_serving_certificate: false
  kubeproxy:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
    win_extra_args: {}
    win_extra_binds: []
    win_extra_env: []
network:
  plugin: canal
  options: {}
  mtu: 0
  node_selector: {}
  update_strategy: null
  tolerations: []
authentication:
  strategy: x509
  sans: []
  webhook: null
addons: ""
addons_include: []
system_images:
  etcd: rancher/mirrored-coreos-etcd:v3.4.15-rancher1
  alpine: rancher/rke-tools:v0.1.80
  nginx_proxy: rancher/rke-tools:v0.1.80
  cert_downloader: rancher/rke-tools:v0.1.80
  kubernetes_services_sidecar: rancher/rke-tools:v0.1.80
  kubedns: rancher/mirrored-k8s-dns-kube-dns:1.15.10
  dnsmasq: rancher/mirrored-k8s-dns-dnsmasq-nanny:1.15.10
  kubedns_sidecar: rancher/mirrored-k8s-dns-sidecar:1.15.10
  kubedns_autoscaler: rancher/mirrored-cluster-proportional-autoscaler:1.8.1
  coredns: rancher/mirrored-coredns-coredns:1.8.0
  coredns_autoscaler: rancher/mirrored-cluster-proportional-autoscaler:1.8.1
  nodelocal: rancher/mirrored-k8s-dns-node-cache:1.15.13
  kubernetes: rancher/hyperkube:v1.20.15-rancher1
  flannel: rancher/mirrored-coreos-flannel:v0.15.1
  flannel_cni: rancher/flannel-cni:v0.3.0-rancher6
  calico_node: rancher/mirrored-calico-node:v3.17.2
  calico_cni: rancher/mirrored-calico-cni:v3.17.2
  calico_controllers: rancher/mirrored-calico-kube-controllers:v3.17.2
  calico_ctl: rancher/mirrored-calico-ctl:v3.17.2
  calico_flexvol: rancher/mirrored-calico-pod2daemon-flexvol:v3.17.2
  canal_node: rancher/mirrored-calico-node:v3.17.2
  canal_cni: rancher/mirrored-calico-cni:v3.17.2
  canal_controllers: rancher/mirrored-calico-kube-controllers:v3.17.2
  canal_flannel: rancher/mirrored-coreos-flannel:v0.15.1
  canal_flexvol: rancher/mirrored-calico-pod2daemon-flexvol:v3.17.2
  weave_node: weaveworks/weave-kube:2.8.1
  weave_cni: weaveworks/weave-npc:2.8.1
  pod_infra_container: rancher/mirrored-pause:3.6
  ingress: rancher/nginx-ingress-controller:nginx-1.2.1-rancher1
  ingress_backend: rancher/mirrored-nginx-ingress-controller-defaultbackend:1.5-rancher1
  ingress_webhook: rancher/mirrored-ingress-nginx-kube-webhook-certgen:v1.1.1
  metrics_server: rancher/mirrored-metrics-server:v0.5.0
  windows_pod_infra_container: rancher/mirrored-pause:3.6
  aci_cni_deploy_container: noiro/cnideploy:5.1.1.0.1ae238a
  aci_host_container: noiro/aci-containers-host:5.1.1.0.1ae238a
  aci_opflex_container: noiro/opflex:5.1.1.0.1ae238a
  aci_mcast_container: noiro/opflex:5.1.1.0.1ae238a
  aci_ovs_container: noiro/openvswitch:5.1.1.0.1ae238a
  aci_controller_container: noiro/aci-containers-controller:5.1.1.0.1ae238a
  aci_gbp_server_container: noiro/gbp-server:5.1.1.0.1ae238a
  aci_opflex_server_container: noiro/opflex-server:5.1.1.0.1ae238a
ssh_key_path: ~/.ssh/id_rsa
ssh_cert_path: ""
ssh_agent_auth: false
authorization:
  mode: rbac
  options: {}
ignore_docker_version: null
kubernetes_version: ""
private_registries: []
ingress:
  provider: ""
  options: {}
  node_selector: {}
  extra_args: {}
  dns_policy: ""
  extra_envs: []
  extra_volumes: []
  extra_volume_mounts: []
  update_strategy: null
  http_port: 0
  https_port: 0
  network_mode: ""
  tolerations: []
  default_backend: null
  default_http_backend_priority_class_name: ""
  nginx_ingress_controller_priority_class_name: ""
cluster_name: ""
cloud_provider:
  name: ""
prefix_path: ""
win_prefix_path: ""
addon_job_timeout: 0
bastion_host:
  address: ""
  port: ""
  user: ""
  ssh_key: ""
  ssh_key_path: ""
  ssh_cert: ""
  ssh_cert_path: ""
monitoring:
  provider: ""
  options: {}
  node_selector: {}
  update_strategy: null
  replicas: null
  tolerations: []
  metrics_server_priority_class_name: ""
restore:
  restore: false
  snapshot_name: ""
rotate_encryption_key: false
dns: null

重现步骤:
./rke up --config ./cluster.yml
结果:

ERRO[0214] Host 192.168.1.7 failed to report Ready status with error: [controlplane] Error getting node 192.168.1.7:  "192.168.1.7" not found 
INFO[0214] [controlplane] Now checking status of node 192.168.1.16, try #1 
ERRO[0239] Host 192.168.1.16 failed to report Ready status with error: [controlplane] Error getting node 192.168.1.16:  "192.168.1.16" not found 
INFO[0239] [controlplane] Now checking status of node 192.168.1.24, try #1 
ERRO[0264] Host 192.168.1.24 failed to report Ready status with error: [controlplane] Error getting node 192.168.1.24:  "192.168.1.24" not found 
INFO[0264] [controlplane] Processing controlplane hosts for upgrade 1 at a time 
INFO[0264] Processing controlplane host 192.168.1.7     
INFO[0264] [controlplane] Now checking status of node 192.168.1.7, try #1 
ERRO[0289] Failed to upgrade hosts: 192.168.1.7 with error [[controlplane] Error getting node 192.168.1.7:  "192.168.1.7" not found] 
FATA[0289] [controlPlane] Failed to upgrade Control Plane: [[[controlplane] Error getting node 192.168.1.7:  "192.168.1.7" not found]]
2

先检查使用kuser来通过ssh访问目标主机的能力；

再检查你的kuser是否具备访问docker的能力：Rancher Docs: Requirements

3

kuser用户可以ssh直接免密登录,并且具备访问docker的能力

image
image1080×146 9.18 KB

4

这个是openssh版本

image
image856×80 6.12 KB

5

而且我用 rke up 进行部署每次都会出现报错，我都用下面命令将环境清空，每次都要部署多次才有一次成功

防火墙规则清理

/sbin/iptables -P INPUT ACCEPT
/sbin/iptables -F

容器清理

docker system prune -f
docker stop (docker ps -aq) docker rm -f (docker ps -aq)
docker volume rm (docker volume ls -q) docker image rm (docker image ls -q)
rm -rf /etc/ceph
/etc/cni
/etc/kubernetes
/opt/cni
/opt/rke
/run/secrets/kubernetes.io
/run/calico
/run/flannel
/var/lib/calico
/var/lib/etcd
/var/lib/cni
/var/lib/kubelet
/var/lib/rancher/rke/log
/var/log/containers
/var/log/pods
/var/run/calico

重启服务

systemctl restart docker

6

可以尝试如下脚本清理节点之后重新添加：

#!/bin/bash

KUBE_SVC='
kubelet
kube-scheduler
kube-proxy
kube-controller-manager
kube-apiserver
'

for kube_svc in ${KUBE_SVC};
do
  # 停止服务
  if [[ `systemctl is-active ${kube_svc}` == 'active' ]]; then
    systemctl stop ${kube_svc}
  fi
  # 禁止服务开机启动
  if [[ `systemctl is-enabled ${kube_svc}` == 'enabled' ]]; then
    systemctl disable ${kube_svc}
  fi
done

# 停止所有容器
docker stop $(docker ps -aq)

# 删除所有容器
docker rm -f $(docker ps -qa)

# 删除所有容器卷
docker volume rm $(docker volume ls -q)

# 卸载mount目录
for mount in $(mount | grep tmpfs | grep '/var/lib/kubelet' | awk '{ print $3 }') /var/lib/kubelet /var/lib/rancher;
do
  umount $mount;
done

# 备份目录
mv /etc/kubernetes /etc/kubernetes-bak-$(date +"%Y%m%d%H%M")
mv /var/lib/etcd /var/lib/etcd-bak-$(date +"%Y%m%d%H%M")
mv /var/lib/rancher /var/lib/rancher-bak-$(date +"%Y%m%d%H%M")
mv /opt/rke /opt/rke-bak-$(date +"%Y%m%d%H%M")

# 删除残留路径
rm -rf /etc/ceph \
    /etc/cni \
    /opt/cni \
    /run/secrets/kubernetes.io \
    /run/calico \
    /run/flannel \
    /var/lib/calico \
    /var/lib/cni \
    /var/lib/kubelet \
    /var/log/containers \
    /var/log/kube-audit \
    /var/log/pods \
    /var/run/calico \
    /usr/libexec/kubernetes

# 清理网络接口
no_del_net_inter='
lo
docker0
eth
ens
bond
'

network_interface=`ls /sys/class/net`

for net_inter in $network_interface;
do
  if ! echo "${no_del_net_inter}" | grep -qE ${net_inter:0:3}; then
    ip link delete $net_inter
  fi
done

# 清理残留进程
port_list='
80
443
6443
2376
2379
2380
8472
9099
10250
10254
'

for port in $port_list;
do
  pid=`netstat -atlnup | grep $port | awk '{print $7}' | awk -F '/' '{print $1}' | grep -v - | sort -rnk2 | uniq`
  if [[ -n $pid ]]; then
    kill -9 $pid
  fi
done

kube_pid=`ps -ef | grep -v grep | grep kube | awk '{print $2}'`

if [[ -n $kube_pid ]]; then
  kill -9 $kube_pid
fi

# 清理Iptables表
## 注意：如果节点Iptables有特殊配置，以下命令请谨慎操作
sudo iptables --flush
sudo iptables --flush --table nat
sudo iptables --flush --table filter
sudo iptables --table nat --delete-chain
sudo iptables --table filter --delete-chain
systemctl restart docker
7

按照这个脚本操作会有时可以成功，有时又不行

8

如果不行，十有八九是因为镜像拉的慢，导致安装某个服务 timeoout 了，这种情况，rke remove 然后再 rke up 应该就可以了

9

镜像拉的慢，我做了镜像加速还是不行，移动云真不行

1 个赞