k8s高可用集群安装

一、安装负载均衡器

k8s负载均衡器官方指南

1、准备三台机器

节点名称	IP
master-1	192.168.1.11
master-2	192.168.1.12
master-3	192.168.1.13

2、在这三台机器分别安装haproxy和keepalived作为负载均衡器

# 安装haproxy
sudo dnf install haproxy -y

# 安装Keepalived
sudo yum install epel-release -y
sudo yum install keepalived -y

# 查看安装成功信息
sudo dnf info haproxy
sudo dnf info keepalived

出现类似信息，说明安装成功

3、k8s负载均衡器配置文件官方指南按需替换成自己的机器ip和端口即可，192.168.1.9 是为keepalived提供的虚拟ip，只要该ip没有被占用，均可，从节点将MASTER改为BACKUP,priority 101改成100，让MASTER占比大

3.1 /etc/keepalived/keepalived.conf

! /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
    router_id LVS_DEVEL
}
vrrp_script check_apiserver {
  script "/etc/keepalived/check_apiserver.sh"
  interval 3
  weight -2
  fall 10
  rise 2
}

vrrp_instance VI_1 {
    state MASTER
    interface ens33
    virtual_router_id 51
    priority 101
    authentication {
        auth_type PASS
        auth_pass 42
    }
    virtual_ipaddress {
        192.168.1.9
    }
    track_script {
        check_apiserver
    }
}

3.2 /etc/keepalived/check_apiserver.sh

#!/bin/sh

errorExit() {
    echo "*** $*" 1>&2
    exit 1
}

curl -sfk --max-time 2 https://localhost:6553/healthz -o /dev/null || errorExit "Error GET https://localhost:6553/healthz"

3.3 授予脚本权限

chmod +x /etc/keepalived/check_apiserver.sh

3.4 /etc/haproxy/haproxy.cfg

# /etc/haproxy/haproxy.cfg
#---------------------------------------------------------------------
# Global settings
#---------------------------------------------------------------------
global
    log stdout format raw local0
    daemon

#---------------------------------------------------------------------
# common defaults that all the 'listen' and 'backend' sections will
# use if not designated in their block
#---------------------------------------------------------------------
defaults
    mode                    http
    log                     global
    option                  httplog
    option                  dontlognull
    option http-server-close
    option forwardfor       except 127.0.0.0/8
    option                  redispatch
    retries                 1
    timeout http-request    10s
    timeout queue           20s
    timeout connect         5s
    timeout client          35s
    timeout server          35s
    timeout http-keep-alive 10s
    timeout check           10s

#---------------------------------------------------------------------
# apiserver frontend which proxys to the control plane nodes
#---------------------------------------------------------------------
frontend apiserver
    bind *:6553
    mode tcp
    option tcplog
    default_backend apiserverbackend

#---------------------------------------------------------------------
# round robin balancing for apiserver
#---------------------------------------------------------------------
backend apiserverbackend
    option httpchk

    http-check connect ssl
    http-check send meth GET uri /healthz
    http-check expect status 200

    mode tcp
    balance     roundrobin
    
    server master-1 192.168.1.11:6443 check verify none
    server master-2 192.168.1.12:6443 check verify none
    server master-3 192.168.1.13:6443 check verify none


    # [...]

3.5 验证haproxy.cfg是否有语法错误，并重启

haproxy -c -f /etc/haproxy/haproxy.cfg

systemctl restart haproxy 
systemctl restart keepalived

在这里插入图片描述

二、安装k8s集群

基础配置，请参照我的上一篇单主节点执行

1、堆叠（Stacked）etcd 拓扑

直接执行初始化即可
优点：操作简单，节点数要求少
缺点：堆叠集群存在耦合失败的风险。如果一个节点发生故障，则 etcd 成员和控制平面实例都将丢失，并且冗余会受到影响。

kubeadm init --image-repository registry.cn-hangzhou.aliyuncs.com/google_containers \
  --apiserver-advertise-address=192.168.1.11 \
  --control-plane-endpoint 192.168.1.9:6553 \
  --pod-network-cidr=10.244.0.0/16 \
  --service-cidr 10.244.0.0/12 \
  --kubernetes-version=v1.23.8 \
  --upload-certs \
  --v=6

2、外部 etcd 拓扑

优点：拓扑结构解耦了控制平面和 etcd 成员。因此它提供了一种 HA 设置，其中失去控制平面实例或者 etcd 成员的影响较小，并且不会像堆叠的 HA 拓扑那样影响集群冗余
缺点：拓扑需要两倍于堆叠 HA 拓扑的主机数量。具有此拓扑的 HA 集群至少需要三个用于控制平面节点的主机和三个用于 etcd 节点的主机官方指南

2.1 准备三台机器

节点名称	IP
etcd-1	192.168.1.3
etcd-2	192.168.1.4
etcd-3	192.168.1.5

2.2 每个etcd节点创建配置文件/etc/systemd/system/kubelet.service.d/20-etcd-service-manager.conf

[Service]
ExecStart=
# 将下面的 "systemd" 替换为你的容器运行时所使用的 cgroup 驱动。
# kubelet 的默认值为 "cgroupfs"。
# 如果需要的话，将 "--container-runtime-endpoint " 的值替换为一个不同的容器运行时。
ExecStart=/usr/bin/kubelet --address=127.0.0.1 --pod-manifest-path=/etc/kubernetes/manifests --cgroup-driver=systemd
Restart=always

2.3 启动kubelet

systemctl daemon-reload
systemctl restart kubelet

# 查看kubelet状态，正常应变为running
systemctl status kubelet

2.4 使用以下脚本文件启动，注意替换自己的IP和主机名

# 使用你的主机 IP 替换 HOST0、HOST1 和 HOST2 的 IP 地址，在etcd-1 上执行以下命令：
export HOST0=192.168.1.3
export HOST1=192.168.1.4
export HOST2=192.168.1.5

# 使用你的主机名更新 NAME0、NAME1 和 NAME2
export NAME0="etcd-1"
export NAME1="etcd-2"
export NAME2="etcd-3"

# 创建临时目录来存储将被分发到其它主机上的文件
mkdir -p /tmp/${HOST0}/ /tmp/${HOST1}/ /tmp/${HOST2}/

HOSTS=(${HOST0} ${HOST1} ${HOST2})
NAMES=(${NAME0} ${NAME1} ${NAME2})

for i in "${!HOSTS[@]}"; do
HOST=${HOSTS[$i]}
NAME=${NAMES[$i]}
cat << EOF > /tmp/${HOST}/kubeadmcfg.yaml
---
apiVersion: "kubeadm.k8s.io/v1beta3"
kind: InitConfiguration
nodeRegistration:
    name: ${NAME}
localAPIEndpoint:
    advertiseAddress: ${HOST}
---
apiVersion: "kubeadm.k8s.io/v1beta3"
kind: ClusterConfiguration
etcd:
    local:
        serverCertSANs:
        - "${HOST}"
        peerCertSANs:
        - "${HOST}"
        extraArgs:
            initial-cluster: ${NAMES[0]}=https://${HOSTS[0]}:2380,${NAMES[1]}=https://${HOSTS[1]}:2380,${NAMES[2]}=https://${HOSTS[2]}:2380
            initial-cluster-state: new
            name: ${NAME}
            listen-peer-urls: https://${HOST}:2380
            listen-client-urls: https://${HOST}:2379
            advertise-client-urls: https://${HOST}:2379
            initial-advertise-peer-urls: https://${HOST}:2380
EOF
done

2.5 在任意etcd节点生成证书

kubeadm init phase certs etcd-ca
#这一操作创建如下两个文件：
#/etc/kubernetes/pki/etcd/ca.crt
#/etc/kubernetes/pki/etcd/ca.key

2.6 为每个成员创建证书

kubeadm init phase certs etcd-server --config=/tmp/${HOST2}/kubeadmcfg.yaml
kubeadm init phase certs etcd-peer --config=/tmp/${HOST2}/kubeadmcfg.yaml
kubeadm init phase certs etcd-healthcheck-client --config=/tmp/${HOST2}/kubeadmcfg.yaml
kubeadm init phase certs apiserver-etcd-client --config=/tmp/${HOST2}/kubeadmcfg.yaml
cp -R /etc/kubernetes/pki /tmp/${HOST2}/
# 清理不可重复使用的证书
find /etc/kubernetes/pki -not -name ca.crt -not -name ca.key -type f -delete

kubeadm init phase certs etcd-server --config=/tmp/${HOST1}/kubeadmcfg.yaml
kubeadm init phase certs etcd-peer --config=/tmp/${HOST1}/kubeadmcfg.yaml
kubeadm init phase certs etcd-healthcheck-client --config=/tmp/${HOST1}/kubeadmcfg.yaml
kubeadm init phase certs apiserver-etcd-client --config=/tmp/${HOST1}/kubeadmcfg.yaml
cp -R /etc/kubernetes/pki /tmp/${HOST1}/
find /etc/kubernetes/pki -not -name ca.crt -not -name ca.key -type f -delete

kubeadm init phase certs etcd-server --config=/tmp/${HOST0}/kubeadmcfg.yaml
kubeadm init phase certs etcd-peer --config=/tmp/${HOST0}/kubeadmcfg.yaml
kubeadm init phase certs etcd-healthcheck-client --config=/tmp/${HOST0}/kubeadmcfg.yaml
kubeadm init phase certs apiserver-etcd-client --config=/tmp/${HOST0}/kubeadmcfg.yaml
# 不需要移动 certs 因为它们是给 HOST0 使用的

# 清理不应从此主机复制的证书
find /tmp/${HOST2} -name ca.key -type f -delete
find /tmp/${HOST1} -name ca.key -type f -delete

2.7 证书已生成，现在必须将它们移动到对应的主机。复制tmp下各自节点证书目录pki至/etc/kubernetes/

在这里插入图片描述

2.8 在对应的etcd节点分别执行，按需取用和替换自己的etcd节点IP

# 镜像处理
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.6
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.6 k8s.gcr.io/pause:3.6

docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.5.1-0
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.5.1-0 k8s.gcr.io/etcd:3.5.1-0

sudo systemctl daemon-reload
sudo systemctl restart kubelet
kubeadm init phase etcd local --config=/tmp/192.168.1.3/kubeadmcfg.yaml
#kubeadm init phase etcd local --config=/tmp/192.168.1.4/kubeadmcfg.yaml
#kubeadm init phase etcd local --config=/tmp/192.168.1.5/kubeadmcfg.yaml

2.9 验证etcd集群

# 验证集群状态
docker run --rm -it \
  --net host \
  -v /etc/kubernetes:/etc/kubernetes registry.cn-hangzhou.aliyuncs.com/google_containers/etcd:3.4.3-0 etcdctl \
  --cert /etc/kubernetes/pki/etcd/peer.crt \
  --key /etc/kubernetes/pki/etcd/peer.key \
  --cacert /etc/kubernetes/pki/etcd/ca.crt \
  --endpoints https://192.168.1.3:2379 endpoint health --cluster

在这里插入图片描述

3、配置完etcd集群，就在第一个节点配置k8s集群启动文件 config kubeadm-config.yaml

apiVersion: kubeadm.k8s.io/v1beta3
kind: InitConfiguration
imageRepository: "registry.cn-hangzhou.aliyuncs.com/google_containers"
localAPIEndpoint:
  advertiseAddress: 192.168.1.11
uploadCerts: true
---
apiVersion: kubeadm.k8s.io/v1beta3
kind: ClusterConfiguration
imageRepository: "registry.cn-hangzhou.aliyuncs.com/google_containers"
kubernetesVersion: v1.23.8
controlPlaneEndpoint: "192.168.1.9:6553"
networking:
  podSubnet: "10.244.0.0/16"
  serviceSubnet: "10.244.0.0/12"
etcd:
  external:
    endpoints:
      - https://192.168.1.3:2379
      - https://192.168.1.4:2379
      - https://192.168.1.5:2379
    caFile: /etc/kubernetes/pki/etcd/ca.crt
    certFile: /etc/kubernetes/pki/apiserver-etcd-client.crt
    keyFile: /etc/kubernetes/pki/apiserver-etcd-client.key

4、从任意etcd节点，复制/etc/kubernetes/pki目录文件到初始化集群的k8s节点

在这里插入图片描述

kubeadm init --config kubeadm-config.yaml --upload-certs --v=6

在这里插入图片描述

# 主节点加入
kubeadm join 192.168.1.9:6553 --token a26srm.c7sssutz83mz94lq \
        --discovery-token-ca-cert-hash sha256:560139f5ea4b8d3a279de53d9d5d503d41c29394c3ba46a4f312f361708b8b71 \
        --control-plane --certificate-key b6e4df72059c9893d2be4d0e5b7fa2e7c466e0400fe39bd244d0fbf7f3e9c04c

# 从节点加入
kubeadm join 192.168.1.9:6553 --token a26srm.c7sssutz83mz94lq \
        --discovery-token-ca-cert-hash sha256:560139f5ea4b8d3a279de53d9d5d503d41c29394c3ba46a4f312f361708b8b71

安装flannel网络插件

apiVersion: v1
kind: Namespace
metadata:
  labels:
    k8s-app: flannel
    pod-security.kubernetes.io/enforce: privileged
  name: kube-flannel
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    k8s-app: flannel
  name: flannel
  namespace: kube-flannel
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    k8s-app: flannel
  name: flannel
rules:
- apiGroups:
  - ""
  resources:
  - pods
  verbs:
  - get
- apiGroups:
  - ""
  resources:
  - nodes
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - nodes/status
  verbs:
  - patch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    k8s-app: flannel
  name: flannel
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: flannel
subjects:
- kind: ServiceAccount
  name: flannel
  namespace: kube-flannel
---
apiVersion: v1
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",
      "EnableNFTables": false,
      "Backend": {
        "Type": "vxlan"
      }
    }
kind: ConfigMap
metadata:
  labels:
    app: flannel
    k8s-app: flannel
    tier: node
  name: kube-flannel-cfg
  namespace: kube-flannel
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    app: flannel
    k8s-app: flannel
    tier: node
  name: kube-flannel-ds
  namespace: kube-flannel
spec:
  selector:
    matchLabels:
      app: flannel
      k8s-app: flannel
  template:
    metadata:
      labels:
        app: flannel
        k8s-app: flannel
        tier: node
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: kubernetes.io/os
                operator: In
                values:
                - linux
      containers:
      - args:
        - --ip-masq
        - --kube-subnet-mgr
        command:
        - /opt/bin/flanneld
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        - name: EVENT_QUEUE_DEPTH
          value: "5000"
        image: registry.cn-hangzhou.aliyuncs.com/1668334351/flannel:v0.26.4
        name: kube-flannel
        resources:
          requests:
            cpu: 100m
            memory: 50Mi
        securityContext:
          capabilities:
            add:
            - NET_ADMIN
            - NET_RAW
          privileged: false
        volumeMounts:
        - mountPath: /run/flannel
          name: run
        - mountPath: /etc/kube-flannel/
          name: flannel-cfg
        - mountPath: /run/xtables.lock
          name: xtables-lock
      hostNetwork: true
      initContainers:
      - args:
        - -f
        - /flannel
        - /opt/cni/bin/flannel
        command:
        - cp
        image: registry.cn-hangzhou.aliyuncs.com/1668334351/flannel-cni-plugin:v1.6.2
        name: install-cni-plugin
        volumeMounts:
        - mountPath: /opt/cni/bin
          name: cni-plugin
      - args:
        - -f
        - /etc/kube-flannel/cni-conf.json
        - /etc/cni/net.d/10-flannel.conflist
        command:
        - cp
        image: registry.cn-hangzhou.aliyuncs.com/1668334351/flannel:v0.26.4
        name: install-cni
        volumeMounts:
        - mountPath: /etc/cni/net.d
          name: cni
        - mountPath: /etc/kube-flannel/
          name: flannel-cfg
      priorityClassName: system-node-critical
      serviceAccountName: flannel
      tolerations:
      - effect: NoSchedule
        operator: Exists
      volumes:
      - hostPath:
          path: /run/flannel
        name: run
      - hostPath:
          path: /opt/cni/bin
        name: cni-plugin
      - hostPath:
          path: /etc/cni/net.d
        name: cni
      - configMap:
          name: kube-flannel-cfg
        name: flannel-cfg
      - hostPath:
          path: /run/xtables.lock
          type: FileOrCreate
        name: xtables-lock