Hadoop Yarn性能调优
版本: hadoop-3.1.3
1 环境
内存 | vCode | 线程数 | |
---|---|---|---|
hadoop101 | 8G | 4核CPU | 4 |
hadoop102 | 8G | 4核CPU | 4 |
hadoop103 | 8G | 4核CPU | 4 |
2 yarn-site.xml 配置
<!-- 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>
<!-- 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 a 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 ashyperthreads) 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(当前服务器无其他应用占用该内存,直接占满) -->
<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(当前服务器无其他应用占用CPU,直接占满) -->
<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>
<!-- container容器最小内存,默认 1G -->
<property>
<description>The minimum allocation for every container request at the Hadoop(Yarn) 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>
<!-- container容器最大内存,默认 8G,修改为 2G (一般设置1/3~1/2 nodemanager内存值)-->
<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>
<!-- container容器最小 CPU 核数,默认 1 个(每个容器下可以产生多少个线程 当前1核=1个线程) -->
<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(建议:与容器最大内存相乘==nodemanager总内存) -->
<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>
<!-- 是否启动一个线程检查每个任务正使用的虚拟内存量,如果任务超出分配值,则直接将其杀掉,默认是 true -->
<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>