前言
kubeadm 和 二进制 部署的区别
kubeadm
优点：
部署很方便，两个参数就可以完成集群的部署和节点的加入
kubeadm init初始化节点kubeadm join节点加入集群
缺点：
- 集群证书有效期只有一年，要么破解，要么升级 k8s 版本
二进制部署
优点：
- 可以自定义集群证书有效期（一般都是十年）
- 所有组件的细节，可以在部署前定制
- 部署过程中，能更好的理解 k8s 各个组件之间的关联
缺点：
- 部署相对 kubeadm 会复杂很多
人生苦短，我选二进制部署
环境准备
| IP | 角色 | 内核版本 |
|---|---|---|
| 192.168.91.8 | master | centos7.6/3.10.0-957.el7.x86_64 |
| 192.168.91.9 | work | centos7.6/3.10.0-957.el7.x86_64 |
答应我，所有节点都要关闭防火墙
systemctl disable firewalld
systemctl stop firewalld答应我，所有节点都要关闭selinux
setenforce 0
sed -i '/SELINUX/s/enforcing/disabled/g' /etc/selinux/config答应我，所有节点都要关闭swap
swapoff -a
sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab答应我，所有节点都要开启内核模块
modprobe ip_vs
modprobe ip_vs_rr
modprobe ip_vs_wrr
modprobe ip_vs_sh
modprobe nf_conntrack
modprobe nf_conntrack_ipv4
modprobe br_netfilter
modprobe overlay答应我，所有节点都要开启模块自动加载服务
cat > /etc/modules-load.d/k8s-modules.conf <<EOF
ip_vs
ip_vs_rr
ip_vs_wrr
ip_vs_sh
nf_conntrack
nf_conntrack_ipv4
br_netfilter
overlay
EOF答应我，记得重启服务，并设置为开机自启
systemctl enable systemd-modules-load
systemctl restart systemd-modules-load答应我，所有节点都要做内核优化
cat <<EOF > /etc/sysctl.d/kubernetes.conf
# 开启数据包转发功能（实现vxlan）
net.ipv4.ip_forward=1
# iptables对bridge的数据进行处理
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.bridge.bridge-nf-call-arptables=1
# 关闭tcp_tw_recycle，否则和NAT冲突，会导致服务不通
net.ipv4.tcp_tw_recycle=0
# 不允许将TIME-WAIT sockets重新用于新的TCP连接
net.ipv4.tcp_tw_reuse=0
# socket监听(listen)的backlog上限
net.core.somaxconn=32768
# 最大跟踪连接数，默认 nf_conntrack_buckets * 4
net.netfilter.nf_conntrack_max=1000000
# 禁止使用 swap 空间，只有当系统 OOM 时才允许使用它
vm.swappiness=0
# 计算当前的内存映射文件数。
vm.max_map_count=655360
# 内核可分配的最大文件数
fs.file-max=6553600
# 持久连接
net.ipv4.tcp_keepalive_time=600
net.ipv4.tcp_keepalive_intvl=30
net.ipv4.tcp_keepalive_probes=10
EOF答应我，让配置生效
sysctl -p /etc/sysctl.d/kubernetes.conf答应我，所有节点都要清空 iptables 规则
iptables -F && iptables -X && iptables -F -t nat && iptables -X -t nat
iptables -P FORWARD ACCEPT安装 containerd
所有节点都需要安装配置 docker 源 （docker 源里面有 containerd）
wget -O /etc/yum.repos.d/docker.repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo查找 containerd 安装包的名称
yum search containerd安装 containerd
yum install -y containerd.io修改 containerd 配置文件
root容器存储路径，修改成磁盘空间充足的路径
sandbox_imagepause 镜像名称以及镜像tag（一定要可以拉取到 pause 镜像的，否则会导致集群初始化的时候 kubelet 重启失败）
bin_dircni 插件存放路径，yum 安装的 containerd 默认存放在/opt/cni/bin目录下
cat <<EOF > /etc/containerd/config.toml
disabled_plugins = []
imports = []
oom_score = 0
plugin_dir = ""
required_plugins = []
root = "/approot1/data/containerd"
state = "/run/containerd"
version = 2
[cgroup]
path = ""
[debug]
address = ""
format = ""
gid = 0
level = ""
uid = 0
[grpc]
address = "/run/containerd/containerd.sock"
gid = 0
max_recv_message_size = 16777216
max_send_message_size = 16777216
tcp_address = ""
tcp_tls_cert = ""
tcp_tls_key = ""
uid = 0
[metrics]
address = ""
grpc_histogram = false
[plugins]
[plugins."io.containerd.gc.v1.scheduler"]
deletion_threshold = 0
mutation_threshold = 100
pause_threshold = 0.02
schedule_delay = "0s"
startup_delay = "100ms"
[plugins."io.containerd.grpc.v1.cri"]
disable_apparmor = false
disable_cgroup = false
disable_hugetlb_controller = true
disable_proc_mount = false
disable_tcp_service = true
enable_selinux = false
enable_tls_streaming = false
ignore_image_defined_volumes = false
max_concurrent_downloads = 3
max_container_log_line_size = 16384
netns_mounts_under_state_dir = false
restrict_oom_score_adj = false
sandbox_image = "registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.6"
selinux_category_range = 1024
stats_collect_period = 10
stream_idle_timeout = "4h0m0s"
stream_server_address = "127.0.0.1"
stream_server_port = "0"
systemd_cgroup = false
tolerate_missing_hugetlb_controller = true
unset_seccomp_profile = ""
[plugins."io.containerd.grpc.v1.cri".cni]
bin_dir = "/opt/cni/bin"
conf_dir = "/etc/cni/net.d"
conf_template = "/etc/cni/net.d/cni-default.conf"
max_conf_num = 1
[plugins."io.containerd.grpc.v1.cri".containerd]
default_runtime_name = "runc"
disable_snapshot_annotations = true
discard_unpacked_layers = false
no_pivot = false
snapshotter = "overlayfs"
[plugins."io.containerd.grpc.v1.cri".containerd.default_runtime]
base_runtime_spec = ""
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_root = ""
runtime_type = ""
[plugins."io.containerd.grpc.v1.cri".containerd.default_runtime.options]
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes]
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
base_runtime_spec = ""
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_root = ""
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
BinaryName = ""
CriuImagePath = ""
CriuPath = ""
CriuWorkPath = ""
IoGid = 0
IoUid = 0
NoNewKeyring = false
NoPivotRoot = false
Root = ""
ShimCgroup = ""
SystemdCgroup = true
[plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime]
base_runtime_spec = ""
container_annotations = []
pod_annotations = []
privileged_without_host_devices = false
runtime_engine = ""
runtime_root = ""
runtime_type = ""
[plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime.options]
[plugins."io.containerd.grpc.v1.cri".image_decryption]
key_model = "node"
[plugins."io.containerd.grpc.v1.cri".registry]
config_path = ""
[plugins."io.containerd.grpc.v1.cri".registry.auths]
[plugins."io.containerd.grpc.v1.cri".registry.configs]
[plugins."io.containerd.grpc.v1.cri".registry.headers]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
endpoint = ["https://docker.mirrors.ustc.edu.cn", "http://hub-mirror.c.163.com"]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."gcr.io"]
endpoint = ["https://gcr.mirrors.ustc.edu.cn"]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."k8s.gcr.io"]
endpoint = ["https://gcr.mirrors.ustc.edu.cn/google-containers/"]
[plugins."io.containerd.grpc.v1.cri".registry.mirrors."quay.io"]
endpoint = ["https://quay.mirrors.ustc.edu.cn"]
[plugins."io.containerd.grpc.v1.cri".x509_key_pair_streaming]
tls_cert_file = ""
tls_key_file = ""
[plugins."io.containerd.internal.v1.opt"]
path = "/opt/containerd"
[plugins."io.containerd.internal.v1.restart"]
interval = "10s"
[plugins."io.containerd.metadata.v1.bolt"]
content_sharing_policy = "shared"
[plugins."io.containerd.monitor.v1.cgroups"]
no_prometheus = false
[plugins."io.containerd.runtime.v1.linux"]
no_shim = false
runtime = "runc"
runtime_root = ""
shim = "containerd-shim"
shim_debug = false
[plugins."io.containerd.runtime.v2.task"]
platforms = ["linux/amd64"]
[plugins."io.containerd.service.v1.diff-service"]
default = ["walking"]
[plugins."io.containerd.snapshotter.v1.aufs"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.btrfs"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.devmapper"]
async_remove = false
base_image_size = ""
pool_name = ""
root_path = ""
[plugins."io.containerd.snapshotter.v1.native"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.overlayfs"]
root_path = ""
[plugins."io.containerd.snapshotter.v1.zfs"]
root_path = ""
[proxy_plugins]
[stream_processors]
[stream_processors."io.containerd.ocicrypt.decoder.v1.tar"]
accepts = ["application/vnd.oci.image.layer.v1.tar+encrypted"]
args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
path = "ctd-decoder"
returns = "application/vnd.oci.image.layer.v1.tar"
[stream_processors."io.containerd.ocicrypt.decoder.v1.tar.gzip"]
accepts = ["application/vnd.oci.image.layer.v1.tar+gzip+encrypted"]
args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
path = "ctd-decoder"
returns = "application/vnd.oci.image.layer.v1.tar+gzip"
[timeouts]
"io.containerd.timeout.shim.cleanup" = "5s"
"io.containerd.timeout.shim.load" = "5s"
"io.containerd.timeout.shim.shutdown" = "3s"
"io.containerd.timeout.task.state" = "2s"
[ttrpc]
address = ""
gid = 0
uid = 0
EOF启动 containerd 服务，并设置为开机启动
systemctl enable containerd
systemctl restart containerd配置 kubernetes 源
所有节点都需要配置
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=0
repo_gpgcheck=0
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF通过yum list命令可以查看当前源的稳定版本，目前的稳定版本是1.23.3-0
yum list kubeadm kubelet安装 kubeadm 以及 kubelet
所有节点都需要安装
yum install不带版本，就会安装当前稳定版本，为了后面文档通用，我这里就在安装的时候带上了版本
yum install -y kubelet-1.23.3-0 kubeadm-1.23.3-0配置命令参数自动补全功能
所有节点都需要安装
yum install -y bash-completion
echo 'source <(kubectl completion bash)' >> $HOME/.bashrc
echo 'source <(kubeadm completion bash)' >> $HOME/.bashrc
source $HOME/.bashrc启动 kubelet 服务
所有节点都要操作
systemctl enable kubelet
systemctl restart kubeletkubeadm 部署 master 节点
注意在 master 节点上操作查看
kubeadm init默认配置
kubeadm config print init-defaults
vim kubeadm.yamlkubeadm 配置 (v1beta3)
advertiseAddress参数需要修改成当前 master 节点的 ip
bindPort参数为 apiserver 服务的访问端口，可以自定义
criSocket参数定义 容器运行时 使用的套接字，默认是 dockershim ，这里需要修改为 contained 的套接字文件，在conf.toml里面可以找到
imagePullPolicy参数定义镜像拉取策略，IfNotPresent本地没有镜像则拉取镜像；Always总是重新拉取镜像；Never从不拉取镜像，本地没有镜像，kubelet 启动 pod 就会报错 （注意驼峰命名，这里的大写别改成小写）
certificatesDir参数定义证书文件存储路径，没特殊要求，可以不修改
controlPlaneEndpoint参数定义稳定访问 ip ，高可用这里可以填 vip
dataDir参数定义 etcd 数据持久化路径，默认/var/lib/etcd，部署前，确认路径所在磁盘空间是否足够
imageRepository参数定义镜像仓库名称，默认k8s.gcr.io，如果要修改，需要注意确定镜像一定是可以拉取的到，并且所有的镜像都是从这个镜像仓库拉取的
kubernetesVersion参数定义镜像版本，和镜像的 tag 一致
podSubnet参数定义 pod 使用的网段，不要和serviceSubnet以及本机网段有冲突
serviceSubnet参数定义 k8s 服务 ip 网段，注意是否和本机网段有冲突
cgroupDriver参数定义 cgroup 驱动，默认是cgroupfs
mode参数定义转发方式，可选为iptables和ipvs
name参数定义节点名称，如果是主机名需要保证可以解析（kubectl get nodes 命令查看到的节点名称）
apiVersion: kubeadm.k8s.io/v1beta3
bootstrapTokens:
- groups:
- system:bootstrappers:kubeadm:default-node-token
token: abcdef.0123456789abcdef
ttl: 24h0m0s
usages:
- signing
- authentication
kind: InitConfiguration
localAPIEndpoint:
advertiseAddress: 192.168.91.8
bindPort: 6443
nodeRegistration:
criSocket: /run/containerd/containerd.sock
imagePullPolicy: IfNotPresent
name: 192.168.91.8
taints: null
---
apiServer:
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta3
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 192.168.91.8:6443
controllerManager: {}
dns: {}
etcd:
local:
dataDir: /var/lib/etcd
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: 1.23.3
networking:
dnsDomain: cluster.local
serviceSubnet: 10.96.0.0/12
podSubnet: 172.22.0.0/16
scheduler: {}
---
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
cgroupDriver: systemd
cgroupsPerQOS: true
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: ipvs集群初始化
kubeadm init --config kubeadm.yaml
以下是
kubeadm init 的过程，
[init] Using Kubernetes version: v1.23.3
[preflight] Running pre-flight checks
[WARNING Service-Kubelet]: kubelet service is not enabled, please run 'systemctl enable kubelet.service'
[preflight] Pulling images required for setting up a Kubernetes cluster
[preflight] This might take a minute or two, depending on the speed of your internet connection
[preflight] You can also perform this action in beforehand using 'kubeadm config images pull'
[certs] Using certificateDir folder "/etc/kubernetes/pki"
[certs] Generating "ca" certificate and key
[certs] Generating "apiserver" certificate and key
[certs] apiserver serving cert is signed for DNS names [192.168.91.8 kubernetes kubernetes.default kubernetes.default.svc kubernetes.default.svc.cluster.local] and IPs [10.96.0.1 192.168.91.8]
[certs] Generating "apiserver-kubelet-client" certificate and key
[certs] Generating "front-proxy-ca" certificate and key
[certs] Generating "front-proxy-client" certificate and key
[certs] Generating "etcd/ca" certificate and key
[certs] Generating "etcd/server" certificate and key
[certs] etcd/server serving cert is signed for DNS names [192.168.91.8 localhost] and IPs [192.168.91.8 127.0.0.1 ::1]
[certs] Generating "etcd/peer" certificate and key
[certs] etcd/peer serving cert is signed for DNS names [192.168.91.8 localhost] and IPs [192.168.91.8 127.0.0.1 ::1]
[certs] Generating "etcd/healthcheck-client" certificate and key
[certs] Generating "apiserver-etcd-client" certificate and key
[certs] Generating "sa" key and public key
[kubeconfig] Using kubeconfig folder "/etc/kubernetes"
[kubeconfig] Writing "admin.conf" kubeconfig file
[kubeconfig] Writing "kubelet.conf" kubeconfig file
[kubeconfig] Writing "controller-manager.conf" kubeconfig file
[kubeconfig] Writing "scheduler.conf" kubeconfig file
[kubelet-start] Writing kubelet environment file with flags to file "/var/lib/kubelet/kubeadm-flags.env"
[kubelet-start] Writing kubelet configuration to file "/var/lib/kubelet/config.yaml"
[kubelet-start] Starting the kubelet
[control-plane] Using manifest folder "/etc/kubernetes/manifests"
[control-plane] Creating static Pod manifest for "kube-apiserver"
[control-plane] Creating static Pod manifest for "kube-controller-manager"
[control-plane] Creating static Pod manifest for "kube-scheduler"
[etcd] Creating static Pod manifest for local etcd in "/etc/kubernetes/manifests"
[wait-control-plane] Waiting for the kubelet to boot up the control plane as static Pods from directory "/etc/kubernetes/manifests". This can take up to 4m0s
[apiclient] All control plane components are healthy after 12.504586 seconds
[upload-config] Storing the configuration used in ConfigMap "kubeadm-config" in the "kube-system" Namespace
[kubelet] Creating a ConfigMap "kubelet-config-1.23" in namespace kube-system with the configuration for the kubelets in the cluster
NOTE: The "kubelet-config-1.23" naming of the kubelet ConfigMap is deprecated. Once the UnversionedKubeletConfigMap feature gate graduates to Beta the default name will become just "kubelet-config". Kubeadm upgrade will handle this transition transparently.
[upload-certs] Skipping phase. Please see --upload-certs
[mark-control-plane] Marking the node 192.168.91.8 as control-plane by adding the labels: [node-role.kubernetes.io/master(deprecated) node-role.kubernetes.io/control-plane node.kubernetes.io/exclude-from-external-load-balancers]
[mark-control-plane] Marking the node 192.168.91.8 as control-plane by adding the taints [node-role.kubernetes.io/master:NoSchedule]
[bootstrap-token] Using token: abcdef.0123456789abcdef
[bootstrap-token] Configuring bootstrap tokens, cluster-info ConfigMap, RBAC Roles
[bootstrap-token] configured RBAC rules to allow Node Bootstrap tokens to get nodes
[bootstrap-token] configured RBAC rules to allow Node Bootstrap tokens to post CSRs in order for nodes to get long term certificate credentials
[bootstrap-token] configured RBAC rules to allow the csrapprover controller automatically approve CSRs from a Node Bootstrap Token
[bootstrap-token] configured RBAC rules to allow certificate rotation for all node client certificates in the cluster
[bootstrap-token] Creating the "cluster-info" ConfigMap in the "kube-public" namespace
[kubelet-finalize] Updating "/etc/kubernetes/kubelet.conf" to point to a rotatable kubelet client certificate and key
[addons] Applied essential addon: CoreDNS
[addons] Applied essential addon: kube-proxy
Your Kubernetes control-plane has initialized successfully!
To start using your cluster, you need to run the following as a regular user:
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config
Alternatively, if you are the root user, you can run:
export KUBECONFIG=/etc/kubernetes/admin.conf
You should now deploy a pod network to the cluster.
Run "kubectl apply -f [podnetwork].yaml" with one of the options listed at:
https://kubernetes.io/docs/concepts/cluster-administration/addons/
You can now join any number of control-plane nodes by copying certificate authorities
and service account keys on each node and then running the following as root:
kubeadm join 192.168.91.8:6443 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:5e2387403e698e95b0eab7197837f2425f7b8610e7b400e54d81c27f3c6f1964 \
--control-plane
Then you can join any number of worker nodes by running the following on each as root:
kubeadm join 192.168.91.8:6443 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:5e2387403e698e95b0eab7197837f2425f7b8610e7b400e54d81c27f3c6f1964以下操作二选一kubectl 不加
--kubeconfig参数，默认找的是$HOME/.kube/config，如果不创建目录，并且将证书复制过去，就要生成环境变量，或者每次使用 kubectl 命令的时候，都要加上--kubeconfig参数指定证书文件，否则 kubectl 命令就找不到集群了
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/configecho 'export KUBECONFIG=/etc/kubernetes/admin.conf' >> $HOME/.bashrc
source ~/.bashrc查看 k8s 组件运行情况
kubectl get pods -n kube-systemNAME READY STATUS RESTARTS AGE
coredns-65c54cc984-cglz9 0/1 Pending 0 12s
coredns-65c54cc984-qwd5b 0/1 Pending 0 12s
etcd-192.168.91.8 1/1 Running 0 27s
kube-apiserver-192.168.91.8 1/1 Running 0 21s
kube-controller-manager-192.168.91.8 1/1 Running 0 21s
kube-proxy-zwdlm 1/1 Running 0 12s
kube-scheduler-192.168.91.8 1/1 Running 0 27s因为还没有网络组件，coredns 没有运行成功
安装 flannel 组件
在 master 节点操作即可
Network参数的 ip 段要和上面 kubeadm 配置文件的podSubnet一样
cat <<EOF> flannel.yaml | kubectl apply -f flannel.yaml
---
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/v1
metadata:
name: flannel
rules:
- apiGroups: ['policy']
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/v1
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": "172.22.0.0/16",
"Backend": {
"Type": "vxlan"
}
}
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds
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
hostNetwork: true
priorityClassName: system-node-critical
tolerations:
- operator: Exists
effect: NoSchedule
serviceAccountName: flannel
initContainers:
- name: install-cni
image: quay.io/coreos/flannel:v0.15.1
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:v0.15.1
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
EOF稍等 2-3 分钟，等待 flannel pod 成为 running 状态 （具体时间视镜像下载速度）
NAME READY STATUS RESTARTS AGE
coredns-65c54cc984-cglz9 1/1 Running 0 2m7s
coredns-65c54cc984-qwd5b 1/1 Running 0 2m7s
etcd-192.168.91.8 1/1 Running 0 2m22s
kube-apiserver-192.168.91.8 1/1 Running 0 2m16s
kube-controller-manager-192.168.91.8 1/1 Running 0 2m16s
kube-flannel-ds-26drg 1/1 Running 0 100s
kube-proxy-zwdlm 1/1 Running 0 2m7s
kube-scheduler-192.168.91.8 1/1 Running 0 2m22swork 节点加入集群
在 master 节点初始化完成的时候，已经给出了加入集群的参数只需要复制一下，到 work 节点执行即可
--node-name参数定义节点名称，如果是主机名需要保证可以解析（kubectl get nodes 命令查看到的节点名称）
kubeadm join 192.168.91.8:6443 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:5e2387403e698e95b0eab7197837f2425f7b8610e7b400e54d81c27f3c6f1964 \
--node-name 192.168.91.9如果忘记记录了，或者以后需要增加节点怎么办？执行下面的命令就可以了
kubeadm token create --print-join-command --ttl=0
输出也很少，这个时候只需要去 master 节点执行
kubectl get nodes 命令就可以查看节点的状态了
[preflight] Running pre-flight checks
[WARNING Service-Kubelet]: kubelet service is not enabled, please run 'systemctl enable kubelet.service'
[preflight] Reading configuration from the cluster...
[preflight] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
[kubelet-start] Writing kubelet configuration to file "/var/lib/kubelet/config.yaml"
[kubelet-start] Writing kubelet environment file with flags to file "/var/lib/kubelet/kubeadm-flags.env"
[kubelet-start] Starting the kubelet
[kubelet-start] Waiting for the kubelet to perform the TLS Bootstrap...
This node has joined the cluster:
* Certificate signing request was sent to apiserver and a response was received.
* The Kubelet was informed of the new secure connection details.
Run 'kubectl get nodes' on the control-plane to see this node join the cluster.节点变成 Ready 的时间取决于 work 节点的 flannel 镜像拉取时间可以通过
kubectl get node -n kube-system查看 flannel 是否为Running状态
NAME STATUS ROLES AGE VERSION
192.168.91.8 Ready control-plane,master 9m34s v1.23.3
192.168.91.9 Ready <none> 6m11s v1.23.3master 节点加入集群
需要先从其中一个 master 节点获取 CA 键哈希值这个值在 kubeadm init 完成时也是已经输出到终端了
kubeadm init 时如果有修改过
certificatesDir参数，/etc/kubernetes/pki/ca.crt这里的路径需要注意确认和修改获取到的 hash 值，使用格式：
sha256:<hash 值>
openssl x509 -pubkey -in /etc/kubernetes/pki/ca.crt | openssl rsa -pubin -outform der 2>/dev/null | openssl dgst -sha256 -hex | sed 's/^.* //'也可以直接创建新的 token ，并且会给出 hash 值，并给出如下的命令，只需要加上--certificate-key和--control-plane参数即可
kubeadm join 192.168.91.8:6443 --token 352obx.dw7rqphzxo6cvz9r --discovery-token-ca-cert-hash sha256:5e2387403e698e95b0eab7197837f2425f7b8610e7b400e54d81c27f3c6f1964
kubeadm token create --print-join-command --ttl=0解密由 kubeadm init 上传的证书 secret对应的 kubeadm join 参数为
--certificate-key
kubeadm init phase upload-certs --upload-certs在需要扩容的 master 节点执行 kubeadm join 命令加入集群
--node-name参数定义节点名称，如果是主机名需要保证可以解析（kubectl get nodes 命令查看到的节点名称）
kubeadm join 192.168.91.8:6443 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:5e2387403e698e95b0eab7197837f2425f7b8610e7b400e54d81c27f3c6f1964 \
--certificate-key a7a12fb565bf94c768f0097898926e4d0805eb7ecc1477b48fdaaf4d27eb26b0 \
--control-plane \
--node-name 192.168.91.10查看节点
kubectl get nodes
NAME STATUS ROLES AGE VERSION
192.168.91.10 Ready control-plane,master 96m v1.23.3
192.168.91.8 Ready control-plane,master 161m v1.23.3
192.168.91.9 Ready <none> 158m v1.23.3查看 master 组件
kubectl get pod -n kube-system | egrep -v 'flannel|dns'
NAME READY STATUS RESTARTS AGE
etcd-192.168.91.10 1/1 Running 0 97m
etcd-192.168.91.8 1/1 Running 0 162m
kube-apiserver-192.168.91.10 1/1 Running 0 97m
kube-apiserver-192.168.91.8 1/1 Running 0 162m
kube-controller-manager-192.168.91.10 1/1 Running 0 97m
kube-controller-manager-192.168.91.8 1/1 Running 0 162m
kube-proxy-6cczc 1/1 Running 0 158m
kube-proxy-bfmzz 1/1 Running 0 97m
kube-proxy-zwdlm 1/1 Running 0 162m
kube-scheduler-192.168.91.10 1/1 Running 0 97m
kube-scheduler-192.168.91.8 1/1 Running 0 162mk8s 组件证书续费
查看当前组件到期时间
kubeadm certs check-expiration根证书其实是10年的，只是组件的证书只有1年
[check-expiration] Reading configuration from the cluster...
[check-expiration] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
CERTIFICATE EXPIRES RESIDUAL TIME CERTIFICATE AUTHORITY EXTERNALLY MANAGED
admin.conf Feb 17, 2023 02:45 UTC 364d ca no
apiserver Feb 17, 2023 02:45 UTC 364d ca no
apiserver-etcd-client Feb 17, 2023 02:45 UTC 364d etcd-ca no
apiserver-kubelet-client Feb 17, 2023 02:45 UTC 364d ca no
controller-manager.conf Feb 17, 2023 02:45 UTC 364d ca no
etcd-healthcheck-client Feb 17, 2023 02:45 UTC 364d etcd-ca no
etcd-peer Feb 17, 2023 02:45 UTC 364d etcd-ca no
etcd-server Feb 17, 2023 02:45 UTC 364d etcd-ca no
front-proxy-client Feb 17, 2023 02:45 UTC 364d front-proxy-ca no
scheduler.conf Feb 17, 2023 02:45 UTC 364d ca no
CERTIFICATE AUTHORITY EXPIRES RESIDUAL TIME EXTERNALLY MANAGED
ca Feb 15, 2032 02:45 UTC 9y no
etcd-ca Feb 15, 2032 02:45 UTC 9y no
front-proxy-ca Feb 15, 2032 02:45 UTC 9y no使用 kubeadm 命令续费1年
前提是证书已经到期了这里使用
date -s 2023-2-18命令修改系统时间来模拟证书到期的情况
kubectl get nodes --kubeconfig /etc/kubernetes/admin.confUnable to connect to the server: x509: certificate has expired or is not yet valid: current time 2023-02-18T00:00:15+08:00 is after 2023-02-17T05:34:40Z因为证书到期，就会出现如下的输出，然后使用下面的命令再次续费一年，然后重启 kubelet 以及重启
etcd kube-apiserver kube-controller-manager kube-scheduler组件所有的 master 节点都操作一遍，或者其中一台 master 节点操作完成后，将
/etc/kubernetes/admin.conf证书文件分发到其他 master 节点，替换掉老的证书文件
cp -r /etc/kubernetes/pki{,.old}
kubeadm certs renew allsystemctl restart kubelet
kubeadm certs check-expiration 再次查看证书，就可以看到，证书到期时间变成 2024 年了
[check-expiration] Reading configuration from the cluster...
[check-expiration] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
CERTIFICATE EXPIRES RESIDUAL TIME CERTIFICATE AUTHORITY EXTERNALLY MANAGED
admin.conf Feb 17, 2024 16:01 UTC 364d ca no
apiserver Feb 17, 2024 16:01 UTC 364d ca no
apiserver-etcd-client Feb 17, 2024 16:01 UTC 364d etcd-ca no
apiserver-kubelet-client Feb 17, 2024 16:01 UTC 364d ca no
controller-manager.conf Feb 17, 2024 16:01 UTC 364d ca no
etcd-healthcheck-client Feb 17, 2024 16:01 UTC 364d etcd-ca no
etcd-peer Feb 17, 2024 16:01 UTC 364d etcd-ca no
etcd-server Feb 17, 2024 16:01 UTC 364d etcd-ca no
front-proxy-client Feb 17, 2024 16:01 UTC 364d front-proxy-ca no
scheduler.conf Feb 17, 2024 16:01 UTC 364d ca no
CERTIFICATE AUTHORITY EXPIRES RESIDUAL TIME EXTERNALLY MANAGED
ca Feb 15, 2032 02:45 UTC 8y no
etcd-ca Feb 15, 2032 02:45 UTC 8y no
front-proxy-ca Feb 15, 2032 02:45 UTC 8y no编译 kubeadm 达成十年契约
编译 kubeadm 需要有 go 语言环境，先来一个 go
wget https://go.dev/dl/go1.17.7.linux-amd64.tar.gz
tar xvf go1.17.7.linux-amd64.tar.gz -C /usr/local/
echo 'PATH=$PATH:/usr/local/go/bin' >> $HOME/.bashrc
source $HOME/.bashrc
go version下载 k8s 源码包，要和当前集群版本一致
wget https://github.com/kubernetes/kubernetes/archive/refs/tags/v1.23.3.tar.gz
tar xvf v1.23.3.tar.gzcd kubernetes-1.23.3/
vim staging/src/k8s.io/client-go/util/cert/cert.go将duration365d * 10改成duration365d * 100
now.Add(duration365d * 100).UTC(),vim cmd/kubeadm/app/constants/constants.go将CertificateValidity = time.Hour * 24 * 365改成CertificateValidity = time.Hour * 24 * 3650
CertificateValidity = time.Hour * 24 * 3650编译 kubeadm
make WHAT=cmd/kubeadm GOFLAGS=-v续费证书
cp -r /etc/kubernetes/pki{,.old}
_output/bin/kubeadm certs renew all
systemctl restart kubelet查看证书到期时间
_output/bin/kubeadm certs check-expiration十年了
[check-expiration] Reading configuration from the cluster...
[check-expiration] FYI: You can look at this config file with 'kubectl -n kube-system get cm kubeadm-config -o yaml'
CERTIFICATE EXPIRES RESIDUAL TIME CERTIFICATE AUTHORITY EXTERNALLY MANAGED
admin.conf Feb 15, 2032 07:08 UTC 9y ca no
apiserver Feb 15, 2032 07:08 UTC 9y ca no
apiserver-etcd-client Feb 15, 2032 07:08 UTC 9y etcd-ca no
apiserver-kubelet-client Feb 15, 2032 07:08 UTC 9y ca no
controller-manager.conf Feb 15, 2032 07:08 UTC 9y ca no
etcd-healthcheck-client Feb 15, 2032 07:08 UTC 9y etcd-ca no
etcd-peer Feb 15, 2032 07:08 UTC 9y etcd-ca no
etcd-server Feb 15, 2032 07:08 UTC 9y etcd-ca no
front-proxy-client Feb 15, 2032 07:08 UTC 9y front-proxy-ca no
scheduler.conf Feb 15, 2032 07:08 UTC 9y ca no
CERTIFICATE AUTHORITY EXPIRES RESIDUAL TIME EXTERNALLY MANAGED
ca Feb 15, 2032 02:45 UTC 9y no
etcd-ca Feb 15, 2032 02:45 UTC 9y no
front-proxy-ca Feb 15, 2032 02:45 UTC 9y no替换 kubeadm 二进制文件，如果有多个 master 节点，也要分发过去，进行替换
mv /usr/bin/kubeadm{,-oneyear}
cp _output/bin/kubeadm /usr/bin/如果是访问$HOME/.kube/conf文件，需要替换 admin.conf如果是 export 设置环境变量的，可以不用替换
mv $HOME/.kube/conf{,-oneyear}
cp /etc/kubernetes/admin.conf $HOME/.kube/conf
