一、概述
其实通过 docker-compose 部署 hive 是在继上篇文章 Hadoop 部署的基础之上叠加的,Hive 做为最常用的数仓服务,所以是有必要进行集成的,感兴趣的小伙伴请认真阅读我以下内容,通过 docker-compose 部署的服务主要是用最少的资源和时间成本快速部署服务,方便小伙伴学习、测试、验证功能等等~
关于 Hadoop 部署可以查阅我以下几篇文章:
- 通过 docker-compose 快速部署 Hadoop 集群详细教程
- 通过 docker-compose 快速部署 Hadoop 集群极简教程
最好是先浏览一下Hadoop 部署的文章,如果不 care 详细过程,就可以只查阅 通过 docker-compose 快速部署 Hadoop 集群极简教程 这篇文章即可~
关于 Hive 的介绍可以查阅我以下文章:大数据Hadoop之——数据仓库Hive
二、前期准备
1)部署 docker
# 安装yum-config-manager配置工具
yum -y install yum-utils
# 建议使用阿里云yum源:(推荐)
#yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo
yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
# 安装docker-ce版本
yum install -y docker-ce
# 启动并开机启动
systemctl enable --now docker
docker --version
2)部署 docker-compose
curl -SL https://github.com/docker/compose/releases/download/v2.16.0/docker-compose-linux-x86_64 -o /usr/local/bin/docker-compose
chmod +x /usr/local/bin/docker-compose
docker-compose --version
三、创建网络
# 创建,注意不能使用hadoop_network,要不然启动hs2服务的时候会有问题!!!
docker network create hadoop-network
# 查看
docker network ls
四、MySQL 部署
1)mysql 镜像
docker pull mysql:5.7
docker tag mysql:5.7 registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/mysql:5.7
2)配置
mkdir -p conf/ data/db/
cat >conf/my.cnf<<EOF
[mysqld]
character-set-server=utf8
log-bin=mysql-bin
server-id=1
pid-file = /var/run/mysqld/mysqld.pid
socket = /var/run/mysqld/mysqld.sock
datadir = /var/lib/mysql
sql_mode=STRICT_TRANS_TABLES,NO_ZERO_IN_DATE,NO_ZERO_DATE,ERROR_FOR_DIVISION_BY_ZERO,NO_AUTO_CREATE_USER,NO_ENGINE_SUBSTITUTION
symbolic-links=0
secure_file_priv =
wait_timeout=120
interactive_timeout=120
default-time_zone = '+8:00'
skip-external-locking
skip-name-resolve
open_files_limit = 10240
max_connections = 1000
max_connect_errors = 6000
table_open_cache = 800
max_allowed_packet = 40m
sort_buffer_size = 2M
join_buffer_size = 1M
thread_cache_size = 32
query_cache_size = 64M
transaction_isolation = READ-COMMITTED
tmp_table_size = 128M
max_heap_table_size = 128M
log-bin = mysql-bin
sync-binlog = 1
binlog_format = ROW
binlog_cache_size = 1M
key_buffer_size = 128M
read_buffer_size = 2M
read_rnd_buffer_size = 4M
bulk_insert_buffer_size = 64M
lower_case_table_names = 1
explicit_defaults_for_timestamp=true
skip_name_resolve = ON
event_scheduler = ON
log_bin_trust_function_creators = 1
innodb_buffer_pool_size = 512M
innodb_flush_log_at_trx_commit = 1
innodb_file_per_table = 1
innodb_log_buffer_size = 4M
innodb_log_file_size = 256M
innodb_max_dirty_pages_pct = 90
innodb_read_io_threads = 4
innodb_write_io_threads = 4
EOF
3)编排
version: '3'
services:
db:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/mysql:5.7 #mysql版本
container_name: mysql
hostname: mysql
volumes:
- ./data/db:/var/lib/mysql
- ./conf/my.cnf:/etc/mysql/mysql.conf.d/mysqld.cnf
restart: always
ports:
- 13306:3306
networks:
- hadoop-network
environment:
MYSQL_ROOT_PASSWORD: 123456 #访问密码
secure_file_priv:
healthcheck:
test: ["CMD-SHELL", "curl -I localhost:3306 || exit 1"]
interval: 10s
timeout: 5s
retries: 3
# 连接外部网络
networks:
hadoop-network:
external: true
4)部署 mysql
docker-compose -f mysql-compose.yaml up -d
docker-compose -f mysql-compose.yaml ps
# 登录容器
mysql -uroot -p123456
四、Hive 部署
1)下载 hive
下载地址:http://archive.apache.org/dist/hive
# 下载
wget http://archive.apache.org/dist/hive/hive-3.1.3/apache-hive-3.1.3-bin.tar.gz
# 解压
tar -zxvf apache-hive-3.1.3-bin.tar.gz
2)配置
images/hive-config/hive-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- 配置hdfs存储目录 -->
<property>
<name>hive.metastore.warehouse.dir</name>
<value>/user/hive_remote/warehouse</value>
</property>
<property>
<name>hive.metastore.local</name>
<value>false</value>
</property>
<!-- 所连接的 MySQL 数据库的地址,hive_local是数据库,程序会自动创建,自定义就行 -->
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://mysql:3306/hive_metastore?createDatabaseIfNotExist=true&useSSL=false&serverTimezone=Asia/Shanghai</value>
</property>
<!-- MySQL 驱动 -->
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<!--<value>com.mysql.cj.jdbc.Driver</value>-->
<value>com.mysql.jdbc.Driver</value>
</property>
<!-- mysql连接用户 -->
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
</property>
<!-- mysql连接密码 -->
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>123456</value>
</property>
<!--元数据是否校验-->
<property>
<name>hive.metastore.schema.verification</name>
<value>false</value>
</property>
<property>
<name>system:user.name</name>
<value>root</value>
<description>user name</description>
</property>
<property>
<name>hive.metastore.uris</name>
<value>thrift://hive-metastore:9083</value>
</property>
<!-- host -->
<property>
<name>hive.server2.thrift.bind.host</name>
<value>0.0.0.0</value>
<description>Bind host on which to run the HiveServer2 Thrift service.</description>
</property>
<!-- hs2端口 默认是10000-->
<property>
<name>hive.server2.thrift.port</name>
<value>10000</value>
</property>
<property>
<name>hive.server2.active.passive.ha.enable</name>
<value>true</value>
</property>
</configuration>
3)启动脚本
#!/usr/bin/env sh
wait_for() {
echo Waiting for $1 to listen on $2...
while ! nc -z $1 $2; do echo waiting...; sleep 1s; done
}
start_hdfs_namenode() {
if [ ! -f /tmp/namenode-formated ];then
${HADOOP_HOME}/bin/hdfs namenode -format >/tmp/namenode-formated
fi
${HADOOP_HOME}/bin/hdfs --loglevel INFO --daemon start namenode
tail -f ${HADOOP_HOME}/logs/*namenode*.log
}
start_hdfs_datanode() {
wait_for $1 $2
${HADOOP_HOME}/bin/hdfs --loglevel INFO --daemon start datanode
tail -f ${HADOOP_HOME}/logs/*datanode*.log
}
start_yarn_resourcemanager() {
${HADOOP_HOME}/bin/yarn --loglevel INFO --daemon start resourcemanager
tail -f ${HADOOP_HOME}/logs/*resourcemanager*.log
}
start_yarn_nodemanager() {
wait_for $1 $2
${HADOOP_HOME}/bin/yarn --loglevel INFO --daemon start nodemanager
tail -f ${HADOOP_HOME}/logs/*nodemanager*.log
}
start_yarn_proxyserver() {
wait_for $1 $2
${HADOOP_HOME}/bin/yarn --loglevel INFO --daemon start proxyserver
tail -f ${HADOOP_HOME}/logs/*proxyserver*.log
}
start_mr_historyserver() {
wait_for $1 $2
${HADOOP_HOME}/bin/mapred --loglevel INFO --daemon start historyserver
tail -f ${HADOOP_HOME}/logs/*historyserver*.log
}
start_hive_metastore() {
if [ ! -f ${HIVE_HOME}/formated ];then
schematool -initSchema -dbType mysql --verbose > ${HIVE_HOME}/formated
fi
$HIVE_HOME/bin/hive --service metastore
}
start_hive_hiveserver2() {
$HIVE_HOME/bin/hive --service hiveserver2
}
case $1 in
hadoop-hdfs-nn)
start_hdfs_namenode
;;
hadoop-hdfs-dn)
start_hdfs_datanode $2 $3
;;
hadoop-yarn-rm)
start_yarn_resourcemanager
;;
hadoop-yarn-nm)
start_yarn_nodemanager $2 $3
;;
hadoop-yarn-proxyserver)
start_yarn_proxyserver $2 $3
;;
hadoop-mr-historyserver)
start_mr_historyserver $2 $3
;;
hive-metastore)
start_hive_metastore $2 $3
;;
hive-hiveserver2)
start_hive_hiveserver2 $2 $3
;;
*)
echo "请输入正确的服务启动命令~"
;;
esac
4)构建镜像 Dockerfile
FROM registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop:v1
COPY hive-config/* ${HIVE_HOME}/conf/
COPY bootstrap.sh /opt/apache/
COPY mysql-connector-java-5.1.49/mysql-connector-java-5.1.49-bin.jar ${HIVE_HOME}/lib/
RUN sudo mkdir -p /home/hadoop/ && sudo chown -R hadoop:hadoop /home/hadoop/
#RUN yum -y install which
开始构建镜像
# 构建镜像
docker build -t registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1 . --no-cache
# 推送镜像(可选)
docker push registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
### 参数解释
# -t:指定镜像名称
# . :当前目录Dockerfile
# -f:指定Dockerfile路径
# --no-cache:不缓存
5)编排
version: '3'
services:
hadoop-hdfs-nn:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-hdfs-nn
hostname: hadoop-hdfs-nn
restart: always
privileged: true
env_file:
- .env
ports:
- "30070:${HADOOP_HDFS_NN_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-hdfs-nn"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_HDFS_NN_PORT} || exit 1"]
interval: 20s
timeout: 20s
retries: 3
hadoop-hdfs-dn-0:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-hdfs-dn-0
hostname: hadoop-hdfs-dn-0
restart: always
depends_on:
- hadoop-hdfs-nn
env_file:
- .env
ports:
- "30864:${HADOOP_HDFS_DN_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-hdfs-dn hadoop-hdfs-nn ${HADOOP_HDFS_NN_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_HDFS_DN_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-hdfs-dn-1:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-hdfs-dn-1
hostname: hadoop-hdfs-dn-1
restart: always
depends_on:
- hadoop-hdfs-nn
env_file:
- .env
ports:
- "30865:${HADOOP_HDFS_DN_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-hdfs-dn hadoop-hdfs-nn ${HADOOP_HDFS_NN_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_HDFS_DN_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-hdfs-dn-2:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-hdfs-dn-2
hostname: hadoop-hdfs-dn-2
restart: always
depends_on:
- hadoop-hdfs-nn
env_file:
- .env
ports:
- "30866:${HADOOP_HDFS_DN_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-hdfs-dn hadoop-hdfs-nn ${HADOOP_HDFS_NN_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_HDFS_DN_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-yarn-rm:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-yarn-rm
hostname: hadoop-yarn-rm
restart: always
env_file:
- .env
ports:
- "30888:${HADOOP_YARN_RM_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-yarn-rm"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "netstat -tnlp|grep :${HADOOP_YARN_RM_PORT} || exit 1"]
interval: 20s
timeout: 20s
retries: 3
hadoop-yarn-nm-0:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-yarn-nm-0
hostname: hadoop-yarn-nm-0
restart: always
depends_on:
- hadoop-yarn-rm
env_file:
- .env
ports:
- "30042:${HADOOP_YARN_NM_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-yarn-nm hadoop-yarn-rm ${HADOOP_YARN_RM_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_YARN_NM_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-yarn-nm-1:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-yarn-nm-1
hostname: hadoop-yarn-nm-1
restart: always
depends_on:
- hadoop-yarn-rm
env_file:
- .env
ports:
- "30043:${HADOOP_YARN_NM_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-yarn-nm hadoop-yarn-rm ${HADOOP_YARN_RM_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_YARN_NM_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-yarn-nm-2:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-yarn-nm-2
hostname: hadoop-yarn-nm-2
restart: always
depends_on:
- hadoop-yarn-rm
env_file:
- .env
ports:
- "30044:${HADOOP_YARN_NM_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-yarn-nm hadoop-yarn-rm ${HADOOP_YARN_RM_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "curl --fail http://localhost:${HADOOP_YARN_NM_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-yarn-proxyserver:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-yarn-proxyserver
hostname: hadoop-yarn-proxyserver
restart: always
depends_on:
- hadoop-yarn-rm
env_file:
- .env
ports:
- "30911:${HADOOP_YARN_PROXYSERVER_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-yarn-proxyserver hadoop-yarn-rm ${HADOOP_YARN_RM_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "netstat -tnlp|grep :${HADOOP_YARN_PROXYSERVER_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hadoop-mr-historyserver:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hadoop-mr-historyserver
hostname: hadoop-mr-historyserver
restart: always
depends_on:
- hadoop-yarn-rm
env_file:
- .env
ports:
- "31988:${HADOOP_MR_HISTORYSERVER_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hadoop-mr-historyserver hadoop-yarn-rm ${HADOOP_YARN_RM_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "netstat -tnlp|grep :${HADOOP_MR_HISTORYSERVER_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 3
hive-metastore:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hive-metastore
hostname: hive-metastore
restart: always
depends_on:
- hadoop-hdfs-dn-2
env_file:
- .env
ports:
- "30983:${HIVE_METASTORE_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hive-metastore hadoop-hdfs-dn-2 ${HADOOP_HDFS_DN_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "netstat -tnlp|grep :${HIVE_METASTORE_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 5
hive-hiveserver2:
image: registry.cn-hangzhou.aliyuncs.com/bigdata_cloudnative/hadoop_hive:v1
user: "hadoop:hadoop"
container_name: hive-hiveserver2
hostname: hive-hiveserver2
restart: always
depends_on:
- hive-metastore
env_file:
- .env
ports:
- "31000:${HIVE_HIVESERVER2_PORT}"
command: ["sh","-c","/opt/apache/bootstrap.sh hive-hiveserver2 hive-metastore ${HIVE_METASTORE_PORT}"]
networks:
- hadoop-network
healthcheck:
test: ["CMD-SHELL", "netstat -tnlp|grep :${HIVE_HIVESERVER2_PORT} || exit 1"]
interval: 30s
timeout: 30s
retries: 5
# 连接外部网络
networks:
hadoop-network:
external: true
6)开始部署
docker-compose -f docker-compose.yaml up -d
# 查看
docker-compose -f docker-compose.yaml ps
简单测试验证
【问题】如果出现以下类似的错误,是因为多次启动,之前的数据还在,但是datanode的IP是已经变了的(宿主机部署就不会有这样的问题,因为宿主机的IP是固定的),所以需要刷新节点,当然也可清理之前的旧数据,不推荐清理旧数据,推荐使用刷新节点的方式(如果有对外挂载的情况下,像我这里没有对外挂载,是因为之前旧容器还在,下面有几种解决方案):
org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.server.protocol.DisallowedDatanodeException): Datanode denied communication with namenode because the host is not in the include-list: DatanodeRegistration(172.30.0.12:9866, datanodeUuid=f8188476-4a88-4cd6-836f-769d510929e4, infoPort=9864, infoSecurePort=0, ipcPort=9867, storageInfo=lv=-57;cid=CID-f998d368-222c-4a9a-88a5-85497a82dcac;nsid=1840040096;c=1680661390829)
【解决方案】文章来源:https://www.toymoban.com/news/detail-703791.html
- 删除旧容器重启启动
# 清理旧容器
docker rm `docker ps -a|grep 'Exited'|awk '{print $1}'`
# 重启启动服务
docker-compose -f docker-compose.yaml up -d
# 查看
docker-compose -f docker-compose.yaml ps
- 登录 namenode 刷新 datanode
docker exec -it hadoop-hdfs-nn hdfs dfsadmin -refreshNodes
- 登录 任意节点刷新 datanode
# 这里以 hadoop-hdfs-dn-0 为例
docker exec -it hadoop-hdfs-dn-0 hdfs dfsadmin -fs hdfs://hadoop-hdfs-nn:9000 -refreshNodes
到此,Hive 的容器化部署就完成了,有任何疑问的小伙伴欢迎给我留言,后续会持续更新相关技术文章,也可关注我的公众号【大数据与云原生技术分享】深入交流技术或私信咨询问题~文章来源地址https://www.toymoban.com/news/detail-703791.html
到了这里,关于通过 docker-compose 快速部署 Hive 详细教程的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!