搜索到
40
篇与
的结果
-
grafana grafana使用要先做nfs挂载卷[root@master01 test]# kubectl get pv NAME CAPACITY ACCESS MODES RECLAIM POLICY STATUS CLAIM STORAGECLASS VOLUMEATTRIBUTESCLASS REASON AGE grafana-pv 2Gi RWO Retain Bound monitor/grafana-pvc nfs-client <unset> 27h[root@master01 test]# cat grafana.yaml # grafana.yaml # 为grafana创建持久存储，用于存放插件等数据，挂载到容器的/var/lib/grafana下 apiVersion: v1 kind: PersistentVolumeClaim metadata: name: grafana-pvc namespace: monitor labels: app: grafana spec: storageClassName: nfs-client accessModes: - ReadWriteOnce resources: requests: storage: 2Gi --- apiVersion: apps/v1 kind: Deployment metadata: name: grafana namespace: monitor spec: selector: matchLabels: app: grafana template: metadata: labels: app: grafana spec: volumes: - name: storage persistentVolumeClaim: claimName: grafana-pvc securityContext: runAsUser: 0 # 必须以root身份运行 containers: - name: grafana image: grafana/grafana # 默认lastest最新，也可以指定版本grafana/grafana:10.4.4 imagePullPolicy: IfNotPresent ports: - containerPort: 3000 name: grafana env: # 配置 grafana 的管理员用户和密码的， - name: GF_SECURITY_ADMIN_USER value: admin - name: GF_SECURITY_ADMIN_PASSWORD value: admin321 readinessProbe: failureThreshold: 10 httpGet: path: /api/health port: 3000 scheme: HTTP periodSeconds: 10 successThreshold: 1 timeoutSeconds: 30 livenessProbe: failureThreshold: 3 httpGet: path: /api/health port: 3000 scheme: HTTP periodSeconds: 10 successThreshold: 1 timeoutSeconds: 1 resources: limits: cpu: 150m memory: 512Mi requests: cpu: 150m memory: 512Mi volumeMounts: - mountPath: /var/lib/grafana name: storage --- apiVersion: v1 kind: Service metadata: name: grafana namespace: monitor spec: type: NodePort ports: - port: 3000 selector: app: grafana [root@master01 /]# kubectl -n monitor get svc NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE alertmanager NodePort 10.99.103.160 <none> 9093:30610/TCP 94m grafana NodePort 10.99.18.224 <none> 3000:30484/TCP 28h prometheus NodePort 10.108.206.132 <none> 9090:31119/TCP 3d1h promoter ClusterIP 10.97.213.227 <none> 8080/TCP 18h redis ClusterIP 10.97.184.21 <none> 6379/TCP,9121/TCP 2d21h 使用grafana出图先使用浏览器访问<你的物理机IP地址>:(1)添加仪表图形(2)选择对接的监控(3)设置需要对接的IP+端口（其他不用修改）(4)添加图形模板(5)查看已经配置好的 -
监控k8s 抓取apiserver的监控指标 - job_name: 'kubernetes-apiservers' kubernetes_sd_configs: - role: endpoints scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - source_labels: [__meta_kubernetes_namespace,__meta_kubernetes_service_name,__meta_kubernetes_endpoint_port_name] # 把符合要求的保留下来 action: keep regex: default;kubernetes;https抓取kube-controller-manager的监控指标 # 1、创建svc，标签选择选中， apiVersion: v1 kind: Service metadata: labels: app.kubernetes.io/component: kube-controller-manager app.kubernetes.io/name: kube-controller-manager k8s-app: kube-controller-manager name: kube-controller-manager namespace: kube-system spec: clusterIP: None ports: - name: https-metrics port: 10257 targetPort: 10257 protocol: TCP selector: component: kube-controller-manager # 2、你可以查看下上述svc其关联的endpoint用的地址都是物理机的地址，而每台机器上的controller-manager都监听在127.0.0.1，所以是无法访问的，需要修改其默认监听 vi /etc/kubernetes/manifests/kube-controller-manager.yaml # 修改--bind-address=127.0.0.1 每台master节点都改 # 3、添加监控 - job_name: 'kube-controller-manager' kubernetes_sd_configs: - role: endpoints scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - source_labels: [__meta_kubernetes_namespace,__meta_kubernetes_service_name,__meta_kubernetes_endpoint_port_name] action: keep regex: kube-system;kube-controller-manager;https-metrics # 这里的https-metrics名字与你svc中为ports起的名字保持一致 抓取kube-scheduler的监控指标 同上 抓取etcd的监控指标 # 1、修改每个master节点上etcd的静态配置yaml - --listen-metrics-urls=http://127.0.0.1:2381 # 2、etcd-service.yaml apiVersion: v1 kind: Service metadata: namespace: kube-system name: etcd labels: k8s-app: etcd spec: selector: component: etcd type: ClusterIP clusterIP: None ports: - name: http port: 2381 targetPort: 2381 protocol: TCP # 3、etcd监控 - job_name: 'etcd' kubernetes_sd_configs: - role: endpoints scheme: http relabel_configs: - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name] action: keep regex: kube-system;etcd;http 自动发现业务服务 - job_name: 'kubernetes-endpoints' kubernetes_sd_configs: - role: endpoints relabel_configs: # 1、匹配元数据__meta_kubernetes_service_annotation_prometheus_io_scrape包含"true"的留下 - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape] action: keep regex: true # 2、__meta_kubernetes_service_annotation_prometheus_io_scheme的值中包含0或1个https，则改名为__scheme__ - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] action: replace target_label: __scheme__ regex: (https?) # 3、__meta_kubernetes_service_annotation_prometheus_io_path的值至少有一个任意字符，则改名为__metrics_path__ - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] action: replace target_label: __metrics_path__ regex: (.+) # 4、提取ip与port拼接到一起格式为: 1.1.1.1:3333，然后赋值给新label名：__address__ - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] action: replace target_label: __address__ regex: ([^:]+)(?::\d+)?;(\d+) # RE2 正则规则，+是一次多多次，?是0次或1次，其中?:表示非匹>配组(意思就是不获取匹配结果) replacement: $1:$2 # 5、添加标签 - action: labelmap regex: __meta_kubernetes_service_label_(.+) # 6、名称空间标签替换为kubernetes_namespace - source_labels: [__meta_kubernetes_namespace] action: replace target_label: kubernetes_namespace # 7、服务名替换为kubernetes_name - source_labels: [__meta_kubernetes_service_name] action: replace target_label: kubernetes_name # 8、pod名替换为kubernetes_pod_name - source_labels: [__meta_kubernetes_pod_name] action: replace target_label: kubernetes_pod_name 自动发现测试 # prome-redis.yaml apiVersion: apps/v1 kind: Deployment metadata: name: redis namespace: monitor spec: selector: matchLabels: app: redis template: metadata: labels: app: redis spec: containers: - name: redis image: redis:4 resources: requests: cpu: 100m memory: 100Mi ports: - containerPort: 6379 - name: redis-exporter image: oliver006/redis_exporter:latest resources: requests: cpu: 100m memory: 100Mi ports: - containerPort: 9121 --- kind: Service apiVersion: v1 metadata: name: redis namespace: monitor annotations: # --------------------------------》 添加 prometheus.io/scrape: 'true' prometheus.io/port: '9121' spec: selector: app: redis ports: - name: redis port: 6379 targetPort: 6379 - name: prom port: 9121 targetPort: 9121
-
prometheus部署 一、 二进制安装prometheus server 物理机直接部署下载最新版二进制包见：https://prometheus.io/download ， 下载历史版本见：https://github.com/prometheus/prometheus/tags LTS： 2.53.x版 注意：最新版本的prometheus，可能会出现grafana上模板没有数据，不兼容的新规则的问题 ========================================》二进制安装prometheus server # 1、先做个软连接方便后续升级 ln -s /monitor/prometheus-2.53.0.linux-amd64 /monitor/prometheus mkdir /monitor/prometheus/data # 创建tsdb数据目录 # 2、添加系统服务 cat > /usr/lib/systemd/system/prometheus.service << 'EOF' [Unit] Description=prometheus server daemon [Service] Restart=on-failure ExecStart=/monitor/prometheus/prometheus --config.file=/monitor/prometheus/prometheus.yml --storage.tsdb.path=/monitor/prometheus/data --storage.tsdb.retention.time=30d --web.enable-lifecycle [Install] WantedBy=multi-user.target EOF # 3、启动 systemctl daemon-reload systemctl enable prometheus.service systemctl start prometheus.service systemctl status prometheus netstat -tunalp |grep 9090测试下载并构建测试程序，作为被监控者，对外暴漏了/metrics接口 yum install golang -y git clone https://github.com/prometheus/client_golang.git cd client_golang/examples/random export GO111MODULE=on export GOPROXY=https://goproxy.cn go build # 得到一个二进制命令random 然后在 3 个独立的终端里面运行 3 个服务： ./random -listen-address=:8080 # 对外暴漏http://localhost:8080/metrics ./random -listen-address=:8081 # 对外暴漏http://localhost:8081/metrics ./random -listen-address=:8082 # 对外暴漏http://localhost:8080/metrics 因为都对外暴漏了/metrics接口，并且数据格式遵循prometheus规范，所以我们可以在prometheus.yml中添加监控项假设8080与8081是生产实例，8082是金丝雀实例，那么我们放到不同的target里然后用标签区分,配置如下 scrape_configs: - job_name: 'example-random' # Override the global default and scrape targets from this job every 5 seconds. scrape_interval: 5s static_configs: - targets: ['192.168.110.101:8080', '192.168.110.101:8081'] labels: group: 'production' - targets: ['192.168.110.101:8082'] labels: group: 'canary'systemctl restart prometheus 然后查看页面http://192.168.110.101:9090/ 点击Status---》Targets，发现有新增的监控job二、 安装prometheus server到k8s#prometheus-cm.yaml apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: monitor data: prometheus.yml: | global: scrape_interval: 15s # Prometheus每隔15s就会从所有配置的目标端点抓取最新的数据 scrape_timeout: 15s # 某个抓取操作在 15 秒内未完成，会被视为超时，不会包含在最新的数据中。 evaluation_interval: 15s # # 每15s对告警规则进行计算 scrape_configs: - job_name: "prometheus" static_configs: - targets: ["localhost:9090"] prometheus-pv-pvc.yamlapiVersion: v1 kind: PersistentVolume metadata: name: prometheus-local labels: app: prometheus spec: accessModes: - ReadWriteOnce capacity: storage: 20Gi storageClassName: local-storage local: path: /data/k8s/prometheus nodeAffinity: required: nodeSelectorTerms: - matchExpressions: - key: kubernetes.io/hostname operator: In values: - master01 persistentVolumeReclaimPolicy: Retain --- apiVersion: v1 kind: PersistentVolumeClaim metadata: name: prometheus-data namespace: monitor spec: selector: matchLabels: app: prometheus accessModes: - ReadWriteOnce resources: requests: storage: 20Gi storageClassName: local-storageprometheus-rbac.yamlapiVersion: v1 kind: ServiceAccount metadata: name: prometheus namespace: monitor --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: prometheus rules: - apiGroups: - '' resources: - nodes - services - endpoints - pods - nodes/proxy verbs: - get - list - watch - apiGroups: - 'extensions' resources: - ingresses verbs: - get - list - watch - apiGroups: - '' resources: - configmaps - nodes/metrics verbs: - get - nonResourceURLs: # 用来对非资源型 metrics 进行操作的权限声明 - /metrics verbs: - get --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: prometheus roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole # 由于我们要获取的资源信息，在每一个 namespace 下面都有可能存在，所以我们这里使用的是 ClusterRole 的资源对象 name: prometheus subjects: - kind: ServiceAccount name: prometheus namespace: monitor prometheus-deploy.yamlapiVersion: apps/v1 kind: Deployment metadata: name: prometheus namespace: monitor labels: app: prometheus spec: selector: matchLabels: app: prometheus template: metadata: labels: app: prometheus spec: serviceAccountName: prometheus securityContext: # 确保这里的缩进使用的是空格 runAsUser: 0 containers: - image: registry.cn-guangzhou.aliyuncs.com/xingcangku/oooo:1.0 name: prometheus args: - '--config.file=/etc/prometheus/prometheus.yml' - '--storage.tsdb.path=/prometheus' - '--storage.tsdb.retention.time=24h' - '--web.enable-admin-api' - '--web.enable-lifecycle' ports: - containerPort: 9090 name: http volumeMounts: - mountPath: '/etc/prometheus' name: config-volume - mountPath: '/prometheus' name: data resources: requests: cpu: 100m memory: 512Mi limits: cpu: 100m memory: 512Mi volumes: - name: data persistentVolumeClaim: claimName: prometheus-data - name: config-volume configMap: name: prometheus-config prometheus-svc.yamlapiVersion: v1 kind: Service metadata: name: prometheus namespace: monitor labels: app: prometheus spec: selector: app: prometheus type: NodePort ports: - name: web port: 9090 targetPort: 9090 #targetPort: http kubectl create namespace monitor kubectl apply -f cm.yaml mkdir /data/k8s/prometheus # 在pv所亲和的节点上创建 kubectl apply -f pv-pvc.yaml kubectl apply -f rbac.yaml kubectl apply -f deploy.yaml kubectl apply -f svc.yaml # 把二进制的停掉 systemctl stop prometheus systemctl disable prometheus # 添加监控项，然后apply -f [root@master01 monitor]# cat prometheus-cm.yaml apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: monitor data: prometheus.yml: | global: scrape_interval: 15s # Prometheus 每隔 15 秒从所有配置的目标端点抓取最新的数据 scrape_timeout: 15s # 某个抓取操作在 15 秒内未完成，会被视为超时，不会包含在最新的数据中。 evaluation_interval: 15s # 每 15 秒对告警规则进行计算 scrape_configs: - job_name: "prometheus" static_configs: - targets: ["localhost:9090"] - job_name: 'example-random' scrape_interval: 5s static_configs: - targets: ['192.168.110.101:8080', '192.168.110.101:8081'] labels: group: 'production' - targets: ['192.168.110.101:8082'] labels: group: 'canary' #重载服务 [root@master01 monitor]# kubectl -n monitor get pods -o wide NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES prometheus-7b644bfcfc-l5twf 1/1 Running 0 5h25m 10.244.0.18 master01 <none> <none> [root@master01 monitor]# curl -X POST "http://10.108.206.132:9090/-/reload"三、监控应用软件（1）服务自带/metrics接口，直接监控，在配置中增加下述target，然后apply -f - job_name: "coredns" static_configs: - targets: ["kube-dns.kube-system.svc.cluster.local:9153"] 等一会后 curl -X POST "http://10.108.206.132:9090/-/reload"（2）应用软件没有自带自带/metrics接口，需要安装对应的exporterexporter官网地址：https://prometheus.io/docs/instrumenting/exporters/ 安装redis yum install redis -y sed -ri 's/bind 127.0.0.1/bind 0.0.0.0/g' /etc/redis.conf sed -ri 's/port 6379/port 16379/g' /etc/redis.conf cat >> /etc/redis.conf << "EOF" requirepass 123456 EOF systemctl restart redis systemctl status redis 添加redis_exporter来采集redis的监控信息 wget https://github.com/oliver006/redis_exporter/releases/download/v1.61.0/redis_exporter-v1.61.0.linux-amd64.tar.gz # 2、安装 tar xf redis_exporter-v1.61.0.linux-amd64.tar.gz mv redis_exporter-v1.61.0.linux-amd64/redis_exporter /usr/bin/ # 3、制作系统服务 cat > /usr/lib/systemd/system/redis_exporter.service << 'EOF' [Unit] Description=Redis Exporter Wants=network-online.target After=network-online.target [Service] User=root Group=root Type=simple ExecStart=/usr/bin/redis_exporter --redis.addr=redis://127.0.0.1:16379 --redis.password=123456 --web.listen-address=0.0.0.0:9122 --exclude-latency-histogram-metrics [Install] WantedBy=multi-user.target EOF #4、启动 systemctl daemon-reload systemctl restart redis_exporter systemctl status redis_exporter # 5、在cm中增加监控项目 - job_name: "redis-server" # 添加这一条 static_configs: - targets: ["192.168.71.101:9122"] kubectl apply -f prometheus-cm.yaml # 6、过一会后，执行prometheus server的reload curl -X POST "http://10.108.206.132:9090/-/reload" # 7、补充说明 如果你的redis-server跑在k8s中，那我们通常不会像上面一样裸部署一个redis_exporter，而是会以`sidecar` 的形式将redis_exporter和主应用redis_server部署在同一个 Pod 中，如下所示 # prome-redis.yaml apiVersion: apps/v1 kind: Deployment metadata: name: redis namespace: monitor spec: selector: matchLabels: app: redis template: metadata: labels: app: redis spec: containers: - name: redis image: redis:4 resources: requests: cpu: 100m memory: 100Mi ports: - containerPort: 6379 - name: redis-exporter image: oliver006/redis_exporter:latest resources: requests: cpu: 100m memory: 100Mi ports: - containerPort: 9121 --- apiVersion: v1 kind: Service metadata: name: redis namespace: monitor spec: selector: app: redis ports: - name: redis port: 6379 targetPort: 6379 - name: prom port: 9121 targetPort: 9121 # 然后你就可以用该svc的clusterip结合9121端口来访问/metrics接口 # curl 上面的svc的clusterip地址:9121/metrics # 添加监控项，直接用svc名字即可， 更新prometheus-cm.yaml 的配置文件如下 - job_name: 'redis' static_configs: - targets: ['redis:9121']
-
webhook开发 侧车容器 一、 先准备好webhook环境之前博客有写二、 准备业务镜像1. 下载镜像 docker pull centos:7 2.配置yum源 rm -f /etc/yum.repos.d/CentOS-Base.repo cat > /etc/yum.repos.d/CentOS-Base.repo <<EOF [base] name=CentOS-\$releasever - Base - mirrors.aliyun.com failovermethod=priority baseurl=http://mirrors.aliyun.com/centos/\$releasever/os/\$basearch/ http://mirrors.aliyuncs.com/centos/\$releasever/os/\$basearch/ http://mirrors.cloud.aliyuncs.com/centos/\$releasever/os/\$basearch/ gpgcheck=1 gpgkey=http://mirrors.aliyun.com/centos/RPM-GPG-KEY-CentOS-7 #released updates [updates] name=CentOS-\$releasever - Updates - mirrors.aliyun.com failovermethod=priority baseurl=http://mirrors.aliyun.com/centos/\$releasever/updates/\$basearch/ http://mirrors.aliyuncs.com/centos/\$releasever/updates/\$basearch/ http://mirrors.cloud.aliyuncs.com/centos/\$releasever/updates/\$basearch/ gpgcheck=1 gpgkey=http://mirrors.aliyun.com/centos/RPM-GPG-KEY-CentOS-7 #additional packages that may be useful [extras] name=CentOS-\$releasever - Extras - mirrors.aliyun.com failovermethod=priority baseurl=http://mirrors.aliyun.com/centos/\$releasever/extras/\$basearch/ http://mirrors.aliyuncs.com/centos/\$releasever/extras/\$basearch/ http://mirrors.cloud.aliyuncs.com/centos/\$releasever/extras/\$basearch/ gpgcheck=1 gpgkey=http://mirrors.aliyun.com/centos/RPM-GPG-KEY-CentOS-7 #additional packages that extend functionality of existing packages [centosplus] name=CentOS-\$releasever - Plus - mirrors.aliyun.com failovermethod=priority baseurl=http://mirrors.aliyun.com/centos/\$releasever/centosplus/\$basearch/ http://mirrors.aliyuncs.com/centos/\$releasever/centosplus/\$basearch/ http://mirrors.cloud.aliyuncs.com/centos/\$releasever/centosplus/\$basearch/ gpgcheck=1 enabled=0 gpgkey=http://mirrors.aliyun.com/centos/RPM-GPG-KEY-CentOS-7 #contrib - packages by Centos Users [contrib] name=CentOS-\$releasever - Contrib - mirrors.aliyun.com failovermethod=priority baseurl=http://mirrors.aliyun.com/centos/\$releasever/contrib/\$basearch/ http://mirrors.aliyuncs.com/centos/\$releasever/contrib/\$basearch/ http://mirrors.cloud.aliyuncs.com/centos/\$releasever/contrib/\$basearch/ gpgcheck=1 enabled=0 gpgkey=http://mirrors.aliyun.com/centos/RPM-GPG-KEY-CentOS-7 EOF 3.安装需要的应用 yum install -y cronie openssh-server ssh wget 4.安装mysql5.7 wget https://dev.mysql.com/get/mysql57-community-release-el7-11.noarch.rpm rpm -ivh mysql57-community-release-el7-11.noarch.rpm yum repolist enabled | grep "mysql.*-community.*" yum install mysql-community-server 5.创建用户mysql并且给权限 chown -R mysql:mysql /var/lib/mysql chmod -R 755 /var/lib/mysql 6.后台启动数据库 /usr/sbin/mysqld --user=mysql & 7.初始化数据库 /usr/sbin/mysqld --initialize 8.查看初始化的密码 grep 'temporary password' /var/log/mysqld.log mysql -u root -p 9.把初始化的密码输入上 ALTER USER 'root'@'localhost' IDENTIFIED BY 'newpassword'; 10.测试创建一个账号还有一个库和一个表 -- 创建用户 'axing' 并设置密码 CREATE USER 'axing'@'localhost' IDENTIFIED BY 'Egon@123'; -- 授予所有权限给用户 'axing' 在所有数据库中 GRANT ALL PRIVILEGES ON *.* TO 'axing'@'localhost' WITH GRANT OPTION; -- 刷新权限表以使更改生效 FLUSH PRIVILEGES; --创建库 CREATE DATABASE my_database; USE my_database; --创建表 CREATE TABLE my_table ( id INT AUTO_INCREMENT PRIMARY KEY, name VARCHAR(100) NOT NULL, created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ); 三、准备测车镜像（1）准备数据库备份的脚本cat jiaoben.py脚本里面有些地方还可以优化，嫌麻烦没完善了。（按这个是可以跑起来的修改好对应的账号密码还有IP地址）#!/bin/bash /usr/sbin/mysqld --user=mysql & /usr/sbin/sshd # 配置 #!/bin/bash # 启动 MySQL 和 SSH 服务 /usr/sbin/mysqld --user=mysql & # 启动 MySQL 数据库服务 /usr/sbin/sshd # 启动 SSH 服务 # 配置变量 MYSQL_HOST="127.0.0.1" # MySQL 数据库主机地址 MYSQL_USER="root" # MySQL 数据库用户名 MYSQL_PASSWORD="Egon@123" # MySQL 数据库密码 BACKUP_DIR="/backup" # 本地备份文件存储目录 REMOTE_HOST="192.168.110.110" # 远程主机地址 REMOTE_USER="root" # 远程主机用户名 REMOTE_DIR="/remote/backup/dir" # 远程备份文件存储目录 host_info="root:1" # 存储用户名和密码的变量 target_ip="192.168.110.110" # 目标主机 IP 地址 # 提取用户名和密码 user=$(echo $host_info | awk -F: '{print $1}') # 从 host_info 中提取用户名 pass=$(echo $host_info | awk -F: '{print $2}') # 从 host_info 中提取密码 # SSH 密钥路径 key_path="/root/.ssh/id_rsa" # SSH 私钥路径 pub_key_path="/root/.ssh/id_rsa.pub" # SSH 公钥路径 # 检查并生成 SSH 密钥对 if [ ! -f "$pub_key_path" ]; then echo "SSH 公钥文件不存在，生成新的密钥对..." # 如果公钥文件不存在，则生成新的密钥对 ssh-keygen -t rsa -b 4096 -f "$key_path" -N "" # 生成新的 SSH 密钥对 else echo "SSH 公钥文件已存在。" # 如果公钥文件已存在，则不进行生成 fi # 使用 expect 自动化 ssh-copy-id 过程 expect << EOF spawn ssh-copy-id -i $pub_key_path $user@$target_ip expect { "yes/no" {send "yes\n"; exp_continue} "password:" {send "$pass\n"} } expect eof EOF # 检查 expect 命令的退出状态 if [ $? -eq 0 ]; then echo "公钥已成功复制到目标主机。" # 如果 expect 命令成功执行，打印成功消息 else echo "公钥复制过程失败。" # 如果 expect 命令失败，打印失败消息 fi # 创建备份目录 mkdir -p $BACKUP_DIR # 创建备份存储目录（如果不存在） # 获取当前时间 TIMESTAMP=$(date +"%F-%H-%M-%S") # 获取当前时间，格式为 YYYY-MM-DD-HH-MM-SS # 备份数据库 mysqldump -h $MYSQL_HOST --all-databases > $BACKUP_DIR/db_backup_$TIMESTAMP.sql # 使用 mysqldump 工具备份所有数据库到本地文件 # 创建远程备份目录（如果不存在） ssh root@$REMOTE_HOST "mkdir -p $REMOTE_DIR" # 在远程主机上创建备份存储目录（如果不存在） # 上传备份到远程主机 scp $BACKUP_DIR/db_backup_$TIMESTAMP.sql $REMOTE_USER@$REMOTE_HOST:$REMOTE_DIR # 使用 scp 工具将备份文件上传到远程主机 # 删除本地备份文件 rm $BACKUP_DIR/db_backup_$TIMESTAMP.sql # 删除本地备份文件，以节省磁盘空间（2）准备定时任务的文件cat crontab0 2 * * * /usr/local/bin/jiaoben.py（3）构建镜像cat dockerfile可以偷懒直接用上面业务镜像 # 使用 CentOS 作为基础镜像 FROM registry.cn-guangzhou.aliyuncs.com/xingcangku/axingcangku:latest # 复制备份脚本 COPY jiaoben.sh /usr/local/bin/jiaoben.sh RUN chmod +x /usr/local/bin/jiaoben.sh # 复制 crontab 文件 COPY crontab /etc/cron.d/backup-cron RUN chmod 0644 /etc/cron.d/backup-cron # 确保 cron 服务在容器中运行 RUN crontab /etc/cron.d/backup-cron # 创建 MySQL 配置文件 .my.cnf RUN echo "[client]" > /root/.my.cnf && \ echo "user=root" >> /root/.my.cnf && \ echo "password=Egon@123" >> /root/.my.cnf && \ chmod 600 /root/.my.cnf # 启动 cron 服务，并保持容器运行 CMD ["crond", "-n"]四、准备webhook.py文件这个是webhook pod里面运行的python文件有两个功能1.检测到带有app:mysql标签的pod的时候，会自动创建一个侧车容器，会定时备份数据给远程主机。2.如果创建的pod没有带有标签会自动添加标签3.labels 中存在 'app: test' 标签，则添加 annotation reloader.stakater.com/auto: "true"# -*- coding: utf-8 -*- from flask import Flask, request, jsonify import base64 import json import ssl import kubernetes.client from kubernetes.client.rest import ApiException from kubernetes import config import os import threading import time # 创建 Flask 应用实例 app = Flask(__name__) # 加载 Kubernetes 集群内的配置 config.load_incluster_config() @app.route('/mutate', methods=['POST']) def mutate_pod(): try: # 从 AdmissionReview 请求中解析 JSON 数据 admission_review = request.get_json() pod = admission_review['request']['object'] patch = [] # 初始化 metadata, labels, 和 annotations 如果它们不存在 # 检查 pod 是否有 metadata 部分，如果没有则添加 if 'metadata' not in pod: patch.append({ "op": "add", "path": "/metadata", "value": {} }) # 检查 metadata 是否有 labels 部分，如果没有则添加 if 'labels' not in pod.get('metadata', {}): patch.append({ "op": "add", "path": "/metadata/labels", "value": {} }) # 检查 metadata 是否有 annotations 部分，如果没有则添加 if 'annotations' not in pod.get('metadata', {}): patch.append({ "op": "add", "path": "/metadata/annotations", "value": {} }) # 获取现有的 labels 和 annotations labels = pod.get('metadata', {}).get('labels', {}) annotations = pod.get('metadata', {}).get('annotations', {}) # 如果 labels 中不存在 'environment' 标签，则添加 if 'environment' not in labels: patch.append({ "op": "add", "path": "/metadata/labels/environment", "value": "production" }) # 如果 labels 中存在 'app: test' 标签，则添加 annotation reloader.stakater.com/auto: "true" if labels.get('app') == 'test': if 'reloader.stakater.com/auto' not in annotations: patch.append({ "op": "add", "path": "/metadata/annotations/reloader.stakater.com~1auto", "value": "true" }) # 如果 labels 中存在 'app: mysql' 标签，则在 Pod 中添加 sidecar 容器 if labels.get('app') == 'mysql': container = { "name": "sidecar-container", "image": "registry.cn-guangzhou.aliyuncs.com/xingcangku/axingcangku:v1.1", "ports": [{"containerPort": 8080}] } patch.append({ "op": "add", "path": "/spec/containers/-", "value": container }) # 构造 AdmissionReview 响应 admission_response = { "apiVersion": "admission.k8s.io/v1", "kind": "AdmissionReview", "response": { "uid": admission_review['request']['uid'], "allowed": True, "patchType": "JSONPatch", "patch": base64.b64encode(json.dumps(patch).encode()).decode() # 对 patch 进行 Base64 编码 } } # 返回 AdmissionReview 响应 return jsonify(admission_response) except Exception as e: # 如果发生异常，返回包含错误消息的响应 return jsonify({ "apiVersion": "admission.k8s.io/v1", "kind": "AdmissionReview", "response": { "uid": admission_review['request']['uid'], "allowed": False, "status": { "message": str(e) # 将异常消息作为响应的一部分 } } }), 500 def keep_alive(): while True: time.sleep(3600) # 每小时休眠一次，保持进程活跃 if __name__ == '__main__': # 创建 SSL 上下文并加载证书 context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH) context.load_cert_chain('/certs/tls.crt', '/certs/tls.key') # 加载 SSL 证书和私钥 # 使用 SSL 上下文启动 Flask 应用，监听所有网络接口的 8080 端口 app.run(host='0.0.0.0', port=8080, ssl_context=context) 五、总结：这个测车容器主要实现了，在使用mysql为业务pod的时候有数据备份的功能。实现了定时自动备份数据的功能。六、更新可以安装ansible直接执行下面的命令部署，但是因为镜像里面的webhook.py文件的定制。 如果需要自定义功能需要按上面的步骤创建镜像然后在下面的代码中更新镜像地址即可。--- - name: Deploy Kubernetes Webhook hosts: localhost connection: local become: yes tasks: # 1. 生成 CA 私钥 - name: Generate CA private key command: openssl genrsa -out ca.key 2048 args: creates: ca.key # 2. 生成自签名 CA 证书 - name: Generate self-signed CA certificate command: > openssl req -x509 -new -nodes -key ca.key -subj "/CN=webhook-service.default.svc" -days 36500 -out ca.crt args: creates: ca.crt # 3. 创建 OpenSSL 配置文件 - name: Create OpenSSL configuration file copy: dest: webhook-openssl.cnf content: | [req] default_bits = 2048 prompt = no default_md = sha256 req_extensions = req_ext distinguished_name = dn [dn] C = CN ST = Shanghai L = Shanghai O = egonlin OU = egonlin CN = webhook-service.default.svc [req_ext] subjectAltName = @alt_names [alt_names] DNS.1 = webhook-service DNS.2 = webhook-service.default DNS.3 = webhook-service.default.svc DNS.4 = webhook-service.default.svc.cluster.local [req_distinguished_name] CN = webhook-service.default.svc [v3_req] keyUsage = critical, digitalSignature, keyEncipherment extendedKeyUsage = serverAuth subjectAltName = @alt_names [v3_ext] authorityKeyIdentifier=keyid,issuer:always basicConstraints=CA:FALSE keyUsage=keyEncipherment,dataEncipherment extendedKeyUsage=serverAuth,clientAuth subjectAltName=@alt_names # 4. 生成 Webhook 服务的私钥 - name: Generate webhook service private key command: openssl genrsa -out webhook.key 2048 args: creates: webhook.key # 5. 使用配置文件生成 CSR - name: Generate CSR command: openssl req -new -key webhook.key -out webhook.csr -config webhook-openssl.cnf args: creates: webhook.csr # 6. 生成 webhook 证书 - name: Generate webhook certificate command: > openssl x509 -req -in webhook.csr -CA ca.crt -CAkey ca.key -CAcreateserial -out webhook.crt -days 36500 -extensions v3_ext -extfile webhook-openssl.cnf args: creates: webhook.crt # 7. 删除旧的 Kubernetes Secret - name: Delete existing Kubernetes Secret command: kubectl delete secret webhook-certs --namespace=default ignore_errors: true # 8. 创建 Kubernetes Secret - name: Create Kubernetes Secret for webhook certificates command: > kubectl create secret tls webhook-certs --cert=webhook.crt --key=webhook.key --namespace=default --dry-run=client -o yaml register: secret_yaml - name: Apply Kubernetes Secret command: kubectl apply -f - args: stdin: "{{ secret_yaml.stdout }}" # 9. 创建 webhook Deployment 和 Service - name: Create webhook deployment YAML copy: dest: webhook-deployment.yaml content: | apiVersion: apps/v1 kind: Deployment metadata: name: webhook-deployment namespace: default spec: replicas: 1 selector: matchLabels: app: webhook template: metadata: labels: app: webhook spec: containers: - name: webhook image: registry.cn-guangzhou.aliyuncs.com/xingcangku/webhook:v1.0 command: [ "python", "/app/webhook.py" ] volumeMounts: - name: webhook-certs mountPath: /certs readOnly: true volumes: - name: webhook-certs secret: secretName: webhook-certs - name: Apply webhook deployment command: kubectl apply -f webhook-deployment.yaml - name: Create webhook service YAML copy: dest: webhook-service.yaml content: | apiVersion: v1 kind: Service metadata: name: webhook-service namespace: default spec: ports: - port: 443 targetPort: 443 selector: app: webhook - name: Apply webhook service command: kubectl apply -f webhook-service.yaml # 10. 生成 base64 编码的 CA 证书 - name: Create base64 encoded CA certificate shell: base64 -w 0 ca.crt > ca.crt.base64 args: creates: ca.crt.base64 # 11. 读取 base64 内容并生成 MutatingWebhookConfiguration YAML - name: Read CA base64 content slurp: src: ca.crt.base64 register: ca_base64 - name: Generate MutatingWebhookConfiguration YAML copy: dest: m-w-c.yaml content: | apiVersion: admissionregistration.k8s.io/v1 kind: MutatingWebhookConfiguration metadata: name: example-mutating-webhook webhooks: - name: example.webhook.com clientConfig: service: name: webhook-service namespace: default path: "/mutate" caBundle: "{{ ca_base64.content | b64decode }}" rules: - operations: ["CREATE"] apiGroups: [""] apiVersions: ["v1"] resources: ["pods"] admissionReviewVersions: ["v1"] sideEffects: None - name: Apply MutatingWebhookConfiguration command: kubectl apply -f m-w-c.yaml
-
k8s 滚动发布 蓝绿发布 金丝雀发布 灰度发布 先部署apiVersion: apps/v1 kind: Deployment metadata: labels: app: production name: production spec: replicas: 1 # 为了测试方便，就设置1个副本吧 selector: matchLabels: app: production strategy: {} template: metadata: labels: app: production spec: containers: - image: nginx:1.18 name: nginx --- apiVersion: v1 kind: Service metadata: labels: app: production name: production spec: ports: - port: 9999 protocol: TCP targetPort: 80 selector: app: production type: ClusterIP status: loadBalancer: {} --- apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: production spec: ingressClassName: nginx rules: - host: egon.ingress.com http: paths: - path: / pathType: Prefix backend: service: name: production port: number: 9999滚动更新apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: canary annotations: nginx.ingress.kubernetes.io/canary: 'true' # 要开启金丝雀发布机制，首先需要启用 Canary nginx.ingress.kubernetes.io/canary-weight: '30' # 分配30%流量到当前Canary版本 spec: ingressClassName: nginx rules: - host: egon.ingress.com http: paths: - path: / pathType: Prefix backend: service: name: canary port: number: 9999金丝雀apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: canary annotations: nginx.ingress.kubernetes.io/canary: 'true' # 要开启金丝雀发布机制，首先需要启用 Canary nginx.ingress.kubernetes.io/canary-by-header: canary nginx.ingress.kubernetes.io/canary-by-header-value: user-value nginx.ingress.kubernetes.io/canary-weight: '30' # 分配30%流量到当前Canary版本 spec: ingressClassName: nginx rules: - host: egon.ingress.com http: paths: - path: / pathType: Prefix backend: service: name: canary port: number: 9999灰度发布apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: canary annotations: nginx.ingress.kubernetes.io/canary: 'true' # 要开启金丝雀发布机制，首先需要启用 Canary nginx.ingress.kubernetes.io/canary-by-cookie: 'users_from_Shanghai' nginx.ingress.kubernetes.io/canary-weight: '30' # 分配30%流量到当前Canary版本 spec: ingressClassName: nginx rules: - host: egon.ingress.com http: paths: - path: / pathType: Prefix backend: service: name: canary port: number: 9999
