StreamPark集成k8s运行Flink实战

集群配置(Centos7)

node1(4vCpu,16G)	node2(4vCpu,16G)	node3(4vCpu,16G)
docker	docker	docker
k8s-master	k8s-node1	k8s-node2
java-8
mysql-57
maven-3.9.6(可选)
flink-1.16.3
streampark-2.1.3_2.12

Docker安装(三台机器)

#卸载自带docker
sudo yum remove docker*
#安装工具类
sudo yum install -y yum-utils

#配置docker的yum地址
sudo yum-config-manager \
--add-repo \
http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo


#安装docker
sudo yum install -y docker-ce docker-ce-cli containerd.io

#	启动&开机启动docker
systemctl enable docker --now

# docker加速配置
sudo mkdir -p /etc/docker
sudo tee /etc/docker/daemon.json <<-'EOF'
{
  "registry-mirrors": ["https://82m9ar63.mirror.aliyuncs.com"],
  "exec-opts": ["native.cgroupdriver=systemd"],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m"
  },
  "storage-driver": "overlay2"
}
EOF
sudo systemctl daemon-reload
sudo systemctl restart docker

安装完成后可以使用docker ps 查看docker运行状态

docker ps

k8s安装

基本环境配置(三台机器)：

确保每个机器使用内网ip互通

#设置每个机器自己的hostname
hostnamectl set-hostname xxx(更换为自己的主机名)

# 将 SELinux 设置为 permissive 模式（相当于将其禁用）
sudo setenforce 0
sudo sed -i 's/^SELINUX=enforcing$/SELINUX=permissive/' /etc/selinux/config

#关闭swap
swapoff -a  
sed -ri 's/.*swap.*/#&/' /etc/fstab

#允许 iptables 检查桥接流量
cat <<EOF | sudo tee /etc/modules-load.d/k8s.conf
br_netfilter
EOF

cat <<EOF | sudo tee /etc/sysctl.d/k8s.conf
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
EOF
sudo sysctl --system

安装kubelet、kubeadm、kubectl(三台机器)

#配置k8s的yum源地址
cat <<EOF | sudo tee /etc/yum.repos.d/kubernetes.repo
[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
EOF


#安装 kubelet，kubeadm，kubectl
sudo yum install -y kubelet-1.20.9 kubeadm-1.20.9 kubectl-1.20.9

#启动kubelet
sudo systemctl enable --now kubelet

#所有机器配置master域名
echo "<你的k8s-master主机ip>  k8s-master" >> /etc/hosts

#ping一下检测连通性
ping k8s-master

初始化master节点(k8s-master机器)

kubeadm init \
--apiserver-advertise-address=<你的k8s-master主机ip> \
--control-plane-endpoint=k8s-master \
--image-repository registry.cn-hangzhou.aliyuncs.com/lfy_k8s_images \
--kubernetes-version v1.20.9 \
--service-cidr=10.96.0.0/16 \
--pod-network-cidr=192.168.0.0/16

记录打印信息并执行3-5行(k8s-master机器)

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 k8s-master:6443 --token 3d05gm.ayjl70fgtg4egst2 \
    --discovery-token-ca-cert-hash sha256:a3d6e581c493d2e02ca2e4736eeb755af671a9df26095c700bc288a514800b39 \
    --control-plane 

Then you can join any number of worker nodes by running the following on each as root:

kubeadm join k8s-master:6443 --token 3d05gm.ayjl70fgtg4egst2 \
    --discovery-token-ca-cert-hash sha256:a3d6e581c493d2e02ca2e4736eeb755af671a9df26095c700bc288a514800b39 

安装Calico网络插件(注意版本问题:使用v3.20)(k8s-master机器)

curl https://docs.projectcalico.org/v3.20/manifests/calico.yaml -O
kubectl apply -f calico.yaml

#检测安装情况(都在runing状态再向下进行)
kubectl get pod -A

加入worker节点(复制打印信息中的内容)(k8s-worker机器)

kubeadm join k8s-master:6443 --token 3d05gm.ayjl70fgtg4egst2 \
    --discovery-token-ca-cert-hash sha256:a3d6e581c493d2e02ca2e4736eeb755af671a9df26095c700bc288a514800b39 

检测节点运行情况(k8s-master机器)

#都在readly状态证明安装完成
kubectl get node 

java安装

上传jdk-8u401-linux-x64.tar.gz到/opt/software目录下

#解压
tar -zxvf jdk-8u401-linux-x64.tar.gz -C /opt/module

#创建环境变量
vim /etc/profile.d/myenv.sh 

#设置JAVA_HOME
#JAVA_HOME
export JAVA_HOME=/opt/module/jdk1.8.0_401
export PATH=${JAVA_HOME}/bin:$PATH

#刷新生效
source /etc/profile.d/myenv.sh 

#检验
java -version

mysql安装

#检查是否安装过MySQL
rpm -qa | grep mysql 
#检查是否存在 mariadb 数据库（内置的MySQL数据库），有则强制删除
rpm -qa | grep mariadb 
#强制删除
rpm -e --nodeps mariadb-libs-5.5.68-1.el7.x86_64 
#强制删除
rpm -e --nodeps mariadb-5.5.68-1.el7.x86_64 


#下载mysql源
curl -O https://repo.mysql.com//mysql57-community-release-el7-11.noarch.rpm

#安装MySQL源
yum localinstall mysql57-community-release-el7-11.noarch.rpm

#安装密钥
rpm --import https://repo.mysql.com/RPM-GPG-KEY-mysql-2022

#安装mysql
yum install mysql-community-server

#启动mysql
systemctl start mysqld

#获取默认密码
grep 'temporary password' /var/log/mysqld.log

#登录mysql
mysql -uroot -p显示的默认密码

#修改密码策略
set global validate_password_policy=0;
set global validate_password_length=1;

#修改密码
ALTER USER 'root'@'localhost' IDENTIFIED BY '新密码';

#授予root用户远程访问权限，并刷新权限使生效(可选)
grant all privileges on *.* to 'root' @'%' identified by '新密码';     

maven安装(用于依赖项下载，可选)

#下载安装包
curl -O https://archive.apache.org/dist/maven/maven-3/3.9.6/binaries/apache-maven-3.9.6-bin.tar.gz

#解压
tar -zxvf apache-maven-3.9.6-bin.tar.gz -C /opt/module

flink安装

#下载安装包
curl -O https://archive.apache.org/dist/flink/flink-1.16.3/flink-1.16.3-bin-scala_2.12.tgz

#解压
tar -zxvf flink-1.16.3-bin-scala_2.12.tgz -C /opt/module

Streampark安装

官网手册：安装部署 | Apache StreamPark (incubating)

上传apache-streampark_2.12-2.1.3-incubating-bin.tar.gz到/opt/software目录下

#解压
tar -zxvf apache-streampark_2.12-2.1.3-incubating-bin.tar.gz -C /opt/module

#初始化表结构、登录mysql
source streampark安装位置/script/schema/mysql-schema.sql
source streampark安装位置/script/data/mysql-data.sql


#修改连接信息,进入到 conf 下，修改 conf/application.yml,找到 spring 这一项，找到 profiles.active 的配置，修改成mysql即可

spring:
  profiles.active: mysql #[h2,pgsql,mysql]


#修改 config/application-mysql.yml
spring:
  datasource:
    username: root
    password: 你的密码如果是纯数字需要加单引号'000000'
    🤣#####!!!!!!上传mysql-connector-java到lib目录下!!!!!!!#######🤣
    driver-class-name: com.mysql.jdbc.Driver   # 请根据mysql-connector-java版本确定具体的路径,例如:使用5.x则此处的驱动名称应该是：com.mysql.jdbc.Driver
    url: jdbc:mysql://localhost:3306/streampark?useSSL=false&useUnicode=true&characterEncoding=UTF-8&allowPublicKeyRetrieval=false&useJDBCCompliantTimezoneShift=true&useLegacyDatetimeCode=false&serverTimezone=GMT%2B8


#修改workspace
进入到 conf 下，修改 conf/application.yml,找到 streampark 这一项，找到 workspace 的配置，修改成一个用户有权限的目录

streampark:
  # HADOOP_USER_NAME 如果是on yarn模式( yarn-prejob | yarn-application | yarn-session)则需要配置 hadoop-user-name
  hadoop-user-name: hdfs
  # 本地的工作空间,用于存放项目源码,构建的目录等.
  workspace:
    local: /opt/streampark_workspace #🤣手动建一下🤣
    remote: hdfs:///streampark   # support hdfs:///streampark/ 、 /streampark 、hdfs://host:ip/streampark/


#启动
startup.sh

#访问节点的10000端口即可进入(默认账号密码：admin / streampark)

集成k8s

官方手册：Flink K8s 集成支持 | Apache StreamPark (incubating)

#StreamPark 直接使用系统 ～/.kube/config 作为 Kubernetes 集群的连接凭证
#通过 StreamPark 所在机器的 kubectl 快速检查目标 Kubernetes 集群的连通性：

kubectl cluster-info

#Kubernetes RBAC 配置,假设使用 Flink Namespace 为 flink-dev 用户为default
kubectl create clusterrolebinding flink-role-binding-default --clusterrole=edit --serviceaccount=flink-dev:default

搭建docker私服

#pull下来registry镜像
docker pull registry:2.7.0


#创建帐号密码文件，写入帐号密码
mkdir -p /mydisk/docker/auth
 
cd /mydisk/docker/auth
 
echo "user:docker passwd:123456" >htpasswd


#加密帐号密码文件
docker run --entrypoint htpasswd registry:2.7.0 -Bbn docker 123456 > /mydisk/docker/auth/htpasswd


#启动镜像服务器
docker run -itd -p 5000:5000 --restart=always --name docker-registry -v /mydisk/docker/auth:/auth -v /mydisk/docker/registry:/var/lib/registry -e "REGISTRY_AUTH=htpasswd" -e "REGISTRY_AUTH_HTPASSWD_REALM=Registry Realm" -e "REGISTRY_AUTH_HTPASSWD_PATH=/auth/htpasswd" registry:2.7.0


#修改本地docker私服配置
vim  /etc/docker/daemon.json
 
#添加你的配置
{
    "insecure-registries": ["私服的IP地址或者域名:端口号"]
}
 
#重启docker
systemctl restart docker.service

docker login 你私服ip或者域名:5000
#输入你的帐号密码

运行个任务

配置flink版本

sql任务

CREATE TABLE datagen_source (
  name VARCHAR,
  score BIGINT
) WITH (
  'connector' = 'datagen'
);


CREATE TABLE datagen_sink (
  name VARCHAR,
  score BIGINT
) WITH (
  'connector' = 'print'
);


INSERT INTO datagen_sink select * from datagen_source;

k8s对外服务类型ClusterIP or NodePort，否则无法与k8s准确交互

k8s pod 模板需要设置否则无法从私服拉取镜像

kubectl create secret generic <secret 名字> \
    -n <namespace 名字> \
    --from-file=.dockerconfigjson=<path/to/.docker/config.json> \
    --type=kubernetes.io/dockerconfigjson

apiVersion: v1
kind: Pod
metadata:
  name: pod-template
spec:
  serviceAccount: default
  containers:
  - name: flink-main-container
    image:
  imagePullSecrets:
  - name: <secret 名字>

提交-发布-运行即可