Kubernetes运行大数据组件-运行hive

小森饭2024-10-30 13:46

部署组件

● mysql

● hive-metastore

● hive-server2

配置文件

xml 复制代码 
apiVersion: v1
kind: ConfigMap
metadata:
  name: hive
data:
  hive-site.xml: |-
    <?xml version="1.0"?>
    <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
    <configuration>
        <property>
            <name>javax.jdo.option.ConnectionUserName</name>
            <value>root</value>
        </property>
        <property>
            <name>javax.jdo.option.ConnectionPassword</name>
            <value>xxxxx</value>
        </property>
        <property>
            <name>javax.jdo.option.ConnectionURL</name>
            <value>jdbc:mysql://192.168.199.58:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false</value>
            <!-- 根据角色修改IP地址 -->
        </property>
        <property>
            <name>javax.jdo.option.ConnectionDriverName</name>
            <value>com.mysql.jdbc.Driver</value>
        </property>
        <property>
            <name>hive.cli.print.current.db</name>
            <value>true</value>
        </property>
        <property>
            <name>hive.cli.print.header</name>
            <value>true</value>
        </property>
        <property>
            <name>hive.exec.post.hooks</name>
            <value>org.apache.atlas.hive.hook.HiveHook</value>
        </property>
        <property>
            <name>hive.metastore.uris</name>
            <value>thrift://192.168.199.57:9083</value>
            <!-- 根据角色修改IP地址 -->
        </property>
        <property>
            <name>hive.exec.scratchdir</name>
            <value>/user/hive/tmp</value>
        </property>
        <property>
            <name>hive.metastore.warehouse.dir</name>
            <value>/user/hive/warehouse</value>
        </property>
        <property>
            <name>hive.querylog.location</name>
            <value>/tmp/hive/querylog</value>
        </property>
        <property>
            <name>hive.server2.webui.host</name>
            <value>0.0.0.0</value>
        </property>
        <property>
            <name>hive.server2.webui.port</name>
            <value>10002</value>
        </property>
        <property>
            <name>hive.server2.thrift.port</name>
            <value>10000</value>
        </property>
    </configuration>

mysql部署文件

yaml 复制代码 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: hive-mysql
  labels:
    app: hive-mysql
spec:
  selector:
    matchLabels:
      app: hive-mysql
  replicas: 1
  template:
    metadata:
      labels:
        app: hive-mysql
    spec:
      containers:
        - name: hive-mysql
          image: mysql:5.7.32
          imagePullPolicy: IfNotPresent
          resources:
            limits:
              cpu: 200m
              memory: 500Mi
          env:
            - name: MYSQL_ROOT_PASSWORD
              value: xxxxxx
          args:
            - --character-set-server=utf8mb4
            - --collation-server=utf8mb4_unicode_ci
          volumeMounts:
            - name: localtime
              mountPath: /etc/localtime
            - name: data
              mountPath: /var/lib/mysql
      volumes:
        - name: localtime
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai
        - name: data
          hostPath:
            path: /var/lib/mysql
      restartPolicy: Always
      hostNetwork: true
      hostAliases:
        - ip: "192.168.199.56"
          hostnames:
            - "bigdata199056"
        - ip: "192.168.199.57"
          hostnames:
            - "bigdata199057"
        - ip: "192.168.199.58"
          hostnames:
            - "bigdata199058"
      nodeSelector:
        hive-mysql: "true"
      tolerations:
        - key: "bigdata"
          value: "true"
          operator: "Equal"
          effect: "NoSchedule"

hive metastore部署文件

yaml 复制代码 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: hive-metastore
  labels:
    app: hive-metastore
spec:
  selector:
    matchLabels:
      app: hive-metastore
  replicas: 1
  template:
    metadata:
      labels:
        app: hive-metastore
    spec:
      initContainers:
        - name: mysql-init
          image: hive:2.3.8
          imagePullPolicy: IfNotPresent
          command:	# 通过schematool校验数据库，决定是否初始化mysql
            - "sh"
            - "-c"
            - "if schematool -dbType mysql -validate; then schematool -dbType mysql -initSchema; fi"
          volumeMounts:
            - name: localtime
              mountPath: /etc/localtime
            - name: hive-config
              mountPath: /opt/hive/conf/hive-site.xml
              subPath: hive-site.xml
      containers:
        - name: hive-metastore
          image: harbor.gistack.cn/library/hive:2.3.8
          imagePullPolicy: IfNotPresent
          resources:
            limits:																					# 根据规划修改
              cpu: 2000m
              memory: 4Gi
          command:
            - "sh"
            - "-c"
            - "hive --service metastore -v"
          volumeMounts:
            - name: localtime
              mountPath: /etc/localtime
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/core-site.xml
              subPath: core-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/hdfs-site.xml
              subPath: hdfs-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/yarn-site.xml
              subPath: yarn-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/mapred-site.xml
              subPath: mapred-site.xml
            - name: hive-config
              mountPath: /opt/hive/conf/hive-site.xml
              subPath: hive-site.xml
      volumes:
        - name: localtime
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai
        - name: hadoop-config
          configMap:
            name: hadoop
        - name: hive-config
          configMap:
            name: hive
      restartPolicy: Always
      hostNetwork: true
      hostAliases:
        - ip: "192.168.199.56"
          hostnames:
            - "bigdata199056"
        - ip: "192.168.199.57"
          hostnames:
            - "bigdata199057"
        - ip: "192.168.199.58"
          hostnames:
            - "bigdata199058"
      nodeSelector:
        hive-metastore: "true"
      tolerations:
        - key: "bigdata"
          value: "true"
          operator: "Equal"
          effect: "NoSchedule"

mysql和hive-metastore部署

shell 复制代码 
> kubectl.exe create -f .\hive-config.yaml -n bigdata
configmap/hive created
> kubectl.exe create -f .\hive-mysql.yaml -n bigdata 
deployment.apps/hive-mysql created
> kubectl.exe create -f .\hive-metastore.yaml -n bigdata
deployment.apps/hive-metastore created
>

hive-metastore初始化数据库和运行情况：

hvie-server2部署

yaml 复制代码 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: hiveserver2
  labels:
    app: hiveserver2
spec:
  selector:
    matchLabels:
      app: hiveserver2
  replicas: 1
  template:
    metadata:
      labels:
        app: hiveserver2
    spec:
      containers:
        - name: hiveserver2
          image: hive:2.3.8
          imagePullPolicy: IfNotPresent
          resources:
            limits:
              cpu: 2000m
              memory: 4Gi
          command:
            - "sh"
            - "-c"
            - "hive --service hiveserver2"
          volumeMounts:
            - name: localtime
              mountPath: /etc/localtime
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/core-site.xml
              subPath: core-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/hdfs-site.xml
              subPath: hdfs-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/yarn-site.xml
              subPath: yarn-site.xml
            - name: hadoop-config
              mountPath: /opt/hadoop/etc/hadoop/mapred-site.xml
              subPath: mapred-site.xml
            - name: hive-config
              mountPath: /opt/hive/conf/hive-site.xml
              subPath: hive-site.xml
      volumes:
        - name: localtime
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai
        - name: hadoop-config
          configMap:
            name: hadoop
        - name: hive-config
          configMap:
            name: hive
      restartPolicy: Always
      hostNetwork: true
      hostAliases:
        - ip: "192.168.199.56"
          hostnames:
            - "bigdata199056"
        - ip: "192.168.199.57"
          hostnames:
            - "bigdata199057"
        - ip: "192.168.199.58"
          hostnames:
            - "bigdata199058"
      nodeSelector:
        hiveserver2: "true"
      tolerations:
        - key: "bigdata"
          value: "true"
          operator: "Equal"
          effect: "NoSchedule"
shell 复制代码 
> kubectl.exe create -f .\hiveserver2.yaml -n bigdata
deployment.apps/hiveserver2 created
>

访问hive web服务：

通过SQL客户端连接：

建表测试：

插入数据，查看任务：

相关推荐
双层吉士憨包18 分钟前
2026数据爬虫实战：如何高效采集Google地图数据的动态IP策略
大数据·网络·人工智能
历程里程碑19 分钟前
滑动窗口------滑动窗口最大值
大数据·python·算法·elasticsearch·搜索引擎·flask·tornado
YangYang9YangYan20 分钟前
大数据与会计专业学习发展指南
大数据·学习
TDengine （老段）23 分钟前
TDengine TSDB 3.4.0.0 上线：虚拟表、流计算性能显著提升，安全能力全面进阶
大数据·数据库·物联网·安全·时序数据库·tdengine·涛思数据
Leo.yuan23 分钟前
制造业常用BOM详解：单层BOM、多层BOM、工艺BOM、虚拟BOM
大数据·数据库·信息可视化·bom
麦兜*25 分钟前
深入剖析云原生Service Mesh数据平面Envoy核心架构：基于xDS协议与WebAssembly实现动态流量管理与安全策略的微服务治理实战指南
云原生·架构·service_mesh
开利网络25 分钟前
第2天：构建多维标签体系——立体化勾勒客户轮廓
大数据·微信小程序
hg011828 分钟前
湖南对非贸易规模连续7年居中西部第一
大数据
牛奶咖啡1334 分钟前
Prometheus+Grafana构建云原生分布式监控系统（十五）_Prometheus中PromQL使用(二)
云原生·prometheus·集合运算·对查询结果排序·直方图原理·统计掉线的实例·检查节点或指标是否存在
雷焰财经1 小时前
中和农信：以综合服务为笔，绘就农业农村现代化新画卷
大数据·金融
热门推荐
01GitHub 镜像站点02OpenCode 入门教程：介绍 · 安装 · 配置第三方 API (如 Claude)032025 年大语言模型发展回顾：关键突破、意外转折与 2026 年展望04Claude Code Skills 实用使用手册05Clawdbot 中文汉化版 接入微信、飞书06Claude Code + GLM4.7 避坑指南：解决 Unable to connect to Anthropic services07OpenClaw部署与配置教程：在Mac mini上接入国产大模型与飞书08在Trae中使用Pencil MCP09UV安装并设置国内源10一文了解国产算子编程语言 TileLang，TileLang 对国产开源生态的影响与启示