大数据之hadoop3入门到精通（二）

cat /etc/hosts
• 1

<!-- 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.capaci
ty.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>
<!-- 是否让 yarn 自动检测硬件进行配置，默认是 false，如果该节点有很多其他应用程序，建议
手动配置。如果该节点没有其他应用程序，可以采用自动 -->
<property>
<description>Enable auto-detection of node capabilities such as
memory and CPU.
</description>
<name>yarn.nodemanager.resource.detect-hardware-capabilities</name>
<value>false</value>
</property>
<!-- 是否将虚拟核数当作 CPU 核数，默认是 false，采用物理 CPU 核数 -->
<property>
<description>Flag to determine if logical processors(such as
hyperthreads) should be counted as cores. Only applicable on Linux
when yarn.nodemanager.resource.cpu-vcores is set to -1 and
yarn.nodemanager.resource.detect-hardware-capabilities is true.
</description>
<name>yarn.nodemanager.resource.count-logical-processors-ascores</name>
<value>false</value>
</property>
<!-- 虚拟核数和物理核数乘数，默认是 1.0 -->
<property>
<description>Multiplier to determine how to convert phyiscal cores to
vcores. This value is used if yarn.nodemanager.resource.cpu-vcores
is set to -1(which implies auto-calculate vcores) and
yarn.nodemanager.resource.detect-hardware-capabilities is set to true. 
The number of vcores will be calculated as number of CPUs * multiplier.
</description>
<name>yarn.nodemanager.resource.pcores-vcores-multiplier</name>
<value>1.0</value>
</property>
<!-- NodeManager 使用内存数，默认 8G，修改为 4G 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 4 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 2G -->
<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>2048</value>
</property>
<!-- 容器最小 CPU 核数，默认 1 个 -->
<property>
<description>The minimum allocation for every container request at the 
RM in terms of virtual CPU cores. Requests lower than this will be set to 
the value of this property. Additionally, a node manager that is configured 
to have fewer virtual cores than this value will be shut down by the 
resource manager.
</description>
<name>yarn.scheduler.minimum-allocation-vcores</name>
<value>1</value>
</property>
<!-- 容器最大 CPU 核数，默认 4 个，修改为 2 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>2</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>
<!-- 虚拟内存和物理内存设置比例,默认 2.1 -->
<property>
<description>Ratio between virtual memory to physical memory when
setting memory limits for containers. Container allocations are
expressed in terms of physical memory, and virtual memory usage is 
allowed to exceed this allocation by this ratio.
</description>
<name>yarn.nodemanager.vmem-pmem-ratio</name>
<value>2.1</value>
</property>

<!-- 指定多队列，增加 hive 队列 -->
<property>
 <name>yarn.scheduler.capacity.root.queues</name>
 <value>default,hive</value>
 <description>
 The queues at the this level (root is the root queue).
 </description>
</property>
<!-- 降低 default 队列资源额定容量为 40%，默认 100% -->
<property>
 <name>yarn.scheduler.capacity.root.default.capacity</name>
 <value>40</value>
</property>
<!-- 降低 default 队列资源最大容量为 60%，默认 100% -->
<property>
 <name>yarn.scheduler.capacity.root.default.maximum-capacity</name>
 <value>60</value>
</property>

<!-- 指定 hive 队列的资源额定容量 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.capacity</name>
 <value>60</value>
</property>
<!-- 用户最多可以使用队列多少资源，1 表示 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.user-limit-factor</name>
 <value>1</value>
</property>
<!-- 指定 hive 队列的资源最大容量 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.maximum-capacity</name>
 <value>80</value>
</property>
<!-- 启动 hive 队列 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.state</name>
 <value>RUNNING</value>
</property>
<!-- 哪些用户有权向队列提交作业 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.acl_submit_applications</name>
 <value>*</value>
</property>
<!-- 哪些用户有权操作队列，管理员权限（查看/杀死） -->
<property>
 <name>yarn.scheduler.capacity.root.hive.acl_administer_queue</name>
 <value>*</value>
</property>
<!-- 哪些用户有权配置提交任务优先级 -->
<property>
 
<name>yarn.scheduler.capacity.root.hive.acl_application_max_priority</name>
 <value>*</value>
</property>
<!-- 任务的超时时间设置：yarn application -appId appId -updateLifetime Timeout
参考资料： https://blog.cloudera.com/enforcing-application-lifetime-slasyarn/ --> <!-- 如果 application 指定了超时时间，则提交到该队列的 application 能够指定的最大超时
时间不能超过该值。
-->
<property>
 <name>yarn.scheduler.capacity.root.hive.maximum-applicationlifetime</name>
 <value>-1</value>
</property>
<!-- 如果 application 没指定超时时间，则用 default-application-lifetime 作为默认
值 -->
<property>
 <name>yarn.scheduler.capacity.root.hive.default-applicationlifetime</name>
 <value>-1</value>
</property>

hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar wordcount -D mapreduce.job.queuename=hive /input /output

<property>
 <name>yarn.cluster.max-application-priority</name>
 <value>5</value>
</property>

hadoop jar /opt/module/hadoop-3.1.3/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar pi 5 2000000

hadoop jar /opt/module/hadoop-
3.1.3/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar pi -D mapreduce.job.priority=5 5 2000000

yarn application -appID application_1611133087930_0009 -updatePriority 5
• 1

<property>
 <name>yarn.resourcemanager.scheduler.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairS
cheduler</value>
 <description>配置使用公平调度器</description>
</property>
<property>
 <name>yarn.scheduler.fair.allocation.file</name>
 <value>/opt/module/hadoop-3.1.3/etc/hadoop/fair-scheduler.xml</value>
 <description>指明公平调度器队列分配配置文件</description>
</property>
<property>
 <name>yarn.scheduler.fair.preemption</name>
 <value>false</value>
 <descriptio

<?xml version="1.0"?>
<allocations>
 <!-- 单个队列中 Application Master 占用资源的最大比例,取值 0-1 ，企业一般配置 0.1 
-->
 <queueMaxAMShareDefault>0.5</queueMaxAMShareDefault>
 <!-- 单个队列最大资源的默认值 test atguigu default -->
 <queueMaxResourcesDefault>4096mb,4vcores</queueMaxResourcesDefault>
 <!-- 增加一个队列 test -->
 <queue name="test">
 <!-- 队列最小资源 -->
 <minResources>2048mb,2vcores</minResources>
 <!-- 队列最大资源 -->
 <maxResources>4096mb,4vcores</maxResources>
 <!-- 队列中最多同时运行的应用数，默认 50，根据线程数配置 -->
 <maxRunningApps>4</maxRunningApps>
 <!-- 队列中 Application Master 占用资源的最大比例 -->
 <maxAMShare>0.5</maxAMShare>
 <!-- 该队列资源权重,默认值为 1.0 -->
 <weight>1.0</weight>
 <!-- 队列内部的资源分配策略 -->
 <schedulingPolicy>fair</schedulingPolicy>
 </queue>
 <!-- 增加一个队列 atguigu -->
 <queue name="atguigu" type="parent">
 <!-- 队列最小资源 -->
 <minResources>2048mb,2vcores</minResources>
 <!-- 队列最大资源 -->
 <maxResources>4096mb,4vcores</maxResources>
 <!-- 队列中最多同时运行的应用数，默认 50，根据线程数配置 -->
 <maxRunningApps>4</maxRunningApps>
 <!-- 队列中 Application Master 占用资源的最大比例 -->
 <maxAMShare>0.5</maxAMShare>
 <!-- 该队列资源权重,默认值为 1.0 -->
 <weight>1.0</weight>
 <!-- 队列内部的资源分配策略 -->
 <schedulingPolicy>fair</schedulingPolicy>
 </queue>
 <!-- 任务队列分配策略,可配置多层规则,从第一个规则开始匹配,直到匹配成功 -->
 <queuePlacementPolicy>
 <!-- 提交任务时指定队列,如未指定提交队列,则继续匹配下一个规则; false 表示：如果指
定队列不存在,不允许自动创建-->
 <rule name="specified" create="false"/>
 <!-- 提交到 root.group.username 队列,若 root.group 不存在,不允许自动创建；若
root.group.user 不存在,允许自动创建 -->
 <rule name="nestedUserQueue" create="true">
 <rule name="primaryGroup" create="false"/>
 </rule>
 <!-- 最后一个规则必须为 reject 或者 default。Reject 表示拒绝创建提交失败，
default 表示把任务提交到 default 队列 -->
 <rule name="reject" />
 </queuePlacementPolicy>
</allocations>

hadoop jar /opt/module/hadoop-
3.1.3/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar pi -Dmapreduce.job.queuename=root.test 1 1

hadoop jar /opt/module/hadoop-
3.1.3/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.1.3.jar pi 1 1