京东云开发者｜IoT运维 - 如何部署一套高可用K8S集群

环境

准备工作

配置ansible(deploy 主机执行)

# ssh-keygen
# for i in 192.168.3.{21..28}; do  ssh-copy-id  -i ~/.ssh/id_rsa.pub $i; done

[root@deploy ~]# cat /etc/ansible/hosts 
[etcd]
192.168.3.21
192.168.3.22
192.168.3.23
[k8s-master]
192.168.3.24
192.168.3.25
192.168.3.26
[k8s-worker]
192.168.3.27
192.168.3.28

[k8s:children]
k8s-master
k8s-worker

优化主机配置

关闭防火墙和selinux

# ansible all -m shell -a "systemctl stop firewalld && systemctl disable firewalld"
# ansible all -m shell -a "sed -i 's/^SELINUX=.*/SELINUX=disabled/g' /etc/selinux/config"

修改limit

关闭交换分区

# swapoff -a
# ansible  k8s  -m shell -a "yes | cp /etc/fstab /etc/fstab_bak"
# ansible  k8s  -m shell -a "cat /etc/fstab_bak | grep -v swap > /etc/fstab"
# ansible  k8s  -m shell -a "echo vm.swappiness = 0 >> /etc/sysctl.d/k8s.conf"
# ansible  k8s  -m shell -a "sysctl -p /etc/sysctl.d/k8s.conf"

配置ipvs

# cat /root/ipvs.sh 
#!/bin/bash
yum -y install ipvsadm ipset
####创建ipvs脚本
 
cat > /etc/sysconfig/modules/ipvs.modules << EOF
#!/bin/bash
modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
modprobe -- nf_conntrack_ipv4
EOF
 
####执行脚本，验证配置
 
chmod 755 /etc/sysconfig/modules/ipvs.modules
bash /etc/sysconfig/modules/ipvs.modules
lsmod | grep -e ip_vs -e nf_conntrack_ipv4

#########################

# ansible k8s  -m script -a "/root/ipvs.sh"

配置网桥转发规则

# cat sysctl.sh 
#!/bin/bash
cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
net.ipv4.ip_forward = 1
EOF

cat <

# ansible k8s  -m script -a "/root/sysctl.sh"

配置etcd集群

生成证书(ansible 主机操作)

# curl -o /usr/bin/cfssl https://pkg.cfssl.org/R1.2/cfssl_linux-amd64
# curl -o /usr/bin/cfssljson https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64
# curl -o /usr/bin/cfssl-certinfo https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64
# chmod +x /usr/bin/cfssl*

创建 CA 配置文件

# mkdir p ssl
# cd /root/ssl
# cat >ca-config.json <

创建 CA 证书签名请求

# cat >ca-csr.json <

生成 CA 证书和私钥

# cfssl gencert -initca ca-csr.json | cfssljson -bare ca

创建etcd的TLS认证证书

# cat > etcd-csr.json <

生成 etcd证书和私钥并分发

# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=etcd etcd-csr.json | cfssljson -bare etcd
# ansible  etcd -m copy -a "src=/root/ssl/ dest=/export/Data/certs/"

ETCD安装以及配置

创建数据目录

# ansible etcd -m shell -a "mkdir -p /export/Data/etcd_data"

下载etcd并分发

# wget https://github.com/etcd-io/etcd/releases/download/v3.5.1/etcd-v3.5.1-linux-amd64.tar.gz
# tar xf etcd-v3.5.1-linux-amd64.tar.gz  && cd etcd-v3.5.1-linux-amd64
# ansible etcd -m copy -a "src=etcd  dest=/usr/bin/"
# ansible etcd -m copy -a "src=etcdutl  dest=/usr/bin/"
# ansible etcd -m copy -a "src=etcdctl  dest=/usr/bin/"
# ansible etcd -m shell -a "chmod +x /usr/bin/etcd*"

配置etcd

# cat etcd_config.sh 
#!/bin/bash

#PEER_NAME指定本节点的主机名称/域名，
#PRIVATE_IP指定本节点的IP(用于后面配置文件的生成)
#ETCD_CLUSTER群集列表，是所有节点信息（内容格式: 各节点名称=https://ip:端口  名称任意但要有标识性）
#ETCD_INITIAL_CLUSTER_TOKEN为该etcd集群Token,同一集群token一致
interface_name=`cat /proc/net/dev | sed -n '3,$p' | awk -F ':' {'print $1'} | grep  -E "^ " | grep -v lo | head -n1`
ipaddr=`ip a | grep $interface_name  | awk '{print $2}' | awk -F"/"  '{print $1}' | awk -F':' '{print $NF}'`
export PEER_NAME=`hostname`
export PRIVATE_IP=`echo $ipaddr | tr -d '\r'`
export ETCD_CLUSTER="etcd1=https://192.168.3.21:2380,etcd2=https://192.168.3.22:2380,etcd3=https://192.168.3.23:2380"
export ETCD_INITIAL_CLUSTER_TOKEN="etcd-cluster-1"


cat > /etc/systemd/system/etcd.service  <

# ansible etcd   -m script -a "/root/etcd_config.sh"

启动ETCD

# ansible etcd -m shell -a "systemctl daemon-reload"
# ansible etcd -m service -a 'name=etcd  state=started'
# ansible etcd -m shell -a "systemctl enable  etcd" 

校验ETCD

注： ansible节点执行，需安装 etcdctl

# cat check_etcd.sh 
#!/bin/bash

HOST1=192.168.3.21
HOST2=192.168.3.22
HOST3=192.168.3.23
ENDPOINTS=$HOST1:2379,$HOST2:2379,$HOST3:2379
#因为开启了证书验证，因此执行命令需加上证书
KEY="--cacert=/root/ssl/ca.pem \
--cert=/root/ssl/etcd.pem \
--key=/root/ssl/etcd-key.pem"


#etcd集群健康信息
etcdctl --endpoints=$ENDPOINTS $KEY endpoint health

#etcd集群状态信息
etcdctl --endpoints=$ENDPOINTS $KEY --write-out=table endpoint status

#etcd集群成员信息
etcdctl --endpoints=$ENDPOINTS $KEY member list -w table

# sh check_etcd.sh 
192.168.3.22:2379 is healthy: successfully committed proposal: took = 6.670434ms
192.168.3.23:2379 is healthy: successfully committed proposal: took = 7.021894ms
192.168.3.21:2379 is healthy: successfully committed proposal: took = 6.938656ms
+-------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
|     ENDPOINT      |        ID        | VERSION | DB SIZE | IS LEADER | IS LEARNER | RAFT TERM | RAFT INDEX | RAFT APPLIED INDEX | ERRORS |
+-------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
| 192.168.3.21:2379 | a30c90f91c6bc0bf |   3.5.1 |   20 kB |     false |      false |         2 |         23 |                 23 |        |
| 192.168.3.22:2379 | 877407b6419f0fed |   3.5.1 |   20 kB |      true |      false |         2 |         23 |                 23 |        |
| 192.168.3.23:2379 | 75b3a36457698e9a |   3.5.1 |   37 kB |     false |      false |         2 |         23 |                 23 |        |
+-------------------+------------------+---------+---------+-----------+------------+-----------+------------+--------------------+--------+
+------------------+---------+-------+---------------------------+---------------------------+------------+
|        ID        | STATUS  | NAME  |        PEER ADDRS         |       CLIENT ADDRS        | IS LEARNER |
+------------------+---------+-------+---------------------------+---------------------------+------------+
| 75b3a36457698e9a | started | etcd3 | https://192.168.3.23:2380 | https://192.168.3.23:2379 |      false |
| 877407b6419f0fed | started | etcd2 | https://192.168.3.22:2380 | https://192.168.3.22:2379 |      false |
| a30c90f91c6bc0bf | started | etcd1 | https://192.168.3.21:2380 | https://192.168.3.21:2379 |      false |
+------------------+---------+-------+---------------------------+---------------------------+------------+

安装配置 CRI-O

安装CRI-O

# cat get_cri-o.sh 
#!/bin/bash
VERSION=1.22
sudo curl -L -o /etc/yum.repos.d/devel:kubic:libcontainers:stable.repo https://download.opensuse.org/repositories/devel:kubic:libcontainers:stable/CentOS_7/devel:kubic:libcontainers:stable.repo
sudo curl -L -o /etc/yum.repos.d/devel:kubic:libcontainers:stable:cri-o:${VERSION}.repo https://download.opensuse.org/repositories/devel:kubic:libcontainers:stable:cri-o:${VERSION}/CentOS_7/devel:kubic:libcontainers:stable:cri-o:${VERSION}.repo

# ansible k8s -m  yum -a "name=cri-o,cri-tools state=latest"
# ansible k8s -m  shell  -a "sudo systemctl enable --now crio"

修改cri-o 存储路径

# ansible k8s -m shell -a "sed -i -e  's?^graphroot =.*?graphroot = "/export/Data/containers/storage"?g' /etc/containers/storage.conf"

配置cgroup

# cat 02-cgroup-manager.conf 
[crio.runtime]
conmon_cgroup = "pod"
cgroup_manager = "systemd"

# ansible k8s -m copy -a "src=02-cgroup-manager.conf   dest=/etc/crio/crio.conf.d/"

配置镜像加速

# cat images_mirr.sh 
#!/bin/bash
cat >> /etc/containers/registries.conf << EOF
[[registry]]
prefix = "docker.io"
location = "hub-mirror.c.163.com"

[[registry.mirror]]
prefix = "docker.io"
location = "hub-mirror.c.163.com"
EOF

# ansible k8s  -m script -a "/root/images_mirr.sh"
# ansible k8s  -m service -a 'name=crio  state=restarted'

配置LB

公有云使用负载均衡代替

高可用LB后续更新，暂用nginx代替

以下操作LB节点执行

[root@lb ~]# yum -y install epel-release.noarch
[root@lb ~]# yum -y install nginx nginx-mod-stream

nginx 配置文件中加入以下配置

stream {
  log_format  main  '$remote_addr [$time_local]'
                    '$protocol $status $bytes_sent $bytes_received'
                    '$session_time';
  server {
    listen 16443;
    proxy_pass kubeapi;
    access_log  /var/log/nginx/access.log  main;
  }
  upstream kubeapi {
    server 192.168.3.24:6443;
    server 192.168.3.25:6443;
    server 192.168.3.26:6443;
  }
}

部署k8s

安装kubeadm、kubelet

# cat kube.sh 
#!/bin/bash
cat <

分发etcd证书

# ansible k8s -m shell -a "mkdir -p /export/Data/certs/"

配置kubelet

# cat  kubelet_conf.sh
#!/bin/bash

cat > /etc/sysconfig/kubelet <

初始第一个master节点

# cat kubeadm_config.yaml 
apiVersion: kubeadm.k8s.io/v1beta2
kind: ClusterConfiguration
kubernetesVersion: v1.22.3
imageRepository: registry.aliyuncs.com/google_containers
controlPlaneEndpoint: "192.168.3.29:16443"
networking:
  serviceSubnet: "10.96.0.0/16"
  podSubnet: "172.16.0.0/16"
  dnsDomain: "cluster.local"
dns:
  type: "CoreDNS"
etcd:
  external:
     endpoints:
     - https://192.168.3.21:2379
     - https://192.168.3.22:2379
     - https://192.168.3.23:2379
     caFile: /export/Data/certs/ca.pem
     certFile: /export/Data/certs/etcd.pem
     keyFile: /export/Data/certs/etcd-key.pem
---
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
cgroupDriver: systemd

---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs

# ansible 192.168.3.24 -m copy -a "src=kubeadm_config.yaml dest=/root"
# ansible  k8s  -m copy -a "src=/root/ssl/ dest=/export/Data/certs/"
#  ansible 192.168.3.24 -m shell  -a "kubeadm init    --config=/root/kubeadm_config.yaml   --upload-certs"

初始化第二个master节点

注: 密钥上步获得

# ansible 192.168.3.25 -m shell  -a "kubeadm join 192.168.3.29:16443 --token de4x51.d923b7l0tbi0692t --discovery-token-ca-cert-hash sha256:b1a8f00caed912ac083d10d8ecd1e92ddf6870c768f91d4e43c91c2614e24e1a --control-plane --certificate-key 0b34ca2ebd85f99ff66b2f57b80708e2ac0368880da52a802e3feb01852f2d81"

初始化第三个master节点

# ansible 192.168.3.26 -m shell  -a "kubeadm join 192.168.3.29:16443 --token de4x51.d923b7l0tbi0692t --discovery-token-ca-cert-hash sha256:b1a8f00caed912ac083d10d8ecd1e92ddf6870c768f91d4e43c91c2614e24e1a --control-plane --certificate-key 0b34ca2ebd85f99ff66b2f57b80708e2ac0368880da52a802e3feb01852f2d81"

初始化worker节点

# ansible  k8s-worker  -m shell -a " kubeadm join 192.168.3.29:16443 --token de4x51.d923b7l0tbi0692t --discovery-token-ca-cert-hash sha256:b1a8f00caed912ac083d10d8ecd1e92ddf6870c768f91d4e43c91c2614e24e1a"

初始化kubectl

# mkdir -p $HOME/.kube
# scp [email protected]:/etc/kubernetes/admin.conf $HOME/.kube/config
# scp [email protected]:/usr/bin/kubectl  /usr/bin/kubectl

验证kubelet

[root@deploy ~]# kubectl  get node
NAME      STATUS   ROLES                  AGE     VERSION
master1   Ready    control-plane,master   41m     v1.22.3
master2   Ready    control-plane,master   13m     v1.22.3
master3   Ready    control-plane,master   12m     v1.22.3
worker1   Ready                     9m18s   v1.22.3
worker2   Ready                     9m19s   v1.22.3

部署网络模型

修改配置

---
# Source: calico/templates/calico-etcd-secrets.yaml
# The following contains k8s Secrets for use with a TLS enabled etcd cluster.
# For information on populating Secrets, see http://kubernetes.io/docs/user-guide/secrets/
apiVersion: v1
kind: Secret
type: Opaque
metadata:
  name: calico-etcd-secrets
  namespace: kube-system
data:
  # Populate the following with etcd TLS configuration if desired, but leave blank if
  # not using TLS for etcd.
  # The keys below should be uncommented and the values populated with the base64
  # encoded contents of each file that would be associated with the TLS data.
  # Example command for encoding a file contents: cat  | base64 -w 0
  etcd-key: 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
  etcd-cert: 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 
  etcd-ca: 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 
---
# Source: calico/templates/calico-config.yaml
# This ConfigMap is used to configure a self-hosted Calico installation.
kind: ConfigMap
apiVersion: v1
metadata:
  name: calico-config
  namespace: kube-system
data:
  # Configure this with the location of your etcd cluster.
  etcd_endpoints: "https://192.168.3.21:2379,https://192.168.3.22:2379,https://192.168.3.23:2379"
  # If you're using TLS enabled etcd uncomment the following.
  # You must also populate the Secret below with these files.
  etcd_ca: "/calico-secrets/etcd-ca"   # "/calico-secrets/etcd-ca"
  etcd_cert: "/calico-secrets/etcd-cert" # "/calico-secrets/etcd-cert"
  etcd_key: "/calico-secrets/etcd-key"  # "/calico-secrets/etcd-key"
  # Typha is disabled.
  typha_service_name: "none"
  # Configure the backend to use.
  calico_backend: "vxlan"

  # Configure the MTU to use for workload interfaces and tunnels.
  # By default, MTU is auto-detected, and explicitly setting this field should not be required.
  # You can override auto-detection by providing a non-zero value.
  veth_mtu: "0"

  # The CNI network configuration to install on each node. The special
  # values in this config will be automatically populated.
  cni_network_config: |-
    {
      "name": "k8s-pod-network",
      "cniVersion": "0.3.1",
      "plugins": [
        {
          "type": "calico",
          "log_level": "info",
          "log_file_path": "/var/log/calico/cni/cni.log",
          "etcd_endpoints": "__ETCD_ENDPOINTS__",
          "etcd_key_file": "__ETCD_KEY_FILE__",
          "etcd_cert_file": "__ETCD_CERT_FILE__",
          "etcd_ca_cert_file": "__ETCD_CA_CERT_FILE__",
          "mtu": __CNI_MTU__,
          "ipam": {
              "type": "calico-ipam"
          },
          "policy": {
              "type": "k8s"
          },
          "kubernetes": {
              "kubeconfig": "__KUBECONFIG_FILEPATH__"
          }
        },
        {
          "type": "portmap",
          "snat": true,
          "capabilities": {"portMappings": true}
        },
        {
          "type": "bandwidth",
          "capabilities": {"bandwidth": true}
        }
      ]
    }

---
# Source: calico/templates/calico-kube-controllers-rbac.yaml

# Include a clusterrole for the kube-controllers component,
# and bind it to the calico-kube-controllers serviceaccount.
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: calico-kube-controllers
rules:
  # Pods are monitored for changing labels.
  # The node controller monitors Kubernetes nodes.
  # Namespace and serviceaccount labels are used for policy.
  - apiGroups: [""]
    resources:
      - pods
      - nodes
      - namespaces
      - serviceaccounts
    verbs:
      - watch
      - list
      - get
  # Watch for changes to Kubernetes NetworkPolicies.
  - apiGroups: ["networking.k8s.io"]
    resources:
      - networkpolicies
    verbs:
      - watch
      - list
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: calico-kube-controllers
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: calico-kube-controllers
subjects:
- kind: ServiceAccount
  name: calico-kube-controllers
  namespace: kube-system
---

---
# Source: calico/templates/calico-node-rbac.yaml
# Include a clusterrole for the calico-node DaemonSet,
# and bind it to the calico-node serviceaccount.
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: calico-node
rules:
  # The CNI plugin needs to get pods, nodes, and namespaces.
  - apiGroups: [""]
    resources:
      - pods
      - nodes
      - namespaces
    verbs:
      - get
  # EndpointSlices are used for Service-based network policy rule
  # enforcement.
  - apiGroups: ["discovery.k8s.io"]
    resources:
      - endpointslices
    verbs:
      - watch 
      - list
  - apiGroups: [""]
    resources:
      - endpoints
      - services
    verbs:
      # Used to discover service IPs for advertisement.
      - watch
      - list
  # Pod CIDR auto-detection on kubeadm needs access to config maps.
  - apiGroups: [""]
    resources:
      - configmaps
    verbs:
      - get
  - apiGroups: [""]
    resources:
      - nodes/status
    verbs:
      # Needed for clearing NodeNetworkUnavailable flag.
      - patch

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: calico-node
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: calico-node
subjects:
- kind: ServiceAccount
  name: calico-node
  namespace: kube-system

---
# Source: calico/templates/calico-node.yaml
# This manifest installs the calico-node container, as well
# as the CNI plugins and network config on
# each master and worker node in a Kubernetes cluster.
kind: DaemonSet
apiVersion: apps/v1
metadata:
  name: calico-node
  namespace: kube-system
  labels:
    k8s-app: calico-node
spec:
  selector:
    matchLabels:
      k8s-app: calico-node
  updateStrategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 1
  template:
    metadata:
      labels:
        k8s-app: calico-node
    spec:
      nodeSelector:
        kubernetes.io/os: linux
      hostNetwork: true
      tolerations:
        # Make sure calico-node gets scheduled on all nodes.
        - effect: NoSchedule
          operator: Exists
        # Mark the pod as a critical add-on for rescheduling.
        - key: CriticalAddonsOnly
          operator: Exists
        - effect: NoExecute
          operator: Exists
      serviceAccountName: calico-node
      # Minimize downtime during a rolling upgrade or deletion; tell Kubernetes to do a "force
      # deletion": https://kubernetes.io/docs/concepts/workloads/pods/pod/#termination-of-pods.
      terminationGracePeriodSeconds: 0
      priorityClassName: system-node-critical
      initContainers:
        # This container installs the CNI binaries
        # and CNI network config file on each node.
        - name: install-cni
          image: docker.mirrors.ustc.edu.cn/calico/cni:v3.21.0
          command: ["/opt/cni/bin/install"]
          envFrom:
          - configMapRef:
              # Allow KUBERNETES_SERVICE_HOST and KUBERNETES_SERVICE_PORT to be overridden for eBPF mode.
              name: kubernetes-services-endpoint
              optional: true
          env:
            # Name of the CNI config file to create.
            - name: CNI_CONF_NAME
              value: "10-calico.conflist"
            # The CNI network config to install on each node.
            - name: CNI_NETWORK_CONFIG
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: cni_network_config
            # The location of the etcd cluster.
            - name: ETCD_ENDPOINTS
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_endpoints
            # CNI MTU Config variable
            - name: CNI_MTU
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: veth_mtu
            # Prevents the container from sleeping forever.
            - name: SLEEP
              value: "false"
          volumeMounts:
            - mountPath: /host/opt/cni/bin
              name: cni-bin-dir
            - mountPath: /host/etc/cni/net.d
              name: cni-net-dir
            - mountPath: /calico-secrets
              name: etcd-certs
          securityContext:
            privileged: true
        # Adds a Flex Volume Driver that creates a per-pod Unix Domain Socket to allow Dikastes
        # to communicate with Felix over the Policy Sync API.
        - name: flexvol-driver
          image: docker.mirrors.ustc.edu.cn/calico/pod2daemon-flexvol:v3.21.0
          volumeMounts:
          - name: flexvol-driver-host
            mountPath: /host/driver
          securityContext:
            privileged: true
      containers:
        # Runs calico-node container on each Kubernetes node. This
        # container programs network policy and routes on each
        # host.
        - name: calico-node
          image: docker.mirrors.ustc.edu.cn/calico/node:v3.21.0
          envFrom:
          - configMapRef:
              # Allow KUBERNETES_SERVICE_HOST and KUBERNETES_SERVICE_PORT to be overridden for eBPF mode.
              name: kubernetes-services-endpoint
              optional: true
          env:
            # The location of the etcd cluster.
            - name: ETCD_ENDPOINTS
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_endpoints
            # Location of the CA certificate for etcd.
            - name: ETCD_CA_CERT_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_ca
            # Location of the client key for etcd.
            - name: ETCD_KEY_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_key
            # Location of the client certificate for etcd.
            - name: ETCD_CERT_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_cert
            # Set noderef for node controller.
            - name: CALICO_K8S_NODE_REF
              valueFrom:
                fieldRef:
                  fieldPath: spec.nodeName
            # Choose the backend to use.
            - name: CALICO_NETWORKING_BACKEND
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: calico_backend
            # Cluster type to identify the deployment type
            - name: CLUSTER_TYPE
              value: "k8s,bgp"
            # Auto-detect the BGP IP address.
            - name: IP
              value: "autodetect"
            # Enable IPIP
            - name: CALICO_IPV4POOL_IPIP
              value: "Never"
            # Enable or Disable VXLAN on the default IP pool.
            - name: CALICO_IPV4POOL_VXLAN
              value: "Always"
            # Set MTU for tunnel device used if ipip is enabled
            - name: FELIX_IPINIPMTU
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: veth_mtu
            # Set MTU for the VXLAN tunnel device.
            - name: FELIX_VXLANMTU
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: veth_mtu
            # Set MTU for the Wireguard tunnel device.
            - name: FELIX_WIREGUARDMTU
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: veth_mtu
            # The default IPv4 pool to create on startup if none exists. Pod IPs will be
            # chosen from this range. Changing this value after installation will have
            # no effect. This should fall within `--cluster-cidr`.
            - name: CALICO_IPV4POOL_CIDR
              value: "172.16.0.0/16"
            # Disable file logging so `kubectl logs` works.
            - name: CALICO_DISABLE_FILE_LOGGING
              value: "true"
            # Set Felix endpoint to host default action to ACCEPT.
            - name: FELIX_DEFAULTENDPOINTTOHOSTACTION
              value: "ACCEPT"
            # Disable IPv6 on Kubernetes.
            - name: FELIX_IPV6SUPPORT
              value: "false"
            - name: FELIX_HEALTHENABLED
              value: "true"
          securityContext:
            privileged: true
          resources:
            requests:
              cpu: 250m
          lifecycle:
            preStop:
              exec:
                command:
                - /bin/calico-node
                - -shutdown
          livenessProbe:
            exec:
              command:
              - /bin/calico-node
              - -felix-live
              #- -bird-live
            periodSeconds: 10
            initialDelaySeconds: 10
            failureThreshold: 6
            timeoutSeconds: 10
          readinessProbe:
            exec:
              command:
              - /bin/calico-node
              - -felix-ready
              #- -bird-ready
            periodSeconds: 10
            timeoutSeconds: 10
          volumeMounts:
            # For maintaining CNI plugin API credentials.
            - mountPath: /host/etc/cni/net.d
              name: cni-net-dir
              readOnly: false
            - mountPath: /lib/modules
              name: lib-modules
              readOnly: true
            - mountPath: /run/xtables.lock
              name: xtables-lock
              readOnly: false
            - mountPath: /var/run/calico
              name: var-run-calico
              readOnly: false
            - mountPath: /var/lib/calico
              name: var-lib-calico
              readOnly: false
            - mountPath: /calico-secrets
              name: etcd-certs
            - name: policysync
              mountPath: /var/run/nodeagent
            # For eBPF mode, we need to be able to mount the BPF filesystem at /sys/fs/bpf so we mount in the
            # parent directory.
            - name: sysfs
              mountPath: /sys/fs/
              # Bidirectional means that, if we mount the BPF filesystem at /sys/fs/bpf it will propagate to the host.
              # If the host is known to mount that filesystem already then Bidirectional can be omitted.
              mountPropagation: Bidirectional
            - name: cni-log-dir
              mountPath: /var/log/calico/cni
              readOnly: true
      volumes:
        # Used by calico-node.
        - name: lib-modules
          hostPath:
            path: /lib/modules
        - name: var-run-calico
          hostPath:
            path: /var/run/calico
        - name: var-lib-calico
          hostPath:
            path: /var/lib/calico
        - name: xtables-lock
          hostPath:
            path: /run/xtables.lock
            type: FileOrCreate
        - name: sysfs
          hostPath:
            path: /sys/fs/
            type: DirectoryOrCreate
        # Used to install CNI.
        - name: cni-bin-dir
          hostPath:
            path: /opt/cni/bin
        - name: cni-net-dir
          hostPath:
            path: /etc/cni/net.d
        # Used to access CNI logs.
        - name: cni-log-dir
          hostPath:
            path: /var/log/calico/cni
        # Mount in the etcd TLS secrets with mode 400.
        # See https://kubernetes.io/docs/concepts/configuration/secret/
        - name: etcd-certs
          secret:
            secretName: calico-etcd-secrets
            defaultMode: 0400
        # Used to create per-pod Unix Domain Sockets
        - name: policysync
          hostPath:
            type: DirectoryOrCreate
            path: /var/run/nodeagent
        # Used to install Flex Volume Driver
        - name: flexvol-driver-host
          hostPath:
            type: DirectoryOrCreate
            path: /usr/libexec/kubernetes/kubelet-plugins/volume/exec/nodeagent~uds
---

apiVersion: v1
kind: ServiceAccount
metadata:
  name: calico-node
  namespace: kube-system

---
# Source: calico/templates/calico-kube-controllers.yaml
# See https://github.com/projectcalico/kube-controllers
apiVersion: apps/v1
kind: Deployment
metadata:
  name: calico-kube-controllers
  namespace: kube-system
  labels:
    k8s-app: calico-kube-controllers
spec:
  # The controllers can only have a single active instance.
  replicas: 1
  selector:
    matchLabels:
      k8s-app: calico-kube-controllers
  strategy:
    type: Recreate
  template:
    metadata:
      name: calico-kube-controllers
      namespace: kube-system
      labels:
        k8s-app: calico-kube-controllers
    spec:
      nodeSelector:
        kubernetes.io/os: linux
      tolerations:
        # Mark the pod as a critical add-on for rescheduling.
        - key: CriticalAddonsOnly
          operator: Exists
        - key: node-role.kubernetes.io/master
          effect: NoSchedule
      serviceAccountName: calico-kube-controllers
      priorityClassName: system-cluster-critical
      # The controllers must run in the host network namespace so that
      # it isn't governed by policy that would prevent it from working.
      hostNetwork: true
      containers:
        - name: calico-kube-controllers
          image: docker.mirrors.ustc.edu.cn/calico/kube-controllers:v3.21.0
          env:
            # The location of the etcd cluster.
            - name: ETCD_ENDPOINTS
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_endpoints
            # Location of the CA certificate for etcd.
            - name: ETCD_CA_CERT_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_ca
            # Location of the client key for etcd.
            - name: ETCD_KEY_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_key
            # Location of the client certificate for etcd.
            - name: ETCD_CERT_FILE
              valueFrom:
                configMapKeyRef:
                  name: calico-config
                  key: etcd_cert
            # Choose which controllers to run.
            - name: ENABLED_CONTROLLERS
              value: policy,namespace,serviceaccount,workloadendpoint,node
          volumeMounts:
            # Mount in the etcd TLS secrets.
            - mountPath: /calico-secrets
              name: etcd-certs
          livenessProbe:
            exec:
              command:
              - /usr/bin/check-status
              - -l
            periodSeconds: 10
            initialDelaySeconds: 10
            failureThreshold: 6
            timeoutSeconds: 10
          readinessProbe:
            exec:
              command:
              - /usr/bin/check-status
              - -r
            periodSeconds: 10
      volumes:
        # Mount in the etcd TLS secrets with mode 400.
        # See https://kubernetes.io/docs/concepts/configuration/secret/
        - name: etcd-certs
          secret:
            secretName: calico-etcd-secrets
            defaultMode: 0440

---

apiVersion: v1
kind: ServiceAccount
metadata:
  name: calico-kube-controllers
  namespace: kube-system

---

# This manifest creates a Pod Disruption Budget for Controller to allow K8s Cluster Autoscaler to evict

apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: calico-kube-controllers
  namespace: kube-system
  labels:
    k8s-app: calico-kube-controllers
spec:
  maxUnavailable: 1
  selector:
    matchLabels:
      k8s-app: calico-kube-controllers

---
# Source: calico/templates/calico-typha.yaml

---
# Source: calico/templates/configure-canal.yaml

---
# Source: calico/templates/kdd-crds.yaml

安装calico

# kubectl  apply -f calico-etcd.yaml

验证集群

[root@deploy ~]# kubectl  get  pod -n kube-system
NAME                                      READY   STATUS    RESTARTS   AGE
calico-kube-controllers-9767fc4b9-tk9fb   1/1     Running   0          6m56s
calico-node-5mc9h                         1/1     Running   0          6m56s
calico-node-dswmp                         1/1     Running   0          6m56s
calico-node-qht2s                         1/1     Running   0          6m56s
calico-node-sdrcg                         1/1     Running   0          6m56s
calico-node-x58lj                         1/1     Running   0          6m56s
coredns-7f6cbbb7b8-fc8rd                  1/1     Running   0          61m
coredns-7f6cbbb7b8-qvw2m                  1/1     Running   0          61m
kube-apiserver-master1                    1/1     Running   2          94m
kube-apiserver-master2                    1/1     Running   0          66m
kube-apiserver-master3                    1/1     Running   0          64m
kube-controller-manager-master1           1/1     Running   2          94m
kube-controller-manager-master2           1/1     Running   0          66m
kube-controller-manager-master3           1/1     Running   0          64m
kube-proxy-bscfn                          1/1     Running   0          62m
kube-proxy-f2fpb                          1/1     Running   0          64m
kube-proxy-kt7nl                          1/1     Running   0          66m
kube-proxy-lzww8                          1/1     Running   0          62m
kube-proxy-zn6gj                          1/1     Running   2          94m
kube-scheduler-master1                    1/1     Running   2          94m
kube-scheduler-master2                    1/1     Running   0          66m
kube-scheduler-master3                    1/1     Running   0          64m

问题与解决

1 、 kubelet日报错 failed to get cgroup stats for "
/system.slice/kubelet.service"

11月 18 09:00:42 master1 kubelet[2424]: E1118 09:00:42.948672    2424 summary_sys_containers.go:47] "Failed to get system container stats" err="failed to get cgroup stats for \"/system.slice/kubelet.service\": failed to get container info for \"/system.slice/kubelet.service\": unknown container \"/system.slice/kubelet.service\"" containerName="/system.slice/kubelet.service"
11月 18 09:00:52 master1 kubelet[2424]: E1118 09:00:52.956142    2424 summary_sys_containers.go:47] "Failed to get system container stats" err="failed to get cgroup stats for \"/system.slice/kubelet.service\": failed to get container info for \"/system.slice/kubelet.service\": unknown container \"/system.slice/kubelet.service\"" containerName="/system.slice/kubelet.service"
11月 18 09:01:02 master1 kubelet[2424]: E1118 09:01:02.961022    2424 summary_sys_containers.go:47] "Failed to get system container stats" err="failed to get cgroup stats for \"/system.slice/kubelet.service\": failed to get container info for \"/system.slice/kubelet.service\": unknown container \"/system.slice/kubelet.service\"" containerName="/system.slice/kubelet.service"
11月 18 09:01:12 master1 kubelet[2424]: E1118 09:01:12.966033    2424 summary_sys_containers.go:47] "Failed to get system container stats" err="failed to get cgroup stats for \"/system.slice/kubelet.service\": failed to get container info for \"/system.slice/kubelet.service\": unknown container \"/system.slice/kubelet.service\"" containerName="/system.slice/kubelet.service"
11月 18 09:01:22 master1 kubelet[2424]: E1118 09:01:22.970644    2424 summary_sys_containers.go:47] "Failed to get system container stats" err="failed to get cgroup stats for \"/system.slice/kubelet.service\": failed to get container info for \"/system.slice/kubelet.service\": unknown container \"/system.slice/kubelet.service\"" containerName="/system.slice/kubelet.service"

解决方案

配置文件中写入 CPUAccounting=true 与 MemoryAccounting=true

[root@master2 ~]# cat /lib/systemd/system/kubelet.service.d/10-kubeadm.conf 
# Note: This dropin only works with kubeadm and kubelet v1.11+
[Service]
CPUAccounting=true
MemoryAccounting=true
Environment="KUBELET_KUBECONFIG_ARGS=--bootstrap-kubeconfig=/etc/kubernetes/bootstrap-kubelet.conf --kubeconfig=/etc/kubernetes/kubelet.conf"
Environment="KUBELET_CONFIG_ARGS=--config=/var/lib/kubelet/config.yaml"
# This is a file that "kubeadm init" and "kubeadm join" generates at runtime, populating the KUBELET_KUBEADM_ARGS variable dynamically
EnvironmentFile=-/var/lib/kubelet/kubeadm-flags.env
# This is a file that the user can use for overrides of the kubelet args as a last resort. Preferably, the user should use
# the .NodeRegistration.KubeletExtraArgs object in the configuration files instead. KUBELET_EXTRA_ARGS should be sourced from this file.
EnvironmentFile=-/etc/sysconfig/kubelet
ExecStart=
ExecStart=/usr/bin/kubelet $KUBELET_KUBECONFIG_ARGS $KUBELET_CONFIG_ARGS $KUBELET_KUBEADM_ARGS $KUBELET_EXTRA_ARGS

2、kubectl get cs 提示 dial tcp 127.0.0.1:10251: connect: connection refused

[root@deploy ~]# kubectl  get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS      MESSAGE                                                                                       ERROR
scheduler            Unhealthy   Get "http://127.0.0.1:10251/healthz": dial tcp 127.0.0.1:10251: connect: connection refused   
etcd-1               Healthy     {"health":"true","reason":""}                                                                 
controller-manager   Healthy     ok                                                                                            
etcd-0               Healthy     {"health":"true","reason":""}                                                                 
etcd-2               Healthy     {"health":"true","reason":""} 

解决方案

注释 port=0

[root@master1 ~]# cat /etc/kubernetes/manifests/kube-scheduler.yaml 
apiVersion: v1
kind: Pod
metadata:
  creationTimestamp: null
  labels:
    component: kube-scheduler
    tier: control-plane
  name: kube-scheduler
  namespace: kube-system
spec:
  containers:
  - command:
    - kube-scheduler
    - --authentication-kubeconfig=/etc/kubernetes/scheduler.conf
    - --authorization-kubeconfig=/etc/kubernetes/scheduler.conf
    - --bind-address=127.0.0.1
    - --kubeconfig=/etc/kubernetes/scheduler.conf
    - --leader-elect=true
#    - --port=0
    image: registry.aliyuncs.com/google_containers/kube-scheduler:v1.22.3
    imagePullPolicy: IfNotPresent

[root@deploy ~]# kubectl  get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME                 STATUS    MESSAGE                         ERROR
scheduler            Healthy   ok                              
controller-manager   Healthy   ok                              
etcd-1               Healthy   {"health":"true","reason":""}   
etcd-2               Healthy   {"health":"true","reason":""}   
etcd-0               Healthy   {"health":"true","reason":""}   

作者：宗庄凯