混沌工程文档: https://chaosblade.io/docs/
helm: https://github.com/helm/helm/releases
chaosblade: https://github.com/chaosblade-io/chaosblade/releases
chaosblade-box: https://github.com/chaosblade-io/chaosblade-box/releases
metrics-server: https://github.com/kubernetes-sigs/metrics-server/releases
ChaosBlade 是什么?
ChaosBlade是一个云原生混沌工程平台,支持多种环境、集群和语言。
包含混沌工程实验工具 chaosblade 和混沌工程平台 chaosblade-box,旨在通过混沌工程帮助企业解决云原生过程中高可用问题。
一、安装部署K8S
1.1 修改服务器名称
[root@VM-8-11-centos ~]# hostnamectl set-hostname master
[root@VM-16-10-centos ~]# hostnamectl set-hostname no1
vim /etc/hosts
# 内容BEGIN
10.0.8.11 master
10.0.16.10 no1
# 内容END
reboot
1.2 关闭防火墙和启用时间同步等
# 关闭防火墙(在3台master运行)
systemctl stop firewalld && systemctl disable firewalld
# 时间同步(在3台master运行)
yum install ntpdate -y && ntpdate time.windows.com
# 关闭swap(在3台master运行)
swapoff -a && sed -ri 's/.*swap.*/#&/' /etc/fstab
# 关闭selinux(在3台master运行)
# sed -i 's/enforcing/disabled/' /etc/selinux/config && setenforce 0
setenforce 0
# 安装必要的系统工具
sudo yum install -y yum-utils device-mapper-persistent-data lvm2
1.3 安装Docker20.10.24
所有master+node+rancher执行
# 1 切换镜像源
[root@master ~]# wget https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo -O /etc/yum.repos.d/docker-ce.repo
# 2 查看当前镜像源中支持的docker版本
[root@master ~]# yum list docker-ce --showduplicates
# 3 安装特定版本的docker-ce
# 必须指定--setopt=obsoletes=0,否则yum会自动安装更高版本
[root@master ~]# yum install --setopt=obsoletes=0 docker-ce-18.06.3.ce-3.el7 -y
或(推荐) yum install -y --setopt=obsoletes=0 docker-ce-20.10.24-3.el8 docker-ce-cli-20.10.24-3.el8
# 4 配置文件
vim /etc/systemd/system/docker.service
# 内容BEGIN
[Unit]
Description=Docker Application Container Engine
Documentation=https://docs.docker.com
After=network-online.target firewalld.service
Wants=network-online.target
[Service]
Type=notify
# the default is not to use systemd for cgroups because the delegate issues still
# exists and systemd currently does not support the cgroup feature set required
# for containers run by docker
ExecStart=/usr/bin/dockerd
ExecReload=/bin/kill -s HUP $MAINPID
# Having non-zero Limit*s causes performance problems due to accounting overhead
# in the kernel. We recommend using cgroups to do container-local accounting.
LimitNOFILE=infinity
LimitNPROC=infinity
LimitCORE=infinity
# Uncomment TasksMax if your systemd version supports it.
# Only systemd 226 and above support this version.
#TasksMax=infinity
TimeoutStartSec=0
# set delegate yes so that systemd does not reset the cgroups of docker containers
Delegate=yes
# kill only the docker process, not all processes in the cgroup
KillMode=process
# restart the docker process if it exits prematurely
Restart=on-failure
StartLimitBurst=3
StartLimitInterval=60s
[Install]
WantedBy=multi-user.target
# 内容END
chmod +x /etc/systemd/system/docker.service
# 5 启动docker
# 重新加载配置文件
systemctl daemon-reload
# 启动docker
systemctl start docker
# 设置开机启动
systemctl enable docker.service
# 6 检查docker状态和版本
[root@master ~]# docker version
# 可以通过修改daemon配置文件/etc/docker/daemon.json来使用加速器
sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
"exec-opts": ["native.cgroupdriver=systemd"],
"registry-mirrors": [
"https://mirror.ccs.tencentyun.com"
]
}
EOF
sudo systemctl daemon-reload && sudo systemctl restart docker
# 7 配置ipv4
# 1 安装ipset和ipvsadm
[root@master ~]# yum install ipset ipvsadmin -y
# 如果提示No package ipvsadmin available.需要使用 yum install -y ipvsadm
# 2 添加需要加载的模块写入脚本文件
[root@master ~]# cat <<EOF > /etc/sysconfig/modules/ipvs.modules
#!/bin/bash
modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
modprobe -- nf_conntrack
EOF
# 3 为脚本文件添加执行权限
[root@master ~]# chmod +x /etc/sysconfig/modules/ipvs.modules
# 4 执行脚本文件
[root@master ~]# /bin/bash /etc/sysconfig/modules/ipvs.modules
# 5 查看对应的模块是否加载成功
[root@master ~]# lsmod | grep -e ip_vs -e nf_conntrack_ipv4
1.4 部署K8S集群1.20.11
网络配置 iptables
vim /etc/sysctl.d/k8s.conf
# 内容BEGIN
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.ipv4.ip_forward=1
vm.swappiness=0
# 内容END
modprobe br_netfilter
sysctl -p /etc/sysctl.d/k8s.conf
配置kubernetes源
vim /etc/yum.repos.d/kubernetes.repo
# 内容BEGIN
[kubernetes]
name=Kubernetes
baseurl=http://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
gpgkey=http://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg
http://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
# 内容END
# 清除缓存
yum clean all
# 把服务器的包信息下载到本地电脑缓存起来,makecache建立一个缓存
yum makecache
安装kubelet kubeadm kubectl
# 当不指定具体版本时,将下载当前yum源对应的最新版本
yum install -y kubelet kubeadm kubectl
# 也可以指定版本,建议指定如下版本, 安装指定版本的kubelet,kubeadm,kubectl
yum install -y kubelet-1.20.11 kubeadm-1.20.11 kubectl-1.20.11
安装完成后,查看K8S版本
# 查看kubelet版本
[root@master ~]# kubelet --version
Kubernetes v1.20.11
# 查看kubeadm版本
[root@master ~]# kubeadm version
kubeadm version: &version.Info{
Major:"1", Minor:"20", GitVersion:"v1.20.11", GitCommit:"27522a29febbcc4badac257763044d0d90c11abd", GitTreeState:"clean", BuildDate:"2021-09-15T19:20:34Z", GoVersion:"go1.15.15", Compiler:"gc", Platform:"linux/amd64"}
# 配置kubelet的cgroup
# 编辑/etc/sysconfig/kubelet,添加下面的配置
KUBELET_CGROUP_ARGS="--cgroup-driver=systemd"
KUBE_PROXY_MODE="ipvs"
# 4 设置kubelet开机自启
[root@master ~]# systemctl daemon-reload
[root@master ~]# systemctl start kubelet
[root@master ~]# systemctl status kubelet
# 没启动成功,报错先不管,后面的 `kubeadm init` 会拉起
[root@master ~]# systemctl enable kubelet
[root@master ~]# systemctl is-enabled kubelet
# 下载 cni-plugins-linux-amd64-v1.2.0.tgz 插件
$ wget https://github.com/containernetworking/plugins/releases/download/v1.2.0/cni-plugins-linux-amd64-v1.2.0.tgz
# 解压 cni-plugins-linux-arm64-v1.2.0.tgz 插件 并且复制到 /opt/cni/bin/
tar -zxvf cni-plugins-linux-amd64-v1.2.0.tgz -C /opt/cni/bin/
准备集群镜像
# 在安装kubernetes集群之前,必须要提前准备好集群需要的镜像,所需镜像可以通过下面命令查看
[root@master ~]# kubeadm config images list
# 下载镜像
# 此镜像在kubernetes的仓库中,由于网络原因,无法连接,下面提供了一种替代方案
images=(
kube-apiserver:v1.20.11
kube-controller-manager:v1.20.11
kube-scheduler:v1.20.11
kube-proxy:v1.20.11
pause:3.2
etcd:3.4.13-0
coredns:1.7.0
)
for imageName in ${images[@]} ; do
docker pull registry.cn-hangzhou.aliyuncs.com/google_containers/$imageName
docker tag registry.cn-hangzhou.aliyuncs.com/google_containers/$imageName k8s.gcr.io/$imageName
docker rmi registry.cn-hangzhou.aliyuncs.com/google_containers/$imageName
done
初始化K8S集群Master
注意,此操作只在规划的K8S Master的MASTER服务器(即本篇master)上执行
# 执行初始化命令 初始化k8s集群
[root@master ~]# kubeadm init \
--kubernetes-version=v1.20.11 \
--pod-network-cidr=10.244.0.0/16 \
--service-cidr=10.96.0.0/12 \
--apiserver-advertise-address=10.0.8.11 \
--ignore-preflight-errors=all
kube-flannel.yml
---
kind: Namespace
apiVersion: v1
metadata:
name: kube-flannel
labels:
k8s-app: flannel
pod-security.kubernetes.io/enforce: privileged
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
labels:
k8s-app: flannel
name: flannel
rules:
- apiGroups:
- ""
resources:
- pods
verbs:
- get
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- nodes/status
verbs:
- patch
- apiGroups:
- networking.k8s.io
resources:
- clustercidrs
verbs:
- list
- watch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
labels:
k8s-app: flannel
name: flannel
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: flannel
subjects:
- kind: ServiceAccount
name: flannel
namespace: kube-flannel
---
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: flannel
name: flannel
namespace: kube-flannel
---
kind: ConfigMap
apiVersion: v1
metadata:
name: kube-flannel-cfg
namespace: kube-flannel
labels:
tier: node
k8s-app: flannel
app: flannel
data:
cni-conf.json: |
{
"name": "cbr0",
"cniVersion": "0.3.1",
"plugins": [
{
"type": "flannel",
"delegate": {
"hairpinMode": true,
"isDefaultGateway": true
}
},
{
"type": "portmap",
"capabilities": {
"portMappings": true
}
}
]
}
net-conf.json: |
{
"Network": "10.244.0.0/16",
"Backend": {
"Type": "vxlan"
}
}
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-flannel-ds
namespace: kube-flannel
labels:
tier: node
app: flannel
k8s-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-plugin
image: docker.io/flannel/flannel-cni-plugin:v1.2.0
command:
- cp
args:
- -f
- /flannel
- /opt/cni/bin/flannel
volumeMounts:
- name: cni-plugin
mountPath: /opt/cni/bin
- name: install-cni
image: docker.io/flannel/flannel:v0.24.0
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: docker.io/flannel/flannel:v0.24.0
command:
- /opt/bin/flanneld
args:
- --ip-masq
- --kube-subnet-mgr
resources:
requests:
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
- name: EVENT_QUEUE_DEPTH
value: &
标签:name,--,Chaos,etc,Engineering,master,install,docker,flannel
From: https://blog.csdn.net/qq_41594280/article/details/141276801