hive使用3

1.配置hive安装目录conf下的hive-site.xml

<!-- 配置访问hadoop的权限，能够让hive访问到 -->
<property>
    <name>hadoop.proxyuser.root.hosts</name>
    <value>*</value>
</property>

<property>
    <name>hadoop.proxyuser.root.users</name>
    <value>*</value>
</property>


<!-- 指定hiveserver2连接的host -->
<property>
    <name>hive.server2.thrift.bind.host</name>
    <value>hadoop-master</value>
</property>
<!-- 指定hiveserver2连接的端口号 -->
<property>
    <name>hive.server2.thrift.port</name>
    <value>10000</value>
</property>




  <property>
      <name>hive.server2.active.passive.ha.enable</name>
      <value>true</value>
      <description>Whether HiveServer2 Active/Passive High Availability be enabled when Hive Interactive sessions are enabled.This will also require hive.server2.support.dynamic.service.discovery to be enabled.</description>
 </property>

2.启动命令

4.作业的log一直报RMContainerAllocator: Going to preempt 1 due to lack of space for maps，作业一直是runing状态。###

这是由于nodemanager的内存设置的过小，yarn的container无法申请到足够的资源.nodemanager配置参考如下:

<property>
	<name>yarn.resourcemanager.hostname</name>
	<value>hadoop-master</value>
	</property>
	<property>
	<name>yarn.nodemanager.aux-services</name>
	<value>mapreduce_shuffle</value>
	</property>

<!-- 选择调度器，默认容量 -->
<property>
	<description>The class to use as the resource scheduler.</description>
	<name>yarn.resourcemanager.scheduler.class</name>
	<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
</property>
<!-- ResourceManager处理调度器请求的线程数量,默认50；如果提交的任务数大于50，可以增加该值，但是不能超过3台 * 4线程 = 12线程（去除其他应用程序实际不能超过8） -->
<property>
	<description>Number of threads to handle scheduler interface.</description>
	<name>yarn.resourcemanager.scheduler.client.thread-count</name>
	<value>8</value>
</property>
<!-- NodeManager使用内存数，默认8G，修改为1.5G内存 -->
<property>
	<description>Amount of physical memory, in MB, that can be allocated 
	for containers. If set to -1 and
	yarn.nodemanager.resource.detect-hardware-capabilities is true, it is
	automatically calculated(in case of Windows and Linux).
	In other cases, the default is 8192MB.
	</description>
	<name>yarn.nodemanager.resource.memory-mb</name>
	<value>4096</value>
</property>
<!-- nodemanager的CPU核数，不按照硬件环境自动设定时默认是8个，修改为1个 -->
<property>
	<description>Number of vcores that can be allocated
	for containers. This is used by the RM scheduler when allocating
	resources for containers. This is not used to limit the number of
	CPUs used by YARN containers. If it is set to -1 and
	yarn.nodemanager.resource.detect-hardware-capabilities is true, it is
	automatically determined from the hardware in case of Windows and Linux.
	In other cases, number of vcores is 8 by default.</description>
	<name>yarn.nodemanager.resource.cpu-vcores</name>
	<value>4</value>
</property>
<!-- 容器最小内存，默认1G -->
<property>
	<description>The minimum allocation for every container request at the RM in MBs. Memory requests lower than this will be set to the value of this	property. Additionally, a node manager that is configured to have less memory	than this value will be shut down by the resource manager.
	</description>
	<name>yarn.scheduler.minimum-allocation-mb</name>
	<value>1024</value>
</property>
<!-- 容器最大内存，默认8G，修改为1.5G -->
<property>
	<description>The maximum allocation for every container request at the RM in MBs. Memory requests higher than this will throw an	InvalidResourceRequestException.
	</description>
	<name>yarn.scheduler.maximum-allocation-mb</name>
	<value>3072</value>
</property>
<!-- 容器最大CPU核数，默认4个，修改为1个 -->
<property>
	<description>The maximum allocation for every container request at the RM in terms of virtual CPU cores. Requests higher than this will throw an
	InvalidResourceRequestException.</description>
	<name>yarn.scheduler.maximum-allocation-vcores</name>
	<value>4</value>
</property>
<!-- 虚拟内存检查，默认打开，修改为关闭 -->
<property>
	<description>Whether virtual memory limits will be enforced for
	containers.</description>
	<name>yarn.nodemanager.vmem-check-enabled</name>
	<value>false</value>
</property>
<!--配置resourcemanager的web ui 的监控页面-->
    <property>
    <name>yarn.resourcemanager.webapp.address</name>
    <value>hadoop-master:8088</value>
    </property>
<!--以下配置值由命令hadoop classpath 获取-->
<property>
    <name>yarn.application.classpath</name>
    <value>/home/chengzhong/hadoop/hadoop-3.3.1/etc/hadoop:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/common/lib/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/common/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/hdfs:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/hdfs/lib/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/hdfs/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/mapreduce/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/yarn:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/yarn/lib/*:/home/chengzhong/hadoop/hadoop-3.3.1/share/hadoop/yarn/*</value>
</property>