Hive的安装和启动

376 阅读1分钟

一、前提准备说明

hive安装前要安装好以下服务:
1、jdk(不讲解)
2、hadoop
3、mysql
4、hive

二、hadoop(单节点)

1、环境变量配置
// 编辑系统全局配置文件
vim /etc/profile
// 新增如下内容
export JAVA_HOME=/usr/java/jdk
PATH=.:$JAVA_HOME/bin:$JAVA_HOME/jre/bin:$PATH
export HADOOP_HOME=/usr/bdp/service/hadoop
PATH=.:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH
export HIVE_HOME=/usr/bdp/service/hive
PATH=.:$HIVE_HOME/bin:$PATH
export SPARK_HOME=/usr/bdp/service/spark
PATH=.:$SPARK_HOME/bin:$SPARK_HOME/sbin:$PATH

export PATH=$PATH
// 刷新配置在当前会话终端里生效
source /etc/profile
2、hadoop-env.sh配置
// 编辑hadoop-env.sh
vim /usr/bdp/service/hadoop/etc/hadoop/hadoop-env.sh
// 修改第37行:设置Hadoop的JDK依赖
export JAVA_HOME=/usr/java/jdk
// 修改第200行:设置Hadoop的日志输出目录
export HADOOP_LOG_DIR=/usr/bdp/data/hadoop/logs
3、core-site.xml配置
// 编辑core-site.xml
vim /usr/bdp/service/hadoop/etc/hadoop/core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <!-- 文件系统名称 -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://localhost:9820</value>
    </property>
    <!-- 其他临时目录都会建立此目录下 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/usr/bdp/data/hadoop</value>
    </property>
    <!-- 允许root用户代理所有主机上的任意用户 -->
    <property>
        <name>hadoop.proxyuser.root.hosts</name>
        <value>*</value>
    </property>
    <!-- 允许root用户代理所有主机上的任意用户组 -->
    <property>
        <name>hadoop.proxyuser.root.groups</name>
        <value>*</value>
    </property>
    <!-- 允许hive用户代理所有主机上的任意用户 -->
    <property>
        <name>hadoop.proxyuser.hive.groups</name>
        <value>*</value>
    </property>
    <!-- 允许hive用户代理所有主机上的任意用户组 -->
    <property>
        <name>hadoop.proxyuser.hive.hosts</name>
        <value>*</value>
    </property>
</configuration>
4、hdfs-site.xml配置
// 编辑hdfs-site.xml
vim /usr/bdp/service/hadoop/etc/hadoop/hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <!-- 关闭HDFS的权限检查 -->
    <property>
        <name>dfs.permissions.enabled</name>
        <value>false</value>
    </property>
</configuration>
5、yarn-site.xml配置
// 编辑yarn-site.xml
vim /usr/bdp/service/hadoop/etc/hadoop/yarn-site.xml
<?xml version="1.0"?>
<configuration>
    <!-- 设置RM的地址为localhost节点 -->
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>localhost</value>
    </property>
    <!-- 启用YARN的WebUI-V2 -->
    <property>
        <name>yarn.webapp.ui2.enable</name>
        <value>true</value>
    </property>
    <!-- 设置AUX服务 -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle,spark_shuffle</value>
    </property>
    <!-- 设置MapReduce的Shuffle实现 -->
    <property>
       <name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
       <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>
    <!-- 设置Spark的Shuffle实现 -->
    <property>
       <name>yarn.nodemanager.aux-services.spark_shuffle.class</name>
       <value>org.apache.spark.network.yarn.YarnShuffleService</value>
    </property>
    <!-- 为每个容器请求分配的最小内存限制为(512M) -->
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>512</value>
    </property>
    <!-- 为每个容器请求分配的最大内存限制为1GB -->
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>2048</value>
    </property>
    <!-- 虚拟内存比例,默认为2.1,此处设置为4倍 -->
    <property>
        <name>yarn.nodemanager.vmem-pmem-ratio</name>
        <value>4</value>
    </property>
    <!-- 用于存放Application的cache数据 -->
    <property>
        <name>yarn.nodemanager.local-dirs</name>
        <value>${hadoop.tmp.dir}/yarn/nm-local-dir</value>
    </property>
    <!-- 开启日志聚合 -->
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>
    <!-- 将日志聚合HDFS的哪个目录下 -->
    <property>
        <name>yarn.nodemanager.remote-app-log-dir</name>
        <value>/apps/yarn/logs</value>
    </property>
    <!-- 日志保存时间10天,单位秒 -->
    <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>864000</value>
    </property>
    <!-- 日志聚合服务器的URL地址 -->
    <property>
        <name>yarn.log.server.url</name>
        <value>http://localhost:19888/apps/yarn/logs</value>
    </property>
</configuration>
6、mapred-site.xml配置
// 编辑mapred-site.xml
vim /usr/bdp/service/hadoop/etc/hadoop/mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <!-- 指定MR框架通过YARN方式运行 -->
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <!-- 历史服务器端口号 -->
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>localhost:10020</value>
    </property>
    <!-- 历史服务器的WEB UI端口号 -->
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>localhost:19888</value>
    </property>
    <!-- 提交MR作业时使用位于HDFS上的暂存目录 -->
    <property>
        <name>yarn.app.mapreduce.am.staging-dir</name>
        <value>/apps/yarn/staging</value>
    </property>
    <!-- 内存中缓存的historyfile文件信息,默认20000 -->
    <property>
        <name>mapreduce.jobhistory.joblist.cache.size</name>
        <value>2000</value>
    </property>
    <!-- 指定MR作业的AM程序的环境变量 -->
    <property>
        <name>yarn.app.mapreduce.am.env</name>
        <value>HADOOP_MAPRED_HOME=/usr/bdp/service/hadoop</value>
    </property>
    <!-- 指定MR做的Map程序的环境变量 -->
    <property>
        <name>mapreduce.map.env</name>
        <value>HADOOP_MAPRED_HOME=/usr/bdp/service/hadoop</value>
    </property>
    <!-- 指定MR做的Reduce程序的环境变量 -->
    <property>
        <name>mapreduce.reduce.env</name>
        <value>HADOOP_MAPRED_HOME=/usr/bdp/service/hadoop</value>
    </property>
</configuration>
7、capacity-scheduler.xml配置
<!-- 
  将yarn.scheduler.capacity.resource-calculator配置的默认值
  由org.apache.hadoop.yarn.util.resource.DefaultResourceCalculator
  改为org.apache.hadoop.yarn.util.resource.DominantResourceCalculator,
  确保资源调度模式采用CPU+Memory方式。
 -->
<property> 
    <name>yarn.scheduler.capacity.resource-calculator</name> 
    <value>org.apache.hadoop.yarn.util.resource.DominantResourceCalculator</value> 
</property>
8、workers配置
// 编辑workers
vim /usr/bdp/service/hadoop/etc/hadoop/workers
localhost
9、start-dfs.sh和stop-dfs.sh配置
# 1、编辑$HADOOP_HOME/sbin目录下的start-dfs.sh
vim /usr/bdp/service/hadoop/sbin/start-dfs.sh
# 新增如下3行
HDFS_NAMENODE_USER=root
HDFS_DATANODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root
# 2、编辑$HADOOP_HOME/sbin目录下的stop-dfs.sh
vim /usr/bdp/service/hadoop/sbin/stop-dfs.sh
# 新增如下3行
HDFS_NAMENODE_USER=root
HDFS_DATANODE_USER=root
HDFS_SECONDARYNAMENODE_USER=root
10、start-yarn.sh和stop-yarn.sh配置
# 1、编辑$HADOOP_HOME/sbin目录下的start-yarn.sh
vim /usr/bdp/service/hadoop/sbin/start-yarn.sh
# 新增如下2行
YARN_RESOURCEMANAGER_USER=root
YARN_NODEMANAGER_USER=root

# 2、编辑$HADOOP_HOME/sbin目录下的stop-yarn.sh
vim /usr/bdp/service/hadoop/sbin/stop-yarn.sh
# 新增如下2行
YARN_RESOURCEMANAGER_USER=root
YARN_NODEMANAGER_USER=root
11、格式化HDFS配置
// 执行HDFS的格式化操作
hdfs namenode -format
// 输出日志如下
[root@localhost service]# hdfs namenode -format
2021-01-23 22:29:16,701 INFO namenode.NameNode: STARTUP_MSG:
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG:   host = localhost/192.168.0.101
STARTUP_MSG:   args = [-format]
STARTUP_MSG:   version = 3.1.0
STARTUP_MSG:   classpath = /usr/bdp/service/hadoop/etc/hadoop:/usr/bdp/service/hadoop/share/hadoop/common/lib/httpcore-4.4.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-util-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-core-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/mockito-all-1.8.5.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-core-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-crypto-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/accessors-smart-1.2.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/stax2-api-3.1.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-simplekdc-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerby-asn1-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jersey-server-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/guava-11.0.2.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-servlet-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-lang-2.6.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/httpclient-4.5.2.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jaxb-impl-2.2.3-1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jsch-0.1.54.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-mapper-asl-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-cli-1.2.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-io-2.5.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-identity-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/xz-1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/slf4j-log4j12-1.7.25.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-server-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerby-config-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/avro-1.7.7.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-math3-3.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/javax.servlet-api-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/log4j-1.2.17.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-annotations-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-io-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/paranamer-2.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/junit-4.11.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-xml-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-http-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jettison-1.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/hadoop-auth-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-beanutils-1.9.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jsr305-3.0.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-server-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/token-provider-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-common-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-compress-1.4.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-configuration2-2.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/curator-recipes-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-jaxrs-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-webapp-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-xc-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-core-asl-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/curator-client-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/curator-framework-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jetty-security-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/zookeeper-3.4.9.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-net-3.6.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/woodstox-core-5.0.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jersey-json-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/hadoop-annotations-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/gson-2.2.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/htrace-core4-4.1.0-incubating.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/snappy-java-1.0.5.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/slf4j-api-1.7.25.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/json-smart-2.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/netty-3.10.5.Final.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/asm-5.0.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-collections-3.2.2.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jersey-core-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jersey-servlet-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-util-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerby-pkix-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jsr311-api-1.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/nimbus-jose-jwt-4.41.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-client-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerb-admin-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-codec-1.11.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/re2j-1.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-logging-1.1.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerby-xdr-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/metrics-core-3.2.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jcip-annotations-1.0-1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jackson-databind-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/hamcrest-core-1.3.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/kerby-util-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jsp-api-2.1.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jul-to-slf4j-1.7.25.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/protobuf-java-2.5.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/jaxb-api-2.2.11.jar:/usr/bdp/service/hadoop/share/hadoop/common/lib/commons-lang3-3.4.jar:/usr/bdp/service/hadoop/share/hadoop/common/hadoop-common-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/common/hadoop-kms-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/hadoop-common-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/common/hadoop-nfs-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/httpcore-4.4.4.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-util-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-core-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-core-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/json-simple-1.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-crypto-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/accessors-smart-1.2.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/stax2-api-3.1.4.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-simplekdc-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerby-asn1-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jersey-server-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/guava-11.0.2.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-servlet-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-lang-2.6.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/httpclient-4.5.2.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jaxb-impl-2.2.3-1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jsch-0.1.54.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-mapper-asl-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-cli-1.2.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-io-2.5.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-identity-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/xz-1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-daemon-1.0.13.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-server-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerby-config-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/avro-1.7.7.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-math3-3.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/javax.servlet-api-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/log4j-1.2.17.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-annotations-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-io-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/paranamer-2.3.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-xml-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-http-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jettison-1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/hadoop-auth-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-beanutils-1.9.3.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jsr305-3.0.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/leveldbjni-all-1.8.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-server-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/token-provider-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-common-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-compress-1.4.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-configuration2-2.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/curator-recipes-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-jaxrs-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-webapp-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-xc-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-core-asl-1.9.13.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/curator-client-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/okio-1.6.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/curator-framework-2.12.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-security-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/zookeeper-3.4.9.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-net-3.6.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/woodstox-core-5.0.3.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jersey-json-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/hadoop-annotations-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/gson-2.2.4.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/htrace-core4-4.1.0-incubating.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/snappy-java-1.0.5.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/json-smart-2.3.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/netty-3.10.5.Final.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/asm-5.0.4.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-collections-3.2.2.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jersey-core-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/okhttp-2.7.5.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jersey-servlet-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-util-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/netty-all-4.0.52.Final.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerby-pkix-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jsr311-api-1.1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/nimbus-jose-jwt-4.41.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-client-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jetty-util-ajax-9.3.19.v20170502.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerb-admin-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-codec-1.11.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/re2j-1.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-logging-1.1.3.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerby-xdr-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jcip-annotations-1.0-1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jackson-databind-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/kerby-util-1.0.1.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/protobuf-java-2.5.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/jaxb-api-2.2.11.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/lib/commons-lang3-3.4.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-httpfs-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-rbf-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-native-client-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-rbf-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-client-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-native-client-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-client-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-nfs-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/hdfs/hadoop-hdfs-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-common-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-shuffle-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-3.1.0-tests.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-app-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-hs-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-hs-plugins-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-nativetask-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-core-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-uploader-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/javax.inject-1.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/snakeyaml-1.16.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/jackson-jaxrs-json-provider-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/jackson-jaxrs-base-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/guice-servlet-4.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/swagger-annotations-1.5.4.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/json-io-2.5.1.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/jersey-guice-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/aopalliance-1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/jersey-client-1.19.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/mssql-jdbc-6.2.1.jre7.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/geronimo-jcache_1.0_spec-1.0-alpha-1.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/fst-2.50.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/java-util-1.9.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/guice-4.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/jackson-module-jaxb-annotations-2.7.8.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/HikariCP-java7-2.4.12.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/metrics-core-3.2.4.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/ehcache-3.3.1.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/lib/dnsjava-2.1.7.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-timeline-pluginstorage-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-common-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-common-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-services-core-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-applications-distributedshell-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-client-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-applications-unmanaged-am-launcher-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-registry-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-applicationhistoryservice-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-router-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-nodemanager-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-tests-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-sharedcachemanager-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-api-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-web-proxy-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-services-api-3.1.0.jar:/usr/bdp/service/hadoop/share/hadoop/yarn/hadoop-yarn-server-resourcemanager-3.1.0.jar
STARTUP_MSG:   build = https://github.com/apache/hadoop -r 16b70619a24cdcf5d3b0fcf4b58ca77238ccbe6d; compiled by 'centos' on 2018-03-30T00:00Z
STARTUP_MSG:   java = 1.8.0_271
************************************************************/
2021-01-23 22:29:16,712 INFO namenode.NameNode: registered UNIX signal handlers for [TERM, HUP, INT]
2021-01-23 22:29:16,725 INFO namenode.NameNode: createNameNode [-format]
Formatting using clusterid: CID-ebe2beee-0cce-4a36-811c-b532fbcd74ff
2021-01-23 22:29:19,074 INFO namenode.FSEditLog: Edit logging is async:true
2021-01-23 22:29:19,111 INFO namenode.FSNamesystem: KeyProvider: null
2021-01-23 22:29:19,112 INFO namenode.FSNamesystem: fsLock is fair: true
2021-01-23 22:29:19,114 INFO namenode.FSNamesystem: Detailed lock hold time metrics enabled: false
2021-01-23 22:29:19,169 INFO namenode.FSNamesystem: fsOwner             = root (auth:SIMPLE)
2021-01-23 22:29:19,169 INFO namenode.FSNamesystem: supergroup          = supergroup
2021-01-23 22:29:19,169 INFO namenode.FSNamesystem: isPermissionEnabled = false
2021-01-23 22:29:19,169 INFO namenode.FSNamesystem: HA Enabled: false
2021-01-23 22:29:19,225 INFO common.Util: dfs.datanode.fileio.profiling.sampling.percentage set to 0. Disabling file IO profiling
2021-01-23 22:29:19,238 INFO blockmanagement.DatanodeManager: dfs.block.invalidate.limit: configured=1000, counted=60, effected=1000
2021-01-23 22:29:19,238 INFO blockmanagement.DatanodeManager: dfs.namenode.datanode.registration.ip-hostname-check=true
2021-01-23 22:29:19,243 INFO blockmanagement.BlockManager: dfs.namenode.startup.delay.block.deletion.sec is set to 000:00:00:00.000
2021-01-23 22:29:19,246 INFO blockmanagement.BlockManager: The block deletion will start around 2021 Jan 23 22:29:19
2021-01-23 22:29:19,253 INFO util.GSet: Computing capacity for map BlocksMap
2021-01-23 22:29:19,253 INFO util.GSet: VM type       = 64-bit
2021-01-23 22:29:19,256 INFO util.GSet: 2.0% max memory 916.4 MB = 18.3 MB
2021-01-23 22:29:19,256 INFO util.GSet: capacity      = 2^21 = 2097152 entries
2021-01-23 22:29:19,272 INFO blockmanagement.BlockManager: dfs.block.access.token.enable = false
2021-01-23 22:29:19,294 INFO Configuration.deprecation: No unit for dfs.namenode.safemode.extension(30000) assuming MILLISECONDS
2021-01-23 22:29:19,294 INFO blockmanagement.BlockManagerSafeMode: dfs.namenode.safemode.threshold-pct = 0.9990000128746033
2021-01-23 22:29:19,294 INFO blockmanagement.BlockManagerSafeMode: dfs.namenode.safemode.min.datanodes = 0
2021-01-23 22:29:19,294 INFO blockmanagement.BlockManagerSafeMode: dfs.namenode.safemode.extension = 30000
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: defaultReplication         = 3
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: maxReplication             = 512
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: minReplication             = 1
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: maxReplicationStreams      = 2
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: redundancyRecheckInterval  = 3000ms
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: encryptDataTransfer        = false
2021-01-23 22:29:19,295 INFO blockmanagement.BlockManager: maxNumBlocksToLog          = 1000
2021-01-23 22:29:19,361 INFO util.GSet: Computing capacity for map INodeMap
2021-01-23 22:29:19,361 INFO util.GSet: VM type       = 64-bit
2021-01-23 22:29:19,361 INFO util.GSet: 1.0% max memory 916.4 MB = 9.2 MB
2021-01-23 22:29:19,361 INFO util.GSet: capacity      = 2^20 = 1048576 entries
2021-01-23 22:29:19,362 INFO namenode.FSDirectory: ACLs enabled? false
2021-01-23 22:29:19,362 INFO namenode.FSDirectory: POSIX ACL inheritance enabled? true
2021-01-23 22:29:19,362 INFO namenode.FSDirectory: XAttrs enabled? true
2021-01-23 22:29:19,362 INFO namenode.NameNode: Caching file names occurring more than 10 times
2021-01-23 22:29:19,368 INFO snapshot.SnapshotManager: Loaded config captureOpenFiles: false, skipCaptureAccessTimeOnlyChange: false, snapshotDiffAllowSnapRootDescendant: true, maxSnapshotLimit: 65536
2021-01-23 22:29:19,379 INFO snapshot.SnapshotManager: SkipList is disabled
2021-01-23 22:29:19,383 INFO util.GSet: Computing capacity for map cachedBlocks
2021-01-23 22:29:19,383 INFO util.GSet: VM type       = 64-bit
2021-01-23 22:29:19,384 INFO util.GSet: 0.25% max memory 916.4 MB = 2.3 MB
2021-01-23 22:29:19,384 INFO util.GSet: capacity      = 2^18 = 262144 entries
2021-01-23 22:29:19,405 INFO metrics.TopMetrics: NNTop conf: dfs.namenode.top.window.num.buckets = 10
2021-01-23 22:29:19,406 INFO metrics.TopMetrics: NNTop conf: dfs.namenode.top.num.users = 10
2021-01-23 22:29:19,406 INFO metrics.TopMetrics: NNTop conf: dfs.namenode.top.windows.minutes = 1,5,25
2021-01-23 22:29:19,409 INFO namenode.FSNamesystem: Retry cache on namenode is enabled
2021-01-23 22:29:19,409 INFO namenode.FSNamesystem: Retry cache will use 0.03 of total heap and retry cache entry expiry time is 600000 millis
2021-01-23 22:29:19,423 INFO util.GSet: Computing capacity for map NameNodeRetryCache
2021-01-23 22:29:19,423 INFO util.GSet: VM type       = 64-bit
2021-01-23 22:29:19,423 INFO util.GSet: 0.029999999329447746% max memory 916.4 MB = 281.5 KB
2021-01-23 22:29:19,423 INFO util.GSet: capacity      = 2^15 = 32768 entries
2021-01-23 22:29:19,490 INFO namenode.FSImage: Allocated new BlockPoolId: BP-937104445-192.168.10.101-1611458959479
2021-01-23 22:29:19,509 INFO common.Storage: Storage directory /usr/bdp/data/hadoop/dfs/name has been successfully formatted.
2021-01-23 22:29:19,517 INFO namenode.FSImageFormatProtobuf: Saving image file /usr/bdp/data/hadoop/dfs/name/current/fsimage.ckpt_0000000000000000000 using no compression
2021-01-23 22:29:19,632 INFO namenode.FSImageFormatProtobuf: Image file /usr/bdp/data/hadoop/dfs/name/current/fsimage.ckpt_0000000000000000000 of size 389 bytes saved in 0 seconds .
2021-01-23 22:29:19,643 INFO namenode.NNStorageRetentionManager: Going to retain 1 images with txid >= 0
2021-01-23 22:29:19,647 INFO namenode.NameNode: SHUTDOWN_MSG:
/************************************************************
SHUTDOWN_MSG: Shutting down NameNode at localhost/192.168.0.101
************************************************************/
12、启动hadoop
# 1、启动HDFS
start-dfs.sh
# 2、启动YARN
start-yarn.sh
# 3、启动MR的作业历史服务
mapred --daemon start historyserver(mr-jobhistory-daemon.sh start historyserver已废弃)
13、验证hadoop是否启动
[root@localhost ~]# jps
85476 Jps
47383 DataNode
49097 RunJar
47242 NameNode
85051 ResourceManager
84730 JobHistoryServer
47628 SecondaryNameNode
85358 NodeManager
访问地址:
HDFS的WebUI地址:http://localhost:9870 
YARN的WebUI地址: http://localhost:8088 
JHS的WebUI地址: http://localhost:19888

三、hive

1、解压配置
# 解压
tar -zxvf apache-hive-3.1.0-bin.tar.gz 
 
# 配置
sudo vim /etc/profile
 
export HIVE_HOME=/home/hadoop/apache-hive-3.1.0-bin
export PATH=$HIVE_HOME/bin:$PATH
2、创建hdfs目录并赋予权限
hdfs dfs -mkdir -p /usr/hive/warehouse
hdfs dfs -mkdir -p /usr/hive/tmp
hdfs dfs -mkdir -p /usr/hive/log
hdfs dfs -chmod g+w /usr/hive/warehouse
hdfs dfs -chmod g+w /usr/hive/tmp
hdfs dfs -chmod g+w /usr/hive/log
3、hive-env.sh配置
#复制创建hive-env.sh
cd /home/hadoop/apache-hive-3.1.0-bin/conf
cp hive-env.sh.template hive-env.sh
vim hive-env.sh
 
# 在hive中添加如下内容
export JAVA_HOME=/opt/jdk1.8.0_161
export HADOOP_HOME=/home/hadoop/hadoop-2.8.4
export HIVE_HOME=/home/hadoop/apache-hive-3.1.0-bin
export HIVE_CONF_DIR=$HIVE_HOME/conf
export HIVE_AUX_JARS_PATH=$HIVE_HOME/lib/*
4、hive-site.xml配置:

#生成hive-site.xml文件
cp -r hive-default.xml.template hive-site.xml 
#配置
vi hive-site.xml
 
# 在文件开头添加如下内容:
<configuration>
  <property>
        <name>system:java.io.tmpdir</name>
        <value>/tmp/hive/java</value>
  </property>
  <property>
        <name>system:user.name</name>
        <value>${user.name}</value>
  </property>
</configuration>
 
# 修改以下属性的value值
 
<configuration>
  <!-- WARNING!!! This file is auto generated for documentation purposes ONLY! -->
  <!-- WARNING!!! Any changes you make to this file will be ignored by Hive.   -->
  <!-- WARNING!!! You must make your changes in hive-site.xml instead.         -->
  <!-- Hive Execution Parameters -->
 <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://192.168.32.128:3306/hive?createDatabaseIfNotExist=true&characterEncoding=UTF-8&useSSL=false</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.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>
</configuration>
5、使用schemaTool初始化mysql数据库
schematool -dbType mysql -initSchema
6、启动hive测试
# hive
7、启动
# nohup hive --service hiveserver2 2>&1 &   

四、异常情况

1、hive和hadoop中的一个jar包版本差异大,可以把hadoop中的jar拿过来替换掉hive中的jar
2、hadoop配置的时候,需要做ssh免密登录
3、hive启动的时候,mysql的jar驱动要复制到hive的lib中
4、查看hive对hadoop的授权命令:hadoop fs -ls /usr/hive
5、hive如果运行报# Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient,请在hive/bin下面运行./hive --service metastore &