2023-02-14 00:55:33 -05:00
|
|
|
|
<?xml version="1.0"?>
|
|
|
|
|
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
|
|
|
|
|
|
|
|
|
|
<!--
|
|
|
|
|
Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
|
contributor license agreements. See the NOTICE file distributed with
|
|
|
|
|
this work for additional information regarding copyright ownership.
|
|
|
|
|
The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
|
(the "License"); you may not use this file except in compliance with
|
|
|
|
|
the License. You may obtain a copy of the License at
|
|
|
|
|
|
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
|
|
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
|
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
|
See the License for the specific language governing permissions and
|
|
|
|
|
limitations under the License.
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- Do not modify this file directly. Instead, copy entries that you -->
|
|
|
|
|
<!-- wish to modify from this file into yarn-site.xml and change them -->
|
|
|
|
|
<!-- there. If yarn-site.xml does not already exist, create it. -->
|
|
|
|
|
|
|
|
|
|
<configuration>
|
|
|
|
|
|
|
|
|
|
<!-- IPC Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Factory to create client IPC classes.</description>
|
|
|
|
|
<name>yarn.ipc.client.factory.class</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Factory to create server IPC classes.</description>
|
|
|
|
|
<name>yarn.ipc.server.factory.class</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Factory to create serializeable records.</description>
|
|
|
|
|
<name>yarn.ipc.record.factory.class</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>RPC class implementation</description>
|
|
|
|
|
<name>yarn.ipc.rpc.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.ipc.HadoopYarnProtoRPC</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Resource Manager Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The hostname of the RM.</description>
|
|
|
|
|
<name>yarn.resourcemanager.hostname</name>
|
|
|
|
|
<value>0.0.0.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the applications manager interface in the RM.</description>
|
|
|
|
|
<name>yarn.resourcemanager.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8032</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The actual address the server will bind to. If this optional address is
|
|
|
|
|
set, the RPC and webapp servers will bind to this address and the port specified in
|
|
|
|
|
yarn.resourcemanager.address and yarn.resourcemanager.webapp.address, respectively. This
|
|
|
|
|
is most useful for making RM listen to all interfaces by setting to 0.0.0.0.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.bind-host</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
If set to true, then ALL container updates will be automatically sent to
|
|
|
|
|
the NM in the next heartbeat</description>
|
|
|
|
|
<name>yarn.resourcemanager.auto-update.containers</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of threads used to handle applications manager requests.</description>
|
|
|
|
|
<name>yarn.resourcemanager.client.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads used to launch/cleanup AM.</description>
|
|
|
|
|
<name>yarn.resourcemanager.amlauncher.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Retry times to connect with NM.</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanager-connect-retries</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Timeout in milliseconds when YARN dispatcher tries to drain the
|
|
|
|
|
events. Typically, this happens when service is stopping. e.g. RM drains
|
|
|
|
|
the ATS events dispatcher when stopping.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.drain-events.timeout</name>
|
|
|
|
|
<value>300000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The threshold used to trigger the logging of event types
|
|
|
|
|
and counts in RM's main event dispatcher. Default length is 5000,
|
|
|
|
|
which means RM will print events info when the queue size cumulatively
|
|
|
|
|
reaches 5000 every time. Such info can be used to reveal what kind of events
|
|
|
|
|
that RM is stuck at processing mostly, it can help to
|
|
|
|
|
narrow down certain performance issues.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.print-events-info.threshold</name>
|
|
|
|
|
<value>5000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Resource manager dispatcher thread cpu monitor sampling rate.
|
|
|
|
|
Units are samples per minute. This controls how often to sample
|
|
|
|
|
the cpu utilization of the resource manager dispatcher thread.
|
|
|
|
|
The cpu utilization is displayed on the RM UI as scheduler busy %.
|
|
|
|
|
Set this to zero to disable the dispatcher thread monitor. Defaults
|
|
|
|
|
to 60 samples per minute.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.cpu-monitor.samples-per-min</name>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Resource manager dispatcher has a thread pool that prints EventQueue,
|
|
|
|
|
configure the corePoolSize of this thread pool,
|
|
|
|
|
the meaning of corePoolSize is the number of threads to keep in the pool.
|
|
|
|
|
the default value is 1.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.print-thread-pool.core-pool-size</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Resource manager dispatcher has a thread pool that prints EventQueue,
|
|
|
|
|
configure the maximumPoolSize of this thread pool,
|
|
|
|
|
the meaning of maximumPoolSize is the maximum number of threads to allow in the pool.
|
|
|
|
|
the default value is 5.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.print-thread-pool.maximum-pool-size</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Resource manager dispatcher has a thread pool that prints EventQueue,
|
|
|
|
|
configure the keepAliveTime of this thread pool,
|
|
|
|
|
The meaning of keepAliveTime is as follows
|
|
|
|
|
when the number of threads is greater than the core,
|
|
|
|
|
this is the maximum time that excess idle threads will wait for new tasks before terminating.
|
|
|
|
|
the default value is 10s.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.dispatcher.print-thread-pool.keep-alive-time</name>
|
|
|
|
|
<value>10s</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The expiry interval for application master reporting.</description>
|
|
|
|
|
<name>yarn.am.liveness-monitor.expiry-interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The Kerberos principal for the resource manager.</description>
|
|
|
|
|
<name>yarn.resourcemanager.principal</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the scheduler interface.</description>
|
|
|
|
|
<name>yarn.resourcemanager.scheduler.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8030</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads to handle scheduler interface.</description>
|
|
|
|
|
<name>yarn.resourcemanager.scheduler.client.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify which handler will be used to process PlacementConstraints.
|
|
|
|
|
Acceptable values are: `placement-processor`, `scheduler` and `disabled`.
|
|
|
|
|
For a detailed explanation of these values, please refer to documentation.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.handler</name>
|
|
|
|
|
<value>disabled</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of times to retry placing of rejected SchedulingRequests</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.retry-attempts</name>
|
|
|
|
|
<value>3</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Constraint Placement Algorithm to be used.</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.algorithm.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.constraint.algorithm.DefaultPlacementAlgorithm</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Placement Algorithm Requests Iterator to be used.</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.algorithm.iterator</name>
|
|
|
|
|
<value>SERIAL</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Threadpool size for the Algorithm used for placement constraint processing.</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.algorithm.pool-size</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Threadpool size for the Scheduler invocation phase of placement constraint processing.</description>
|
|
|
|
|
<name>yarn.resourcemanager.placement-constraints.scheduler.pool-size</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comma separated class names of ApplicationMasterServiceProcessor
|
|
|
|
|
implementations. The processors will be applied in the order
|
|
|
|
|
they are specified.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-master-service.processors</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
This configures the HTTP endpoint for YARN Daemons.The following
|
|
|
|
|
values are supported:
|
|
|
|
|
- HTTP_ONLY : Service is provided only on http
|
|
|
|
|
- HTTPS_ONLY : Service is provided only on https
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.http.policy</name>
|
|
|
|
|
<value>HTTP_ONLY</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The http address of the RM web application.
|
|
|
|
|
If only a host is provided as the value,
|
|
|
|
|
the webapp will be served on a random port.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8088</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The https address of the RM web application.
|
|
|
|
|
If only a host is provided as the value,
|
|
|
|
|
the webapp will be served on a random port.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.https.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8090</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Kerberos keytab file to be used for spnego filter for the RM web
|
|
|
|
|
interface.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.spnego-keytab-file</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Kerberos principal to be used for spnego filter for the RM web
|
|
|
|
|
interface.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.spnego-principal</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Add button to kill application in the RM Application view.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.ui-actions.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>To enable RM web ui2 application.</description>
|
|
|
|
|
<name>yarn.webapp.ui2.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable tools section in all ui1 webapp.</description>
|
|
|
|
|
<name>yarn.webapp.ui1.tools.enable</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Explicitly provide WAR file path for ui2 if needed.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.webapp.ui2.war-file-path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable services rest api on ResourceManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.webapp.api-service.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.resourcemanager.resource-tracker.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8031</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.resourcemanager.resource-tracker.nm.ip-hostname-check</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Are acls enabled.</description>
|
|
|
|
|
<name>yarn.acl.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Are reservation acls enabled.</description>
|
|
|
|
|
<name>yarn.acl.reservation-enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>ACL of who can be admin of the YARN cluster.</description>
|
|
|
|
|
<name>yarn.admin.acl</name>
|
|
|
|
|
<value>*</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the RM admin interface.</description>
|
|
|
|
|
<name>yarn.resourcemanager.admin.address</name>
|
|
|
|
|
<value>${yarn.resourcemanager.hostname}:8033</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads used to handle RM admin interface.</description>
|
|
|
|
|
<name>yarn.resourcemanager.admin.client.thread-count</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Maximum time to wait to establish connection to
|
|
|
|
|
ResourceManager.</description>
|
|
|
|
|
<name>yarn.resourcemanager.connect.max-wait.ms</name>
|
|
|
|
|
<value>900000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How often to try connecting to the
|
|
|
|
|
ResourceManager.</description>
|
|
|
|
|
<name>yarn.resourcemanager.connect.retry-interval.ms</name>
|
|
|
|
|
<value>30000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default maximum number of application attempts, if unset by
|
|
|
|
|
the user. Each application master can specify its individual maximum number of application
|
|
|
|
|
attempts via the API, but the individual number cannot be more than the global upper bound in
|
|
|
|
|
yarn.resourcemanager.am.global.max-attempts. The default number is set to 2, to
|
|
|
|
|
allow at least one retry for AM.</description>
|
|
|
|
|
<name>yarn.resourcemanager.am.max-attempts</name>
|
|
|
|
|
<value>2</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How often to check that containers are still alive. </description>
|
|
|
|
|
<name>yarn.resourcemanager.container.liveness-monitor.interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The keytab for the resource manager.</description>
|
|
|
|
|
<name>yarn.resourcemanager.keytab</name>
|
|
|
|
|
<value>/etc/krb5.keytab</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Flag to enable override of the default kerberos authentication
|
|
|
|
|
filter with the RM authentication filter to allow authentication using
|
|
|
|
|
delegation tokens(fallback to kerberos if the tokens are missing). Only
|
|
|
|
|
applicable when the http authentication type is kerberos.</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.delegation-token-auth-filter.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Flag to enable cross-origin (CORS) support in the RM. This flag
|
|
|
|
|
requires the CORS filter initializer to be added to the filter initializers
|
|
|
|
|
list in core-site.xml.</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.cross-origin.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How long to wait until a node manager is considered dead.</description>
|
|
|
|
|
<name>yarn.nm.liveness-monitor.expiry-interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Path to file with nodes to include.</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodes.include-path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Path to file with nodes to exclude.</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodes.exclude-path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The expiry interval for node IP caching. -1 disables the caching</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-ip-cache.expiry-interval-secs</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads to handle resource tracker calls.</description>
|
|
|
|
|
<name>yarn.resourcemanager.resource-tracker.client.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<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>8192</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used by node labels. If set to true, the port should be included in the
|
|
|
|
|
node name. Only usable if your scheduler supports node labels.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.include-port-in-node-name</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable RM to recover state after starting. If true, then
|
|
|
|
|
yarn.resourcemanager.store.class must be specified. </description>
|
|
|
|
|
<name>yarn.resourcemanager.recovery.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Should RM fail fast if it encounters any errors. By defalt, it
|
|
|
|
|
points to ${yarn.fail-fast}. Errors include:
|
|
|
|
|
1) exceptions when state-store write/read operations fails.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.fail-fast</name>
|
|
|
|
|
<value>${yarn.fail-fast}</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Should YARN fail fast if it encounters any errors.
|
|
|
|
|
This is a global config for all other components including RM,NM etc.
|
|
|
|
|
If no value is set for component-specific config (e.g yarn.resourcemanager.fail-fast),
|
|
|
|
|
this value will be the default.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.fail-fast</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable RM work preserving recovery. This configuration is private
|
|
|
|
|
to YARN for experimenting the feature.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.work-preserving-recovery.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Set the amount of time RM waits before allocating new
|
|
|
|
|
containers on work-preserving-recovery. Such wait period gives RM a chance
|
|
|
|
|
to settle down resyncing with NMs in the cluster on recovery, before assigning
|
|
|
|
|
new containers to applications.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.work-preserving-recovery.scheduling-wait-ms</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The class to use as the persistent store.
|
|
|
|
|
|
|
|
|
|
If org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore
|
|
|
|
|
is used, the store is implicitly fenced; meaning a single ResourceManager
|
|
|
|
|
is able to use the store at any point in time. More details on this
|
|
|
|
|
implicit fencing, along with setting up appropriate ACLs is discussed
|
|
|
|
|
under yarn.resourcemanager.zk-state-store.root-node.acl.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.store.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When automatic failover is enabled, number of zookeeper
|
|
|
|
|
operation retry times in ActiveStandbyElector</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.failover-controller.active-standby-elector.zk.retries</name>
|
|
|
|
|
<!--<value>3</value>-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The maximum number of completed applications RM state
|
|
|
|
|
store keeps, less than or equals to ${yarn.resourcemanager.max-completed-applications}.
|
|
|
|
|
By default, it equals to ${yarn.resourcemanager.max-completed-applications}.
|
|
|
|
|
This ensures that the applications kept in the state store are consistent with
|
|
|
|
|
the applications remembered in RM memory.
|
|
|
|
|
Any values larger than ${yarn.resourcemanager.max-completed-applications} will
|
|
|
|
|
be reset to ${yarn.resourcemanager.max-completed-applications}.
|
|
|
|
|
Note that this value impacts the RM recovery performance. Typically,
|
|
|
|
|
a smaller value indicates better performance on RM recovery.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.state-store.max-completed-applications</name>
|
|
|
|
|
<value>${yarn.resourcemanager.max-completed-applications}</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Full path of the ZooKeeper znode where RM state will be
|
|
|
|
|
stored. This must be supplied when using
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore
|
|
|
|
|
as the value for yarn.resourcemanager.store.class</description>
|
|
|
|
|
<name>yarn.resourcemanager.zk-state-store.parent-path</name>
|
|
|
|
|
<value>/rmstore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
ACLs to be used for the root znode when using ZKRMStateStore in an HA
|
|
|
|
|
scenario for fencing.
|
|
|
|
|
|
|
|
|
|
ZKRMStateStore supports implicit fencing to allow a single
|
|
|
|
|
ResourceManager write-access to the store. For fencing, the
|
|
|
|
|
ResourceManagers in the cluster share read-write-admin privileges on the
|
|
|
|
|
root node, but the Active ResourceManager claims exclusive create-delete
|
|
|
|
|
permissions.
|
|
|
|
|
|
|
|
|
|
By default, when this property is not set, we use the ACLs from
|
|
|
|
|
yarn.resourcemanager.zk-acl for shared admin access and
|
|
|
|
|
rm-address:random-number for username-based exclusive create-delete
|
|
|
|
|
access.
|
|
|
|
|
|
|
|
|
|
This property allows users to set ACLs of their choice instead of using
|
|
|
|
|
the default mechanism. For fencing to work, the ACLs should be
|
|
|
|
|
carefully set differently on each ResourceManager such that all the
|
|
|
|
|
ResourceManagers have shared admin access and the Active ResourceManager
|
|
|
|
|
takes over (exclusively) the create-delete access.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.zk-state-store.root-node.acl</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>URI pointing to the location of the FileSystem path where
|
|
|
|
|
RM state will be stored. This must be supplied when using
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
|
|
|
|
|
as the value for yarn.resourcemanager.store.class</description>
|
|
|
|
|
<name>yarn.resourcemanager.fs.state-store.uri</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn/system/rmstore</value>
|
|
|
|
|
<!--value>hdfs://localhost:9000/rmstore</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>the number of retries to recover from IOException in
|
|
|
|
|
FileSystemRMStateStore.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.fs.state-store.num-retries</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Retry interval in milliseconds in FileSystemRMStateStore.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.fs.state-store.retry-interval-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Local path where the RM state will be stored when using
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.recovery.LeveldbRMStateStore
|
|
|
|
|
as the value for yarn.resourcemanager.store.class</description>
|
|
|
|
|
<name>yarn.resourcemanager.leveldb-state-store.path</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn/system/rmstore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The time in seconds between full compactions of the leveldb
|
|
|
|
|
database. Setting the interval to zero disables the full compaction
|
|
|
|
|
cycles.</description>
|
|
|
|
|
<name>yarn.resourcemanager.leveldb-state-store.compaction-interval-secs</name>
|
|
|
|
|
<value>3600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable RM high-availability. When enabled,
|
|
|
|
|
(1) The RM starts in the Standby mode by default, and transitions to
|
|
|
|
|
the Active mode when prompted to.
|
|
|
|
|
(2) The nodes in the RM ensemble are listed in
|
|
|
|
|
yarn.resourcemanager.ha.rm-ids
|
|
|
|
|
(3) The id of each RM either comes from yarn.resourcemanager.ha.id
|
|
|
|
|
if yarn.resourcemanager.ha.id is explicitly specified or can be
|
|
|
|
|
figured out by matching yarn.resourcemanager.address.{id} with local address
|
|
|
|
|
(4) The actual physical addresses come from the configs of the pattern
|
|
|
|
|
- {rpc-config}.{id}</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable automatic failover.
|
|
|
|
|
By default, it is enabled only when HA is enabled</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable embedded automatic failover.
|
|
|
|
|
By default, it is enabled only when HA is enabled.
|
|
|
|
|
The embedded elector relies on the RM state store to handle fencing,
|
|
|
|
|
and is primarily intended to be used in conjunction with ZKRMStateStore.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.automatic-failover.embedded</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The base znode path to use for storing leader information,
|
|
|
|
|
when using ZooKeeper based leader election.</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.automatic-failover.zk-base-path</name>
|
|
|
|
|
<value>/yarn-leader-election</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Index at which last section of application id (with each section
|
|
|
|
|
separated by _ in application id) will be split so that application znode
|
|
|
|
|
stored in zookeeper RM state store will be stored as two different znodes
|
|
|
|
|
(parent-child). Split is done from the end.
|
|
|
|
|
For instance, with no split, appid znode will be of the form
|
|
|
|
|
application_1352994193343_0001. If the value of this config is 1, the
|
|
|
|
|
appid znode will be broken into two parts application_1352994193343_000
|
|
|
|
|
and 1 respectively with former being the parent node.
|
|
|
|
|
application_1352994193343_0002 will then be stored as 2 under the parent
|
|
|
|
|
node application_1352994193343_000. This config can take values from 0 to 4.
|
|
|
|
|
0 means there will be no split. If configuration value is outside this
|
|
|
|
|
range, it will be treated as config value of 0(i.e. no split). A value
|
|
|
|
|
larger than 0 (up to 4) should be configured if you are storing a large number
|
|
|
|
|
of apps in ZK based RM state store and state store operations are failing due to
|
|
|
|
|
LenError in Zookeeper.</description>
|
|
|
|
|
<name>yarn.resourcemanager.zk-appid-node.split-index</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Index at which the RM Delegation Token ids will be split so
|
|
|
|
|
that the delegation token znodes stored in the zookeeper RM state store
|
|
|
|
|
will be stored as two different znodes (parent-child). The split is done
|
|
|
|
|
from the end. For instance, with no split, a delegation token znode will
|
|
|
|
|
be of the form RMDelegationToken_123456789. If the value of this config is
|
|
|
|
|
1, the delegation token znode will be broken into two parts:
|
|
|
|
|
RMDelegationToken_12345678 and 9 respectively with former being the parent
|
|
|
|
|
node. This config can take values from 0 to 4. 0 means there will be no
|
|
|
|
|
split. If the value is outside this range, it will be treated as 0 (i.e.
|
|
|
|
|
no split). A value larger than 0 (up to 4) should be configured if you are
|
|
|
|
|
running a large number of applications, with long-lived delegation tokens
|
|
|
|
|
and state store operations (e.g. failover) are failing due to LenError in
|
|
|
|
|
Zookeeper.</description>
|
|
|
|
|
<name>yarn.resourcemanager.zk-delegation-token-node.split-index</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Specifies the maximum size of the data that can be stored
|
|
|
|
|
in a znode. Value should be same or less than jute.maxbuffer configured
|
|
|
|
|
in zookeeper. Default value configured is 1MB.</description>
|
|
|
|
|
<name>yarn.resourcemanager.zk-max-znode-size.bytes</name>
|
|
|
|
|
<value>1048576</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Name of the cluster. In a HA setting,
|
|
|
|
|
this is used to ensure the RM participates in leader
|
|
|
|
|
election for this cluster and ensures it does not affect
|
|
|
|
|
other clusters</description>
|
|
|
|
|
<name>yarn.resourcemanager.cluster-id</name>
|
|
|
|
|
<!--value>yarn-cluster</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The range of values above base epoch that the RM will use before
|
|
|
|
|
wrapping around</description>
|
|
|
|
|
<name>yarn.resourcemanager.epoch.range</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The list of RM nodes in the cluster when HA is
|
|
|
|
|
enabled. See description of yarn.resourcemanager.ha
|
|
|
|
|
.enabled for full details on how this is used.</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.rm-ids</name>
|
|
|
|
|
<!--value>rm1,rm2</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The id (string) of the current RM. When HA is enabled, this
|
|
|
|
|
is an optional config. The id of current RM can be set by explicitly
|
|
|
|
|
specifying yarn.resourcemanager.ha.id or figured out by matching
|
|
|
|
|
yarn.resourcemanager.address.{id} with local address
|
|
|
|
|
See description of yarn.resourcemanager.ha.enabled
|
|
|
|
|
for full details on how this is used.</description>
|
|
|
|
|
<name>yarn.resourcemanager.ha.id</name>
|
|
|
|
|
<!--value>rm1</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the class to be used by Clients, AMs and
|
|
|
|
|
NMs to failover to the Active RM. It should extend
|
|
|
|
|
org.apache.hadoop.yarn.client.RMFailoverProxyProvider</description>
|
|
|
|
|
<name>yarn.client.failover-proxy-provider</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is not enabled, the class to be used by Clients, AMs and
|
|
|
|
|
NMs to retry connecting to the Active RM. It should extend
|
|
|
|
|
org.apache.hadoop.yarn.client.RMFailoverProxyProvider</description>
|
|
|
|
|
<name>yarn.client.failover-no-ha-proxy-provider</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.client.DefaultNoHARMFailoverProxyProvider</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the max number of times
|
|
|
|
|
FailoverProxyProvider should attempt failover. When set,
|
|
|
|
|
this overrides the yarn.resourcemanager.connect.max-wait.ms. When
|
|
|
|
|
not set, this is inferred from
|
|
|
|
|
yarn.resourcemanager.connect.max-wait.ms.</description>
|
|
|
|
|
<name>yarn.client.failover-max-attempts</name>
|
|
|
|
|
<!--value>15</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the sleep base (in milliseconds) to be
|
|
|
|
|
used for calculating the exponential delay between failovers. When set,
|
|
|
|
|
this overrides the yarn.resourcemanager.connect.* settings. When
|
|
|
|
|
not set, yarn.resourcemanager.connect.retry-interval.ms is used instead.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.client.failover-sleep-base-ms</name>
|
|
|
|
|
<!--value>500</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the maximum sleep time (in milliseconds)
|
|
|
|
|
between failovers. When set, this overrides the
|
|
|
|
|
yarn.resourcemanager.connect.* settings. When not set,
|
|
|
|
|
yarn.resourcemanager.connect.retry-interval.ms is used instead.</description>
|
|
|
|
|
<name>yarn.client.failover-sleep-max-ms</name>
|
|
|
|
|
<!--value>15000</value-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the number of retries per
|
|
|
|
|
attempt to connect to a ResourceManager. In other words,
|
|
|
|
|
it is the ipc.client.connect.max.retries to be used during
|
|
|
|
|
failover attempts</description>
|
|
|
|
|
<name>yarn.client.failover-retries</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>When HA is enabled, the number of retries per
|
|
|
|
|
attempt to connect to a ResourceManager on socket timeouts. In other
|
|
|
|
|
words, it is the ipc.client.connect.max.retries.on.timeouts to be used
|
|
|
|
|
during failover attempts</description>
|
|
|
|
|
<name>yarn.client.failover-retries-on-socket-timeouts</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The maximum number of completed applications RM keeps. </description>
|
|
|
|
|
<name>yarn.resourcemanager.max-completed-applications</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Interval at which the delayed token removal thread runs</description>
|
|
|
|
|
<name>yarn.resourcemanager.delayed.delegation-token.removal-interval-ms</name>
|
|
|
|
|
<value>30000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Maximum size in bytes for configurations that can be provided
|
|
|
|
|
by application to RM for delegation token renewal.
|
|
|
|
|
By experiment, its roughly 128 bytes per key-value pair.
|
|
|
|
|
The default value 12800 allows roughly 100 configs, may be less.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token.max-conf-size-bytes</name>
|
|
|
|
|
<value>12800</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If true, ResourceManager will always try to cancel delegation
|
|
|
|
|
tokens after the application completes, even if the client sets
|
|
|
|
|
shouldCancelAtEnd false. References to delegation tokens are tracked,
|
|
|
|
|
so they will not be canceled until all sub-tasks are done using them.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token.always-cancel</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If true, ResourceManager will have proxy-user privileges.
|
|
|
|
|
Use case: In a secure cluster, YARN requires the user hdfs delegation-tokens to
|
|
|
|
|
do localization and log-aggregation on behalf of the user. If this is set to true,
|
|
|
|
|
ResourceManager is able to request new hdfs delegation tokens on behalf of
|
|
|
|
|
the user. This is needed by long-running-service, because the hdfs tokens
|
|
|
|
|
will eventually expire and YARN requires new valid tokens to do localization
|
|
|
|
|
and log-aggregation. Note that to enable this use case, the corresponding
|
|
|
|
|
HDFS NameNode has to configure ResourceManager as the proxy-user so that
|
|
|
|
|
ResourceManager can itself ask for new tokens on behalf of the user when
|
|
|
|
|
tokens are past their max-life-time.</description>
|
|
|
|
|
<name>yarn.resourcemanager.proxy-user-privileges.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Interval for the roll over for the master key used to generate
|
|
|
|
|
application tokens
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.am-rm-tokens.master-key-rolling-interval-secs</name>
|
|
|
|
|
<value>86400</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Interval for the roll over for the master key used to generate
|
|
|
|
|
container tokens. It is expected to be much greater than
|
|
|
|
|
yarn.nm.liveness-monitor.expiry-interval-ms and
|
|
|
|
|
yarn.resourcemanager.rm.container-allocation.expiry-interval-ms. Otherwise the
|
|
|
|
|
behavior is undefined.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.container-tokens.master-key-rolling-interval-secs</name>
|
|
|
|
|
<value>86400</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The heart-beat interval in milliseconds for every NodeManager in the cluster.</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanagers.heartbeat-interval-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enables heart-beat interval scaling. The NodeManager
|
|
|
|
|
heart-beat interval will scale based on the difference between the CPU
|
|
|
|
|
utilization on the node and the cluster-wide average CPU utilization.
|
|
|
|
|
</description>
|
|
|
|
|
<name>
|
|
|
|
|
yarn.resourcemanager.nodemanagers.heartbeat-interval-scaling-enable
|
|
|
|
|
</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If heart-beat interval scaling is enabled, this is the
|
|
|
|
|
minimum heart-beat interval in milliseconds
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanagers.heartbeat-interval-min-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If heart-beat interval scaling is enabled, this is the
|
|
|
|
|
maximum heart-beat interval in milliseconds</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanagers.heartbeat-interval-max-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If heart-beat interval scaling is enabled, this controls
|
|
|
|
|
the degree of adjustment when speeding up heartbeat intervals.
|
|
|
|
|
At 1.0, 20% less than average CPU utilization will result in a 20%
|
|
|
|
|
decrease in heartbeat interval.
|
|
|
|
|
</description>
|
|
|
|
|
<name>
|
|
|
|
|
yarn.resourcemanager.nodemanagers.heartbeat-interval-speedup-factor
|
|
|
|
|
</name>
|
|
|
|
|
<value>1.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If heart-beat interval scaling is enabled, this controls
|
|
|
|
|
the degree of adjustment when slowing down heartbeat intervals.
|
|
|
|
|
At 1.0, 20% greater than average CPU utilization will result in a 20%
|
|
|
|
|
increase in heartbeat interval.
|
|
|
|
|
</description>
|
|
|
|
|
<name>
|
|
|
|
|
yarn.resourcemanager.nodemanagers.heartbeat-interval-slowdown-factor
|
|
|
|
|
</name>
|
|
|
|
|
<value>1.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The Number of consecutive missed heartbeats after which node will be
|
|
|
|
|
skipped from scheduling</description>
|
|
|
|
|
<name>yarn.scheduler.skip.node.multiplier</name>
|
|
|
|
|
<value>2</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The minimum allowed version of a connecting nodemanager. The valid values are
|
|
|
|
|
NONE (no version checking), EqualToRM (the nodemanager's version is equal to
|
|
|
|
|
or greater than the RM version), or a Version String.</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanager.minimum.version</name>
|
|
|
|
|
<value>NONE</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable a set of periodic monitors (specified in
|
|
|
|
|
yarn.resourcemanager.scheduler.monitor.policies) that affect the
|
|
|
|
|
scheduler.</description>
|
|
|
|
|
<name>yarn.resourcemanager.scheduler.monitor.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The list of SchedulingEditPolicy classes that interact with
|
|
|
|
|
the scheduler. A particular module may be incompatible with the
|
|
|
|
|
scheduler, other policies, or a configuration of either.</description>
|
|
|
|
|
<name>yarn.resourcemanager.scheduler.monitor.policies</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.resourcemanager.monitor.capacity.ProportionalCapacityPreemptionPolicy</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The class to use as the configuration provider.
|
|
|
|
|
If org.apache.hadoop.yarn.LocalConfigurationProvider is used,
|
|
|
|
|
the local configuration will be loaded.
|
|
|
|
|
If org.apache.hadoop.yarn.FileSystemBasedConfigurationProvider is used,
|
|
|
|
|
the configuration which will be loaded should be uploaded to remote File system first.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.configuration.provider-class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.LocalConfigurationProvider</value>
|
|
|
|
|
<!-- <value>org.apache.hadoop.yarn.FileSystemBasedConfigurationProvider</value> -->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The value specifies the file system (e.g. HDFS) path where ResourceManager
|
|
|
|
|
loads configuration if yarn.resourcemanager.configuration.provider-class
|
|
|
|
|
is set to org.apache.hadoop.yarn.FileSystemBasedConfigurationProvider.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.configuration.file-system-based-store</name>
|
|
|
|
|
<value>/yarn/conf</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that controls whether yarn system metrics is
|
|
|
|
|
published to the Timeline server (version one) or not, by RM.
|
|
|
|
|
This configuration is now deprecated in favor of
|
|
|
|
|
yarn.system-metrics-publisher.enabled.</description>
|
|
|
|
|
<name>yarn.resourcemanager.system-metrics-publisher.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that controls whether yarn system metrics is
|
|
|
|
|
published on the Timeline service or not by RM And NM.</description>
|
|
|
|
|
<name>yarn.system-metrics-publisher.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that controls whether yarn container events are
|
|
|
|
|
published to the timeline service or not by RM. This configuration setting
|
|
|
|
|
is for ATS V2.</description>
|
|
|
|
|
<name>yarn.rm.system-metrics-publisher.emit-container-events</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of worker threads that send the yarn system metrics
|
|
|
|
|
data.</description>
|
|
|
|
|
<name>yarn.resourcemanager.system-metrics-publisher.dispatcher.pool-size</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
This setting enables/disables timeline server v1 publisher to publish timeline events in batch.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.enable-batch</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The size of timeline server v1 publisher sending events in one request.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.batch-size</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When enable batch publishing in timeline server v1, we must avoid that the
|
|
|
|
|
publisher waits for a batch to be filled up and hold events in buffer for long
|
|
|
|
|
time. So we add another thread which send event's in the buffer periodically.
|
|
|
|
|
This config sets the interval of the cyclical sending thread.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.interval-seconds</name>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of diagnostics/failure messages can be saved in RM for
|
|
|
|
|
log aggregation. It also defines the number of diagnostics/failure
|
|
|
|
|
messages can be shown in log aggregation web ui.</description>
|
|
|
|
|
<name>yarn.resourcemanager.max-log-aggregation-diagnostics-in-memory</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Node Manager Configs -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM DelegationTokenRenewer thread count
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token-renewer.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM secret key update interval in ms
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation.key.update-interval</name>
|
|
|
|
|
<value>86400000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM delegation token maximum lifetime in ms
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation.token.max-lifetime</name>
|
|
|
|
|
<value>604800000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM delegation token update interval in ms
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation.token.renew-interval</name>
|
|
|
|
|
<value>86400000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
This configuration is used for
|
|
|
|
|
how often the tokens are scanned for expired tokens in milliseconds.
|
|
|
|
|
the background thread(delegation token remover thread)
|
|
|
|
|
will delete expired tokens after the configured time.
|
|
|
|
|
the default value is 1h.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation.token.remove-scan-interval</name>
|
|
|
|
|
<value>1h</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM DelegationTokenRenewer thread timeout
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token-renewer.thread-timeout</name>
|
|
|
|
|
<value>60s</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Default maximum number of retries for each RM DelegationTokenRenewer thread
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token-renewer.thread-retry-max-attempts</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Time interval between each RM DelegationTokenRenewer thread retry attempt
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.delegation-token-renewer.thread-retry-interval</name>
|
|
|
|
|
<value>60s</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Thread pool size for RMApplicationHistoryWriter.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.history-writer.multi-threaded-dispatcher.pool-size</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comma-separated list of values (in minutes) for schedule queue related
|
|
|
|
|
metrics.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.metrics.runtime.buckets</name>
|
|
|
|
|
<value>60,300,1440</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Interval for the roll over for the master key used to generate
|
|
|
|
|
NodeManager tokens. It is expected to be set to a value much larger
|
|
|
|
|
than yarn.nm.liveness-monitor.expiry-interval-ms.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-tokens.master-key-rolling-interval-secs</name>
|
|
|
|
|
<value>86400</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable the ResourceManager reservation system.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.reservation-system.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Java class to use as the ResourceManager reservation system.
|
|
|
|
|
By default, is set to
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.reservation.CapacityReservationSystem
|
|
|
|
|
when using CapacityScheduler and is set to
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.reservation.FairReservationSystem
|
|
|
|
|
when using FairScheduler.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.reservation-system.class</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The plan follower policy class name to use for the ResourceManager
|
|
|
|
|
reservation system.
|
|
|
|
|
By default, is set to
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.reservation.CapacitySchedulerPlanFollower
|
|
|
|
|
is used when using CapacityScheduler, and is set to
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.reservation.FairSchedulerPlanFollower
|
|
|
|
|
when using FairScheduler.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.reservation-system.plan.follower</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Step size of the reservation system in ms
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.reservation-system.planfollower.time-step</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The expiry interval for a container
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.rm.container-allocation.expiry-interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable/disable resource profiles
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.resource-profiles.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
If resource profiles is enabled, source file for the profiles
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.resource-profiles.source-file</name>
|
|
|
|
|
<value>resource-profiles.json</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Node Manager Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The hostname of the NM.</description>
|
|
|
|
|
<name>yarn.nodemanager.hostname</name>
|
|
|
|
|
<value>0.0.0.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the container manager in the NM.</description>
|
|
|
|
|
<name>yarn.nodemanager.address</name>
|
|
|
|
|
<value>${yarn.nodemanager.hostname}:0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The actual address the server will bind to. If this optional address is
|
|
|
|
|
set, the RPC and webapp servers will bind to this address and the port specified in
|
|
|
|
|
yarn.nodemanager.address and yarn.nodemanager.webapp.address, respectively. This is
|
|
|
|
|
most useful for making NM listen to all interfaces by setting to 0.0.0.0.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.bind-host</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Environment variables that should be forwarded from the NodeManager's
|
|
|
|
|
environment to the container's, specified as a comma separated list of
|
|
|
|
|
VARNAME=value pairs.
|
|
|
|
|
|
|
|
|
|
To define environment variables individually, you can specify
|
|
|
|
|
multiple properties of the form yarn.nodemanager.admin-env.VARNAME,
|
|
|
|
|
where VARNAME is the name of the environment variable. This is the only
|
|
|
|
|
way to add a variable when its value contains commas.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.admin-env</name>
|
|
|
|
|
<value>MALLOC_ARENA_MAX=$MALLOC_ARENA_MAX</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
* PATH components that will be prepended to the user's path.
|
|
|
|
|
* If this is defined and the user does not define PATH, NM will also
|
|
|
|
|
* append ":$PATH" to prevent this from eclipsing the PATH defined in
|
|
|
|
|
* the container. This feature is only available for Linux.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.force.path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Environment variables that containers may override rather than use NodeManager's default.</description>
|
|
|
|
|
<name>yarn.nodemanager.env-whitelist</name>
|
|
|
|
|
<value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_HOME,PATH,LANG,TZ</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>who will execute(launch) the containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-executor.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Comma separated List of container state transition listeners.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-state-transition-listener.classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads container manager uses.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-manager.thread-count</name>
|
|
|
|
|
<value>20</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads collector service uses.</description>
|
|
|
|
|
<name>yarn.nodemanager.collector-service.thread-count</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads used in cleanup.</description>
|
|
|
|
|
<name>yarn.nodemanager.delete.thread-count</name>
|
|
|
|
|
<value>4</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
How long the container executor should wait for the exit code file to
|
|
|
|
|
appear after a reacquired container has exited.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-executor.exit-code-file.timeout-ms</name>
|
|
|
|
|
<value>2000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
At the NM, the policy to determine whether to queue an
|
|
|
|
|
OPPORTUNISTIC container or not.
|
|
|
|
|
If set to BY_QUEUE_LEN, uses the queue capacity, as set by
|
|
|
|
|
yarn.nodemanager.opportunistic-containers-max-queue-length
|
|
|
|
|
to limit how many containers to accept/queue.
|
|
|
|
|
If set to BY_RESOURCES, limits the number of containers
|
|
|
|
|
accepted based on the resource capacity of the node.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.opportunistic-containers-queue-policy</name>
|
|
|
|
|
<value>BY_QUEUE_LEN</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Max number of OPPORTUNISTIC containers to queue at the
|
|
|
|
|
nodemanager (NM). If the value is 0 or negative,
|
|
|
|
|
NMs do not allow any OPPORTUNISTIC containers.
|
|
|
|
|
If the value is positive, the NM caps the number of OPPORTUNISTIC
|
|
|
|
|
containers that can be queued at the NM.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.opportunistic-containers-max-queue-length</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Number of seconds after an application finishes before the nodemanager's
|
|
|
|
|
DeletionService will delete the application's localized file directory
|
|
|
|
|
and log directory.
|
|
|
|
|
|
|
|
|
|
To diagnose YARN application problems, set this property's value large
|
|
|
|
|
enough (for example, to 600 = 10 minutes) to permit examination of these
|
|
|
|
|
directories. After changing the property's value, you must restart the
|
|
|
|
|
nodemanager in order for it to have an effect.
|
|
|
|
|
|
|
|
|
|
The roots of YARN applications' work directories is configurable with
|
|
|
|
|
the yarn.nodemanager.local-dirs property (see below), and the roots
|
|
|
|
|
of the YARN applications' log directories is configurable with the
|
|
|
|
|
yarn.nodemanager.log-dirs property (see also below).
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.delete.debug-delay-sec</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Keytab for NM.</description>
|
|
|
|
|
<name>yarn.nodemanager.keytab</name>
|
|
|
|
|
<value>/etc/krb5.keytab</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>List of directories to store localized files in. An
|
|
|
|
|
application's localized file directory will be found in:
|
|
|
|
|
${yarn.nodemanager.local-dirs}/usercache/${user}/appcache/application_${appid}.
|
|
|
|
|
Individual containers' work directories, called container_${contid}, will
|
|
|
|
|
be subdirectories of this.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.local-dirs</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/nm-local-dir</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>It limits the maximum number of files which will be localized
|
|
|
|
|
in a single local directory. If the limit is reached then sub-directories
|
|
|
|
|
will be created and new files will be localized in them. If it is set to
|
|
|
|
|
a value less than or equal to 36 [which are sub-directories (0-9 and then
|
|
|
|
|
a-z)] then NodeManager will fail to start. For example; [for public
|
|
|
|
|
cache] if this is configured with a value of 40 ( 4 files +
|
|
|
|
|
36 sub-directories) and the local-dir is "/tmp/local-dir1" then it will
|
|
|
|
|
allow 4 files to be created directly inside "/tmp/local-dir1/filecache".
|
|
|
|
|
For files that are localized further it will create a sub-directory "0"
|
|
|
|
|
inside "/tmp/local-dir1/filecache" and will localize files inside it
|
|
|
|
|
until it becomes full. If a file is removed from a sub-directory that
|
|
|
|
|
is marked full, then that sub-directory will be used back again to
|
|
|
|
|
localize files.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.local-cache.max-files-per-directory</name>
|
|
|
|
|
<value>8192</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Address where the localizer IPC is.</description>
|
|
|
|
|
<name>yarn.nodemanager.localizer.address</name>
|
|
|
|
|
<value>${yarn.nodemanager.hostname}:8040</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Address where the collector service IPC is.</description>
|
|
|
|
|
<name>yarn.nodemanager.collector-service.address</name>
|
|
|
|
|
<value>${yarn.nodemanager.hostname}:8048</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that controls whether yarn container events are
|
|
|
|
|
published to the timeline service or not by NM. This configuration setting
|
|
|
|
|
is for ATS V2.</description>
|
|
|
|
|
<name>yarn.nodemanager.emit-container-events</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Interval in between cache cleanups.</description>
|
|
|
|
|
<name>yarn.nodemanager.localizer.cache.cleanup.interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Target size of localizer cache in MB, per nodemanager. It is
|
|
|
|
|
a target retention size that only includes resources with PUBLIC and
|
|
|
|
|
PRIVATE visibility and excludes resources with APPLICATION visibility
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.localizer.cache.target-size-mb</name>
|
|
|
|
|
<value>10240</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads to handle localization requests.</description>
|
|
|
|
|
<name>yarn.nodemanager.localizer.client.thread-count</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Number of threads to use for localization fetching.</description>
|
|
|
|
|
<name>yarn.nodemanager.localizer.fetch.thread-count</name>
|
|
|
|
|
<value>4</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-localizer.java.opts</name>
|
|
|
|
|
<value>-Xmx256m</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The log level for container localizer while it is an independent process.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-localizer.log.level</name>
|
|
|
|
|
<value>INFO</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Where to store container logs. An application's localized log directory
|
|
|
|
|
will be found in ${yarn.nodemanager.log-dirs}/application_${appid}.
|
|
|
|
|
Individual containers' log directories will be below this, in directories
|
|
|
|
|
named container_{$contid}. Each container directory will contain the files
|
|
|
|
|
stderr, stdin, and syslog generated by that container.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-dirs</name>
|
|
|
|
|
<value>${yarn.log.dir}/userlogs</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The permissions settings used for the creation of container
|
|
|
|
|
directories when using DefaultContainerExecutor. This follows
|
|
|
|
|
standard user/group/all permissions format.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.default-container-executor.log-dirs.permissions</name>
|
|
|
|
|
<value>710</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether to enable log aggregation. Log aggregation collects
|
|
|
|
|
each container's logs and moves these logs onto a file-system, for e.g.
|
|
|
|
|
HDFS, after the application completes. Users can configure the
|
|
|
|
|
"yarn.nodemanager.remote-app-log-dir" and
|
|
|
|
|
"yarn.nodemanager.remote-app-log-dir-suffix" properties to determine
|
|
|
|
|
where these logs are moved to. Users can access the logs via the
|
|
|
|
|
Application Timeline Server.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.log-aggregation-enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether to enable application placement based on user ID passed via
|
|
|
|
|
application tags. When it is enabled, userid=<userId>
|
|
|
|
|
pattern will be checked and if found, the application will be placed
|
|
|
|
|
onto the found user's queue,
|
|
|
|
|
if the original user has enough rights on the passed user's queue.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-tag-based-placement.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comma separated list of users who can use the application tag based
|
|
|
|
|
placement, if it is enabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-tag-based-placement.username.whitelist</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How long to keep aggregation logs before deleting them. -1 disables.
|
|
|
|
|
Be careful set this too small and you will spam the name node.</description>
|
|
|
|
|
<name>yarn.log-aggregation.retain-seconds</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How long to wait between aggregated log retention checks.
|
|
|
|
|
If set to 0 or a negative value then the value is computed as one-tenth
|
|
|
|
|
of the aggregated log retention time. Be careful set this too small and
|
|
|
|
|
you will spam the name node.</description>
|
|
|
|
|
<name>yarn.log-aggregation.retain-check-interval-seconds</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The log files created under NM Local Directories
|
|
|
|
|
will be logged if it exceeds the configured bytes. This
|
|
|
|
|
only takes effect if log4j level is at least Debug.</description>
|
|
|
|
|
<name>yarn.log-aggregation.debug.filesize</name>
|
|
|
|
|
<value>104857600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Specify which log file controllers we will support. The first
|
|
|
|
|
file controller we add will be used to write the aggregated logs.
|
|
|
|
|
This comma separated configuration will work with the configuration:
|
|
|
|
|
yarn.log-aggregation.file-controller.%s.class which defines the supported
|
|
|
|
|
file controller's class. By default, the TFile controller would be used.
|
|
|
|
|
The user could override this configuration by adding more file controllers.
|
|
|
|
|
To support back-ward compatibility, make sure that we always
|
|
|
|
|
add TFile file controller.</description>
|
|
|
|
|
<name>yarn.log-aggregation.file-formats</name>
|
|
|
|
|
<value>TFile</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Class that supports TFile read and write operations.</description>
|
|
|
|
|
<name>yarn.log-aggregation.file-controller.TFile.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.logaggregation.filecontroller.tfile.LogAggregationTFileController</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
How long for ResourceManager to wait for NodeManager to report its
|
|
|
|
|
log aggregation status. If waiting time of which the log aggregation
|
|
|
|
|
status is reported from NodeManager exceeds the configured value, RM
|
|
|
|
|
will report log aggregation status for this NodeManager as TIME_OUT.
|
|
|
|
|
This configuration will be used in NodeManager as well to decide
|
|
|
|
|
whether and when to delete the cached log aggregation status.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.log-aggregation-status.time-out.ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether to clean up nodemanager logs when log aggregation is enabled. Setting to
|
|
|
|
|
false disables the cleanup nodemanager logging, and it causes disk full in the long run. Users
|
|
|
|
|
can set to false for test-only purpose.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.log-aggregation.enable-local-cleanup</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time in seconds to retain user logs. Only applicable if
|
|
|
|
|
log aggregation is disabled
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log.retain-seconds</name>
|
|
|
|
|
<value>10800</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Where to aggregate logs to.</description>
|
|
|
|
|
<name>yarn.nodemanager.remote-app-log-dir</name>
|
|
|
|
|
<value>/tmp/logs</value>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<description>The remote log dir will be created at
|
|
|
|
|
{yarn.nodemanager.remote-app-log-dir}/${user}/{thisParam}
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.remote-app-log-dir-suffix</name>
|
|
|
|
|
<value>logs</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If set to true, the older application log directory
|
|
|
|
|
will be considered while fetching application logs.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.remote-app-log-dir-include-older</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If the NodeManager creates the remote-app-log-dir folder,
|
|
|
|
|
it will be created with this groupname.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.remote-app-log-dir.groupname</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Generate additional logs about container launches.
|
|
|
|
|
Currently, this creates a copy of the launch script and lists the
|
|
|
|
|
directory contents of the container work dir. When listing directory
|
|
|
|
|
contents, we follow symlinks to a max-depth of 5(including symlinks
|
|
|
|
|
which point to outside the container work dir) which may lead to a
|
|
|
|
|
slowness in launching containers.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-container-debug-info.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Amount of physical memory, in MB, that is reserved
|
|
|
|
|
for non-YARN processes. This configuration is only used if
|
|
|
|
|
yarn.nodemanager.resource.detect-hardware-capabilities is set
|
|
|
|
|
to true and yarn.nodemanager.resource.memory-mb is -1. If set
|
|
|
|
|
to -1, this amount is calculated as
|
|
|
|
|
20% of (system memory - 2*HADOOP_HEAPSIZE)
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.system-reserved-memory-mb</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether YARN CGroups memory tracking is enabled.</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.memory.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether YARN CGroups strict memory enforcement is enabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.memory.enforced</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>If memory limit is enforced, this the percentage of soft limit
|
|
|
|
|
compared to the memory assigned to the container. If there is memory
|
|
|
|
|
pressure container memory usage will be pushed back to its soft limit
|
|
|
|
|
by swapping out memory.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.memory.cgroups.soft-limit-percentage</name>
|
|
|
|
|
<value>90.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Container swappiness is the likelihood a page will be swapped
|
|
|
|
|
out compared to be kept in memory. Value is between 0-100.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.memory.cgroups.swappiness</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether physical memory limits will be enforced for
|
|
|
|
|
containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.pmem-check-enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether virtual memory limits will be enforced for
|
|
|
|
|
containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.vmem-check-enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<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>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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-as-cores</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Thread pool size for LogAggregationService in Node Manager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.logaggregation.threadpool-size-max</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Percentage of CPU that can be allocated
|
|
|
|
|
for containers. This setting allows users to limit the amount of
|
|
|
|
|
CPU that YARN containers use. Currently functional only
|
|
|
|
|
on Linux using cgroups. The default is to use 100% of CPU.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource.percentage-physical-cpu-limit</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<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>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>NM Webapp address.</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.address</name>
|
|
|
|
|
<value>${yarn.nodemanager.hostname}:8042</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The https adddress of the NM web application.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.https.address</name>
|
|
|
|
|
<value>0.0.0.0:8044</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Kerberos keytab file to be used for spnego filter for the NM web
|
|
|
|
|
interface.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.spnego-keytab-file</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Kerberos principal to be used for spnego filter for the NM web
|
|
|
|
|
interface.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.spnego-principal</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How often to monitor the node and the containers.
|
|
|
|
|
If 0 or negative, monitoring is disabled.</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-monitor.interval-ms</name>
|
|
|
|
|
<value>3000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Class that calculates current resource utilization.</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-calculator.class</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable container monitor</description>
|
|
|
|
|
<name>yarn.nodemanager.container-monitor.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How often to monitor containers. If not set, the value for
|
|
|
|
|
yarn.nodemanager.resource-monitor.interval-ms will be used.
|
|
|
|
|
If 0 or negative, container monitoring is disabled.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-monitor.interval-ms</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Flag to enable the container log monitor which enforces
|
|
|
|
|
container log directory size limits.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-log-monitor.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>How often to check the usage of a container's log directories
|
|
|
|
|
in milliseconds</description>
|
|
|
|
|
<name>yarn.nodemanager.container-log-monitor.interval-ms</name>
|
|
|
|
|
<value>60000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The disk space limit, in bytes, for a single
|
|
|
|
|
container log directory</description>
|
|
|
|
|
<name>yarn.nodemanager.container-log-monitor.dir-size-limit-bytes</name>
|
|
|
|
|
<value>1000000000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The disk space limit, in bytes, for all of a container's
|
|
|
|
|
logs</description>
|
|
|
|
|
<name>yarn.nodemanager.container-log-monitor.total-size-limit-bytes</name>
|
|
|
|
|
<value>10000000000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Class that calculates containers current resource utilization.
|
|
|
|
|
If not set, the value for yarn.nodemanager.resource-calculator.class will
|
|
|
|
|
be used.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-monitor.resource-calculator.class</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The nodemanager health check scripts to run.</description>
|
|
|
|
|
<name>yarn.nodemanager.health-checker.scripts</name>
|
|
|
|
|
<value>script</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Health check script time out period.</description>
|
|
|
|
|
<name>yarn.nodemanager.health-checker.timeout-ms</name>
|
|
|
|
|
<value>1200000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether or not to run the node health script
|
|
|
|
|
before the NM starts up.</description>
|
|
|
|
|
<name>yarn.nodemanager.health-checker.run-before-startup</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Frequency of running node health scripts.</description>
|
|
|
|
|
<name>yarn.nodemanager.health-checker.interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Frequency of running disk health checker code.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.interval-ms</name>
|
|
|
|
|
<value>120000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The minimum fraction of number of disks to be healthy for the
|
|
|
|
|
nodemanager to launch new containers. This correspond to both
|
|
|
|
|
yarn.nodemanager.local-dirs and yarn.nodemanager.log-dirs. i.e. If there
|
|
|
|
|
are less number of healthy local-dirs (or log-dirs) available, then
|
|
|
|
|
new containers will not be launched on this node.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.min-healthy-disks</name>
|
|
|
|
|
<value>0.25</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable/Disable the disk utilisation percentage
|
|
|
|
|
threshold for disk health checker.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.disk-utilization-threshold.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description> Enable/Disable the minimum disk free
|
|
|
|
|
space threshold for disk health checker.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.disk-free-space-threshold.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The maximum percentage of disk space utilization allowed after
|
|
|
|
|
which a disk is marked as bad. Values can range from 0.0 to 100.0.
|
|
|
|
|
If the value is greater than or equal to 100, the nodemanager will check
|
|
|
|
|
for full disk. This applies to yarn.nodemanager.local-dirs and
|
|
|
|
|
yarn.nodemanager.log-dirs when
|
|
|
|
|
yarn.nodemanager.disk-health-checker.disk-utilization-threshold.enabled is true.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage</name>
|
|
|
|
|
<value>90.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The low threshold percentage of disk space used when a bad disk is
|
|
|
|
|
marked as good. Values can range from 0.0 to 100.0. This applies to
|
|
|
|
|
yarn.nodemanager.local-dirs and yarn.nodemanager.log-dirs.
|
|
|
|
|
Note that if its value is more than yarn.nodemanager.disk-health-checker.
|
|
|
|
|
max-disk-utilization-per-disk-percentage or not set, it will be set to the same value as
|
|
|
|
|
yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.disk-utilization-watermark-low-per-disk-percentage</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The minimum space in megabytes that must be available on a disk for
|
|
|
|
|
it to be used. If space on a disk falls below this threshold, it will be marked
|
|
|
|
|
as bad. This applies to yarn.nodemanager.local-dirs and
|
|
|
|
|
yarn.nodemanager.log-dirs when
|
|
|
|
|
yarn.nodemanager.disk-health-checker.disk-free-space-threshold.enabled is true.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The minimum space in megabytes that must be available on a bad
|
|
|
|
|
disk for it to be marked as good. This value should not be less
|
|
|
|
|
than yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb.
|
|
|
|
|
If it is less than yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb,
|
|
|
|
|
or it is not set, it will be set to the
|
|
|
|
|
same value as yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb.
|
|
|
|
|
This applies to yarn.nodemanager.local-dirs and yarn.nodemanager.log-dirs.</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.min-free-space-per-disk-watermark-high-mb</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The path to the Linux container executor.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.path</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The class which should help the LCE handle resources.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.resources-handler.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.util.DefaultLCEResourcesHandler</value>
|
|
|
|
|
<!-- <value>org.apache.hadoop.yarn.server.nodemanager.util.CgroupsLCEResourcesHandler</value> -->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The cgroups hierarchy under which to place YARN proccesses (cannot contain commas).
|
|
|
|
|
If yarn.nodemanager.linux-container-executor.cgroups.mount is false
|
|
|
|
|
(that is, if cgroups have been pre-configured) and the YARN user has write
|
|
|
|
|
access to the parent directory, then the directory will be created.
|
|
|
|
|
If the directory already exists, the administrator has to give YARN
|
|
|
|
|
write permissions to it recursively.
|
|
|
|
|
This property only applies when the LCE resources handler is set to
|
|
|
|
|
CgroupsLCEResourcesHandler.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.hierarchy</name>
|
|
|
|
|
<value>/hadoop-yarn</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether the LCE should attempt to mount cgroups if not found.
|
|
|
|
|
This property only applies when the LCE resources handler is set to
|
|
|
|
|
CgroupsLCEResourcesHandler.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.mount</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This property sets the path from which YARN will read the
|
|
|
|
|
CGroups configuration. YARN has built-in functionality to discover the
|
|
|
|
|
system CGroup mount paths, so use this property only if YARN's automatic
|
|
|
|
|
mount path discovery does not work.
|
|
|
|
|
|
|
|
|
|
The path specified by this property must exist before the NodeManager is
|
|
|
|
|
launched.
|
|
|
|
|
If yarn.nodemanager.linux-container-executor.cgroups.mount is set to true,
|
|
|
|
|
YARN will first try to mount the CGroups at the specified path before
|
|
|
|
|
reading them.
|
|
|
|
|
If yarn.nodemanager.linux-container-executor.cgroups.mount is set to
|
|
|
|
|
false, YARN will read the CGroups at the specified path.
|
|
|
|
|
If this property is empty, YARN tries to detect the CGroups location.
|
|
|
|
|
|
|
|
|
|
Please refer to NodeManagerCgroups.html in the documentation for further
|
|
|
|
|
details.
|
|
|
|
|
This property only applies when the LCE resources handler is set to
|
|
|
|
|
CgroupsLCEResourcesHandler.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.mount-path</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Delay in ms between attempts to remove linux cgroup</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.delete-delay-ms</name>
|
|
|
|
|
<value>20</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This determines which of the two modes that LCE should use on
|
|
|
|
|
a non-secure cluster. If this value is set to true, then all containers
|
|
|
|
|
will be launched as the user specified in
|
|
|
|
|
yarn.nodemanager.linux-container-executor.nonsecure-mode.local-user. If
|
|
|
|
|
this value is set to false, then containers will run as the user who
|
|
|
|
|
submitted the application.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.nonsecure-mode.limit-users</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The UNIX user that containers will run as when
|
|
|
|
|
Linux-container-executor is used in nonsecure mode (a use case for this
|
|
|
|
|
is using cgroups) if the
|
|
|
|
|
yarn.nodemanager.linux-container-executor.nonsecure-mode.limit-users is
|
|
|
|
|
set to true.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.nonsecure-mode.local-user</name>
|
|
|
|
|
<value>nobody</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The allowed pattern for UNIX user names enforced by
|
|
|
|
|
Linux-container-executor when used in nonsecure mode (use case for this
|
|
|
|
|
is using cgroups). The default value is taken from /usr/sbin/adduser</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.nonsecure-mode.user-pattern</name>
|
|
|
|
|
<value>^[_.A-Za-z0-9][-@_.A-Za-z0-9]{0,255}?[$]?$</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This flag determines whether apps should run with strict resource limits
|
|
|
|
|
or be allowed to consume spare resources if they need them. For example, turning the
|
|
|
|
|
flag on will restrict apps to use only their share of CPU, even if the node has spare
|
|
|
|
|
CPU cycles. The default value is false i.e. use available resources. Please note that
|
|
|
|
|
turning this flag on may reduce job throughput on the cluster. This setting does
|
|
|
|
|
not apply to other subsystems like memory.</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.strict-resource-usage</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Comma separated list of runtimes that are allowed when using
|
|
|
|
|
LinuxContainerExecutor. The allowed values are default, docker, runc, and
|
|
|
|
|
javasandbox.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.allowed-runtimes</name>
|
|
|
|
|
<value>default</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Default container runtime to use.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.type</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This configuration setting determines the capabilities
|
|
|
|
|
assigned to docker containers when they are launched. While these may not
|
|
|
|
|
be case-sensitive from a docker perspective, it is best to keep these
|
|
|
|
|
uppercase. To run without any capabilities, set this value to
|
|
|
|
|
"none" or "NONE"</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.capabilities</name>
|
|
|
|
|
<value>CHOWN,DAC_OVERRIDE,FSETID,FOWNER,MKNOD,NET_RAW,SETGID,SETUID,SETFCAP,SETPCAP,NET_BIND_SERVICE,SYS_CHROOT,KILL,AUDIT_WRITE</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Default docker image to be used when the docker runtime is
|
|
|
|
|
selected.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.image-name</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Default option to decide whether to pull the latest image
|
|
|
|
|
or not.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.image-update</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This configuration setting determines if privileged docker
|
|
|
|
|
containers are allowed on this cluster. Privileged containers are granted
|
|
|
|
|
the complete set of capabilities and are not subject to the limitations
|
|
|
|
|
imposed by the device cgroup controller. In other words, privileged
|
|
|
|
|
containers can do almost everything that the host can do. Use with
|
|
|
|
|
extreme care.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.privileged-containers.allowed</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This configuration setting determines who is allowed to run
|
|
|
|
|
privileged docker containers on this cluster. Use with extreme care.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.privileged-containers.acl</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The set of networks allowed when launching containers using the
|
|
|
|
|
DockerContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.allowed-container-networks</name>
|
|
|
|
|
<value>host,none,bridge</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The network used when launching containers using the
|
|
|
|
|
DockerContainerRuntime when no network is specified in the request
|
|
|
|
|
. This network must be one of the (configurable) set of allowed container
|
|
|
|
|
networks.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.default-container-network</name>
|
|
|
|
|
<value>host</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The set of runtimes allowed when launching containers using the
|
|
|
|
|
DockerContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.allowed-container-runtimes</name>
|
|
|
|
|
<value>runc</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This configuration setting determines whether the host's PID
|
|
|
|
|
namespace is allowed for docker containers on this cluster.
|
|
|
|
|
Use with care.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.host-pid-namespace.allowed</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Property to enable docker user remapping</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.enable-userremapping.allowed</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>lower limit for acceptable uids of user remapped user</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.userremapping-uid-threshold</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>lower limit for acceptable gids of user remapped user</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.userremapping-gid-threshold</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether or not users are allowed to request that Docker
|
|
|
|
|
containers honor the debug deletion delay. This is useful for
|
|
|
|
|
troubleshooting Docker container related launch failures.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.delayed-removal.allowed</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>A configurable value to pass to the Docker Stop command. This value
|
|
|
|
|
defines the number of seconds between the docker stop command sending
|
|
|
|
|
a SIGTERM and a SIGKILL.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.stop.grace-period</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default list of read-only mounts to be bind-mounted
|
|
|
|
|
into all Docker containers that use DockerContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.default-ro-mounts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default list of read-write mounts to be bind-mounted
|
|
|
|
|
into all Docker containers that use DockerContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.default-rw-mounts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default list of tmpfs mounts to be mounted into all Docker
|
|
|
|
|
containers that use DockerContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.docker.default-tmpfs-mounts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The runC image tag to manifest plugin
|
|
|
|
|
class to be used.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.runtime.runc.ImageTagToManifestPlugin</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The runC manifest to resources plugin class to
|
|
|
|
|
be used.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.manifest-to-resources-plugin</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.runtime.runc.HdfsManifestToResourcesPlugin</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The HDFS location under which the oci image manifests, layers,
|
|
|
|
|
and configs directories exist.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-toplevel-dir</name>
|
|
|
|
|
<value>/runc-root</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Target count of layer mounts that we should keep on disk
|
|
|
|
|
at one time.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.layer-mounts-to-keep</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The interval in seconds between executions of
|
|
|
|
|
reaping layer mounts.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.layer-mounts-interval-secs</name>
|
|
|
|
|
<value>600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Image to be used if no other image is specified.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-name</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Allow or disallow privileged containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.privileged-containers.allowed</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The set of networks allowed when launching containers
|
|
|
|
|
using the RuncContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.allowed-container-networks</name>
|
|
|
|
|
<value>host,none,bridge</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The set of runtimes allowed when launching containers
|
|
|
|
|
using the RuncContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.allowed-container-runtimes</name>
|
|
|
|
|
<value>runc</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>ACL list for users allowed to run privileged
|
|
|
|
|
containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.privileged-containers.acl</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Allow host pid namespace for runC containers.
|
|
|
|
|
Use with care.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.host-pid-namespace.allowed</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default list of read-only mounts to be bind-mounted
|
|
|
|
|
into all runC containers that use RuncContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.default-ro-mounts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The default list of read-write mounts to be bind-mounted
|
|
|
|
|
into all runC containers that use RuncContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.default-rw-mounts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Path to the seccomp profile to use with runC
|
|
|
|
|
containers</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.seccomp-profile</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The HDFS location where the runC image tag to hash
|
|
|
|
|
file exists.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.hdfs-hash-file</name>
|
|
|
|
|
<value>/runc-root/image-tag-to-hash</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The local file system location where the runC image tag
|
|
|
|
|
to hash file exists.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.local-hash-file</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The interval in seconds between refreshing the hdfs image tag
|
|
|
|
|
to hash cache.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.cache-refresh-interval-secs</name>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of manifests to cache in the image tag
|
|
|
|
|
to hash cache.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.num-manifests-to-cache</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The timeout value in seconds for the values in
|
|
|
|
|
the stat cache.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.hdfs-manifest-to-resources-plugin.stat-cache-timeout-interval-secs</name>
|
|
|
|
|
<value>360</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The size of the stat cache which stores stats of the
|
|
|
|
|
layers and config.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.runc.hdfs-manifest-to-resources-plugin.stat-cache-size</name>
|
|
|
|
|
<value>500</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The mode in which the Java Container Sandbox should run detailed by
|
|
|
|
|
the JavaSandboxLinuxContainerRuntime.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.sandbox-mode</name>
|
|
|
|
|
<value>disabled</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Permissions for application local directories.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.sandbox-mode.local-dirs.permissions</name>
|
|
|
|
|
<value>read</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Location for non-default java policy file.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.sandbox-mode.policy</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The group which will run by default without the java security
|
|
|
|
|
manager.</description>
|
|
|
|
|
<name>yarn.nodemanager.runtime.linux.sandbox-mode.whitelist-group</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This flag determines whether memory limit will be set for the Windows Job
|
|
|
|
|
Object of the containers launched by the default container executor.</description>
|
|
|
|
|
<name>yarn.nodemanager.windows-container.memory-limit.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This flag determines whether CPU limit will be set for the Windows Job
|
|
|
|
|
Object of the containers launched by the default container executor.</description>
|
|
|
|
|
<name>yarn.nodemanager.windows-container.cpu-limit.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Interval of time the linux container executor should try cleaning up
|
|
|
|
|
cgroups entry when cleaning up a container.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.linux-container-executor.cgroups.delete-timeout-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>T-file compression types used to compress aggregated logs.</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.compression-type</name>
|
|
|
|
|
<value>none</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The kerberos principal for the node manager.</description>
|
|
|
|
|
<name>yarn.nodemanager.principal</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>A comma separated list of services where service name should only
|
|
|
|
|
contain a-zA-Z0-9_ and can not start with numbers</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<!--<value>mapreduce_shuffle</value>-->
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Boolean indicating whether loading aux services from a manifest
|
|
|
|
|
is enabled. If enabled, aux services may be dynamically modified through
|
|
|
|
|
reloading the manifest via filesystem changes or a REST API. When
|
|
|
|
|
enabled, aux services configuration properties unrelated to the manifest
|
|
|
|
|
will be ignored.</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.manifest.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>A file containing auxiliary service specifications.</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.manifest</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Length of time in ms to wait between reloading aux services
|
|
|
|
|
manifest. If 0 or less, manifest will not be reloaded.</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.manifest.reload-ms</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Provide local directory which includes the related jar file as well as all the dependencies’
|
|
|
|
|
jar file. We could specify the single jar file or use ${local_dir_to_jar}/* to load all
|
|
|
|
|
jars under the dep directory.</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.%s.classpath</name>
|
|
|
|
|
<value>NONE</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Normally this configuration shouldn't be manually set. The class would be loaded from customized
|
|
|
|
|
classpath if it does not belong to system-classes. By default, the package org.apache.hadoop is part of the
|
|
|
|
|
system-classes. If for example the class CustomAuxService is in the package org.apache.hadoop, it will not be
|
|
|
|
|
loaded from the customized classpath. To solve this, either the package of CustomAuxService could be changed,
|
|
|
|
|
or a separate system-classes could be configured which excludes the package org.apache.hadoop.</description>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.%s.system-classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>No. of ms to wait between sending a SIGTERM and SIGKILL to a container</description>
|
|
|
|
|
<name>yarn.nodemanager.sleep-delay-before-sigkill.ms</name>
|
|
|
|
|
<value>250</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max time to wait for a process to come up when trying to cleanup a container</description>
|
|
|
|
|
<name>yarn.nodemanager.process-kill-wait.ms</name>
|
|
|
|
|
<value>5000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The minimum allowed version of a resourcemanager that a nodemanager will connect to.
|
|
|
|
|
The valid values are NONE (no version checking), EqualToNM (the resourcemanager's version is
|
|
|
|
|
equal to or greater than the NM version), or a Version String.</description>
|
|
|
|
|
<name>yarn.nodemanager.resourcemanager.minimum.version</name>
|
|
|
|
|
<value>NONE</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Maximum size of contain's diagnostics to keep for relaunching
|
|
|
|
|
container case.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-diagnostics-maximum-size</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Minimum container restart interval in milliseconds.</description>
|
|
|
|
|
<name>yarn.nodemanager.container-retry-minimum-interval-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max number of threads in NMClientAsync to process container
|
|
|
|
|
management events</description>
|
|
|
|
|
<name>yarn.client.nodemanager-client-async.thread-pool-max-size</name>
|
|
|
|
|
<value>500</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max time to wait to establish a connection to NM</description>
|
|
|
|
|
<name>yarn.client.nodemanager-connect.max-wait-ms</name>
|
|
|
|
|
<value>180000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time interval between each attempt to connect to NM</description>
|
|
|
|
|
<name>yarn.client.nodemanager-connect.retry-interval-ms</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Max time to wait for NM to connect to RM.
|
|
|
|
|
When not set, proxy will fall back to use value of
|
|
|
|
|
yarn.resourcemanager.connect.max-wait.ms.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resourcemanager.connect.max-wait.ms</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Time interval between each NM attempt to connect to RM.
|
|
|
|
|
When not set, proxy will fall back to use value of
|
|
|
|
|
yarn.resourcemanager.connect.retry-interval.ms.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resourcemanager.connect.retry-interval.ms</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Maximum number of proxy connections to cache for node managers. If set
|
|
|
|
|
to a value greater than zero then the cache is enabled and the NMClient
|
|
|
|
|
and MRAppMaster will cache the specified number of node manager proxies.
|
|
|
|
|
There will be at max one proxy per node manager. Ex. configuring it to a
|
|
|
|
|
value of 5 will make sure that client will at max have 5 proxies cached
|
|
|
|
|
with 5 different node managers. These connections for these proxies will
|
|
|
|
|
be timed out if idle for more than the system wide idle timeout period.
|
|
|
|
|
Note that this could cause issues on large clusters as many connections
|
|
|
|
|
could linger simultaneously and lead to a large number of connection
|
|
|
|
|
threads. The token used for authentication will be used only at
|
|
|
|
|
connection creation time. If a new token is received then the earlier
|
|
|
|
|
connection should be closed in order to use the new token. This and
|
|
|
|
|
(yarn.client.nodemanager-client-async.thread-pool-max-size) are related
|
|
|
|
|
and should be in sync (no need for them to be equal).
|
|
|
|
|
If the value of this property is zero then the connection cache is
|
|
|
|
|
disabled and connections will use a zero idle timeout to prevent too
|
|
|
|
|
many connection threads on large clusters.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.client.max-cached-nodemanagers-proxies</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable the node manager to recover after starting</description>
|
|
|
|
|
<name>yarn.nodemanager.recovery.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The local filesystem directory in which the node manager will
|
|
|
|
|
store state when recovery is enabled.</description>
|
|
|
|
|
<name>yarn.nodemanager.recovery.dir</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn-nm-recovery</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The time in seconds between full compactions of the NM state
|
|
|
|
|
database. Setting the interval to zero disables the full compaction
|
|
|
|
|
cycles.</description>
|
|
|
|
|
<name>yarn.nodemanager.recovery.compaction-interval-secs</name>
|
|
|
|
|
<value>3600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether the nodemanager is running under supervision. A
|
|
|
|
|
nodemanager that supports recovery and is running under supervision
|
|
|
|
|
will not try to cleanup containers as it exits with the assumption
|
|
|
|
|
it will be immediately be restarted and recover containers.</description>
|
|
|
|
|
<name>yarn.nodemanager.recovery.supervised</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Adjustment to the container OS scheduling priority. In Linux, passed
|
|
|
|
|
directly to the nice command. If unspecified then containers are launched
|
|
|
|
|
without any explicit OS priority.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-executor.os.sched.priority.adjustment</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable container metrics
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-metrics.enable</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Container metrics flush period in ms. Set to -1 for flush on completion.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-metrics.period-ms</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The delay time ms to unregister container metrics after completion.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-metrics.unregister-delay-ms</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Class used to calculate current container resource utilization.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-monitor.process-tree.class</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable NodeManager disk health checker
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-health-checker.enable</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Number of threads to use in NM log cleanup. Used when log aggregation
|
|
|
|
|
is disabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log.deletion-threads-count</name>
|
|
|
|
|
<value>4</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The Windows group that the windows-container-executor should run as.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.windows-secure-container-executor.group</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Map Reduce Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
|
|
|
|
|
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- WebAppProxy Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The kerberos principal for the proxy, if the proxy is not
|
|
|
|
|
running as part of the RM.</description>
|
|
|
|
|
<name>yarn.web-proxy.principal</name>
|
|
|
|
|
<value/>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Keytab for WebAppProxy, if the proxy is not running as part of
|
|
|
|
|
the RM.</description>
|
|
|
|
|
<name>yarn.web-proxy.keytab</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address for the web proxy as HOST:PORT, if this is not
|
|
|
|
|
given then the proxy will run as part of the RM</description>
|
|
|
|
|
<name>yarn.web-proxy.address</name>
|
|
|
|
|
<value/>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The actual address the web proxy will bind to. If this optional
|
|
|
|
|
address is set, it overrides only the hostname portion of yarn.web-proxy.address.
|
|
|
|
|
This is useful for making the web proxy server listen on all interfaces by setting
|
|
|
|
|
it to 0.0.0.0 </description>
|
|
|
|
|
<name>yarn.web-proxy.bind-host</name>
|
|
|
|
|
<value/>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable the web proxy connection timeout, default is enabled.</description>
|
|
|
|
|
<name>yarn.resourcemanager.proxy.timeout.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The web proxy connection timeout.</description>
|
|
|
|
|
<name>yarn.resourcemanager.proxy.connection.timeout</name>
|
|
|
|
|
<value>60000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Applications' Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
CLASSPATH for YARN applications. A comma-separated list
|
|
|
|
|
of CLASSPATH entries. When this value is empty, the following default
|
|
|
|
|
CLASSPATH for YARN applications would be used.
|
|
|
|
|
For Linux:
|
|
|
|
|
$HADOOP_CONF_DIR,
|
|
|
|
|
$HADOOP_COMMON_HOME/share/hadoop/common/*,
|
|
|
|
|
$HADOOP_COMMON_HOME/share/hadoop/common/lib/*,
|
|
|
|
|
$HADOOP_HDFS_HOME/share/hadoop/hdfs/*,
|
|
|
|
|
$HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*,
|
|
|
|
|
$HADOOP_YARN_HOME/share/hadoop/yarn/*,
|
|
|
|
|
$HADOOP_YARN_HOME/share/hadoop/yarn/lib/*
|
|
|
|
|
For Windows:
|
|
|
|
|
%HADOOP_CONF_DIR%,
|
|
|
|
|
%HADOOP_COMMON_HOME%/share/hadoop/common/*,
|
|
|
|
|
%HADOOP_COMMON_HOME%/share/hadoop/common/lib/*,
|
|
|
|
|
%HADOOP_HDFS_HOME%/share/hadoop/hdfs/*,
|
|
|
|
|
%HADOOP_HDFS_HOME%/share/hadoop/hdfs/lib/*,
|
|
|
|
|
%HADOOP_YARN_HOME%/share/hadoop/yarn/*,
|
|
|
|
|
%HADOOP_YARN_HOME%/share/hadoop/yarn/lib/*
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.application.classpath</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Timeline Service Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Indicate what is the current version of the running
|
|
|
|
|
timeline service. For example, if "yarn.timeline-service.version" is 1.5,
|
|
|
|
|
and "yarn.timeline-service.enabled" is true, it means the cluster will and
|
|
|
|
|
should bring up the timeline service v.1.5 (and nothing else).
|
|
|
|
|
On the client side, if the client uses the same version of timeline service,
|
|
|
|
|
it should succeed. If the client chooses to use a smaller version in spite of this,
|
|
|
|
|
then depending on how robust the compatibility story is between versions,
|
|
|
|
|
the results may vary.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.version</name>
|
|
|
|
|
<value>1.0f</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
In the server side it indicates whether timeline service is enabled or not.
|
|
|
|
|
And in the client side, users can enable it to indicate whether client wants
|
|
|
|
|
to use timeline service. If its enabled in the client side along with
|
|
|
|
|
security, then yarn client tries to fetch the delegation tokens for the
|
|
|
|
|
timeline server.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The hostname of the timeline service web application.</description>
|
|
|
|
|
<name>yarn.timeline-service.hostname</name>
|
|
|
|
|
<value>0.0.0.0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>This is default address for the timeline server to start the
|
|
|
|
|
RPC server.</description>
|
|
|
|
|
<name>yarn.timeline-service.address</name>
|
|
|
|
|
<value>${yarn.timeline-service.hostname}:10200</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The http address of the timeline service web application.</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.address</name>
|
|
|
|
|
<value>${yarn.timeline-service.hostname}:8188</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The https address of the timeline service web application.</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.https.address</name>
|
|
|
|
|
<value>${yarn.timeline-service.hostname}:8190</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The actual address the server will bind to. If this optional address is
|
|
|
|
|
set, the RPC and webapp servers will bind to this address and the port specified in
|
|
|
|
|
yarn.timeline-service.address and yarn.timeline-service.webapp.address, respectively.
|
|
|
|
|
This is most useful for making the service listen to all interfaces by setting to
|
|
|
|
|
0.0.0.0.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.bind-host</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Defines the max number of applications could be fetched using REST API or
|
|
|
|
|
application history protocol and shown in timeline server web ui.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.generic-application-history.max-applications</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Store class name for timeline store.</description>
|
|
|
|
|
<name>yarn.timeline-service.store-class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable age off of timeline store data.</description>
|
|
|
|
|
<name>yarn.timeline-service.ttl-enable</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time to live for timeline store data in milliseconds.</description>
|
|
|
|
|
<name>yarn.timeline-service.ttl-ms</name>
|
|
|
|
|
<value>604800000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Store file name for leveldb timeline store.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-timeline-store.path</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn/timeline</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Length of time to wait between deletion cycles of leveldb timeline store in milliseconds.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-timeline-store.ttl-interval-ms</name>
|
|
|
|
|
<value>300000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Size of read cache for uncompressed blocks for leveldb timeline store in bytes.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-timeline-store.read-cache-size</name>
|
|
|
|
|
<value>104857600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Size of cache for recently read entity start times for leveldb timeline store in number of entities.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-timeline-store.start-time-read-cache-size</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Size of cache for recently written entity start times for leveldb timeline store in number of entities.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-timeline-store.start-time-write-cache-size</name>
|
|
|
|
|
<value>10000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Handler thread count to serve the client RPC requests.</description>
|
|
|
|
|
<name>yarn.timeline-service.handler-thread-count</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.http-authentication.type</name>
|
|
|
|
|
<value>simple</value>
|
|
|
|
|
<description>
|
|
|
|
|
Defines authentication used for the timeline server HTTP endpoint.
|
|
|
|
|
Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME#
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.http-authentication.simple.anonymous.allowed</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
<description>
|
|
|
|
|
Indicates if anonymous requests are allowed by the timeline server when using
|
|
|
|
|
'simple' authentication.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The Kerberos principal for the timeline server.</description>
|
|
|
|
|
<name>yarn.timeline-service.principal</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The Kerberos keytab for the timeline server.</description>
|
|
|
|
|
<name>yarn.timeline-service.keytab</name>
|
|
|
|
|
<value>/etc/krb5.keytab</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Comma separated list of UIs that will be hosted</description>
|
|
|
|
|
<name>yarn.timeline-service.ui-names</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Default maximum number of retries for timeline service client
|
|
|
|
|
and value -1 means no limit.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.client.max-retries</name>
|
|
|
|
|
<value>30</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Client policy for whether timeline operations are non-fatal.
|
|
|
|
|
Should the failure to obtain a delegation token be considered an application
|
|
|
|
|
failure (option = false), or should the client attempt to continue to
|
|
|
|
|
publish information without it (option=true)</description>
|
|
|
|
|
<name>yarn.timeline-service.client.best-effort</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Default retry time interval for timeline servive client.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.client.retry-interval-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The time period for which timeline v2 client will wait for draining
|
|
|
|
|
leftover entities after stop.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.client.drain-entities.timeout.ms</name>
|
|
|
|
|
<value>2000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Enable timeline server to recover state after starting. If
|
|
|
|
|
true, then yarn.timeline-service.state-store-class must be specified.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.recovery.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Store class name for timeline state store.</description>
|
|
|
|
|
<name>yarn.timeline-service.state-store-class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timeline.recovery.LeveldbTimelineStateStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Store file name for leveldb state store.</description>
|
|
|
|
|
<name>yarn.timeline-service.leveldb-state-store.path</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn/timeline</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Timeline Service v1.5 Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.cache-store-class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timeline.MemoryTimelineStore</value>
|
|
|
|
|
<description>Caching storage timeline server v1.5 is using. </description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.active-dir</name>
|
|
|
|
|
<value>/tmp/entity-file-history/active</value>
|
|
|
|
|
<description>HDFS path to store active application’s timeline data</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.done-dir</name>
|
|
|
|
|
<value>/tmp/entity-file-history/done/</value>
|
|
|
|
|
<description>HDFS path to store done application’s timeline data</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.group-id-plugin-classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
Plugins that can translate a timeline entity read request into
|
|
|
|
|
a list of timeline entity group ids, separated by commas.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.group-id-plugin-classpath</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
Classpath for all plugins defined in
|
|
|
|
|
yarn.timeline-service.entity-group-fs-store.group-id-plugin-classes.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.summary-store</name>
|
|
|
|
|
<description>Summary storage for ATS v1.5</description>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.scan-interval-seconds</name>
|
|
|
|
|
<description>
|
|
|
|
|
Scan interval for ATS v1.5 entity group file system storage reader.This
|
|
|
|
|
value controls how frequent the reader will scan the HDFS active directory
|
|
|
|
|
for application status.
|
|
|
|
|
</description>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.cleaner-interval-seconds</name>
|
|
|
|
|
<description>
|
|
|
|
|
Scan interval for ATS v1.5 entity group file system storage cleaner.This
|
|
|
|
|
value controls how frequent the reader will scan the HDFS done directory
|
|
|
|
|
for stale application data.
|
|
|
|
|
</description>
|
|
|
|
|
<value>3600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.retain-seconds</name>
|
|
|
|
|
<description>
|
|
|
|
|
How long the ATS v1.5 entity group file system storage will keep an
|
|
|
|
|
application's data in the done directory.
|
|
|
|
|
</description>
|
|
|
|
|
<value>604800</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.leveldb-cache-read-cache-size</name>
|
|
|
|
|
<description>
|
|
|
|
|
Read cache size for the leveldb cache storage in ATS v1.5 plugin storage.
|
|
|
|
|
</description>
|
|
|
|
|
<value>10485760</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.app-cache-size</name>
|
|
|
|
|
<description>
|
|
|
|
|
Size of the reader cache for ATS v1.5 reader. This value controls how many
|
|
|
|
|
entity groups the ATS v1.5 server should cache. If the number of active
|
|
|
|
|
read entity groups is greater than the number of caches items, some reads
|
|
|
|
|
may return empty data. This value must be greater than 0.
|
|
|
|
|
</description>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.client.fd-flush-interval-secs</name>
|
|
|
|
|
<description>
|
|
|
|
|
Flush interval for ATS v1.5 writer. This value controls how frequent
|
|
|
|
|
the writer will flush the HDFS FSStream for the entity/domain.
|
|
|
|
|
</description>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.client.fd-clean-interval-secs</name>
|
|
|
|
|
<description>
|
|
|
|
|
Scan interval for ATS v1.5 writer. This value controls how frequent
|
|
|
|
|
the writer will scan the HDFS FSStream for the entity/domain.
|
|
|
|
|
If the FSStream is stale for a long time, this FSStream will be close.
|
|
|
|
|
</description>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.client.fd-retain-secs</name>
|
|
|
|
|
<description>
|
|
|
|
|
How long the ATS v1.5 writer will keep an FSStream open.
|
|
|
|
|
If this fsstream does not write anything for this configured time,
|
|
|
|
|
it will be close.
|
|
|
|
|
</description>
|
|
|
|
|
<value>300</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Timeline Service v2 Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.writer.class</name>
|
|
|
|
|
<description>
|
|
|
|
|
Storage implementation ATS v2 will use for the TimelineWriter service.
|
|
|
|
|
</description>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timelineservice.storage.HBaseTimelineWriterImpl</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.reader.class</name>
|
|
|
|
|
<description>
|
|
|
|
|
Storage implementation ATS v2 will use for the TimelineReader service.
|
|
|
|
|
</description>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.timelineservice.storage.HBaseTimelineReaderImpl</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.timeline-service.client.internal-timers-ttl-secs</name>
|
|
|
|
|
<description>
|
|
|
|
|
How long the internal Timer Tasks can be alive in writer. If there is no
|
|
|
|
|
write operation for this configured time, the internal timer tasks will
|
|
|
|
|
be close.
|
|
|
|
|
</description>
|
|
|
|
|
<value>420</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that controls how often the timeline collector
|
|
|
|
|
flushes the timeline writer.</description>
|
|
|
|
|
<name>yarn.timeline-service.writer.flush-interval-seconds</name>
|
|
|
|
|
<value>60</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The setting that decides the capacity of the queue to hold
|
|
|
|
|
asynchronous timeline entities.</description>
|
|
|
|
|
<name>yarn.timeline-service.writer.async.queue.capacity</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time period till which the application collector will be alive
|
|
|
|
|
in NM, after the application master container finishes.</description>
|
|
|
|
|
<name>yarn.timeline-service.app-collector.linger-period.ms</name>
|
|
|
|
|
<value>60000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time line V2 client tries to merge these many number of
|
|
|
|
|
async entities (if available) and then call the REST ATS V2 API to submit.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.timeline-client.number-of-async-entities-to-merge</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The setting that controls how long the final value
|
|
|
|
|
of a metric of a completed app is retained before merging into
|
|
|
|
|
the flow sum. Up to this time after an application is completed
|
|
|
|
|
out-of-order values that arrive can be recognized and discarded at the
|
|
|
|
|
cost of increased storage.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.hbase.coprocessor.app-final-value-retention-milliseconds
|
|
|
|
|
</name>
|
|
|
|
|
<value>259200000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The setting that controls how often in-memory app level
|
|
|
|
|
aggregation is kicked off in timeline collector.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.app-aggregation-interval-secs</name>
|
|
|
|
|
<value>15</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The default hdfs location for flowrun coprocessor jar.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.hbase.coprocessor.jar.hdfs.location
|
|
|
|
|
</name>
|
|
|
|
|
<value>/hbase/coprocessor/hadoop-yarn-server-timelineservice.jar</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The value of this parameter sets the prefix for all tables that are part of
|
|
|
|
|
timeline service in the hbase storage schema. It can be set to "dev."
|
|
|
|
|
or "staging." if it is to be used for development or staging instances.
|
|
|
|
|
This way the data in production tables stays in a separate set of tables
|
|
|
|
|
prefixed by "prod.".
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.hbase-schema.prefix</name>
|
|
|
|
|
<value>prod.</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description> Optional URL to an hbase-site.xml configuration file to be
|
|
|
|
|
used to connect to the timeline-service hbase cluster. If empty or not
|
|
|
|
|
specified, then the HBase configuration will be loaded from the classpath.
|
|
|
|
|
When specified the values in the specified configuration file will override
|
|
|
|
|
those from the ones that are present on the classpath.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.hbase.configuration.file
|
|
|
|
|
</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Removes the UUID if represent and limit the the flowname length with
|
|
|
|
|
the given value for ATSv2. In case the value is negative or 0,
|
|
|
|
|
it only removes the UUID and does not limit the flow name.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.flowname.max-size
|
|
|
|
|
</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Shared Cache Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether the shared cache is enabled</description>
|
|
|
|
|
<name>yarn.sharedcache.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The root directory for the shared cache</description>
|
|
|
|
|
<name>yarn.sharedcache.root-dir</name>
|
|
|
|
|
<value>/sharedcache</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The level of nested directories before getting to the checksum
|
|
|
|
|
directories. It must be non-negative.</description>
|
|
|
|
|
<name>yarn.sharedcache.nested-level</name>
|
|
|
|
|
<value>3</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The implementation to be used for the SCM store</description>
|
|
|
|
|
<name>yarn.sharedcache.store.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.sharedcachemanager.store.InMemorySCMStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The implementation to be used for the SCM app-checker</description>
|
|
|
|
|
<name>yarn.sharedcache.app-checker.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.sharedcachemanager.RemoteAppChecker</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>A resource in the in-memory store is considered stale
|
|
|
|
|
if the time since the last reference exceeds the staleness period.
|
|
|
|
|
This value is specified in minutes.</description>
|
|
|
|
|
<name>yarn.sharedcache.store.in-memory.staleness-period-mins</name>
|
|
|
|
|
<value>10080</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Initial delay before the in-memory store runs its first check
|
|
|
|
|
to remove dead initial applications. Specified in minutes.</description>
|
|
|
|
|
<name>yarn.sharedcache.store.in-memory.initial-delay-mins</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The frequency at which the in-memory store checks to remove
|
|
|
|
|
dead initial applications. Specified in minutes.</description>
|
|
|
|
|
<name>yarn.sharedcache.store.in-memory.check-period-mins</name>
|
|
|
|
|
<value>720</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the admin interface in the SCM (shared cache manager)</description>
|
|
|
|
|
<name>yarn.sharedcache.admin.address</name>
|
|
|
|
|
<value>0.0.0.0:8047</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of threads used to handle SCM admin interface (1 by default)</description>
|
|
|
|
|
<name>yarn.sharedcache.admin.thread-count</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the web application in the SCM (shared cache manager)</description>
|
|
|
|
|
<name>yarn.sharedcache.webapp.address</name>
|
|
|
|
|
<value>0.0.0.0:8788</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The frequency at which a cleaner task runs.
|
|
|
|
|
Specified in minutes.</description>
|
|
|
|
|
<name>yarn.sharedcache.cleaner.period-mins</name>
|
|
|
|
|
<value>1440</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Initial delay before the first cleaner task is scheduled.
|
|
|
|
|
Specified in minutes.</description>
|
|
|
|
|
<name>yarn.sharedcache.cleaner.initial-delay-mins</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The time to sleep between processing each shared cache
|
|
|
|
|
resource. Specified in milliseconds.</description>
|
|
|
|
|
<name>yarn.sharedcache.cleaner.resource-sleep-ms</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the node manager interface in the SCM
|
|
|
|
|
(shared cache manager)</description>
|
|
|
|
|
<name>yarn.sharedcache.uploader.server.address</name>
|
|
|
|
|
<value>0.0.0.0:8046</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of threads used to handle shared cache manager
|
|
|
|
|
requests from the node manager (50 by default)</description>
|
|
|
|
|
<name>yarn.sharedcache.uploader.server.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The address of the client interface in the SCM
|
|
|
|
|
(shared cache manager)</description>
|
|
|
|
|
<name>yarn.sharedcache.client-server.address</name>
|
|
|
|
|
<value>0.0.0.0:8045</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of threads used to handle shared cache manager
|
|
|
|
|
requests from clients (50 by default)</description>
|
|
|
|
|
<name>yarn.sharedcache.client-server.thread-count</name>
|
|
|
|
|
<value>50</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The algorithm used to compute checksums of files (SHA-256 by
|
|
|
|
|
default)</description>
|
|
|
|
|
<name>yarn.sharedcache.checksum.algo.impl</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.sharedcache.ChecksumSHA256Impl</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The replication factor for the node manager uploader for the
|
|
|
|
|
shared cache (10 by default)</description>
|
|
|
|
|
<name>yarn.sharedcache.nm.uploader.replication.factor</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The number of threads used to upload files from a node manager
|
|
|
|
|
instance (20 by default)</description>
|
|
|
|
|
<name>yarn.sharedcache.nm.uploader.thread-count</name>
|
|
|
|
|
<value>20</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
ACL protocol for use in the Timeline server.
|
|
|
|
|
</description>
|
|
|
|
|
<name>security.applicationhistory.protocol.acl</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Minicluster Configuration (for testing only!) -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Set to true for MiniYARNCluster unit tests
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.is.minicluster</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Set for MiniYARNCluster unit tests to control resource monitoring
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.minicluster.control-resource-monitoring</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Set to false in order to allow MiniYARNCluster to run tests without
|
|
|
|
|
port conflicts.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.minicluster.fixed.ports</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Set to false in order to allow the NodeManager in MiniYARNCluster to
|
|
|
|
|
use RPC to talk to the RM.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.minicluster.use-rpc</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
As yarn.nodemanager.resource.memory-mb property but for the NodeManager
|
|
|
|
|
in a MiniYARNCluster.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.minicluster.yarn.nodemanager.resource.memory-mb</name>
|
|
|
|
|
<value>4096</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Node Labels Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable node labels feature
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-labels.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
URI for NodeLabelManager. The default value is
|
|
|
|
|
/tmp/hadoop-yarn-${user}/node-labels/ in the local filesystem.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-labels.fs-store.root-dir</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Set configuration type for node labels. Administrators can specify
|
|
|
|
|
"centralized", "delegated-centralized" or "distributed".
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-labels.configuration-type</name>
|
|
|
|
|
<value>centralized</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Distributed Node Labels Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.node-labels.configuration-type" is configured with "distributed"
|
|
|
|
|
in RM, Administrators can configure in NM the provider for the
|
|
|
|
|
node labels by configuring this parameter. Administrators can
|
|
|
|
|
configure "config", "script" or the class name of the provider. Configured
|
|
|
|
|
class needs to extend
|
|
|
|
|
org.apache.hadoop.yarn.server.nodemanager.nodelabels.NodeLabelsProvider.
|
|
|
|
|
If "config" is configured, then "ConfigurationNodeLabelsProvider" and if
|
|
|
|
|
"script" is configured, then "ScriptNodeLabelsProvider" will be used.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.nodemanager.node-labels.provider" is configured with "config",
|
|
|
|
|
"Script" or the configured class extends AbstractNodeLabelsProvider, then
|
|
|
|
|
periodically node labels are retrieved from the node labels provider. This
|
|
|
|
|
configuration is to define the interval period.
|
|
|
|
|
If -1 is configured then node labels are retrieved from provider only
|
|
|
|
|
during initialization. Defaults to 10 mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider.fetch-interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Interval at which NM syncs its node labels with RM. NM will send its loaded
|
|
|
|
|
labels every x intervals configured, along with heartbeat to RM.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.resync-interval-ms</name>
|
|
|
|
|
<value>120000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.nodemanager.node-labels.provider" is configured with "config"
|
|
|
|
|
then ConfigurationNodeLabelsProvider fetches the partition label from this
|
|
|
|
|
parameter.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider.configured-node-partition</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.nodemanager.node-labels.provider" is configured with "Script"
|
|
|
|
|
then this configuration provides the timeout period after which it will
|
|
|
|
|
interrupt the script which queries the Node labels. Defaults to 20 mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider.fetch-timeout-ms</name>
|
|
|
|
|
<value>1200000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Delegated-centralized Node Labels Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When node labels "yarn.node-labels.configuration-type" is
|
|
|
|
|
of type "delegated-centralized", administrators should configure
|
|
|
|
|
the class for fetching node labels by ResourceManager. Configured
|
|
|
|
|
class needs to extend
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.nodelabels.
|
|
|
|
|
RMNodeLabelsMappingProvider.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-labels.provider</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.node-labels.configuration-type" is configured with
|
|
|
|
|
"delegated-centralized", then node labels of all nodes
|
|
|
|
|
are updated by periodically retrieving node labels from the
|
|
|
|
|
provider. If -1 is configured then node labels are retrieved
|
|
|
|
|
from provider only once for each node after it registers.
|
|
|
|
|
Defaults to 30 mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-labels.provider.fetch-interval-ms</name>
|
|
|
|
|
<value>1800000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.node-labels.configuration-type" is configured with
|
|
|
|
|
"delegated-centralized", then node labels of newly registered
|
|
|
|
|
nodes are updated by periodically retrieving node labels from
|
|
|
|
|
the provider. Defaults to 30 secs.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-labels.provider.update-newly-registered-nodes-interval-ms</name>
|
|
|
|
|
<value>30000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Overwrites default-node-label-expression only for the ApplicationMaster
|
|
|
|
|
container. It is disabled by default.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-labels.am.default-node-label-expression</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to indicate whether the AM can be allocated to non-exclusive nodes or not.
|
|
|
|
|
Default is false.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-labels.am.allow-non-exclusive-allocation</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Distributed Node Attributes Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
This property determines which provider will be plugged by the
|
|
|
|
|
node manager to collect node-attributes. Administrators can
|
|
|
|
|
configure "config", "script" or the class name of the provider.
|
|
|
|
|
Configured class needs to extend
|
|
|
|
|
org.apache.hadoop.yarn.server.nodemanager.nodelabels.NodeAttributesProvider.
|
|
|
|
|
If "config" is configured, then "ConfigurationNodeLabelsProvider" and if
|
|
|
|
|
"script" is configured, then "ScriptBasedNodeAttributesProvider"
|
|
|
|
|
will be used.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The node attribute script NM runs to collect node attributes.
|
|
|
|
|
Script output Line starting with "NODE_ATTRIBUTE:" will be
|
|
|
|
|
considered as a record of node attribute, attribute name, type
|
|
|
|
|
and value should be delimited by comma. Each of such lines
|
|
|
|
|
will be parsed to a node attribute.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider.script.path</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Command arguments passed to the node attribute script.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider.script.opts</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Time interval that determines how long NM fetches node attributes
|
|
|
|
|
from a given provider. If -1 is configured then node labels are
|
|
|
|
|
retrieved from provider only during initialization. Defaults to 10 mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider.fetch-interval-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Timeout period after which NM will interrupt the node attribute
|
|
|
|
|
provider script which queries node attributes. Defaults to 20 mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider.fetch-timeout-ms</name>
|
|
|
|
|
<value>1200000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When "yarn.nodemanager.node-attributes.provider" is configured with
|
|
|
|
|
"config" then ConfigurationNodeAttributesProvider fetches node attributes
|
|
|
|
|
from this parameter.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.provider.configured-node-attributes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Interval at which NM syncs its node attributes with RM. NM will send its loaded
|
|
|
|
|
attributes every x intervals configured, along with heartbeat to RM.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-attributes.resync-interval-ms</name>
|
|
|
|
|
<value>120000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Timeout in seconds for YARN node graceful decommission.
|
|
|
|
|
This is the maximal time to wait for running containers and applications to complete
|
|
|
|
|
before transition a DECOMMISSIONING node into DECOMMISSIONED.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nodemanager-graceful-decommission-timeout-secs</name>
|
|
|
|
|
<value>3600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Timeout in seconds of DecommissioningNodesWatcher internal polling.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.decommissioning-nodes-watcher.poll-interval-secs</name>
|
|
|
|
|
<value>20</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used to specify custom web services for Resourcemanager. Value can be
|
|
|
|
|
classnames separated by comma.
|
|
|
|
|
Ex: org.apache.hadoop.yarn.server.resourcemanager.webapp.RMWebServices,
|
|
|
|
|
org.apache.hadoop.yarn.server.resourcemanager.webapp.DummyClass
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.http.rmwebapp.external.classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used to specify custom scheduler page
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.http.rmwebapp.scheduler.page.class</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used to specify custom DAO classes used by custom web services.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.http.rmwebapp.custom.dao.classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used to specify custom DAO classes used by custom web services which requires
|
|
|
|
|
root unwrapping.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.http.rmwebapp.custom.unwrapped.dao.classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Used to specify custom WebServices class to bind with RMWebApp overriding
|
|
|
|
|
the default RMWebServices.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.webapp.custom.webservice.class</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The Node Label script to run. Script output Line starting with
|
|
|
|
|
"NODE_PARTITION:" will be considered as Node Label Partition. In case of
|
|
|
|
|
multiple lines have this pattern, then last one will be considered
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider.script.path</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The arguments to pass to the Node label script.</description>
|
|
|
|
|
<name>yarn.nodemanager.node-labels.provider.script.opts</name>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Federation Configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to indicate whether the RM is participating in Federation or not.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Initial delay for federation state-store heartbeat service. Value is followed by a unit
|
|
|
|
|
specifier: ns, us, ms, s, m, h, d for nanoseconds, microseconds, milliseconds, seconds,
|
|
|
|
|
minutes, hours, days respectively. Values should provide units,
|
|
|
|
|
but seconds are assumed
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.state-store.heartbeat.initial-delay</name>
|
|
|
|
|
<value>30s</value>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Machine list file to be loaded by the FederationSubCluster Resolver
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.machine-list</name>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Class name for SubClusterResolver
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.subcluster-resolver.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.federation.resolver.DefaultSubClusterResolverImpl</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Store class name for federation state store
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.state-store.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.federation.store.impl.MemoryFederationStateStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The time in seconds after which the federation state store local cache
|
|
|
|
|
will be refreshed periodically
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.cache-ttl.secs</name>
|
|
|
|
|
<value>300</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The registry base directory for federation.</description>
|
|
|
|
|
<name>yarn.federation.registry.base-dir</name>
|
|
|
|
|
<value>yarnfederation/</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The number of retries to clear the app in the FederationStateStore,
|
|
|
|
|
the default value is 1, that is, after the app fails to clean up, it will retry the cleanup again.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.state-store.clean-up-retry-count</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Clear the sleep time of App retry in FederationStateStore.
|
|
|
|
|
When the app fails to clean up,
|
|
|
|
|
it will sleep for a period of time and then try to clean up.
|
|
|
|
|
The default value is 1s.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.federation.state-store.clean-up-retry-sleep-time</name>
|
|
|
|
|
<value>1s</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- Other Configuration -->
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The registry implementation to use.</description>
|
|
|
|
|
<name>yarn.registry.class</name>
|
|
|
|
|
<value>org.apache.hadoop.registry.client.impl.FSRegistryOperationsService</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The interval that the yarn client library uses to poll the
|
|
|
|
|
completion status of the asynchronous API of application client protocol.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.client.application-client-protocol.poll-interval-ms</name>
|
|
|
|
|
<value>200</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The duration (in ms) the YARN client waits for an expected state change
|
|
|
|
|
to occur. -1 means unlimited wait time.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.client.application-client-protocol.poll-timeout-ms</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>RSS usage of a process computed via
|
|
|
|
|
/proc/pid/stat is not very accurate as it includes shared pages of a
|
|
|
|
|
process. /proc/pid/smaps provides useful information like
|
|
|
|
|
Private_Dirty, Private_Clean, Shared_Dirty, Shared_Clean which can be used
|
|
|
|
|
for computing more accurate RSS. When this flag is enabled, RSS is computed
|
|
|
|
|
as Min(Shared_Dirty, Pss) + Private_Clean + Private_Dirty. It excludes
|
|
|
|
|
read-only shared mappings in RSS computation.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container-monitor.procfs-tree.smaps-based-rss.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
URL for log aggregation server
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.log.server.url</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
URL for log aggregation server web service
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.log.server.web-service.url</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
RM Application Tracking URL
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.tracking.url.generator</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Class to be used for YarnAuthorizationProvider
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.authorization-provider</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Defines how often NMs wake up to upload log files.
|
|
|
|
|
The default value is -1. By default, the logs will be uploaded when
|
|
|
|
|
the application is finished. By setting this configuration logs can
|
|
|
|
|
be uploaded periodically while the application is running.
|
|
|
|
|
The minimum positive accepted value can be configured by the setting
|
|
|
|
|
"yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds.min".
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Defines the positive minimum hard limit for
|
|
|
|
|
"yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds".
|
|
|
|
|
If this configuration has been set less than its default value (3600)
|
|
|
|
|
the NodeManager may raise a warning.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds.min</name>
|
|
|
|
|
<value>3600</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Define how many aggregated log files per application per NM
|
|
|
|
|
we can have in remote file system. By default, the total number of
|
|
|
|
|
aggregated log files per application per NM is 30.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.num-log-files-per-app</name>
|
|
|
|
|
<value>30</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable/disable intermediate-data encryption at YARN level. For now,
|
|
|
|
|
this only is used by the FileSystemRMStateStore to setup right
|
|
|
|
|
file-system security attributes.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.intermediate-data-encryption.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Flag to enable cross-origin (CORS) support in the NM. This flag
|
|
|
|
|
requires the CORS filter initializer to be added to the filter initializers
|
|
|
|
|
list in core-site.xml.</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.cross-origin.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Defines maximum application priority in a cluster.
|
|
|
|
|
If an application is submitted with a priority higher than this value, it will be
|
|
|
|
|
reset to this maximum value.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.cluster.max-application-priority</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The default log aggregation policy class. Applications can
|
|
|
|
|
override it via LogAggregationContext. This configuration can provide
|
|
|
|
|
some cluster-side default behavior so that if the application doesn't
|
|
|
|
|
specify any policy via LogAggregationContext administrators of the cluster
|
|
|
|
|
can adjust the policy globally.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.policy.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.logaggregation.AllContainerLogAggregationPolicy</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The default parameters for the log aggregation policy. Applications can
|
|
|
|
|
override it via LogAggregationContext. This configuration can provide
|
|
|
|
|
some cluster-side default behavior so that if the application doesn't
|
|
|
|
|
specify any policy via LogAggregationContext administrators of the cluster
|
|
|
|
|
can adjust the policy globally.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.log-aggregation.policy.parameters</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable/Disable AMRMProxyService in the node manager. This service is used to
|
|
|
|
|
intercept calls from the application masters to the resource manager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.amrmproxy.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The address of the AMRMProxyService listener.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.amrmproxy.address</name>
|
|
|
|
|
<value>0.0.0.0:8049</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The number of threads used to handle requests by the AMRMProxyService.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.amrmproxy.client.thread-count</name>
|
|
|
|
|
<value>25</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The comma separated list of class names that implement the
|
|
|
|
|
RequestInterceptor interface. This is used by the AMRMProxyService to create
|
|
|
|
|
the request processing pipeline for applications.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.amrmproxy.interceptor-class.pipeline</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.amrmproxy.DefaultRequestInterceptor</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether AMRMProxy HA is enabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.amrmproxy.ha.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Setting that controls whether distributed scheduling is enabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.distributed-scheduling.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Setting that controls whether opportunistic container allocation
|
|
|
|
|
is enabled.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.opportunistic-container-allocation.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Maximum number of opportunistic containers to be allocated per
|
|
|
|
|
Application Master heartbeat.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.opportunistic.max.container-allocation.per.am.heartbeat</name>
|
|
|
|
|
<value>-1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Number of nodes to be used by the Opportunistic Container Allocator for
|
|
|
|
|
dispatching containers during container allocation.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.opportunistic-container-allocation.nodes-used</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Frequency for computing least loaded NMs.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.sorting-nodes-interval-ms</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comparator for determining node load for Distributed Scheduling.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.load-comparator</name>
|
|
|
|
|
<value>QUEUE_LENGTH</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Value of standard deviation used for calculation of queue limit thresholds.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.queue-limit-stdev</name>
|
|
|
|
|
<value>1.0f</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Min length of container queue at NodeManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.min-queue-length</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Max length of container queue at NodeManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.max-queue-length</name>
|
|
|
|
|
<value>15</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Min queue wait time for a container at a NodeManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.min-queue-wait-time-ms</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Max queue wait time for a container queue at a NodeManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.nm-container-queuing.max-queue-wait-time-ms</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Use container pause as the preemption policy over kill in the container
|
|
|
|
|
queue at a NodeManager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.opportunistic-containers-use-pause-for-preemption</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Error filename pattern, to identify the file in the container's
|
|
|
|
|
Log directory which contain the container's error log. As error file
|
|
|
|
|
redirection is done by client/AM and yarn will not be aware of the error
|
|
|
|
|
file name. YARN uses this pattern to identify the error file and tail
|
|
|
|
|
the error log as diagnostics when the container execution returns non zero
|
|
|
|
|
value. Filename patterns are case sensitive and should match the
|
|
|
|
|
specifications of FileSystem.globStatus(Path) api. If multiple filenames
|
|
|
|
|
matches the pattern, first file matching the pattern will be picked.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container.stderr.pattern</name>
|
|
|
|
|
<value>{*stderr*,*STDERR*}</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Size of the container error file which needs to be tailed, in bytes.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.container.stderr.tail.bytes </name>
|
|
|
|
|
<value>4096</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Choose different implementation of node label's storage
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-labels.fs-store.impl.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.nodelabels.FileSystemNodeLabelsStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The replication factor for the FS store
|
|
|
|
|
files. Default value is 0, means it will use file system
|
|
|
|
|
default replication.</description>
|
|
|
|
|
<name>yarn.fs-store.file.replication</name>
|
|
|
|
|
<value>0</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable the CSRF filter for the RM web app
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.rest-csrf.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the custom header name to use for CSRF
|
|
|
|
|
protection.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.rest-csrf.custom-header</name>
|
|
|
|
|
<value>X-XSRF-Header</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the list of HTTP methods that do not
|
|
|
|
|
require CSRF protection
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.rest-csrf.methods-to-ignore</name>
|
|
|
|
|
<value>GET,OPTIONS,HEAD</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable the CSRF filter for the NM web app
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.rest-csrf.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the custom header name to use for CSRF
|
|
|
|
|
protection.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.rest-csrf.custom-header</name>
|
|
|
|
|
<value>X-XSRF-Header</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the list of HTTP methods that do not
|
|
|
|
|
require CSRF protection
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.rest-csrf.methods-to-ignore</name>
|
|
|
|
|
<value>GET,OPTIONS,HEAD</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The name of disk validator.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.disk-validator</name>
|
|
|
|
|
<value>basic</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable the CSRF filter for the timeline service web app
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.rest-csrf.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the custom header name to use for CSRF
|
|
|
|
|
protection.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.rest-csrf.custom-header</name>
|
|
|
|
|
<value>X-XSRF-Header</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Optional parameter that indicates the list of HTTP methods that do not
|
|
|
|
|
require CSRF protection
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.rest-csrf.methods-to-ignore</name>
|
|
|
|
|
<value>GET,OPTIONS,HEAD</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable the XFS filter for YARN
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.webapp.xfs-filter.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Property specifying the xframe options value.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.webapp.xfs-filter.xframe-options</name>
|
|
|
|
|
<value>SAMEORIGIN</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Property specifying the xframe options value.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.webapp.xfs-filter.xframe-options</name>
|
|
|
|
|
<value>SAMEORIGIN</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Property specifying the xframe options value.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.webapp.xfs-filter.xframe-options</name>
|
|
|
|
|
<value>SAMEORIGIN</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The least amount of time(msec.) an inactive (decommissioned or shutdown) node can
|
|
|
|
|
stay in the nodes list of the resourcemanager after being declared untracked.
|
|
|
|
|
A node is marked untracked if and only if it is absent from both include and
|
|
|
|
|
exclude nodemanager lists on the RM. All inactive nodes are checked twice per
|
|
|
|
|
timeout interval or every 10 minutes, whichever is lesser, and marked appropriately.
|
|
|
|
|
The same is done when refreshNodes command (graceful or otherwise) is invoked.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.node-removal-untracked.timeout-ms</name>
|
|
|
|
|
<value>60000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The RMAppLifetimeMonitor Service uses this value as monitor interval
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-timeouts.monitor.interval-ms</name>
|
|
|
|
|
<value>3000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specifies what the RM does regarding HTTPS enforcement for communication
|
|
|
|
|
with AM Web Servers, as well as generating and providing certificates.
|
|
|
|
|
Possible values are:
|
|
|
|
|
- NONE - the RM will do nothing special.
|
|
|
|
|
- LENIENT - the RM will generate and provide a keystore and truststore
|
|
|
|
|
to the AM, which it is free to use for HTTPS in its tracking URL web
|
|
|
|
|
server. The RM proxy will still allow HTTP connections to AMs that opt
|
|
|
|
|
not to use HTTPS.
|
|
|
|
|
- STRICT - this is the same as LENIENT, except that the RM proxy will
|
|
|
|
|
only allow HTTPS connections to AMs; HTTP connections will be blocked
|
|
|
|
|
and result in a warning page to the user.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-https.policy</name>
|
|
|
|
|
<value>NONE</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Defines the limit of the diagnostics message of an application
|
|
|
|
|
attempt, in kilo characters (character count * 1024).
|
|
|
|
|
When using ZooKeeper to store application state behavior, its
|
|
|
|
|
important to limit the size of the diagnostic messages to
|
|
|
|
|
prevent YARN from overwhelming ZooKeeper. In cases where
|
|
|
|
|
yarn.resourcemanager.state-store.max-completed-applications is set to
|
|
|
|
|
a large number, it may be desirable to reduce the value of this property
|
|
|
|
|
to limit the total data stored.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.app.attempt.diagnostics.limit.kc</name>
|
|
|
|
|
<value>64</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable cross-origin (CORS) support for timeline service v1.x or
|
|
|
|
|
Timeline Reader in timeline service v2. For timeline service v2, also add
|
|
|
|
|
org.apache.hadoop.security.HttpCrossOriginFilterInitializer to the
|
|
|
|
|
configuration hadoop.http.filter.initializers in core-site.xml.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.http-cross-origin.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The comma separated list of class names that implement the
|
|
|
|
|
RequestInterceptor interface. This is used by the RouterClientRMService
|
|
|
|
|
to create the request processing pipeline for users.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.clientrm.interceptor-class.pipeline</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.router.clientrm.DefaultClientRequestInterceptor</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The thread pool executor size of per user in Router ClientRM Service FederationClientInterceptor.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.interceptor.user.threadpool-size</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Size of LRU cache for Router ClientRM Service and RMAdmin Service.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.pipeline.cache-max-size</name>
|
|
|
|
|
<value>25</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The comma separated list of class names that implement the
|
|
|
|
|
RequestInterceptor interface. This is used by the RouterRMAdminService
|
|
|
|
|
to create the request processing pipeline for users.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.rmadmin.interceptor-class.pipeline</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.router.rmadmin.DefaultRMAdminRequestInterceptor</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The actual address the server will bind to. If this optional address is
|
|
|
|
|
set, the RPC and webapp servers will bind to this address and the port specified in
|
|
|
|
|
yarn.router.address and yarn.router.webapp.address, respectively. This is
|
|
|
|
|
most useful for making Router listen to all interfaces by setting to 0.0.0.0.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.bind-host</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comma-separated list of PlacementRules to determine how applications
|
|
|
|
|
submitted by certain users get mapped to certain queues. Default is
|
|
|
|
|
user-group, which corresponds to UserGroupMappingPlacementRule.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.queue-placement-rules</name>
|
|
|
|
|
<value>user-group</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The comma separated list of class names that implement the
|
|
|
|
|
RequestInterceptor interface. This is used by the RouterWebServices
|
|
|
|
|
to create the request processing pipeline for users.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.webapp.interceptor-class.pipeline</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.router.webapp.DefaultRequestInterceptorREST</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The http address of the Router web application.
|
|
|
|
|
If only a host is provided as the value,
|
|
|
|
|
the webapp will be served on a random port.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.webapp.address</name>
|
|
|
|
|
<value>0.0.0.0:8089</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The https address of the Router web application.
|
|
|
|
|
If only a host is provided as the value,
|
|
|
|
|
the webapp will be served on a random port.
|
|
|
|
|
</description>
|
|
|
|
|
<name> yarn.router.webapp.https.address</name>
|
|
|
|
|
<value>0.0.0.0:8091</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
It is TimelineClient 1.5 configuration whether to store active
|
|
|
|
|
application’s timeline data with in user directory i.e
|
|
|
|
|
${yarn.timeline-service.entity-group-fs-store.active-dir}/${user.name}
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.entity-group-fs-store.with-user-dir</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- resource types configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.resource-types</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
The resource types to be used for scheduling. Use resource-types.xml
|
|
|
|
|
to specify details about the individual resource types.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.webapp.filter-entity-list-by-user</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable display of applications per user as an admin
|
|
|
|
|
configuration.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.webapp.filter-invalid-xml-chars</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable filter of invalid xml 1.0 characters present in the
|
|
|
|
|
value of diagnostics field of apps output from RM WebService.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The type of configuration store to use for scheduler configurations.
|
|
|
|
|
Default is "file", which uses file based capacity-scheduler.xml to
|
|
|
|
|
retrieve and change scheduler configuration. To enable API based
|
|
|
|
|
scheduler configuration, use either "memory" (in memory storage, no
|
|
|
|
|
persistence across restarts), "leveldb" (leveldb based storage), or
|
|
|
|
|
"zk" (zookeeper based storage). API based configuration is only useful
|
|
|
|
|
when using a scheduler which supports mutable configuration. Currently
|
|
|
|
|
only capacity scheduler supports this.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.store.class</name>
|
|
|
|
|
<value>file</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The class to use for configuration mutation ACL policy if using a mutable
|
|
|
|
|
configuration provider. Controls whether a mutation request is allowed.
|
|
|
|
|
The DefaultConfigurationMutationACLPolicy checks if the requestor is a
|
|
|
|
|
YARN admin.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.mutation.acl-policy.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.DefaultConfigurationMutationACLPolicy</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The storage path for LevelDB implementation of configuration store,
|
|
|
|
|
when yarn.scheduler.configuration.store.class is configured to be
|
|
|
|
|
"leveldb".
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.leveldb-store.path</name>
|
|
|
|
|
<value>${hadoop.tmp.dir}/yarn/system/confstore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The compaction interval for LevelDB configuration store in secs,
|
|
|
|
|
when yarn.scheduler.configuration.store.class is configured to be
|
|
|
|
|
"leveldb". Default is one day.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.leveldb-store.compaction-interval-secs</name>
|
|
|
|
|
<value>86400</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The max number of configuration change log entries kept in config
|
|
|
|
|
store, when yarn.scheduler.configuration.store.class is configured to be
|
|
|
|
|
"leveldb" or "zk". Default is 1000 for either.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.store.max-logs</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The file system directory to store the configuration files. The path
|
|
|
|
|
can be any format as long as it follows hadoop compatible schema,
|
|
|
|
|
for example value "file:///path/to/dir" means to store files on local
|
|
|
|
|
file system, value "hdfs:///path/to/dir" means to store files on HDFS.
|
|
|
|
|
If resource manager HA is enabled, recommended to use hdfs schema so
|
|
|
|
|
it works in fail-over scenario.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.fs.path</name>
|
|
|
|
|
<value>file://${hadoop.tmp.dir}/yarn/system/schedconf</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The max number of configuration file in filesystem.
|
|
|
|
|
Default is 100 for either.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.max.version</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
ZK root node path for configuration store when using zookeeper-based
|
|
|
|
|
configuration store.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.scheduler.configuration.zk-store.parent-path</name>
|
|
|
|
|
<value>/confstore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Provides an option for client to load supported resource types from RM
|
|
|
|
|
instead of depending on local resource-types.xml file.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.client.load.resource-types.from-server</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
This setting controls if pluggable device framework is enabled.
|
|
|
|
|
Disabled by default
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.pluggable-device-framework.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Configure vendor device plugin class name here. Comma separated.
|
|
|
|
|
The class must be found in CLASSPATH. The pluggable device framework will
|
|
|
|
|
load these classes.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.pluggable-device-framework.device-classes</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When yarn.nodemanager.resource.gpu.allowed-gpu-devices=auto specified,
|
|
|
|
|
YARN NodeManager needs to run GPU discovery binary (now only support
|
|
|
|
|
nvidia-smi) to get GPU-related information.
|
|
|
|
|
When value is empty (default), YARN NodeManager will try to locate
|
|
|
|
|
discovery executable itself.
|
|
|
|
|
An example of the config value is: /usr/local/bin/nvidia-smi
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.gpu.path-to-discovery-executables</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable additional discovery/isolation of resources on the NodeManager,
|
|
|
|
|
split by comma. By default, this is empty.
|
|
|
|
|
Acceptable values: { "yarn.io/gpu", "yarn.io/fpga"}.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specifies whether the initialization of the Node Manager should continue
|
|
|
|
|
if a certain device (GPU, FPGA, etc) was not found in the system. If set
|
|
|
|
|
to "true", then an exception will be thrown if a device is missing or
|
|
|
|
|
an error occurred during discovery.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fail-fast</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify GPU devices which can be managed by YARN NodeManager, split by comma
|
|
|
|
|
Number of GPU devices will be reported to RM to make scheduling decisions.
|
|
|
|
|
Set to auto (default) let YARN automatically discover GPU resource from
|
|
|
|
|
system.
|
|
|
|
|
|
|
|
|
|
Manually specify GPU devices if auto detect GPU device failed or admin
|
|
|
|
|
only want subset of GPU devices managed by YARN. GPU device is identified
|
|
|
|
|
by their minor device number and index. A common approach to get minor
|
|
|
|
|
device number of GPUs is using "nvidia-smi -q" and search "Minor Number"
|
|
|
|
|
output.
|
|
|
|
|
|
|
|
|
|
When manual specify minor numbers, admin needs to include indice of GPUs
|
|
|
|
|
as well, format is index:minor_number[,index:minor_number...]. An example
|
|
|
|
|
of manual specification is "0:0,1:1,2:2,3:4" to allow YARN NodeManager to
|
|
|
|
|
manage GPU devices with indice 0/1/2/3 and minor number 0/1/2/4.
|
|
|
|
|
numbers .
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.gpu.allowed-gpu-devices</name>
|
|
|
|
|
<value>auto</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify docker command plugin for GPU. By default uses Nvidia docker V1.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.gpu.docker-plugin</name>
|
|
|
|
|
<value>nvidia-docker-v1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify end point of nvidia-docker-plugin.
|
|
|
|
|
Please find documentation: https://github.com/NVIDIA/nvidia-docker/wiki
|
|
|
|
|
For more details.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.gpu.docker-plugin.nvidia-docker-v1.endpoint</name>
|
|
|
|
|
<value>http://localhost:3476/v1.0/docker/cli</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify one vendor plugin to handle FPGA devices discovery/IP download/configure.
|
|
|
|
|
Only IntelFpgaOpenclPlugin is supported by default.
|
|
|
|
|
We only allow one NM configured with one vendor FPGA plugin now since the end user can put the same
|
|
|
|
|
vendor's cards in one host. And this also simplify our design.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fpga.vendor-plugin.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.resourceplugin.fpga.IntelFpgaOpenclPlugin</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
When yarn.nodemanager.resource.fpga.allowed-fpga-devices=auto specified,
|
|
|
|
|
YARN NodeManager needs to run FPGA discovery binary (now only support
|
|
|
|
|
IntelFpgaOpenclPlugin) to get FPGA information.
|
|
|
|
|
When value is empty (default), YARN NodeManager will try to locate
|
|
|
|
|
discovery executable from vendor plugin's preference
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fpga.path-to-discovery-executables</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Specify FPGA devices which can be managed by YARN NodeManager, split by comma
|
|
|
|
|
Number of FPGA devices will be reported to RM to make scheduling decisions.
|
|
|
|
|
Set to auto (default) let YARN automatically discover FPGA resource from
|
|
|
|
|
system.
|
|
|
|
|
|
|
|
|
|
Manually specify FPGA devices if admin only want subset of FPGA devices managed by YARN.
|
|
|
|
|
At present, since we can only configure one major number in c-e.cfg, FPGA device is
|
|
|
|
|
identified by their minor device number. A common approach to get minor
|
|
|
|
|
device number of FPGA is using "aocl diagnose" and check uevent with device name.
|
|
|
|
|
A sample manual value for this is like "0,1"
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fpga.allowed-fpga-devices</name>
|
|
|
|
|
<value>auto</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Absolute path to a script or executable that returns the available FPGA cards.
|
|
|
|
|
The returned string must be a single line and follow the format:
|
|
|
|
|
"deviceA/N:M,deviceB/X:Y". Example: "acl0/243:0,acl1/243:1". The numbers after
|
|
|
|
|
the "/" character are the device major and minor numbers.
|
|
|
|
|
|
|
|
|
|
When the script is enabled, auto-discovery is disabled the "aocl" command is not
|
|
|
|
|
invoked to verify the available cards.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fpga.device-discovery-script</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
List of FPGA available devices in the given node.
|
|
|
|
|
The value must follow the format: "deviceA/N:M,deviceB/X:Y".
|
|
|
|
|
Example: "acl0/243:0,acl1/243:1". The numbers after
|
|
|
|
|
the "/" character are the device major and minor numbers.
|
|
|
|
|
|
|
|
|
|
When this property is used, both auto-discovery and external script are ignored.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.resource-plugins.fpga.available-devices</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The http address of the timeline reader web application.</description>
|
|
|
|
|
<name>yarn.timeline-service.reader.webapp.address</name>
|
|
|
|
|
<value>${yarn.timeline-service.webapp.address}</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The https address of the timeline reader web application.</description>
|
|
|
|
|
<name>yarn.timeline-service.reader.webapp.https.address</name>
|
|
|
|
|
<value>${yarn.timeline-service.webapp.https.address}</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The actual address timeline reader will bind to. If this optional address is
|
|
|
|
|
set, the reader server will bind to this address and the port specified in
|
|
|
|
|
yarn.timeline-service.reader.webapp.address.
|
|
|
|
|
This is most useful for making the service listen to all interfaces by setting to
|
|
|
|
|
0.0.0.0.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.timeline-service.reader.bind-host</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether to enable the NUMA awareness for containers in Node Manager.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.numa-awareness.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether to read the NUMA topology from the system or from the
|
|
|
|
|
configurations. If the value is true then NM reads the NUMA topology from
|
|
|
|
|
system using the command 'numactl --hardware'. If the value is false then NM
|
|
|
|
|
reads the topology from the configurations
|
|
|
|
|
'yarn.nodemanager.numa-awareness.node-ids'(for node id's),
|
|
|
|
|
'yarn.nodemanager.numa-awareness.<NODE_ID>.memory'(for each node memory),
|
|
|
|
|
'yarn.nodemanager.numa-awareness.<NODE_ID>.cpus'(for each node cpus).
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.numa-awareness.read-topology</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
NUMA node id's in the form of comma separated list. Memory and No of CPUs
|
|
|
|
|
will be read using the properties
|
|
|
|
|
'yarn.nodemanager.numa-awareness.<NODE_ID>.memory' and
|
|
|
|
|
'yarn.nodemanager.numa-awareness.<NODE_ID>.cpus' for each id specified
|
|
|
|
|
in this value. This property value will be read only when
|
|
|
|
|
'yarn.nodemanager.numa-awareness.read-topology=false'.
|
|
|
|
|
|
|
|
|
|
For example, if yarn.nodemanager.numa-awareness.node-ids=0,1
|
|
|
|
|
then need to specify memory and cpus for node id's '0' and '1' like below,
|
|
|
|
|
yarn.nodemanager.numa-awareness.0.memory=73717
|
|
|
|
|
yarn.nodemanager.numa-awareness.0.cpus=4
|
|
|
|
|
yarn.nodemanager.numa-awareness.1.memory=73727
|
|
|
|
|
yarn.nodemanager.numa-awareness.1.cpus=4
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.numa-awareness.node-ids</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The numactl command path which controls NUMA policy for processes or
|
|
|
|
|
shared memory.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.numa-awareness.numactl.cmd</name>
|
|
|
|
|
<value>/usr/bin/numactl</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable elastic memory control. This is a Linux only feature.
|
|
|
|
|
When enabled, the node manager adds a listener to receive an
|
|
|
|
|
event, if all the containers exceeded a limit.
|
|
|
|
|
The limit is specified by yarn.nodemanager.resource.memory-mb.
|
|
|
|
|
If this is not set, the limit is set based on the capabilities.
|
|
|
|
|
See yarn.nodemanager.resource.detect-hardware-capabilities
|
|
|
|
|
for details.
|
|
|
|
|
The limit applies to the physical or virtual (rss+swap) memory
|
|
|
|
|
depending on whether yarn.nodemanager.pmem-check-enabled or
|
|
|
|
|
yarn.nodemanager.vmem-check-enabled is set.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.elastic-memory-control.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The name of a JVM class. The class must implement the Runnable
|
|
|
|
|
interface. It is called,
|
|
|
|
|
if yarn.nodemanager.elastic-memory-control.enabled
|
|
|
|
|
is set and the system reaches its memory limit.
|
|
|
|
|
When called the handler must preempt a container,
|
|
|
|
|
since all containers are frozen by cgroups.
|
|
|
|
|
Once preempted some memory is released, so that the
|
|
|
|
|
kernel can resume all containers. Because of this the
|
|
|
|
|
handler has to act quickly.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.elastic-memory-control.oom-handler</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.resources.DefaultOOMHandler</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The path to the oom-listener tool. Elastic memory control is only
|
|
|
|
|
supported on Linux. It relies on kernel events. The tool forwards
|
|
|
|
|
these kernel events to the standard input, so that the node manager
|
|
|
|
|
can preempt containers, in and out-of-memory scenario.
|
|
|
|
|
You rarely need to update this setting.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.elastic-memory-control.oom-listener.path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Maximum time to wait for an OOM situation to get resolved before
|
|
|
|
|
bringing down the node.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.elastic-memory-control.timeout-sec</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
</property>
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
URI for NodeAttributeManager. The default value is
|
|
|
|
|
/tmp/hadoop-yarn-${user}/node-attribute/ in the local filesystem.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-attribute.fs-store.root-dir</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Choose different implementation of node attribute's storage
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-attribute.fs-store.impl.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.resourcemanager.nodelabels.FileSystemNodeAttributeStore</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<!-- CSI configuration -->
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
CSI driver adaptor addresses on a node manager.
|
|
|
|
|
This configuration will be loaded by the resource manager to initiate
|
|
|
|
|
a client for each adaptor in order to communicate with CSI drivers.
|
|
|
|
|
Note, these addresses should be mapped to the adaptor addresses which
|
|
|
|
|
runs the controller plugin.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.csi-driver-adaptor.addresses</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
CSI driver names running on this node, multiple driver names need to
|
|
|
|
|
be delimited by comma. The driver name should be same value returned
|
|
|
|
|
by the getPluginInfo call.For each of the CSI driver name, it must
|
|
|
|
|
to define following two corresponding properties:
|
|
|
|
|
"yarn.nodemanager.csi-driver.${NAME}.endpoint"
|
|
|
|
|
"yarn.nodemanager.csi-driver-adaptor.${NAME}.address"
|
|
|
|
|
The 1st property defines where the driver's endpoint is;
|
|
|
|
|
2nd property defines where the mapping csi-driver-adaptor's address is.
|
|
|
|
|
What's more, an optional csi-driver-adaptor class can be defined
|
|
|
|
|
for each csi-driver:
|
|
|
|
|
"yarn.nodemanager.csi-driver.${NAME}.class"
|
|
|
|
|
once given, the adaptor will be initiated with the given class instead
|
|
|
|
|
of the default implementation
|
|
|
|
|
org.apache.hadoop.yarn.csi.adaptor.DefaultCsiAdaptorImpl. User can plug
|
|
|
|
|
customized adaptor code for csi-driver with this configuration
|
|
|
|
|
if necessary.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.csi-driver.names</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>The cleanup interval for activities in milliseconds.</description>
|
|
|
|
|
<name>yarn.resourcemanager.activities-manager.cleanup-interval-ms</name>
|
|
|
|
|
<value>5000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time to live for scheduler activities in milliseconds.</description>
|
|
|
|
|
<name>yarn.resourcemanager.activities-manager.scheduler-activities.ttl-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Time to live for app activities in milliseconds.</description>
|
|
|
|
|
<name>yarn.resourcemanager.activities-manager.app-activities.ttl-ms</name>
|
|
|
|
|
<value>600000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max queue length for app activities.</description>
|
|
|
|
|
<name>yarn.resourcemanager.activities-manager.app-activities.max-queue-length</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Containers launcher implementation for determining how containers
|
|
|
|
|
are launched within NodeManagers.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.nodemanager.containers-launcher.class</name>
|
|
|
|
|
<value>org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainersLauncher</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Enable the Pre processing of Application Submission context with server side configuration
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.submission-preprocessor.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Path to file with hosts for the submission processor to handle.</description>
|
|
|
|
|
<name>yarn.resourcemanager.submission-preprocessor.file-path</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Submission processor refresh interval</description>
|
|
|
|
|
<name>yarn.resourcemanager.submission-preprocessor.file-refresh-interval-ms</name>
|
|
|
|
|
<value>60000</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Comma-separated list of partitions. If a label P is in this list,
|
|
|
|
|
then the RM will enforce that an app has resource requests with label
|
|
|
|
|
P iff that app's node label expression is P.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.node-labels.exclusive-enforced-partitions</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Prefix used to identify the YARN tag which contains workflow ID. If a tag coming in application
|
|
|
|
|
submission context has this prefix, whatever follows the prefix will be considered as workflow ID
|
|
|
|
|
associated with the application. This configuration is used by features such as workflow priority
|
|
|
|
|
for identifying the workflow associated with an application.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.workflow-id.tag-prefix</name>
|
|
|
|
|
<value>workflowid:</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Whether or not to allow application submissions via REST. Default is true.</description>
|
|
|
|
|
<name>yarn.webapp.enable-rest-app-submissions</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The maximum number of application attempts. It's a global
|
|
|
|
|
setting for all application masters. Each application master can specify
|
|
|
|
|
its individual maximum number of application attempts via the API, but the
|
|
|
|
|
individual number cannot be more than the global upper bound. If it is,
|
|
|
|
|
the resourcemanager will override it. The default number value is set to
|
|
|
|
|
yarn.resourcemanager.am.max-attempts.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.am.global.max-attempts</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max number of application tags set by user in ApplicationSubmissionContext
|
|
|
|
|
while submitting application</description>
|
|
|
|
|
<name>yarn.resourcemanager.application.max-tags</name>
|
|
|
|
|
<value>10</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Max length of each application tag set by user in ApplicationSubmissionContext
|
|
|
|
|
while submitting application.</description>
|
|
|
|
|
<name>yarn.resourcemanager.application.max-tag.length</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>Specifies whether application tags should be converted to lowercase or not.</description>
|
|
|
|
|
<name>yarn.resourcemanager.application-tag-based-placement.force-lowercase</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether to enable RM to mark inactive nodes as untracked after the timeout
|
|
|
|
|
specified by yarn.resourcemanager.node-removal-untracked.timeout-ms and
|
|
|
|
|
then remove them from nodes list for the YARN cluster without configured
|
|
|
|
|
include path, which means RM can periodically clear inactive nodes to
|
|
|
|
|
avoid increasing memory to store these data when enabled, most desired by
|
|
|
|
|
elastic cloud environment with frequent auto-scaling operations.
|
|
|
|
|
It works only when the YARN cluster doesn't utilize include file, the key
|
|
|
|
|
configurations are as follows:
|
|
|
|
|
yarn.resourcemanager.nodes.exclude-path=/path-to-exclude-file
|
|
|
|
|
yarn.resourcemanager.nodes.include-path=
|
|
|
|
|
yarn.resourcemanager.node-removal-untracked.timeout-ms=60000
|
|
|
|
|
In this situation, the inactive nodes will never be marked as untracked
|
|
|
|
|
and removed from the nodes list unless this configuration is enabled:
|
|
|
|
|
yarn.resourcemanager.enable-node-untracked-without-include-path=true
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.resourcemanager.enable-node-untracked-without-include-path</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.scheduler.app-placement-allocator.class</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
In the absence of APPLICATION_PLACEMENT_TYPE_CLASS from the RM
|
|
|
|
|
application scheduling environments, the value of this config
|
|
|
|
|
is used to determine the default implementation of AppPlacementAllocator.
|
|
|
|
|
If APPLICATION_PLACEMENT_TYPE_CLASS is absent from the application
|
|
|
|
|
scheduling env and this config also has no value present, then
|
|
|
|
|
default implementation LocalityAppPlacementAllocator is used.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.keytab.file</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
The keytab file used by router to login as its
|
|
|
|
|
service principal. The principal name is configured with
|
|
|
|
|
dfs.federation.router.kerberos.principal.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.kerberos.principal</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
The Router service principal. This is typically set to
|
|
|
|
|
router/_HOST@REALM.TLD. Each Router will substitute _HOST with its
|
|
|
|
|
own fully qualified hostname at startup. The _HOST placeholder
|
|
|
|
|
allows using the same configuration setting on both Router setup.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.kerberos.principal.hostname</name>
|
|
|
|
|
<value></value>
|
|
|
|
|
<description>
|
|
|
|
|
Optional.
|
|
|
|
|
The hostname for the Router containing this
|
|
|
|
|
configuration file. Will be different for each machine.
|
|
|
|
|
Defaults to current hostname.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.webapp.appsinfo-enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
<description>
|
|
|
|
|
This configuration is used to enable the cache of AppsInfo.
|
|
|
|
|
If it is set to true, the cache is enabled.
|
|
|
|
|
If it is set to false, the cache is not enabled.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.webapp.appsinfo-cached-count</name>
|
|
|
|
|
<value>100</value>
|
|
|
|
|
<description>
|
|
|
|
|
When yarn.router.appsinfo-enabled is set to true,
|
|
|
|
|
the number of cached appsInfo.
|
|
|
|
|
Default is 100
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.webapp.cross-origin.enabled</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
<description>
|
|
|
|
|
Flag to enable cross-origin (CORS) support for Yarn Router.
|
|
|
|
|
For Yarn Router, also add
|
|
|
|
|
org.apache.hadoop.security.HttpCrossOriginFilterInitializer to the
|
|
|
|
|
configuration hadoop.http.filter.initializers in core-site.xml.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.federation.state-store.max-applications</name>
|
|
|
|
|
<value>1000</value>
|
|
|
|
|
<description>
|
|
|
|
|
Yarn federation state-store supports querying the maximum number of apps.
|
|
|
|
|
Default is 1000.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.interceptor.user-thread-pool.minimum-pool-size</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
<description>
|
|
|
|
|
This configurable is used to set the corePoolSize(minimumPoolSize)
|
|
|
|
|
of the thread pool of the interceptor.
|
|
|
|
|
Default is 5.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.interceptor.user-thread-pool.maximum-pool-size</name>
|
|
|
|
|
<value>5</value>
|
|
|
|
|
<description>
|
|
|
|
|
This configuration is used to set the default value of maximumPoolSize
|
|
|
|
|
of the thread pool of the interceptor.
|
|
|
|
|
Default is 5.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.interceptor.user-thread-pool.keep-alive-time</name>
|
|
|
|
|
<value>0s</value>
|
|
|
|
|
<description>
|
|
|
|
|
This configurable is used to set the keepAliveTime of the thread pool of the interceptor.
|
|
|
|
|
Default is 0s.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.submit.interval.time</name>
|
|
|
|
|
<value>10ms</value>
|
|
|
|
|
<description>
|
|
|
|
|
The interval Time between calling different subCluster requests.
|
|
|
|
|
Default is 10ms.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.interceptor.allow-partial-result.enable</name>
|
|
|
|
|
<value>false</value>
|
|
|
|
|
<description>
|
|
|
|
|
This configuration represents whether to allow the interceptor to
|
|
|
|
|
return partial SubCluster results.
|
|
|
|
|
If true, we will ignore the exception to some subClusters during the calling process,
|
|
|
|
|
and return result.
|
|
|
|
|
If false, if an exception occurs in a subCluster during the calling process,
|
|
|
|
|
an exception will be thrown directly.
|
|
|
|
|
Default is false.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
2023-03-08 16:41:55 -05:00
|
|
|
|
<property>
|
|
|
|
|
<name>yarn.router.asc-interceptor-max-size</name>
|
|
|
|
|
<value>1MB</value>
|
|
|
|
|
<description>
|
|
|
|
|
We define the size limit of ApplicationSubmissionContext.
|
|
|
|
|
If the size of the ApplicationSubmissionContext is larger than this value,
|
|
|
|
|
We will throw an exception. the default value is 1MB.
|
|
|
|
|
</description>
|
|
|
|
|
</property>
|
|
|
|
|
|
2023-02-15 18:01:20 -05:00
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The number of threads to use for the Router scheduled executor service.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.subcluster.cleaner.interval.time</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
The interval at which the subClusterCleaner runs. Default is 60s.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.subcluster.cleaner.interval.time</name>
|
|
|
|
|
<value>60s</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
SubCluster heartbeat timeout. Default is 30mins.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.subcluster.heartbeat.expiration.time</name>
|
|
|
|
|
<value>30m</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Whether to enable deregisterSubCluster. Default is true.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.deregister.subcluster.enabled</name>
|
|
|
|
|
<value>true</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
|
|
|
|
<property>
|
|
|
|
|
<description>
|
|
|
|
|
Number of Router Scheduler Threads.
|
|
|
|
|
</description>
|
|
|
|
|
<name>yarn.router.scheduled.executor.threads</name>
|
|
|
|
|
<value>1</value>
|
|
|
|
|
</property>
|
|
|
|
|
|
2023-02-14 00:55:33 -05:00
|
|
|
|
</configuration>
|