Mac M3 Pro 部署Spark-2.3.2 On Hive-3.1.3

mac的配置如下

1、下载安装包

官网

Apache Projects Releases

在search中搜索hadoop、hive

spark : Index of /dist/spark/spark-2.3.2

网盘

Hadoop https://pan.baidu.com/s/1p4BXq2mvby2B76lmpiEjnA?pwd=r62r 提取码: r62r

Hive https://pan.baidu.com/s/12PUQfy_mi914wd6p7iWsBw?pwd=bnrr 提取码: bnrr

Spark二进制包 https://pan.baidu.com/s/1fJ5yRH_9K7VFlixBJ1MH1g?pwd=v987 提取码: v987

Spark源码打好的包 https://pan.baidu.com/s/1H0OxQOnuswBfoIZjNB8jEA?pwd=9yks 提取码: 9yks

Spark源码包 https://pan.baidu.com/s/1p_IRlhwT1eQxrIK3jVHbww?pwd=bhkx 提取码: bhkx

Zookeeper https://pan.baidu.com/s/1j6iy5bZkrY-GKGItenRB2w?pwd=irrx 提取码: irrx

mysql-connector-java-8.0.15.jar https://pan.baidu.com/s/1YHVMrG66lIHVHEH-jcUsVQ?pwd=4ipc 提取码: 4ipc

与hive兼容的spark版本可通过hive源码的pom.xml中查看

2、解压安装

Hadoop、Zookeeper 请查看

Mac M3 Pro安装Hadoop-3.3.6-CSDN博客

Mac M3 Pro 安装 Zookeeper-3.4.6-CSDN博客

mysql 可直接使用 brew install mysql 进行安装

bash 复制代码
# 将安装包移动到目标目录
mv ~/Download/apache-hive-3.1.3-bin.tar.gz /opt/module
mv ~/Download/spark-2.3.2-bin-without-hadoop.tgz /opt/module

# 进入目标目录
cd /opt/module

# 解压安装包
tar -zxvf apache-hive-3.1.3-bin.tar.gz
tar -zxvf spark-2.3.2-bin-without-hadoop.tgz

# 修改目录名
mv apache-hive-3.1.3-bin hive
mv spark-2.3.2-bin-without-hadoop spark

# 添加mysql-connector-java-8.0.15.jar到lib目录
mv ~/Download/mysql-connector-java-8.0.15.jar /opt/module/hive/lib

# 添加环境变量

sudo vim /etc/profile

export JAVA_HOME="/Library/Java/JavaVirtualMachines/jdk8/Contents/Home"
export MYSQL_HOME="/opt/homebrew/Cellar/mysql@8.0/8.0.36_1"

export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export HADOOP_HOME=/opt/module/hadoop
export JAVA_LIBRARY_PATH="$HADOOP_HOME/lib/native"
export HADOOP_COMMON_LIB_NATIVE_DIR="$HADOOP_HOME/lib/native"
export HADOOP_LOG_DIR=$HADOOP_HOME/logs
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HIVE_HOME=/opt/module/hive
export HIVE_CONF_DIR=$HIVE_HOME/conf
export HIVE_AUX_JARS_PATH=$HIVE_HOME/lib
export HADOOP_USER_NAME=hdfs
export SPARK_HOME=/opt/module/spark
export ZOOKEEPER_HOME=/opt/module/zookeeper
export PATH="$JAVA_HOME/bin:$MYSQL_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin:$SPARK_HOME/bin:$ZOOKEEPER_HOME/bin:$PATH:."

# 保存后使其生效
source /etc/profile

3、修改配置

bash 复制代码
cd /opt/module/hive/conf
cp hive-env.sh.template hive-env.sh
cp hive-default.xml.template hive-site.xml
vim hive-env.sh
# 添加
export HADOOP_HEAPSIZE=4096

vim hive-site.xml

# 下面的内容与本地环境比较,存在的则修改,不存在的则添加
XML 复制代码
<property>
    <name>hive.execution.engine</name>
    <value>spark</value>
  </property>
<property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/user/hive/warehouse</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://127.0.0.1:3306/hive?createDatabaseIfNotExist=true&amp;useSSL=false</value>
  </property>
   <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.cj.jdbc.Driver</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
  </property>
    <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>root</value>
  </property>
  <!--元数据是否校验-->
   <property>
    <name>hive.metastore.schema.verification</name>
    <value>false</value>
  </property>
   <property>
    <name>hive.server2.thrift.port</name>
    <value>10000</value>
    <description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'binary'.</description>
  </property>
  <property>
    <name>spark.yarn.jars</name>
    <value>hdfs:///spark/spark-jars/*.jar</value>
  </property>
  <property>
    <name>hive.spark.client.connect.timeout</name>
    <value>1000ms</value>
  </property>
  <property>
    <name>hive.exec.scratchdir</name> 
    <value>/tmp/hive</value>
  </property>
  <property>
    <name>hive.querylog.location</name>
    <value>${java.io.tmpdir}/${user.name}</value>
  </property>
   <property>
    <name>hive.server2.thrift.port</name>
    <value>10000</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.long.polling.timeout</name>
    <value>5000ms</value>
  </property>
  
   <property>
    <name>hive.server2.enable.doAs</name>
    <value>false</value>
  </property>
  
  <property>
    <name>spark.home</name>
    <value>/opt/module/spark</value>
  </property> 
  <property>
    <name>spark.master</name>
    <value>spark://127.0.0.1:7077</value>
  </property>
    <property>
        <name>spark.submit.deployMode</name>
        <value>client</value>
    </property> 
    <property>
        <name>spark.eventLog.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>spark.eventLog.dir</name>
        <value>hdfs:///spark/log</value>
    </property>
    <property>
        <name>spark.serializer</name>
        <value>org.apache.spark.serializer.KryoSerializer</value>
    </property>
    <property>
        <name>spark.executor.memeory</name>
        <value>8g</value>
    </property>
    <property>
        <name>spark.driver.memeory</name>
        <value>8g</value>
    </property>
    <property>
        <name>spark.executor.extraJavaOptions</name>
        <value>-XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"</value>
    </property>
    <property>
        <name>hive.support.concurrency</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.exec.dynamic.partition.mode</name>
        <value>nonstrict</value>
    </property>
bash 复制代码
cd /opt/module/spark/conf
cp slaves.template slaves
vim slaves

# 末尾添加
127.0.0.1

cp spark-env.sh.template spark-env.sh

vim spark-env.sh

# 末尾添加

export JAVA_HOME=/Library/Java/JavaVirtualMachines/jdk8/Contents/Home
export SPARK_DIST_CLASSPATH=$(/opt/module/hadoop/bin/hadoop classpath)
export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop/

export SPARK_MASTER_HOST=127.0.0.1
export SPARK_MASTER_PORT=7077
export SPARK_MASTER_HOST=127.0.0.1
export SPARK_LOCAL_IP=127.0.0.1
export SPARK_EXECUTOR_MEMORY=8192m

cp spark-defaults.conf.template spark-defaults.conf

vim spark-defaults.conf

# 末尾添加

spark.master                     spark://master:7077
spark.home                       /opt/module/spark
spark.eventLog.enabled           true
spark.eventLog.dir               hdfs:///spark/log
spark.serializer                 org.apache.spark.serializer.KryoSerializer
spark.executor.memory            4g
spark.driver.memory              4g
spark.executor.extraJavaOptions  -XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"
spark.yarn.archive               hdfs:///spark/jars/spark2.3.2-without-hive-libs.jar
spark.yarn.jars                  hdfs:///spark/jars/spark2.3.2-without-hive-libs.jar


# 拷贝hive-site.xml到spark的conf目录

cp /opt/module/hive/conf/hive-site.xml /opt/module/spark/conf

4、将spark的jars上传到hdfs

bash 复制代码
# hdfs上创建必要的目录
hdfs dfs -mkdir /tmp
hdfs dfs -mkdir /tmp/hive
hdfs dfs -mkdir /tmp/logs
hdfs dfs -mkdir /tmp/spark

hdfs dfs -mkdir /spark
hdfs dfs -mkdir /spark/jars
hdfs dfs -mkdir /spark/spark-jars
hdfs dfs -mkdir /spark/log

# 安装目录创建目录
mkdir -p  $SPARK_HOME/work  $SPARK_HOME/logs  $SPARK_HOME/run
mkdir -p  $HIVE_HOME/logs

# Spark 安装包默认会缺少 log4j slf4j 和 hadoop-comment之类的jar包,需要从hadoop、hive按照包目录中去复制到jars下去,如果没有就从开发时的maven仓库中去拷贝,或者到下载的spark-package-2.3.2.tgz中获取

slf4j-api-1.7.21.jar
slf4j-log4j12-1.7.21.jar
log4j-1.2-api-2.17.1.jar
log4j-api-2.17.1.jar
log4j-core-2.17.1.jar
log4j-slf4j-impl-2.17.1.jar
log4j-web-2.17.1.jar
hadoop-common-3.3.6.jar
spark-network-common_2.11-2.3.2.jar

# 进入spark安装包目录,将jars进行打包
cd /opt/module/spark

jar cv0f spark-2.3.2-without-hive-libs.jar -C ./jars .

# 在hdfs上创建存放jar包目录
hdfs dfs -put spark2.3.2-without-hive-libs.jar /spark/jars/
hdfs dfs -put jars/* /spark/spark-jars

5、mysql中创建hive库

sql 复制代码
CREATE DATABASE hive;

6、hive初始化数据库

bash 复制代码
cd /opt/module/hive/bin

schematool -initSchema -dbType mysql --verbose

7、启动Spark

bash 复制代码
# 先跑一下测试示例验证spark是否正常
cd /opt/module/spark/bin

spark-submit \
--class org.apache.spark.examples.SparkPi \
--master yarn \
--deploy-mode client \
--driver-memory 1G \
--num-executors 3 \
--executor-memory 1G \
--executor-cores 1 \
/opt/module/spark/examples/jars/spark-examples_*.jar 10

# 如果出现下面的计算结果则表示成功
Pi is roughly 3.1391191391191393

# 启动spark
cd ..
./bin/start-all.sh

# 通过jps查看进程是否正常
jps -l

# 查看是否有如下进程
org.apache.spark.deploy.master.Master
org.apache.spark.deploy.worker.Worker
org.apache.spark.executor.CoarseGrainedExecutorBackend

# 如未启动成功请到日志目录中/opt/module/spark/logs 查看时间为最近的日志文件,根据报错进程排查
# 启动成功后可访问web ui界面,打开地址 http://127.0.0.1:8080/

8、启动HIVE

bash 复制代码
cd /opt/module/hive

nohup ./bin/hive --service metastore &
nohup ./bin/hive --service hiveserver2 &

# 检查是否启动成功

ps -ef | grep HiveMetaStore

ps -ef | grep hiveserver2

# 如果启动失败 可以tail -999f nohup.out文件

# 如果成功则可以看下hive的webui界面,http://127.0.0.1:10002/

9、检查是否成功

bash 复制代码
# 使用beeline 进入hive
beeline -u 'jdbc:hive2://127.0.0.1:10000'

select version();

select current_user();

set hive.execution.engine;

# 创建表 t1

CREATE TABLE `t1`(`id` bigint,`name` string,`address` string);

# 向表t1中插入数据

INSERT INTO t1 VALUES(1,'one','beijing'),(2,'two','shanghai'),(3,'three','guangzhou'),(4,'four','shenzhen'),(5,'five','huzhou'),(6,'six','jiaxing'),(7,'seven','ningbo'),(8,'eight','shaoxing'),(9,'nine','nanjing');

10、执行表操作后查看控制台

参考地址

https://blog.csdn.net/qq_35745940/article/details/122152096

https://www.cnblogs.com/lenmom/p/10356643.html

相关推荐
说私域15 分钟前
社交电商专业赋能高校教育与产业协同发展:定制开发AI智能名片及2+1链动商城小程序的创新驱动
大数据·人工智能·小程序
WeeJot嵌入式2 小时前
macOS开发环境配置与应用开发指南
macos
Kika写代码2 小时前
【大数据技术基础】 课程 第8章 数据仓库Hive的安装和使用 大数据基础编程、实验和案例教程(第2版)
大数据·数据仓库·hive
okmacong3 小时前
4、MAC地址、ARP协议解析
服务器·网络·macos
zhixingheyi_tian3 小时前
Spark 之 SparkSessionExtensions
大数据·分布式·spark
ProtonBase3 小时前
分布式 Data Warebase - 构筑 AI 时代数据基石
大数据·数据库·数据仓库·人工智能·分布式·数据分析·数据库系统
Mephisto.java3 小时前
【大数据学习 | Spark-Core】Spark的分区器(HashPartitioner和RangePartitioner)
大数据·elasticsearch·oracle·spark·sqlite·flume·memcached
菜鸟小贤贤3 小时前
mac安装Pytest、Allure、brew
python·macos·自动化·pytest
叶子上的考拉4 小时前
Spark SQL操作
大数据·sql·spark
小江村儿的文杰4 小时前
UE4 iOS Package的过程与XCode工程中没有游戏Content的原因
macos·ios·ue4·xcode