path: root/ambari-server/src/main/resources/stacks/HDP/2.2/services/YARN/configuration/yarn-site.xml

<?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.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration supports_final="true" xmlns:xi="http://www.w3.org/2001/XInclude">

  <property>
    <name>yarn.application.classpath</name>
    <value>$HADOOP_CONF_DIR,/usr/hdp/current/hadoop-client/*,/usr/hdp/current/hadoop-client/lib/*,/usr/hdp/current/hadoop-hdfs-client/*,/usr/hdp/current/hadoop-hdfs-client/lib/*,/usr/hdp/current/hadoop-yarn-client/*,/usr/hdp/current/hadoop-yarn-client/lib/*</value>
    <description>Classpath for typical applications.</description>
  </property>
  <property>
    <name>hadoop.registry.rm.enabled</name>
    <value>false</value>
    <description>
      Is the registry enabled: does the RM start it up, create the user and system paths, and purge service records when containers, application attempts and applications complete
    </description>
    <value-attributes>
      <type>boolean</type>
    </value-attributes>
  </property>
  <property>
    <name>hadoop.registry.zk.quorum</name>
    <value>localhost:2181</value>
    <property-type>DONT_ADD_ON_UPGRADE</property-type>
    <description>
      List of hostname:port pairs defining the zookeeper quorum binding for the registry
    </description>
  </property>
  <property>
    <name>yarn.nodemanager.recovery.enabled</name>
    <value>true</value>
    <description>Enable the node manager to recover after starting</description>
  </property>
  <property>
    <name>yarn.nodemanager.recovery.dir</name>
    <value>{{yarn_log_dir_prefix}}/nodemanager/recovery-state</value>
    <description>
      The local filesystem directory in which the node manager will store
      state when recovery is enabled.
    </description>
  </property>
  <property>
    <name>yarn.client.nodemanager-connect.retry-interval-ms</name>
    <value>10000</value>
    <description>Time interval between each attempt to connect to NM</description>
  </property>
  <property>
    <name>yarn.client.nodemanager-connect.max-wait-ms</name>
    <value>60000</value>
    <description>Max time to wait to establish a connection to NM</description>
  </property>
  <property>
    <name>yarn.resourcemanager.recovery.enabled</name>
    <value>true</value>
    <description>
      Enable RM to recover state after starting.
      If true, then yarn.resourcemanager.store.class must be specified.
    </description>
  </property>
  <property>
    <name>yarn.resourcemanager.work-preserving-recovery.enabled</name>
    <value>true</value>
    <description>
      Enable RM work preserving recovery. This configuration is private to YARN for experimenting the feature.
    </description>
    <display-name>Enable Work Preserving Restart</display-name>
    <value-attributes>
      <type>boolean</type>
    </value-attributes>
  </property>
  <property>
    <name>yarn.resourcemanager.store.class</name>
    <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
    <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.
    </description>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>localhost:2181</value>
    <property-type>DONT_ADD_ON_UPGRADE</property-type>
    <description>
      List Host:Port of the ZooKeeper servers to be used by the RM. comma separated host:port pairs, each corresponding to a zk server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002" If the optional chroot suffix is used the example would look like: "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002/app/a" where the client would be rooted at "/app/a" and all paths would be relative to this root - ie getting/setting/etc...  "/foo/bar" would result in operations being run on "/app/a/foo/bar" (from the server perspective).
    </description>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-state-store.parent-path</name>
    <value>/rmstore</value>
    <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>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-acl</name>
    <value>world:anyone:rwcda </value>
    <description>ACL's to be used for ZooKeeper znodes.</description>
  </property>
  <property>
    <name>yarn.resourcemanager.work-preserving-recovery.scheduling-wait-ms</name>
    <value>10000</value>
    <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>
  </property>
  <property>
    <name>yarn.resourcemanager.connect.retry-interval.ms</name>
    <value>30000</value>
    <description>How often to try connecting to the ResourceManager.</description>
  </property>
  <property>
    <name>yarn.resourcemanager.connect.max-wait.ms</name>
    <value>900000</value>
    <description>Maximum time to wait to establish connection to ResourceManager</description>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-retry-interval-ms</name>
    <value>1000</value>
    <description>"Retry interval in milliseconds when connecting to ZooKeeper.
      When HA is enabled, the value here is NOT used. It is generated
      automatically from yarn.resourcemanager.zk-timeout-ms and
      yarn.resourcemanager.zk-num-retries."
    </description>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-num-retries</name>
    <value>1000</value>
    <description>Number of times RM tries to connect to ZooKeeper.</description>
  </property>
  <property>
    <name>yarn.resourcemanager.zk-timeout-ms</name>
    <value>10000</value>
    <description>ZooKeeper session timeout in milliseconds. Session expiration is managed by the ZooKeeper cluster itself, not by the client. This value is used by the cluster to determine when the client's session expires. Expirations happens when the cluster does not hear from the client within the specified session timeout period (i.e. no heartbeat).</description>
  </property>
  <property>
    <name>yarn.resourcemanager.state-store.max-completed-applications</name>
    <value>${yarn.resourcemanager.max-completed-applications}</value>
    <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>
  </property>
  <property>
    <name>yarn.resourcemanager.fs.state-store.retry-policy-spec</name>
    <value>2000, 500</value>
    <description>hdfs client retry policy specification. hdfs client retry is always enabled. Specified in pairs of sleep-time and number-of-retries and (t0, n0), (t1, n1), ..., the first n0 retries sleep t0 milliseconds on average, the following n1 retries sleep t1 milliseconds on average, and so on.</description>
  </property>
  <property>
    <name>yarn.resourcemanager.fs.state-store.uri</name>
    <value> </value>
    <description>RI 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>
  </property>
  <property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>false</value>
    <description>enable RM HA or not</description>
  </property>
  <property>
    <name>yarn.nodemanager.linux-container-executor.resources-handler.class</name>
    <value>org.apache.hadoop.yarn.server.nodemanager.util.DefaultLCEResourcesHandler</value>
    <description>Pre-requisite to use CGroups</description>
  </property>
  <property>
    <name>yarn.nodemanager.linux-container-executor.cgroups.hierarchy</name>
    <value>hadoop-yarn</value>
    <description>Name of the Cgroups hierarchy under which all YARN jobs will be launched</description>
  </property>
  <property>
    <name>yarn.nodemanager.linux-container-executor.cgroups.mount</name>
    <value>false</value>
    <description>If true, YARN will automount the CGroup, however the directory needs to already exist; else, the cgroup should be mounted by the admin</description>
  </property>
  <property>
    <name>yarn.nodemanager.linux-container-executor.cgroups.strict-resource-usage</name>
    <value>false</value>
    <description>Strictly limit CPU resource usage to allocated usage even if spare CPU is available</description>
  </property>
  <property>
    <name>yarn.nodemanager.resource.cpu-vcores</name>
    <value>8</value>
    <description></description>
    <display-name>Number of virtual cores</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>32</maximum>
    </value-attributes>
    <depends-on>
      <property>
        <type>yarn-site</type>
        <name>yarn.nodemanager.resource.percentage-physical-cpu-limit</name>
      </property>
    </depends-on>
  </property>
  <property>
    <name>yarn.nodemanager.resource.percentage-physical-cpu-limit</name>
    <value>80</value>
    <description>The amount of CPU allocated for YARN containers - only effective when used with CGroups</description>
    <display-name>Percentage of physical CPU allocated for all containers on a node</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>100</maximum>
      <increment-step>1</increment-step>
    </value-attributes>
  </property>
  <property>
    <name>yarn.node-labels.manager-class</name>
    <value>org.apache.hadoop.yarn.server.resourcemanager.nodelabels.MemoryRMNodeLabelsManager</value>
    <description>If user want to enable this feature, specify it to "org.apache.hadoop.yarn.server.resourcemanager.nodelabels.RMNodeLabelsManager</description>
  </property>
  <property>
    <name>yarn.node-labels.fs-store.retry-policy-spec</name>
    <value>2000, 500</value>
    <description></description>
  </property>
  <property>
    <name>yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb</name>
    <value>1000</value>
    <description>This is related to disk size on the machines, admins should set one of yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb or yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage but not both. If both are set, the more conservative value will be used</description>
  </property>
  <property>
    <name>yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage</name>
    <value>90</value>
    <description>This is related to disk size on the machines, admins should set one of yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb or yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage but not both. If both are set, the more conservative value will be used</description>
  </property>
  <property>
    <name>yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds</name>
    <value>-1</value>
    <description>Defines how often NMs wake up to upload log files. The default value is -1. By default, the logs will be uploaded whenthe application is finished. By setting this configure, logs can be uploaded periodically when the application is running. The minimum rolling-interval-seconds can be set is 3600.</description>
  </property>
  <property>
    <name>yarn.nodemanager.log-aggregation.debug-enabled</name>
    <value>false</value>
    <description>
      This configuration is for debug and test purpose.
      By setting this configuration as true.
      We can break the lower bound of yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds</description>
  </property>
  <property>
    <name>yarn.nodemanager.log-aggregation.num-log-files-per-app</name>
    <value>30</value>
    <description>This is temporary solution. The configuration will be deleted once, we find a more scalable method to only write a single log file per LRS.</description>
  </property>
  <property>
    <name>yarn.resourcemanager.system-metrics-publisher.enabled</name>
    <value>true</value>
    <description></description>
  </property>
  <property>
    <name>yarn.resourcemanager.system-metrics-publisher.dispatcher.pool-size</name>
    <value>10</value>
    <description></description>
  </property>
  <property>
    <name>yarn.timeline-service.client.max-retries</name>
    <value>30</value>
    <description></description>
  </property>
  <property>
    <name>yarn.timeline-service.client.retry-interval-ms</name>
    <value>1000</value>
    <description></description>
  </property>
  <property>
    <name>yarn.timeline-service.ttl-enable</name>
    <value>true</value>
    <description>
      Enable age off of timeline store data.
    </description>
    <value-attributes>
      <type>boolean</type>
    </value-attributes>
  </property>

  <property>
    <name>yarn.timeline-service.recovery.enabled</name>
    <value>false</value>
    <description>Enable timeline server to recover state after starting. If
      true, then yarn.timeline-service.state-store-class must be specified.
    </description>
  </property>
  <property>
    <name>yarn.timeline-service.state-store-class</name>
    <value>org.apache.hadoop.yarn.server.timeline.recovery.LeveldbTimelineStateStore</value>
    <description>Store class name for timeline state store.</description>
  </property>
  <property>
    <name>yarn.timeline-service.leveldb-state-store.path</name>
    <value>/hadoop/yarn/timeline</value>
    <description>Store file name for leveldb state store.</description>
    <value-attributes>
      <type>directory</type>
    </value-attributes>
  </property>

  <property>
    <name>yarn.timeline-service.leveldb-timeline-store.path</name>
    <value>/hadoop/yarn/timeline</value>
    <description>Store file name for leveldb timeline store.</description>
    <value-attributes>
      <type>directory</type>
    </value-attributes>
  </property>
  <property>
    <name>yarn.timeline-service.leveldb-timeline-store.read-cache-size</name>
    <value>104857600</value>
    <description>
      Size of read cache for uncompressed blocks for leveldb timeline store in bytes.
    </description>
  </property>
  <property>
    <name>yarn.timeline-service.leveldb-timeline-store.start-time-read-cache-size</name>
    <value>10000</value>
    <description>
      Size of cache for recently read entity start times for leveldb timeline store in number of entities.
    </description>
  </property>
  <property>
    <name>yarn.timeline-service.leveldb-timeline-store.start-time-write-cache-size</name>
    <value>10000</value>
    <description>
      Size of cache for recently written entity start times for leveldb timeline store in number of entities.
    </description>
  </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></description>
  </property>
  <property>
    <name>yarn.resourcemanager.webapp.delegation-token-auth-filter.enabled</name>
    <value>false</value>
    <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>
  </property>
  <property>
    <name>yarn.resourcemanager.bind-host</name>
    <value>0.0.0.0</value>
    <description>Default value is 0.0.0.0, when this is set the service will bind on all interfaces.  I think these two options (blank, "0.0.0.0" sans quotes) should be the two available values, with blank as the default.</description>
  </property>
  <property>
    <name>yarn.nodemanager.bind-host</name>
    <value>0.0.0.0</value>
    <description>Default value is 0.0.0.0, when this is set the service will bind on all interfaces.  I think these two options (blank, "0.0.0.0" sans quotes) should be the two available values, with blank as the default.</description>
  </property>
  <property>
    <name>yarn.timeline-service.bind-host</name>
    <value>0.0.0.0</value>
    <description>Default value is 0.0.0.0, when this is set the service will bind on all interfaces.  I think these two options (blank, "0.0.0.0" sans quotes) should be the two available values, with blank as the default.</description>
  </property>
  <property>
    <name>yarn.node-labels.fs-store.root-dir</name>
    <value>/system/yarn/node-labels</value>
    <description></description>
  </property>
  <property>
    <name>yarn.scheduler.minimum-allocation-vcores</name>
    <value>1</value>
    <description></description>
    <display-name>Minimum Container Size (VCores)</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>8</maximum>
      <increment-step>1</increment-step>
    </value-attributes>
    <depends-on>
      <property>
        <type>yarn-site</type>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
      </property>
    </depends-on>
  </property>
  <property>
    <name>yarn.scheduler.maximum-allocation-vcores</name>
    <value>8</value>
    <description></description>
    <display-name>Maximum Container Size (VCores)</display-name>
    <value-attributes>
      <type>int</type>
      <minimum>0</minimum>
      <maximum>8</maximum>
      <increment-step>1</increment-step>
    </value-attributes>
    <depends-on>
      <property>
        <type>yarn-site</type>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
      </property>
    </depends-on>
  </property>
  <property>
    <name>yarn.node-labels.enabled</name>
    <value>false</value>
    <description>
      Enable node labels to restrict YARN applications so that they run only on cluster nodes that have a specified node label.
    </description>
    <display-name>Node Labels</display-name>
    <value-attributes>
      <type>boolean</type>
    </value-attributes>
    <value-attributes>
      <type>value-list</type>
      <entries>
        <entry>
          <value>true</value>
          <label>Enabled</label>
        </entry>
        <entry>
          <value>false</value>
          <label>Disabled</label>
        </entry>
      </entries>
      <selection-cardinality>1</selection-cardinality>
    </value-attributes>
  </property>
  <property>
    <name>yarn.node-labels.manager-class</name>
    <value>org.apache.hadoop.yarn.server.resourcemanager.nodelabels.MemoryRMNodeLabelsManager</value>
    <description>If user want to enable this feature, specify it to "org.apache.hadoop.yarn.server.resourcemanager.nodelabels.RMNodeLabelsManager</description>
    <deleted>true</deleted>
  </property>
  <property>
    <name>yarn.nodemanager.container-executor.class</name>
    <value>org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor</value>
    <description>ContainerExecutor for launching containers</description>
    <depends-on>
      <property>
        <type>yarn-env</type>
        <name>yarn_cgroups_enabled</name>
      </property>
    </depends-on>
  </property>
  <property>
    <name>yarn.nodemanager.linux-container-executor.group</name>
    <value>hadoop</value>
    <description>Unix group of the NodeManager</description>
    <depends-on>
      <property>
        <type>yarn-env</type>
        <name>yarn_cgroups_enabled</name>
      </property>
        <property>
          <type>cluster-env</type>
          <name>user_group</name>
        </property>
    </depends-on>
  </property>
  <property>
    <name>yarn.resourcemanager.scheduler.monitor.enable</name>
    <value>false</value>
    <display-name>Pre-emption</display-name>
    <value-attributes>
      <type>value-list</type>
      <entries>
        <entry>
          <value>true</value>
          <label>Enabled</label>
        </entry>
        <entry>
          <value>false</value>
          <label>Disabled</label>
        </entry>
      </entries>
      <selection-cardinality>1</selection-cardinality>
    </value-attributes>
  </property>
</configuration>