Centos7 使用RKE部署高可用k8s集群

一、RKE介绍
1、介绍：RKE是经过CNCF认证的Kubernetes发行版,并且全部组件完全在Docker容器内运行
Rancher Server只能在使用RKE或K3s安装的Kubernetes集群中运行
2、节点环境准备

firewall-cmd --permanent --add-port=22/tcp
firewall-cmd --permanent --add-port=80/tcp
firewall-cmd --permanent --add-port=443/tcp
firewall-cmd --permanent --add-port=30000-32767/tcp
firewall-cmd --permanent --add-port=30000-32767/udp
firewall-cmd --reload

2、同步节点时间

yum install ntpdate -y
ntpdate time.windows.com

3、安装docker

任何运行Rancher Server的节点上都需要安装Docker
sudo  yum install -y yum-utils device-mapper-persistent-data lvm2
sudo  yum-config-manager --add-repo   https://download.docker.com/linux/centos/docker-ce.repo
sudo  yum install  docker-ce-18.09.3-3.el7

4、安装kubectl

cat << EOF > /etc/yum.repos.d/kubernetes.repo
[kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=1
repo_gpgcheck=1
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

sudo yum install -y kubectl

5、安装RKE

Rancher Kubernetes Engine用于构建Kubernetes集群的CLI
下载地址： https://github.com/rancher/rke/releases/tag/v1.1.3
mv rke_linux-amd64 rke
chmod +x rke
mv rke /usr/local/bin
rke

6、安装Helm

Kubernetes的软件包管理工具
下载地址：https://github.com/helm/helm
tar -zxvf helm-v3.3.1-linux-amd64.tar.gz
cd linux-amd64
mv helm /usr/local/bin
chown -R admin:admin /usr/local/bin/helm
helm version

7、配置ssh免密连接

用户加入docker用户组，让其可以执行docker命令
sudo usermod -aG docker admin

切换成admin用户，在执行rke up命令的主机上执行创建ssh公私钥 并把公钥分发到各个节点上
ssh-keygen -t rsa
ssh-copy-id 192.168.112.120
ssh-copy-id 192.168.112.121

8、配置操作系统参数支持k8s集群 (所有节点上都要执行)

sudo swapoff -a
sudo vi /etc/sysctl.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
sudo sysctl -p

9、使用rke创建集群初始化配置文件

rke config --name  cluster.yml
RKE使用一个名为cluster.yml确定如何在集群中的节点上部署Kubernetes
# If you intened to deploy Kubernetes in an air-gapped environment,
# please consult the documentation on how to configure custom RKE images.
nodes:
- address: "192.168.30.110"
  port: "22"
  internal_address: ""
  role: [controlplane,etcd,worker]
  hostname_override: "node1"
  user: admin
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
  taints: []
- address: "192.168.30.129"
  port: "22"
  internal_address: ""
  role: [controlplane,etcd,worker]
  hostname_override: "node2"
  user: admin
  docker_socket: /var/run/docker.sock
  ssh_key: ""
  ssh_key_path: ~/.ssh/id_rsa
  ssh_cert: ""
  ssh_cert_path: ""
  labels: {}
  taints: []
- address: "192.168.30.133"
  port: "22"
  internal_address: ""
  role: [controlplane,etcd,worker]
  hostname_override: "node3"
  user: admin
  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: []
    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: []
    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: []
    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
    generate_serving_certificate: false
  kubeproxy:
    image: ""
    extra_args: {}
    extra_binds: []
    extra_env: []
network:
  plugin: flannel
  options: {}
  mtu: 0
  node_selector: {}
  update_strategy: null
authentication:
  strategy: x509
  sans: []
  webhook: null
addons: ""
addons_include: []
system_images:
  etcd: rancher/coreos-etcd:v3.4.3-rancher1
  alpine: rancher/rke-tools:v0.1.58
  nginx_proxy: rancher/rke-tools:v0.1.58
  cert_downloader: rancher/rke-tools:v0.1.58
  kubernetes_services_sidecar: rancher/rke-tools:v0.1.58
  kubedns: rancher/k8s-dns-kube-dns:1.15.2
  dnsmasq: rancher/k8s-dns-dnsmasq-nanny:1.15.2
  kubedns_sidecar: rancher/k8s-dns-sidecar:1.15.2
  kubedns_autoscaler: rancher/cluster-proportional-autoscaler:1.7.1
  coredns: rancher/coredns-coredns:1.6.9
  coredns_autoscaler: rancher/cluster-proportional-autoscaler:1.7.1
  nodelocal: rancher/k8s-dns-node-cache:1.15.7
  kubernetes: rancher/hyperkube:v1.18.3-rancher2
  flannel: rancher/coreos-flannel:v0.12.0
  flannel_cni: rancher/flannel-cni:v0.3.0-rancher6
  calico_node: rancher/calico-node:v3.13.4
  calico_cni: rancher/calico-cni:v3.13.4
  calico_controllers: rancher/calico-kube-controllers:v3.13.4
  calico_ctl: rancher/calico-ctl:v3.13.4
  calico_flexvol: rancher/calico-pod2daemon-flexvol:v3.13.4
  canal_node: rancher/calico-node:v3.13.4
  canal_cni: rancher/calico-cni:v3.13.4
  canal_flannel: rancher/coreos-flannel:v0.12.0
  canal_flexvol: rancher/calico-pod2daemon-flexvol:v3.13.4
  weave_node: weaveworks/weave-kube:2.6.4
  weave_cni: weaveworks/weave-npc:2.6.4
  pod_infra_container: rancher/pause:3.1
  ingress: rancher/nginx-ingress-controller:nginx-0.32.0-rancher1
  ingress_backend: rancher/nginx-ingress-controller-defaultbackend:1.5-rancher1
  metrics_server: rancher/metrics-server:v0.3.6
  windows_pod_infra_container: rancher/kubelet-pause:v0.1.4
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
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: {}
  node_selector: {}
  update_strategy: null
  replicas: null
restore:
  restore: false
  snapshot_name: ""
dns: null

cluster.yaml

10、部署

rke up

11、设置环境变量

export KUBECONFIG=/home/admin/kube_config_cluster.yml
mkdir ~/.kube
cp kube_config_cluster.yml ~/.kube/config
　　通过RKE安装k8s集群成功,启动的时候有些节点启动的比较慢。需要稍微等待一段时间.

　　可以先找一台网络好一点的，pull全部镜像，再保存到本地，cp到所有主机

docker save -o images.tgz `docker images|awk 'NR>1 {print $1":"$2}'`

二、RKE的环境清理
1、rancher-node-1,2,3中分别执行以下命令

mkdir rancher
cat > rancher/clear.sh << EOF
df -h|grep kubelet |awk -F % '{print $2}'|xargs umount 
rm /var/lib/kubelet/* -rf
rm /etc/kubernetes/* -rf
rm /var/lib/rancher/* -rf
rm /var/lib/etcd/* -rf
rm /var/lib/cni/* -rf

rm -rf /var/run/calico 

iptables -F && iptables -t nat -F

ip link del flannel.1

docker ps -a|awk '{print $1}'|xargs docker rm -f
docker volume ls|awk '{print $2}'|xargs docker volume rm

rm -rf /var/etcd/
rm -rf /run/kubernetes/
docker rm -fv $(docker ps -aq)
docker volume rm  $(docker volume ls)
rm -rf /etc/cni
rm -rf /opt/cni

systemctl restart docker
EOF
sh rancher/clear.sh  清理脚本

2、清理残留目录结束。如果还有问题可能需要卸载所有节点上的docker

首先查看Docker版本
# yum list installed | grep docker
docker-ce.x86_64  18.05.0.ce-3.el7.centos @docker-ce-edge
 
执行卸载
# yum -y remove docker-ce.x86_64
 
删除存储目录
# rm -rf /etc/docker
# rm -rf /run/docker
# rm -rf /var/lib/dockershim
# rm -rf /var/lib/docker

如果发现删除不掉，需要先 umount，如
# umount /var/lib/docker/devicemapper

卸载docker
rke up --config=./rancher-cluster.yml  rke启动执行是幂等操作的 有时候需要多次执行才能成功

3、rke多次安装和卸载k8s集群问题

启动的时候提示ectd的集群健康检查失败
清空节点上所有k8s的相关目录。卸载和删除docker所有相关目录。重新安装docker
最后在执行rke启动命令

三、扩容节点，缩容节点

1、添加节点

　
修改cluster.yal 将需要添加的节点配置，然后运行
more cluster.yml
nodes:
  - address: 172.20.101.103
    user: ptmind
    role: [controlplane,worker,etcd]
  - address: 172.20.101.104
    user: ptmind
    role: [controlplane,worker,etcd]
  - address: 172.20.101.105
    user: ptmind
    role: [controlplane,worker,etcd]

  - address: 172.20.101.106
    user: ptmind
    role: [worker]
    labels: {traefik: traefik-outer}

2、执行添加节点操作

rke up --update-only

3、rke 删除节点

修改cluster.yal 将需要删除的节点配置删除，然后运行
more cluster.yml
nodes:
  - address: 172.20.101.103
    user: ptmind
    role: [controlplane,worker,etcd]
  - address: 172.20.101.104
    user: ptmind
    role: [controlplane,worker,etcd]
  - address: 172.20.101.105
    user: ptmind
    role: [controlplane,worker,etcd]

删除#  - address: 172.20.101.106
删除#    user: ptmind
删除#    role: [worker]
删除#    labels: {traefik: traefik-outer}

4、执行删除节点操作

rke up --update-only
问题：当node节点处于NotReady状态下，对节点不可做操作，比如做了删除节点操作，会报错，删除不了节点。
解决办法：
　1、手动删除节点上的组件。
　2、通过命令移除节点的角色
kubectl label node prod-129 node-role.kubernetes.io/controlplane-
　　问题：k8s 集群的节点处于 SchedulingDisabled
　　解决方法：
kubectl patch node NodeName -p "{\"spec\":{\"unschedulable\":false}}"

　　或者：

设置不可调度
kubectl cordon node07-ingress
取消节点不可调度
kubectl uncordon node07-ingress
驱逐节点的pod
kubectl drain --ignore-daemonsets --delete-local-data node07-ingress
删除节点
kubectl delete node node07-ingress