day02-作业

 

1.节点规划

img

2.部署过程

2.1 系统初始化

# cat /etc/security/limits.conf
root               soft   core           unlimited
root               hard   core           unlimited
root               soft   nproc           1000000
root               hard   nproc           1000000
root               soft   nofile          1000000
root               hard   nofile          1000000
root               soft   memlock         32000
root               hard   memlock         32000
root               soft   msgqueue        8192000
root               hard   msgqueue        8192000
# cat /etc/sysctl.conf
net.ipv4.ip_forward=1
vm.max_map_count=262144
kernel.pid_max=4194303
fs.file-max=1000000
net.ipv4.tcp_max_tw_buckets=6000
net.netfilter.nf_conntrack_max=2097152
net.bridge.bridge-nf-call-ip6tables=1
net.bridge.bridge-nf-call-iptables=1
vm.swappiness=0
# swapoff -a
# cat /etc/fstab
注释掉swap
#/swap.img none swap sw 0 0
启用内核模块
# cat /etc/modules-load.d/modules.conf
# /etc/modules: kernel modules to load at boot time.
#
# This file contains the names of kernel modules that should be loaded
# at boot time, one per line. Lines beginning with "#" are ignored.
ip_vs
ip_vs_lc
ip_vs_lblc
ip_vs_lblcr
ip_vs_rr
ip_vs_wrr
ip_vs_sh
ip_vs_dh
ip_vs_fo
ip_vs_nq
ip_vs_sed
ip_vs_ftp
ip_vs_sh
ip_tables
ip_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
xt_set
br_netfilter
nf_conntrack
overlay
# reboot

2.2 ha01 和 ha02 的部署  

# apt install keepalived haproxy -y
root@ha01:~# cat /etc/keepalived/keepalived.conf
! Configuration File for keepalived

global_defs {
  notification_email {
    acassen
  }
  notification_email_from Alexandre.Cassen@firewall.loc
  smtp_server 192.168.200.1
  smtp_connect_timeout 30
  router_id LVS_DEVEL
}

vrrp_instance VI_1 {
  state MASTER
  interface eth0
  virtual_router_id 51
  priority 100
  advert_int 1
  unicast_src_ip 10.0.6.7
  unicast_peer {
        10.0.6.8
  }
  authentication {
      auth_type PASS
      auth_pass 1111
  }
  virtual_ipaddress {
       10.0.6.188 dev eth0 label eth0:1
       10.0.6.189 dev eth0 label eth0:2
       10.0.6.190 dev eth0 label eth0:3
       10.0.6.191 dev eth0 label eth0:4
  }
}
root@ha02:~# cat /etc/keepalived/keepalived.conf
! Configuration File for keepalived

global_defs {
  notification_email {
    acassen
  }
  notification_email_from Alexandre.Cassen@firewall.loc
  smtp_server 192.168.200.1
  smtp_connect_timeout 30
  router_id LVS_DEVEL
}

vrrp_instance VI_1 {
  state BACKUP
  interface eth0
  virtual_router_id 51
  priority 80
  advert_int 1
  unicast_src_ip 10.0.6.8
  unicast_peer {
        10.0.6.7
  }
  authentication {
      auth_type PASS
      auth_pass 1111
  }
  virtual_ipaddress {
       10.0.6.188 dev eth0 label eth0:1
       10.0.6.189 dev eth0 label eth0:2
       10.0.6.190 dev eth0 label eth0:3
       10.0.6.191 dev eth0 label eth0:4
  }
}
# systemctl enable keepalived && systemctl start keepalived
# cat /etc/haproxy/haproxy.cfg
global
log /dev/log local0
log /dev/log local1 notice
chroot /var/lib/haproxy
stats socket /run/haproxy/admin.sock mode 660 level admin expose-fd listeners
stats timeout 30s
user haproxy
group haproxy
daemon

# Default SSL material locations
ca-base /etc/ssl/certs
crt-base /etc/ssl/private

# See: https://ssl-config.mozilla.org/#server=haproxy&server-version=2.0.3&config=intermediate
      ssl-default-bind-ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:DHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES256-GCM-SHA384
      ssl-default-bind-ciphersuites TLS_AES_128_GCM_SHA256:TLS_AES_256_GCM_SHA384:TLS_CHACHA20_POLY1305_SHA256
      ssl-default-bind-options ssl-min-ver TLSv1.2 no-tls-tickets

defaults
log global
mode http
option httplog
option dontlognull
      timeout connect 5000
      timeout client  50000
      timeout server  50000
errorfile 400 /etc/haproxy/errors/400.http
errorfile 403 /etc/haproxy/errors/403.http
errorfile 408 /etc/haproxy/errors/408.http
errorfile 500 /etc/haproxy/errors/500.http
errorfile 502 /etc/haproxy/errors/502.http
errorfile 503 /etc/haproxy/errors/503.http
errorfile 504 /etc/haproxy/errors/504.http
listen k8s_api_server_6443
bind 10.0.6.188:6443
mode tcp
server 10.0.6.1 10.0.6.1:6443 check inter 2000 fall 3 rise 5
server 10.0.6.2 10.0.6.2:6443 check inter 2000 fall 3 rise 5
server 10.0.6.3 10.0.6.3:6443 check inter 2000 fall 3 rise 5
# sysctl -w net.ipv4.ip_nonlocal_bind=1
# echo 'net.ipv4.ip_nonlocal_bind = 1' >> /etc/sysctl.conf && sysctl -p
# systemctl enable haproxy && systemctl restart haproxy.service
测试vip的迁移和6443端口的监听

2.3 harbor的安装

上传harbor的离线安装包

上传使用的域名的证书

# tar -xf harbor-offline-installer-v2.7.2.tgz
# cp harbor.yml.tmpl harbor.yml
# mkdir /data   # 最好是挂载nas等共享存储,防止数据丢失
# 安装docker 和 docker-compose
# ./install.sh --with-trivy --with-chartmuseum
等待安装完成
win 设置域名解析

docker ps 查看容器是否正常

配置service文件
# docker-compose down
root@harbor:~/harbor# cat /lib/systemd/system/harbor.service
[Unit]
Description=Harbor
After=docker.service systemd-networkd.service systemd-resolved.service
Requires=docker.service
Documentation=http://github.com/vmware/harbor
  
[Service]
Type=simple
Restart=on-failure
RestartSec=5
ExecStart=/usr/bin/docker-compose -f /root/harbor/docker-compose.yml up
ExecStop=/usr/bin/docker-compose -f /root/harbor/docker-compose.yml down
  
[Install]
WantedBy=multi-user.target
# systemctl daemon-reload && systemctl enable harbor && systemctl start harbor
测试镜像的上传下载
/etc/hosts 添加域名解析
# docker login harbor.20180622.xyz
# docker push harbor.20180622.xyz/baseimages/nginx:1.18

2.4 kubeasz部署k8s

2.4.1 配置ssh的免密钥登录
# ssh-keygen -t rsa-sha2-512 -b 4096
# cat ssh_no_passwd.sh
#!/bin/bash
RED='echo -e \033[01;31m'
GREEN='echo -e \033[01;32m'
END='\033[0m'
#IP地址列表
#master,node,etcd
IP="
10.0.6.1
10.0.6.2
10.0.6.3
10.0.6.4
10.0.6.5
10.0.6.6
10.0.6.11
10.0.6.12
10.0.6.13
"
for node in $IP;do
sshpass -v -p 1 ssh-copy-id -o StrictHostKeyChecking=no root@$node
 if [ $? -eq 0 ];then
    $GREEN "$node密钥copy完成" $END
  else
    $RED "$node密钥copy失败" $END
  fi
done
2.4.2 部署过程
root@deploy:~# apt install ansible git -y
root@deploy:~# export release=3.5.2
root@deploy:~# wget https://github.com/easzlab/kubeasz/releases/download/${release}/ezdown
root@deploy:~# chmod +x ./ezdown
root@deploy:~# ./ezdown -D

创建 python的软链接

# cat ssh_ln_python3.sh
#!/bin/bash
RED='echo -e \033[01;31m'
GREEN='echo -e \033[01;32m'
END='\033[0m'
#IP地址列表
#master,node,etcd
IP="
10.0.6.1
10.0.6.2
10.0.6.3
10.0.6.4
10.0.6.5
10.0.6.6
10.0.6.11
10.0.6.12
10.0.6.13
"
for node in $IP;do
ssh $node "ln -sv /usr/bin/python3 /usr/bin/python"
 if [ $? -eq 0 ];then
    $GREEN "$node 软链接成功" $END
  else
    $RED "$node 软链接成功" $END
  fi
done

修改配置文件

root@deploy:/etc/kubeasz# cat clusters/k8s-01/hosts
# 'etcd' cluster should have odd member(s) (1,3,5,...)
[etcd]
10.0.6.4
10.0.6.5
10.0.6.6

# master node(s), set unique 'k8s_nodename' for each node
# CAUTION: 'k8s_nodename' must consist of lower case alphanumeric characters, '-' or '.',
# and must start and end with an alphanumeric character
[kube_master]
10.0.6.1 k8s_nodename='10.0.6.1'
10.0.6.2 k8s_nodename='10.0.6.2'
#10.0.6.3 k8s_nodename='10.0.6.3'

# work node(s), set unique 'k8s_nodename' for each node
# CAUTION: 'k8s_nodename' must consist of lower case alphanumeric characters, '-' or '.',
# and must start and end with an alphanumeric character
[kube_node]
10.0.6.11 k8s_nodename='10.0.6.11'
10.0.6.12 k8s_nodename='10.0.6.12'
#10.0.6.13 k8s_nodename='10.0.6.13'

# [optional] harbor server, a private docker registry
# 'NEW_INSTALL': 'true' to install a harbor server; 'false' to integrate with existed one
[harbor]
#10.0.6.8 NEW_INSTALL=false

# [optional] loadbalance for accessing k8s from outside
[ex_lb]
#10.0.6.6 LB_ROLE=backup EX_APISERVER_VIP=10.0.6.250 EX_APISERVER_PORT=8443
#10.0.6.7 LB_ROLE=master EX_APISERVER_VIP=10.0.6.250 EX_APISERVER_PORT=8443

# [optional] ntp server for the cluster
[chrony]
#10.0.6.1

[all:vars]
# --------- Main Variables ---------------
# Secure port for apiservers
SECURE_PORT="6443"

# Cluster container-runtime supported: docker, containerd
# if k8s version >= 1.24, docker is not supported
CONTAINER_RUNTIME="containerd"

# Network plugins supported: calico, flannel, kube-router, cilium, kube-ovn
CLUSTER_NETWORK="calico"

# Service proxy mode of kube-proxy: 'iptables' or 'ipvs'
PROXY_MODE="ipvs"

# K8S Service CIDR, not overlap with node(host) networking
SERVICE_CIDR="10.100.0.0/16"

# Cluster CIDR (Pod CIDR), not overlap with node(host) networking
CLUSTER_CIDR="10.200.0.0/16"

# NodePort Range
NODE_PORT_RANGE="30000-62767"

# Cluster DNS Domain
CLUSTER_DNS_DOMAIN="cluster.local"

# -------- Additional Variables (don't change the default value right now) ---
# Binaries Directory
bin_dir="/usr/local/bin"

# Deploy Directory (kubeasz workspace)
base_dir="/etc/kubeasz"

# Directory for a specific cluster
cluster_dir="{{ base_dir }}/clusters/k8s-01"

# CA and other components cert/key Directory
ca_dir="/etc/kubernetes/ssl"

# Default 'k8s_nodename' is empty
k8s_nodename=''
root@deploy:/etc/kubeasz# cat clusters/k8s-01/config.yml 
############################
# prepare
############################
# 可选离线安装系统软件包 (offline|online)
INSTALL_SOURCE: "online"

# 可选进行系统安全加固 github.com/dev-sec/ansible-collection-hardening
OS_HARDEN: false


############################
# role:deploy
############################
# default: ca will expire in 100 years
# default: certs issued by the ca will expire in 50 years
CA_EXPIRY: "876000h"
CERT_EXPIRY: "438000h"

# force to recreate CA and other certs, not suggested to set 'true'
CHANGE_CA: false

# kubeconfig 配置参数
CLUSTER_NAME: "cluster1"
CONTEXT_NAME: "context-{{ CLUSTER_NAME }}"

# k8s version
K8S_VER: "1.26.1"

# set unique 'k8s_nodename' for each node, if not set(default:'') ip add will be used
# CAUTION: 'k8s_nodename' must consist of lower case alphanumeric characters, '-' or '.',
# and must start and end with an alphanumeric character (e.g. 'example.com'),
# regex used for validation is '[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*'
K8S_NODENAME: "{%- if k8s_nodename != '' -%} \
                  {{ k8s_nodename|replace('_', '-')|lower }} \
              {%- else -%} \
                  {{ inventory_hostname }} \
              {%- endif -%}"

############################
# role:etcd
############################
# 设置不同的wal目录,可以避免磁盘io竞争,提高性能
ETCD_DATA_DIR: "/var/lib/etcd"
ETCD_WAL_DIR: ""


############################
# role:runtime [containerd,docker]
############################
# ------------------------------------------- containerd
# [.]启用容器仓库镜像
ENABLE_MIRROR_REGISTRY: true

# [containerd]基础容器镜像
SANDBOX_IMAGE: "harbor.20180622.xyz/baseimages/pause:3.9"

# [containerd]容器持久化存储目录
CONTAINERD_STORAGE_DIR: "/var/lib/containerd"

# ------------------------------------------- docker
# [docker]容器存储目录
DOCKER_STORAGE_DIR: "/var/lib/docker"

# [docker]开启Restful API
ENABLE_REMOTE_API: false

# [docker]信任的HTTP仓库
INSECURE_REG: '["http://easzlab.io.local:5000"]'


############################
# role:kube-master
############################
# k8s 集群 master 节点证书配置,可以添加多个ip和域名(比如增加公网ip和域名)
MASTER_CERT_HOSTS:
 - "10.0.6.188"
 - "kubeapi.20180622.xyz"
 #- "www.test.com"

# node 节点上 pod 网段掩码长度(决定每个节点最多能分配的pod ip地址)
# 如果flannel 使用 --kube-subnet-mgr 参数,那么它将读取该设置为每个节点分配pod网段
# https://github.com/coreos/flannel/issues/847
NODE_CIDR_LEN: 24


############################
# role:kube-node
############################
# Kubelet 根目录
KUBELET_ROOT_DIR: "/var/lib/kubelet"

# node节点最大pod 数
MAX_PODS: 200

# 配置为kube组件(kubelet,kube-proxy,dockerd等)预留的资源量
# 数值设置详见templates/kubelet-config.yaml.j2
KUBE_RESERVED_ENABLED: "no"

# k8s 官方不建议草率开启 system-reserved, 除非你基于长期监控,了解系统的资源占用状况;
# 并且随着系统运行时间,需要适当增加资源预留,数值设置详见templates/kubelet-config.yaml.j2
# 系统预留设置基于 4c/8g 虚机,最小化安装系统服务,如果使用高性能物理机可以适当增加预留
# 另外,集群安装时候apiserver等资源占用会短时较大,建议至少预留1g内存
SYS_RESERVED_ENABLED: "no"


############################
# role:network [flannel,calico,cilium,kube-ovn,kube-router]
############################
# ------------------------------------------- flannel
# [flannel]设置flannel 后端"host-gw","vxlan"等
FLANNEL_BACKEND: "vxlan"
DIRECT_ROUTING: false

# [flannel]
flannel_ver: "v0.19.2"

# ------------------------------------------- calico
# [calico] IPIP隧道模式可选项有: [Always, CrossSubnet, Never],跨子网可以配置为Always与CrossSubnet(公有云建议使用always比较省事,其他的话需要修改各自公有云的网络配置,具体可以参考各个公有云说明)
# 其次CrossSubnet为隧道+BGP路由混合模式可以提升网络性能,同子网配置为Never即可.
CALICO_IPV4POOL_IPIP: "Always"

# [calico]设置 calico-node使用的host IP,bgp邻居通过该地址建立,可手工指定也可以自动发现
IP_AUTODETECTION_METHOD: "can-reach={{ groups['kube_master'][0] }}"

# [calico]设置calico 网络 backend: brid, vxlan, none
CALICO_NETWORKING_BACKEND: "brid"

# [calico]设置calico 是否使用route reflectors
# 如果集群规模超过50个节点,建议启用该特性
CALICO_RR_ENABLED: false

# CALICO_RR_NODES 配置route reflectors的节点,如果未设置默认使用集群master节点
# CALICO_RR_NODES: ["192.168.1.1", "192.168.1.2"]
CALICO_RR_NODES: []

# [calico]更新支持calico 版本: ["3.19", "3.23"]
calico_ver: "v3.24.5"

# [calico]calico 主版本
calico_ver_main: "{{ calico_ver.split('.')[0] }}.{{ calico_ver.split('.')[1] }}"

# ------------------------------------------- cilium
# [cilium]镜像版本
cilium_ver: "1.12.4"
cilium_connectivity_check: true
cilium_hubble_enabled: false
cilium_hubble_ui_enabled: false

# ------------------------------------------- kube-ovn
# [kube-ovn]选择 OVN DB and OVN Control Plane 节点,默认为第一个master节点
OVN_DB_NODE: "{{ groups['kube_master'][0] }}"

# [kube-ovn]离线镜像tar包
kube_ovn_ver: "v1.5.3"

# ------------------------------------------- kube-router
# [kube-router]公有云上存在限制,一般需要始终开启 ipinip;自有环境可以设置为 "subnet"
OVERLAY_TYPE: "full"

# [kube-router]NetworkPolicy 支持开关
FIREWALL_ENABLE: true

# [kube-router]kube-router 镜像版本
kube_router_ver: "v0.3.1"
busybox_ver: "1.28.4"


############################
# role:cluster-addon
############################
# coredns 自动安装
dns_install: "no"
corednsVer: "1.9.3"
ENABLE_LOCAL_DNS_CACHE: false
dnsNodeCacheVer: "1.22.13"
# 设置 local dns cache 地址
LOCAL_DNS_CACHE: "169.254.20.10"

# metric server 自动安装
metricsserver_install: "no"
metricsVer: "v0.5.2"

# dashboard 自动安装
dashboard_install: "no"
dashboardVer: "v2.7.0"
dashboardMetricsScraperVer: "v1.0.8"

# prometheus 自动安装
prom_install: "no"
prom_namespace: "monitor"
prom_chart_ver: "39.11.0"

# nfs-provisioner 自动安装
nfs_provisioner_install: "no"
nfs_provisioner_namespace: "kube-system"
nfs_provisioner_ver: "v4.0.2"
nfs_storage_class: "managed-nfs-storage"
nfs_server: "192.168.1.10"
nfs_path: "/data/nfs"

# network-check 自动安装
network_check_enabled: false
network_check_schedule: "*/5 * * * *"

############################
# role:harbor
############################
# harbor version,完整版本号
HARBOR_VER: "v2.6.3"
HARBOR_DOMAIN: "harbor.easzlab.io.local"
HARBOR_PATH: /var/data
HARBOR_TLS_PORT: 8443
HARBOR_REGISTRY: "{{ HARBOR_DOMAIN }}:{{ HARBOR_TLS_PORT }}"

# if set 'false', you need to put certs named harbor.pem and harbor-key.pem in directory 'down'
HARBOR_SELF_SIGNED_CERT: true

# install extra component
HARBOR_WITH_NOTARY: false
HARBOR_WITH_TRIVY: false
HARBOR_WITH_CHARTMUSEUM: true
2.4.2.1 准备工作
root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 01
2.4.2.2 etcd的初始化
root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 02
验证etcd服务状态
root@etcd01:~# export NODE_IPS="10.0.6.4 10.0.6.5 10.0.6.6"

root@etcd01:~# for ip in ${NODE_IPS}; do
 ETCDCTL_API=3 /usr/local/bin/etcdctl \
 --endpoints=https://${ip}:2379 \
 --cacert=/etc/kubernetes/ssl/ca.pem \
 --cert=/etc/kubernetes/ssl/etcd.pem \
 --key=/etc/kubernetes/ssl/etcd-key.pem \
endpoint health; done
 
https://10.0.6.4:2379 is healthy: successfully committed proposal: took = 9.879125ms
https://10.0.6.5:2379 is healthy: successfully committed proposal: took = 21.645162ms
https://10.0.6.6:2379 is healthy: successfully committed proposal: took = 7.334946ms
2.4.2.3 运行时的部署
上传nerdctl的压缩文件到/root下
root@deploy:~# tar -xf nerdctl-1.3.0-linux-amd64.tar.gz -C /etc/kubeasz/bin/containerd-bin/
修改yml配置文件时 注意提前备份

root@deploy:/etc/kubeasz# cat roles/containerd/templates/nerdctl.toml.j2
namespace = "k8s.io"
debug = false
debug_full = false
insecure_registry = true

root@deploy:/etc/kubeasz# cat roles/containerd/tasks/main.yml
- name: 获取是否已经安装containerd
shell: 'systemctl is-active containerd || echo "NoFound"'
register: containerd_svc

- name: 分发 harbor 的解析文件
shell: "echo '10.0.6.9 harbor.20180622.xyz' >> /etc/hosts"

- block:
   - name: 准备containerd相关目录
    file: name={{ item }} state=directory
    with_items:
     - "{{ bin_dir }}"
     - "/etc/containerd"
     - "/etc/nerdctl/" # nerdctl的配置文件

   - name: 加载内核模块 overlay
    modprobe: name=overlay state=present

   - name: 下载 containerd 二进制文件
    copy: src={{ base_dir }}/bin/containerd-bin/{{ item }} dest={{ bin_dir }}/{{ item }} mode=0755
    with_items:
     - containerd
     - containerd-shim
     - containerd-shim-runc-v1
     - containerd-shim-runc-v2
     - crictl
     - ctr
     - runc
     - nerdctl  #分发nerdctl等工具
     - containerd-rootless-setuptool.sh
     - containerd-rootless.sh
    tags: upgrade

   - name: 添加 crictl 自动补全
    lineinfile:
      dest: ~/.bashrc
      state: present
      regexp: 'crictl completion'
      line: 'source <(crictl completion bash) # generated by kubeasz'
 
   - name: 创建 containerd 配置文件
    template: src=config.toml.j2 dest=/etc/containerd/config.toml
    tags: upgrade

   - name: 创建nerdctl的配置文件
    template: src=nerdctl.toml.j2 dest=/etc/nerdctl/nerdctl.toml
    tags: upgrade

   - name: 创建systemd unit文件
    template: src=containerd.service.j2 dest=/etc/systemd/system/containerd.service
    tags: upgrade

   - name: 创建 crictl 配置
    template: src=crictl.yaml.j2 dest=/etc/crictl.yaml

   - name: 开机启用 containerd 服务
    shell: systemctl enable containerd
    ignore_errors: true

   - name: 开启 containerd 服务
    shell: systemctl daemon-reload && systemctl restart containerd
    tags: upgrade

   - name: 轮询等待containerd服务运行
    shell: "systemctl is-active containerd.service"
    register: containerd_status
     until: '"active" in containerd_status.stdout'
    retries: 8
    delay: 2
    tags: upgrade
when: "'NoFound' in containerd_svc.stdout"
 

containerd的配置文件

root@deploy:/etc/kubeasz# cat roles/containerd/templates/config.toml.j2
disabled_plugins = []
imports = []
oom_score = 0
plugin_dir = ""
required_plugins = []
root = "{{ CONTAINERD_STORAGE_DIR }}"
state = "/run/containerd"
temp = ""
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_ca = ""
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"]
  device_ownership_from_security_context = false
  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
  enable_unprivileged_icmp = false
  enable_unprivileged_ports = 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 = "{{ SANDBOX_IMAGE }}"
  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 = "{{ bin_dir }}"
    conf_dir = "/etc/cni/net.d"
    conf_template = "/etc/cni/net.d/10-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
    ignore_rdt_not_enabled_errors = 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]

     [plugins."io.containerd.grpc.v1.cri".registry.auths]

     [plugins."io.containerd.grpc.v1.cri".registry.configs]
       [plugins."io.containerd.grpc.v1.cri".registry.configs."easzlab.io.local:5000".tls]
        insecure_skip_verify = true

       [plugins."io.containerd.grpc.v1.cri".registry.configs."harbor.20180622.xyz".tls]
        insecure_skip_verify = true
       [plugins."io.containerd.grpc.v1.cri".registry.configs."harbor.20180622.xyz".auth]
        username = "admin"
        password = "123456"

       [plugins."io.containerd.grpc.v1.cri".registry.configs."{{ HARBOR_REGISTRY }}".tls]
        insecure_skip_verify = true

     [plugins."io.containerd.grpc.v1.cri".registry.headers]

     [plugins."io.containerd.grpc.v1.cri".registry.mirrors]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."easzlab.io.local:5000"]
        endpoint = ["http://easzlab.io.local:5000"]

       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."harbor.20180622.xyz"]
        endpoint = ["https://harbor.20180622.xyz"]

       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."{{ HARBOR_REGISTRY }}"]
        endpoint = ["https://{{ HARBOR_REGISTRY }}"]
{% if ENABLE_MIRROR_REGISTRY %}
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
        endpoint = ["https://docker.nju.edu.cn/", "https://kuamavit.mirror.aliyuncs.com"]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."gcr.io"]
        endpoint = ["https://gcr.nju.edu.cn"]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."k8s.gcr.io"]
        endpoint = ["https://gcr.nju.edu.cn/google-containers/"]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."quay.io"]
        endpoint = ["https://quay.nju.edu.cn"]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."ghcr.io"]
        endpoint = ["https://ghcr.nju.edu.cn"]
       [plugins."io.containerd.grpc.v1.cri".registry.mirrors."nvcr.io"]
        endpoint = ["https://ngc.nju.edu.cn"]
{% endif %}

   [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
root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 03
2.4.2.4 master的部署
root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 04
2.4.2.5 node的部署
root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 05
2.4.2.6 calico的部署
注意calico的yml文件中的下面的变量
- name: CALICO_IPV4POOL_CIDR
value: "{{ CLUSTER_CIDR }}"

root@deploy:/etc/kubeasz/bin# docker tag easzlab.io.local:5000/calico/cni:v3.24.5 harbor.20180622.xyz/baseimages/calico-cni:v3.24.5
docker tag easzlab.io.local:5000/calico/node:v3.24.5 harbor.20180622.xyz/baseimages/calico-node:v3.24.5
docker tag easzlab.io.local:5000/calico/kube-controllers:v3.24.5 harbor.20180622.xyz/baseimages/calico-kube-controllers:v3.24.5

docker push harbor.20180622.xyz/baseimages/calico-cni:v3.24.5
docker push harbor.20180622.xyz/baseimages/calico-node:v3.24.5
docker push harbor.20180622.xyz/baseimages/calico-kube-controllers:v3.24.5

root@deploy:/etc/kubeasz# grep -i image roles/calico/templates/calico-v3.24.yaml.j2
        image: harbor.20180622.xyz/baseimages/calico-cni:v3.24.5
        imagePullPolicy: IfNotPresent
        image: harbor.20180622.xyz/baseimages/calico-node:v3.24.5
        imagePullPolicy: IfNotPresent
        image: harbor.20180622.xyz/baseimages/calico-node:v3.24.5
        imagePullPolicy: IfNotPresent
        image: harbor.20180622.xyz/baseimages/calico-kube-controllers:v3.24.5
        imagePullPolicy: IfNotPresent

root@deploy:/etc/kubeasz# ./ezctl setup k8s-01 06

root@master01:~# calicoctl node status
Calico process is running.

IPv4 BGP status
+--------------+-------------------+-------+----------+-------------+
| PEER ADDRESS |     PEER TYPE     | STATE | SINCE   |   INFO     |
+--------------+-------------------+-------+----------+-------------+
| 10.0.6.2     | node-to-node mesh | up   | 04:15:07 | Established |
| 10.0.6.11   | node-to-node mesh | up   | 04:15:07 | Established |
| 10.0.6.12   | node-to-node mesh | up   | 04:15:10 | Established |
+--------------+-------------------+-------+----------+-------------+

IPv6 BGP status
No IPv6 peers found.

复制config文件到master节点,用于kubectl命令的执行

root@deploy:/etc/kubeasz# scp /root/.kube/config 10.0.6.1:/root/.kube

修改 config 中的server 的地址为 负载均衡的地址,用于高可用

 

测试通信

root@master01:~# kubectl run net-test --image=centos:7.9.2009 sleep 10000
root@master01:~# kubectl exec -it net-test -- bash
2.4.2.7 node扩节点
root@deploy:/etc/kubeasz# ./ezctl add-node k8s-01 10.0.6.13
2.4.2.8 master扩节点
在添加master节点时,首次网络更新源失败,导致在再次添加报 master节点已存在
需要在hosts文件中删除 master中的ip地址
root@deploy:/etc/kubeasz# ./ezctl add-master k8s-01 10.0.6.3
root@deploy:/etc/kubeasz# kubectl get node -A
NAME       STATUS                     ROLES   AGE     VERSION
10.0.6.1   Ready,SchedulingDisabled   master   4h13m   v1.26.1
10.0.6.11   Ready                      node     4h7m   v1.26.1
10.0.6.12   Ready                      node     4h7m   v1.26.1
10.0.6.13   Ready                      node     27m     v1.26.1
10.0.6.2   Ready,SchedulingDisabled   master   4h13m   v1.26.1
10.0.6.3   Ready,SchedulingDisabled   master   115s   v1.26.1

root@master03:~# calicoctl node status
Calico process is running.

IPv4 BGP status
+--------------+-------------------+-------+----------+-------------+
| PEER ADDRESS |     PEER TYPE     | STATE | SINCE   |   INFO     |
+--------------+-------------------+-------+----------+-------------+
| 10.0.6.1     | node-to-node mesh | up   | 07:47:55 | Established |
| 10.0.6.2     | node-to-node mesh | up   | 07:48:16 | Established |
| 10.0.6.11   | node-to-node mesh | up   | 07:47:43 | Established |
| 10.0.6.12   | node-to-node mesh | up   | 07:47:34 | Established |
| 10.0.6.13   | node-to-node mesh | up   | 07:48:04 | Established |
+--------------+-------------------+-------+----------+-------------+

IPv6 BGP status
No IPv6 peers found.

2.5 k8s版本升级

上传升级包

kubernetes-client-linux-amd64.tar.gz kubernetes-node-linux-amd64.tar.gz kubernetes-server-linux-amd64.tar.gz kubernetes.tar.gz

root@deploy:/etc/kubeasz# tar -xf /root/kubernetes-client-linux-amd64.tar.gz -C /usr/local/bin/
root@deploy:/etc/kubeasz# tar -xf /root/kubernetes-node-linux-amd64.tar.gz -C /usr/local/bin/
root@deploy:/etc/kubeasz# tar -xf /root/kubernetes-server-linux-amd64.tar.gz -C /usr/local/bin/
root@deploy:/etc/kubeasz# tar -xf /root/kubernetes.tar.gz -C /usr/local/bin/
root@deploy:/usr/local/bin/kubernetes# cd /usr/local/bin/kubernetes/server/bin/
root@deploy:/usr/local/bin/kubernetes/server/bin# \cp kube-apiserver kube-controller-manager kube-scheduler kubelet kube-proxy kubectl /etc/kubeasz/bin/
验证版本
root@deploy:/usr/local/bin/kubernetes/server/bin# /etc/kubeasz/bin/kube-apiserver --version
Kubernetes v1.26.4

执行批量升级操作
root@deploy:/etc/kubeasz# ./ezctl upgrade k8s-01

root@deploy:/etc/kubeasz# kubectl get node -A
NAME       STATUS                     ROLES   AGE     VERSION
10.0.6.1   Ready,SchedulingDisabled   master   4h30m   v1.26.4
10.0.6.11   Ready                      node     4h24m   v1.26.4
10.0.6.12   Ready                      node     4h24m   v1.26.4
10.0.6.13   Ready                      node     44m     v1.26.4
10.0.6.2   Ready,SchedulingDisabled   master   4h30m   v1.26.4
10.0.6.3   Ready,SchedulingDisabled   master   19m     v1.26.4
上面命令显示的是 kubelet 的版本

设置不可调度

kubectl cordon 节点名

取消不可调度

kubectl uncordon 节点名

驱逐节点上的pod

kubectl drain

2.6 coredns的部署

root@master01:~/20230416-cases/1.coredns# cat coredns-v1.9.4.yaml
# __MACHINE_GENERATED_WARNING__

apiVersion: v1
kind: ServiceAccount
metadata:
name: coredns
namespace: kube-system
labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
  kubernetes.io/bootstrapping: rbac-defaults
  addonmanager.kubernetes.io/mode: Reconcile
name: system:coredns
rules:
- apiGroups:
- ""
resources:
- endpoints
- services
- pods
- namespaces
verbs:
- list
- watch
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- apiGroups:
- discovery.k8s.io
resources:
- endpointslices
verbs:
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
annotations:
  rbac.authorization.kubernetes.io/autoupdate: "true"
labels:
  kubernetes.io/bootstrapping: rbac-defaults
  addonmanager.kubernetes.io/mode: EnsureExists
name: system:coredns
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:coredns
subjects:
- kind: ServiceAccount
name: coredns
namespace: kube-system
---
apiVersion: v1
kind: ConfigMap
metadata:
name: coredns
namespace: kube-system
labels:
    addonmanager.kubernetes.io/mode: EnsureExists
data:
Corefile: |
  .:53 {
      errors
      health {
          lameduck 5s
      }
      ready
      kubernetes cluster.local in-addr.arpa ip6.arpa {
          pods insecure
          fallthrough in-addr.arpa ip6.arpa
          ttl 30
      }
      prometheus :9153
      #forward . /etc/resolv.conf {
      forward . 223.6.6.6 {
          max_concurrent 1000
      }
      cache 600
      loop
      reload
      loadbalance
  }
      myserver.online {
        forward . 172.16.16.16:53
      }

---
apiVersion: apps/v1
kind: Deployment
metadata:
name: coredns
namespace: kube-system
labels:
  k8s-app: kube-dns
  kubernetes.io/cluster-service: "true"
  addonmanager.kubernetes.io/mode: Reconcile
  kubernetes.io/name: "CoreDNS"
spec:
 # replicas: not specified here:
 # 1. In order to make Addon Manager do not reconcile this replicas parameter.
 # 2. Default is 1.
 # 3. Will be tuned in real time if DNS horizontal auto-scaling is turned on.
replicas: 2
strategy:
  type: RollingUpdate
  rollingUpdate:
    maxUnavailable: 1
selector:
  matchLabels:
    k8s-app: kube-dns
template:
  metadata:
    labels:
      k8s-app: kube-dns
  spec:
    securityContext:
      seccompProfile:
        type: RuntimeDefault
    priorityClassName: system-cluster-critical
    serviceAccountName: coredns
    affinity:
      podAntiAffinity:
        preferredDuringSchedulingIgnoredDuringExecution:
        - weight: 100
          podAffinityTerm:
            labelSelector:
              matchExpressions:
                - key: k8s-app
                  operator: In
                  values: ["kube-dns"]
            topologyKey: kubernetes.io/hostname
    tolerations:
      - key: "CriticalAddonsOnly"
        operator: "Exists"
    nodeSelector:
      kubernetes.io/os: linux
    containers:
    - name: coredns
      image: harbor.20180622.xyz/baseimages/coredns:1.9.4
      imagePullPolicy: IfNotPresent
      resources:
        limits:
          memory: 256Mi
          cpu: 200m
        requests:
          cpu: 100m
          memory: 70Mi
      args: [ "-conf", "/etc/coredns/Corefile" ]
      volumeMounts:
      - name: config-volume
        mountPath: /etc/coredns
        readOnly: true
      ports:
      - containerPort: 53
        name: dns
        protocol: UDP
      - containerPort: 53
        name: dns-tcp
        protocol: TCP
      - containerPort: 9153
        name: metrics
        protocol: TCP
      livenessProbe:
        httpGet:
          path: /health
          port: 8080
          scheme: HTTP
        initialDelaySeconds: 60
        timeoutSeconds: 5
        successThreshold: 1
        failureThreshold: 5
      readinessProbe:
        httpGet:
          path: /ready
          port: 8181
          scheme: HTTP
      securityContext:
        allowPrivilegeEscalation: false
        capabilities:
          add:
          - NET_BIND_SERVICE
          drop:
          - all
        readOnlyRootFilesystem: true
    dnsPolicy: Default
    volumes:
      - name: config-volume
        configMap:
          name: coredns
          items:
          - key: Corefile
            path: Corefile
---
apiVersion: v1
kind: Service
metadata:
name: kube-dns
namespace: kube-system
annotations:
  prometheus.io/port: "9153"
  prometheus.io/scrape: "true"
labels:
  k8s-app: kube-dns
  kubernetes.io/cluster-service: "true"
  addonmanager.kubernetes.io/mode: Reconcile
  kubernetes.io/name: "CoreDNS"
spec:
selector:
  k8s-app: kube-dns
clusterIP: 10.100.0.2
ports:
- name: dns
  port: 53
  protocol: UDP
- name: dns-tcp
  port: 53
  protocol: TCP
- name: metrics
  port: 9153
  protocol: TCP

测试

root@master01:~/20230416-cases/1.coredns# kubectl exec -it net-test -- bash 
[root@net-test /]# ping 223.5.5.5
PING 223.5.5.5 (223.5.5.5) 56(84) bytes of data.
64 bytes from 223.5.5.5: icmp_seq=1 ttl=127 time=83.3 ms
^C
--- 223.5.5.5 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 83.352/83.352/83.352/0.000 ms
[root@net-test /]# ping www.baidu.com
PING www.a.shifen.com (180.101.50.188) 56(84) bytes of data.
64 bytes from 180.101.50.188 (180.101.50.188): icmp_seq=1 ttl=127 time=59.2 ms
64 bytes from 180.101.50.188 (180.101.50.188): icmp_seq=2 ttl=127 time=56.9 ms

部署dashboard

 

 

 生成kubeconfig文件用于登录

kuboard 的安装

root@harbor:~# apt install nfs-server -y

 

root@harbor:~# cat /etc/exports
# /etc/exports: the access control list for filesystems which may be exported
# to NFS clients. See exports(5).
#
# Example for NFSv2 and NFSv3:
# /srv/homes hostname1(rw,sync,no_subtree_check) hostname2(ro,sync,no_subtree_check)
#
# Example for NFSv4:
# /srv/nfs4 gss/krb5i(rw,sync,fsid=0,crossmnt,no_subtree_check)
# /srv/nfs4/homes gss/krb5i(rw,sync,no_subtree_check)
/data/k8sdata/kuboard *(rw,no_root_squash,no_subtree_check)

root@harbor:~# mkdir -p /data/k8sdata/kuboard
root@harbor:~# exportfs -av
exporting *:/data/k8sdata/kuboard

修改yml文件中的 nfs的地址,保存

root@master01:~/20230416-cases/3.kuboard# kubectl apply -f kuboard-all-in-one.yaml

 

 

 


​kubesphers 的安装

 

 

 
 

 

posted @ 2023-04-27 17:49  请你猜猜我是谁  阅读(35)  评论(0编辑  收藏  举报