背景：为了后期上kubesphere 3.0，所以安装1.18.x
这里我们采用堆叠拓扑的方式构建高可用集群，因为k8s 集群etcd采用了raft算法保证集群一致性，所以高可用必须保证至少3台master+2work
准备5台虚拟机centOS7（http://mirrors.aliyun.com/centos/7.8.2003/isos/x86_64/） 2c 8g 40g
172.16.5.224 k8smaster1
172.16.5.225 k8smaster2
172.16.5.226 k8smaster3
172.16.5.227 k8sworker1
172.16.5.228 k8sworker2
172.16.5.230 vip
首先在每台机器上执行以下脚本，这段脚本将会帮助你初始安装docker+k8s三件套：
#!/bin/bash # 在 master 节点和 worker 节点都要执行 # 安装 docker # 参考文档如下 # https://docs.docker.com/install/linux/docker-ce/centos/ # https://docs.docker.com/install/linux/linux-postinstall/ # 卸载旧版本 yum remove -y docker docker-client docker-client-latest docker-common docker-latest docker-latest-logrotate docker-logrotate docker-selinux docker-engine-selinux docker-engine # 设置 yum repository yum install -y yum-utils device-mapper-persistent-data lvm2 yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo # 安装并启动 docker yum install -y docker-ce docker-ce-cli containerd.io systemctl enable docker systemctl start docker # 安装 nfs-utils # 必须先安装 nfs-utils 才能挂载 nfs 网络存储 yum install -y nfs-utils yum -y install wget # 关闭 防火墙 systemctl stop firewalld systemctl disable firewalld # 关闭 SeLinux setenforce 0 sed -i "s/SELINUX=enforcing/SELINUX=disabled/g" /etc/selinux/config # 关闭 swap swapoff -a yes | cp /etc/fstab /etc/fstab_bak cat /etc/fstab_bak |grep -v swap > /etc/fstab # 修改 /etc/sysctl.conf # 如果有配置，则修改 sed -i "s#^net.ipv4.ip_forward.*#net.ipv4.ip_forward=1#g" /etc/sysctl.conf sed -i "s#^net.bridge.bridge-nf-call-ip6tables.*#net.bridge.bridge-nf-call-ip6tables=1#g" /etc/sysctl.conf sed -i "s#^net.bridge.bridge-nf-call-iptables.*#net.bridge.bridge-nf-call-iptables=1#g" /etc/sysctl.conf # 可能没有，追加 echo "net.ipv4.ip_forward = 1" >> /etc/sysctl.conf echo "net.bridge.bridge-nf-call-ip6tables = 1" >> /etc/sysctl.conf echo "net.bridge.bridge-nf-call-iptables = 1" >> /etc/sysctl.conf # 执行命令以应用 sysctl -p # 配置K8S的yum源 cat <<EOF > /etc/yum.repos.d/kubernetes.repo [kubernetes] name=Kubernetes baseurl=http://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64 enabled=1 gpgcheck=0 repo_gpgcheck=0 gpgkey=http://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg http://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg EOF # 卸载旧版本 yum remove -y kubelet kubeadm kubectl # 安装kubelet、kubeadm、kubectl yum install -y kubelet-1.18.6 kubeadm-1.18.6 kubectl-1.18.6 # 修改docker Cgroup Driver为systemd # # 将/usr/lib/systemd/system/docker.service文件中的这一行 ExecStart=/usr/bin/dockerd -H fd:// --containerd=/run/containerd/containerd.sock # # 修改为 ExecStart=/usr/bin/dockerd -H fd:// --containerd=/run/containerd/containerd.sock --exec-opt native.cgroupdriver=systemd # 如果不修改，在添加 worker 节点时可能会碰到如下错误 # [WARNING IsDockerSystemdCheck]: detected "cgroupfs" as the Docker cgroup driver. The recommended driver is "systemd". # Please follow the guide at https://kubernetes.io/docs/setup/cri/ sed -i "s#^ExecStart=/usr/bin/dockerd.*#ExecStart=/usr/bin/dockerd -H fd:// --containerd=/run/containerd/containerd.sock --exec-opt native.cgroupdriver=systemd --data-root=/data/docker#g" /usr/lib/systemd/system/docker.service # 设置 docker 镜像，提高 docker 镜像下载速度和稳定性 # 如果您访问 https://hub.docker.io 速度非常稳定，亦可以跳过这个步骤 curl -sSL https://get.daocloud.io/daotools/set_mirror.sh | sh -s http://f1361db2.m.daocloud.io # 重启 docker，并启动 kubelet systemctl daemon-reload systemctl restart docker systemctl enable kubelet && systemctl start kubelet docker version
接着我们进入master1修改hosts加入k8sapi地址(这里是实现高可用的重点)并初始化集群：
cat>>/etc/hosts<<EOF
172.16.5.224 k8sapi
EOF
kubeadm init --image-repository registry.cn-hangzhou.aliyuncs.com/google_containers --pod-network-cidr=10.244.0.0/16 --ignore-preflight-errors=cri --control-plane-endpoint "k8sapi:6443" --kubernetes-version=1.18.6
mkdir -p $HOME/.kube
cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
chown $(id -u):$(id -g) $HOME/.kube/config
登录master2、master3，host里把域名指向master1的ip：
cat>>/etc/hosts<<EOF
172.16.5.224 k8sapi
EOF
mkdir /etc/kubernetes/pki/
mkdir /etc/kubernetes/pki/etcd
重新登录master1并执行，拷贝证书到master2、master3：
cd /etc/kubernetes/pki/
scp ca.crt ca.key sa.key sa.pub front-proxy-ca.crt front-proxy-ca.key root@172.16.5.225:/etc/kubernetes/pki/
scp ca.crt ca.key sa.key sa.pub front-proxy-ca.crt front-proxy-ca.key root@172.16.5.226:/etc/kubernetes/pki/
cd etcd
scp ca.crt ca.key root@172.16.5.225:/etc/kubernetes/pki/etcd/
scp ca.crt ca.key root@172.16.5.226:/etc/kubernetes/pki/etcd/
再次登录master2、master3并分别执行：
kubeadm join k8sapi:6443 --token u6vw2b.b2avyx7blrzrwths
--discovery-token-ca-cert-hash sha256:0c25b70c44b71c5f2f359155dc3f48f323fbe59a79db3abaf34bf947a4bf7989
--control-plane
mkdir -p $HOME/.kube
cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
chown $(id -u):$(id -g) $HOME/.kube/config
登录worker1、worker2、（worker3）并执行：
cat>>/etc/hosts<<EOF
172.16.5.224 k8sapi
EOF
kubeadm join k8sapi:6443 --token u6vw2b.b2avyx7blrzrwths
--discovery-token-ca-cert-hash sha256:0c25b70c44b71c5f2f359155dc3f48f323fbe59a79db3abaf34bf947a4bf7989
修改master1、master2、master3的host 域名指向127.0.0.1
vi /etc/hosts
127.0.0.1 k8sapi
在master1、master2、master3 原生安装Keepalived（1主2从），并用systemctl注册成自启动服务
yum install -y keepalived
配置master：
vi /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
notification_email {
root@localhost
}
notification_email_from root@localhost
smtp_server 127.0.0.1
smtp_connect_timeout 30
router_id LVS_DEVEL
vrrp_skip_check_adv_addr
#vrrp_strict #把这王八蛋注释掉,不然严格遵守vvrp协议,访问不了vip的
vrrp_garp_interval 0
vrrp_gna_interval 0
}
vrrp_instance VI_1 {
state MASTER
interface ens33 #此处为自己的ip名，可使用命令 ip a/ip addr/ifconfig 查看
virtual_router_id 51 #默认51，可以换一个地址，避免冲突，主备id要一样
priority 100
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
172.16.5.230 #此处为VIP/浮动ip/虚拟ip
}
}
配置backup：
! Configuration File for keepalived
global_defs {
notification_email {
root@localhost
}
notification_email_from root@localhost
smtp_server localhost
smtp_connect_timeout 30
router_id LVS_DEVEL
vrrp_skip_check_adv_addr
#vrrp_strict
vrrp_garp_interval 0
vrrp_gna_interval 0
}
vrrp_instance VI_1 {
state BACKUP
interface ens33 #此处为自己的ip名，可使用命令 ip a/ip addr/ifconfig 查看
virtual_router_id 51
priority 90 #权重，两台backup配置不同的权重
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
172.16.5.230 #此处为VIP/浮动ip/虚拟ip
}
}
systemctl start keepalived //启动服务
systemctl enable keepalived //开机自启动
然后让所有wokrer的host指向这个vip
vi /etc/hosts
172.16.5.230 k8sapi
最后在任意master节点执行安装网络插件：
kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
无法访问，则单独上传到服务器：
---
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
name: psp.flannel.unprivileged
annotations:
seccomp.security.alpha.kubernetes.io/allowedProfileNames: docker/default
seccomp.security.alpha.kubernetes.io/defaultProfileName: docker/default
apparmor.security.beta.kubernetes.io/allowedProfileNames: runtime/default
apparmor.security.beta.kubernetes.io/defaultProfileName: runtime/default
spec:
privileged: false
volumes:
- configMap
- secret
- emptyDir
- hostPath
allowedHostPaths:
- pathPrefix: "/etc/cni/net.d"
- pathPrefix: "/etc/kube-flannel"
- pathPrefix: "/run/flannel"
readOnlyRootFilesystem: false
# Users and groups
runAsUser:
rule: RunAsAny
supplementalGroups:
rule: RunAsAny
fsGroup:
rule: RunAsAny
# Privilege Escalation
allowPrivilegeEscalation: false
defaultAllowPrivilegeEscalation: false
# Capabilities
allowedCapabilities: ['NET_ADMIN', 'NET_RAW']
defaultAddCapabilities: []
requiredDropCapabilities: []
# Host namespaces
hostPID: false
hostIPC: false
hostNetwork: true
hostPorts:
- min: 0
max: 65535
# SELinux
seLinux:
# SELinux is unused in CaaSP
rule: 'RunAsAny'
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
name: flannel
rules:
- apiGroups: ['extensions']
resources: ['podsecuritypolicies']
verbs: ['use']
resourceNames: ['psp.flannel.unprivileged']
- apiGroups:
- ""
resources:
- pods
verbs:
- get
- apiGroups:
- ""
resources:
- nodes
verbs:
- list
- watch
- apiGroups:
- ""
resources:
- nodes/status
verbs:
- patch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
name: flannel
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: flannel
subjects:
- kind: ServiceAccount
name: flannel
namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: flannel
namespace: kube-system
---
kind: ConfigMap
apiVersion: v1
metadata:
name: kube-flannel-cfg
namespace: kube-system
labels:
tier: node
app: flannel
data:
cni-conf.json: |
{
"name": "cbr0",
"cniVersion": "0.3.1",
"plugins": [
{
"type": "flannel",
"delegate": {
"hairpinMode": true,
"isDefaultGateway": true
}
},
{
"type": "portmap",
"capabilities": {
"portMappings": true
}
}
]
}
net-conf.json: |
{
"Network": "10.244.0.0/16",
"Backend": {
"Type": "vxlan"
}
}
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds-amd64
namespace: kube-system
labels:
tier: node
app: flannel
spec:
selector:
matchLabels:
app: flannel
template:
metadata:
labels:
tier: node
app: flannel
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- key: kubernetes.io/arch
operator: In
values:
- amd64
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.12.0-amd64
command:
- cp
args:
- -f
- /etc/kube-flannel/cni-conf.json
- /etc/cni/net.d/10-flannel.conflist
volumeMounts:
- name: cni
mountPath: /etc/cni/net.d
- name: flannel-cfg
mountPath: /etc/kube-flannel/
containers:
- name: kube-flannel
image: quay.io/coreos/flannel:v0.12.0-amd64
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
cpu: "100m"
memory: "50Mi"
limits:
cpu: "100m"
memory: "50Mi"
securityContext:
privileged: false
capabilities:
add: ["NET_ADMIN", "NET_RAW"]
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: run
mountPath: /run/flannel
- name: flannel-cfg
mountPath: /etc/kube-flannel/
volumes:
- name: run
hostPath:
path: /run/flannel
- name: cni
hostPath:
path: /etc/cni/net.d
- name: flannel-cfg
configMap:
name: kube-flannel-cfg
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds-arm64
namespace: kube-system
labels:
tier: node
app: flannel
spec:
selector:
matchLabels:
app: flannel
template:
metadata:
labels:
tier: node
app: flannel
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- key: kubernetes.io/arch
operator: In
values:
- arm64
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.12.0-arm64
command:
- cp
args:
- -f
- /etc/kube-flannel/cni-conf.json
- /etc/cni/net.d/10-flannel.conflist
volumeMounts:
- name: cni
mountPath: /etc/cni/net.d
- name: flannel-cfg
mountPath: /etc/kube-flannel/
containers:
- name: kube-flannel
image: quay.io/coreos/flannel:v0.12.0-arm64
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
cpu: "100m"
memory: "50Mi"
limits:
cpu: "100m"
memory: "50Mi"
securityContext:
privileged: false
capabilities:
add: ["NET_ADMIN", "NET_RAW"]
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: run
mountPath: /run/flannel
- name: flannel-cfg
mountPath: /etc/kube-flannel/
volumes:
- name: run
hostPath:
path: /run/flannel
- name: cni
hostPath:
path: /etc/cni/net.d
- name: flannel-cfg
configMap:
name: kube-flannel-cfg
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds-arm
namespace: kube-system
labels:
tier: node
app: flannel
spec:
selector:
matchLabels:
app: flannel
template:
metadata:
labels:
tier: node
app: flannel
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- key: kubernetes.io/arch
operator: In
values:
- arm
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.12.0-arm
command:
- cp
args:
- -f
- /etc/kube-flannel/cni-conf.json
- /etc/cni/net.d/10-flannel.conflist
volumeMounts:
- name: cni
mountPath: /etc/cni/net.d
- name: flannel-cfg
mountPath: /etc/kube-flannel/
containers:
- name: kube-flannel
image: quay.io/coreos/flannel:v0.12.0-arm
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
cpu: "100m"
memory: "50Mi"
limits:
cpu: "100m"
memory: "50Mi"
securityContext:
privileged: false
capabilities:
add: ["NET_ADMIN", "NET_RAW"]
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: run
mountPath: /run/flannel
- name: flannel-cfg
mountPath: /etc/kube-flannel/
volumes:
- name: run
hostPath:
path: /run/flannel
- name: cni
hostPath:
path: /etc/cni/net.d
- name: flannel-cfg
configMap:
name: kube-flannel-cfg
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds-ppc64le
namespace: kube-system
labels:
tier: node
app: flannel
spec:
selector:
matchLabels:
app: flannel
template:
metadata:
labels:
tier: node
app: flannel
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- key: kubernetes.io/arch
operator: In
values:
- ppc64le
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.12.0-ppc64le
command:
- cp
args:
- -f
- /etc/kube-flannel/cni-conf.json
- /etc/cni/net.d/10-flannel.conflist
volumeMounts:
- name: cni
mountPath: /etc/cni/net.d
- name: flannel-cfg
mountPath: /etc/kube-flannel/
containers:
- name: kube-flannel
image: quay.io/coreos/flannel:v0.12.0-ppc64le
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
cpu: "100m"
memory: "50Mi"
limits:
cpu: "100m"
memory: "50Mi"
securityContext:
privileged: false
capabilities:
add: ["NET_ADMIN", "NET_RAW"]
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: run
mountPath: /run/flannel
- name: flannel-cfg
mountPath: /etc/kube-flannel/
volumes:
- name: run
hostPath:
path: /run/flannel
- name: cni
hostPath:
path: /etc/cni/net.d
- name: flannel-cfg
configMap:
name: kube-flannel-cfg
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds-s390x
namespace: kube-system
labels:
tier: node
app: flannel
spec:
selector:
matchLabels:
app: flannel
template:
metadata:
labels:
tier: node
app: flannel
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
- key: kubernetes.io/arch
operator: In
values:
- s390x
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.12.0-s390x
command:
- cp
args:
- -f
- /etc/kube-flannel/cni-conf.json
- /etc/cni/net.d/10-flannel.conflist
volumeMounts:
- name: cni
mountPath: /etc/cni/net.d
- name: flannel-cfg
mountPath: /etc/kube-flannel/
containers:
- name: kube-flannel
image: quay.io/coreos/flannel:v0.12.0-s390x
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
cpu: "100m"
memory: "50Mi"
limits:
cpu: "100m"
memory: "50Mi"
securityContext:
privileged: false
capabilities:
add: ["NET_ADMIN", "NET_RAW"]
env:
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
volumeMounts:
- name: run
mountPath: /run/flannel
- name: flannel-cfg
mountPath: /etc/kube-flannel/
volumes:
- name: run
hostPath:
path: /run/flannel
- name: cni
hostPath:
path: /etc/cni/net.d
- name: flannel-cfg
configMap:
name: kube-flannel-cfg
先拉取依赖镜像
docker pull quay.io/coreos/flannel:v0.12.0-amd64
把上面文件保存到服务器然后执行下面命令
kubectl apply -f kube-flannel.yml
最终效果：
