Hadoop 生产配置文件V2
生产环境的配置文件调优 ！！! Apache Hadoop 2.7.3 && NN HA && RM HA且仅针对于HDFS && Yarn 本身配置文件，不包括Gc 等其他单独角色调优 ,可供与参考或者直接使用。当然并不一定是最优化。
Core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed 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. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://flashHadoopDev</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:///app/hadoop/tmp/</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>VECS02907:2181,VECS02908:2181,VECS02909:2181</value>
</property>
<property>
<name>io.compression.codecs</name>
<value>org.apache.hadoop.io.compress.SnappyCodec,org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec,org.apache.hadoop.io.compress.Lz4Codec</value>
</property>
<property>
<name>fs.trash.interval</name>
<value>2880</value>
</property>
<!-- <property>
<name>net.topology.script.file.name</name>
<value>/apps/hadoop-conf/rack.sh</value>
</property>
-->
<!-- HealthMonitor check namenode 的超时设置，默认50000ms，改为5mins -->
<property>
<name>ha.health-monitor.rpc-timeout.ms</name>
<value>300000</value>
</property>
<!-- zk failover的session 超时设置，默认5000ms，改为3mins -->
<property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>180000</value>
</property>
<property>
<name>hadoop.proxyuser.deploy.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.deploy.groups</name>
<value>*</value>
</property>
</configuration>
hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed 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. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>dfs.nameservices</name>
<value>flashHadoopDev</value>
</property>
<!-- flashHadoopDev -->
<property>
<name>dfs.ha.namenodes.flashHadoopDev</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.flashHadoopDev.nn1</name>
<value>VECS02907:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.flashHadoopDev.nn2</name>
<value>VECS02908:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.flashHadoopDev.nn1</name>
<value>VECS02907:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.flashHadoopDev.nn2</name>
<value>VECS02908:50070</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.flashHadoopDev</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir.flashHadoopDev</name>
<value>qjournal://VECS02907:8485;VECS02908:8485;VECS02909:8485/flashHadoopDev</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///data1/data/flashHadoopDev/namenode/,file:///data2/data/flashHadoopDev/namenode/</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///data1/HDATA/dfs/local,
file:///data2/HDATA/dfs/local,
file:///data3/HDATA/dfs/local,
file:///data4/HDATA/dfs/local,
file:///data5/HDATA/dfs/local,
file:///data6/HDATA/dfs/local,
file:///data7/HDATA/dfs/local,
file:///data8/HDATA/dfs/local</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/data1/data/flashHadoopDev/journal</value>
</property>
<property>
<name>dfs.qjournal.start-segment.timeout.ms</name>
<value>60000</value>
</property>
<property>
<name>dfs.qjournal.prepare-recovery.timeout.ms</name>
<value>240000</value>
</property>
<property>
<name>dfs.qjournal.accept-recovery.timeout.ms</name>
<value>240000</value>
</property>
<property>
<name>dfs.qjournal.finalize-segment.timeout.ms</name>
<value>240000</value>
</property>
<property>
<name>dfs.qjournal.select-input-streams.timeout.ms</name>
<value>60000</value>
</property>
<property>
<name>dfs.qjournal.get-journal-state.timeout.ms</name>
<value>240000</value>
</property>
<property>
<name>dfs.qjournal.new-epoch.timeout.ms</name>
<value>240000</value>
</property>
<property>
<name>dfs.qjournal.write-txns.timeout.ms</name>
<value>60000</value>
</property>
<property>
<name>dfs.namenode.acls.enabled</name>
<value>true</value>
<description>Number of replication for each chunk.</description>
</property>
<!--需要根据实际配置进行修改-->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/hdfs/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.permissions.superusergroup</name>
<value>hadoop</value>
</property>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>16384</value>
</property>
<property>
<name>dfs.hosts.exclude</name>
<value>/app/hadoop/etc/hadoop/exclude.list</value>
<description> List of nodes to decommission </description>
</property>
<property>
<name>dfs.datanode.fsdataset.volume.choosing.policy</name>
<value>org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy</value>
</property>
<property>
<name>dfs.datanode.available-space-volume-choosing-policy.balanced-space-threshold</name>
<value>10737418240</value>
</property>
<property>
<name>dfs.datanode.available-space-volume-choosing-policy.balanced-space-preference-fraction</name>
<value>0.75</value>
</property>
<!-- 2018.06.19 Disk parameter change 每个盘预留1.4T空间-->
<property>
<name>dfs.datanode.du.reserved</name>
<value>1503238553600</value>
<description>Reserved space in bytes per volume. Always leave this much space free for non dfs use. </description>
</property>
<property>
<name>dfs.datanode.failed.volumes.tolerated</name>
<value>1</value>
<description>The number of volumes that are allowed to fail before a datanode stops offering service. By default any volume failure will cause a datanode to shutdown. </description>
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.size</name>
<value>1000</value>
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.expiry.ms</name>
<value>10000</value>
</property>
<property>
<name>dfs.client.read.shortcircuit</name>
<value>true</value>
</property>
<property>
<name>dfs.domain.socket.path</name>
<value>/var/run/hadoop-hdfs/dn_socket</value>
</property>
<property>
<name>dfs.client.read.shortcircuit.skip.checksum</name>
<value>false</value>
</property>
<property>
<name>dfs.block.size</name>
<value>134217728</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.handler.count</name>
<value>200</value>
</property>
<property>
<name>dfs.datanode.handler.count</name>
<value>40</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.namenode.datanode.registration.ip-hostname-check</name>
<value>false</value>
</property>
</configuration>
yarn-site.xml
<?xml version="1.0"?>
<!--
Licensed 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. See accompanying LICENSE file.
-->
<configuration>
<!-- Site specific YARN configuration properties -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<description>Where to aggregate logs to.</description>
<name>yarn.nodemanager.remote-app-log-dir</name>
<value>hdfs://flashHadoopDev/tmp/logs</value>
</property>
<property>
<name>yarn.nodemanager.remote-app-log-dir-suffix</name>
<value>logs</value>
</property>
<property>
<description>Classpath for typical applications.</description>
<name>yarn.application.classpath</name>
<value>
$HADOOP_CONF_DIR,
$HADOOP_COMMON_HOME/*,$HADOOP_COMMON_HOME/lib/*,
$HADOOP_HDFS_HOME/*,$HADOOP_HDFS_HOME/lib/*,
$HADOOP_MAPRED_HOME/*,$HADOOP_MAPRED_HOME/lib/*,
$HADOOP_YARN_HOME/*,$HADOOP_YARN_HOME/lib/*,
$HADOOP_COMMON_HOME/share/hadoop/common/*,
$HADOOP_COMMON_HOME/share/hadoop/common/lib/*,
$HADOOP_COMMON_HOME/share/hadoop/hdfs/*,
$HADOOP_COMMON_HOME/share/hadoop/hdfs/lib/*,
$HADOOP_COMMON_HOME/share/hadoop/mapreduce/*,
$HADOOP_COMMON_HOME/share/hadoop/mapreduce/lib/*,
$HADOOP_COMMON_HOME/share/hadoop/yarn/*,
$HADOOP_COMMON_HOME/share/hadoop/yarn/lib/*
</value>
</property>
<!-- resourcemanager config -->
<property>
<name>yarn.resourcemanager.connect.retry-interval.ms</name>
<value>2000</value>
</property>
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.embedded</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>FLASH_YARN_DEV</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>VECS02907</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>VECS02908</value>
</property>
<!-- CapacityScheduler -->
<property>
<name>yarn.resourcemanager.scheduler.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
</property>
<!-- CapacityScheduler End-->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.app.mapreduce.am.scheduler.connection.wait.interval-ms</name>
<value>5000</value>
</property>
<!-- 下线yarn nodemanager的列表文件。-->
<property>
<name>yarn.resourcemanager.nodes.exclude-path</name>
<value>/app/hadoop/etc/hadoop/yarn.exclude</value>
<final>true</final>
</property>
<!-- ZKRMStateStore config -->
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>VECS02908:2181,VECS02907:2181,VECS02909:2181</value>
</property>
<property>
<name>yarn.resourcemanager.zk.state-store.address</name>
<value>VECS02908:2181,VECS02907:2181,VECS02909:2181</value>
</property>
<!-- applications manager interface -->
<!--客户端通过该地址向RM提交对应用程序操作-->
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>VECS02907:23140</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>VECS02908:23140</value>
</property>
<!-- scheduler interface -->
<!--向RM调度资源地址-->
<property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>VECS02907:23130</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>VECS02908:23130</value>
</property>
<!-- RM admin interface -->
<property>
<name>yarn.resourcemanager.admin.address.rm1</name>
<value>VECS02907:23141</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address.rm2</name>
<value>VECS02908:23141</value>
</property>
<!-- RM resource-tracker interface nm向rm汇报心跳&& 领取任务-->
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>VECS02907:23125</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>VECS02908:23125</value>
</property>
<!-- RM web application interface -->
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>VECS02907:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>VECS02908:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.https.address.rm1</name>
<value>VECS02907:23189</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.https.address.rm2</name>
<value>VECS02908:23189</value>
</property>
<property>
<name>yarn.log.server.url</name>
<value>http://VECS02909:19888/jobhistory/logs</value>
</property>
<property>
<name>yarn.web-proxy.address</name>
<value>VECS02907:54315</value>
</property>
<!-- Node Manager Configs -->
<property>
<description>Address where the localizer IPC is.</description>
<name>yarn.nodemanager.localizer.address</name>
<value>0.0.0.0:23344</value>
</property>
<property>
<description>NM Webapp address.</description>
<name>yarn.nodemanager.webapp.address</name>
<value>0.0.0.0:8042</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.local-dirs</name>
<value>file:///data8/HDATA/yarn/local,
file:///data7/HDATA/yarn/local,
file:///data6/HDATA/yarn/local,
file:///data5/HDATA/yarn/local,
file:///data4/HDATA/yarn/local,
file:///data3/HDATA/yarn/local,
file:///data2/HDATA/yarn/local,
file:///data1/HDATA/yarn/local</value>
</property>
<property>
<name>yarn.nodemanager.log-dirs</name>
<value>file:///data8/HDATA/yarn/logs,
file:///data7/HDATA/yarn/logs,
file:///data6/HDATA/yarn/logs,
file:///data5/HDATA/yarn/logs,
file:///data4/HDATA/yarn/logs,
file:///data3/HDATA/yarn/logs,
file:///data2/HDATA/yarn/logs,
file:///data1/HDATA/yarn/logs</value>
</property>
<property>
<name>yarn.nodemanager.delete.debug-delay-sec</name>
<value>1200</value>
</property>
<property>
<name>mapreduce.shuffle.port</name>
<value>23080</value>
</property>
<property>
<name>yarn.resourcemanager.work-preserving-recovery.enabled</name>
<value>true</value>
</property>
<!-- tuning -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>20480</value>
</property>
<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>8</value>
</property>
<!-- tuning yarn container -->
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>2048</value>
</property>
<property>
<name>yarn.scheduler.maximum-allocation-mb</name>
<value>8192</value>
</property>
<property>
<name>yarn.scheduler.increment-allocation-mb</name>
<value>512</value>
</property>
<property>
<name>yarn.scheduler.fair.allow-undeclared-pools</name>
<value>false</value>
</property>
<property>
<name>yarn.scheduler.fair.allow-undeclared-pools</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.pmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.vmem-pmem-ratio</name>
<value>2.1</value>
<description>Ratio between virtual memory to physical memory when setting memory limits for containers</description>
</property>
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>1209600</value>
</property>
<!-- 新增新特性 -->
<property>
<name>yarn.node-labels.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.node-labels.fs-store.root-dir</name>
<value>hdfs://flashHadoopDev/yarn/yarn-node-labels/</value>
</property>
<!-- timeline server -->
<property>
<name>yarn.timeline-service.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.system-metrics-publisher.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.timeline-service.generic-application-history.enabled</name>
<value>true</value>
</property>
</configuration>
mapred-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed 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. See accompanying LICENSE file.
-->
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>VECS02909:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>VECS02909:19888</value>
</property>
<property>
<name>yarn.app.mapreduce.am.staging-dir</name>
<value>/user</value>
</property>
<!-- tuning mapreduce -->
<property>
<name>mapreduce.map.memory.mb</name>
<value>2048</value>
</property>
<property>
<name>mapreduce.map.java.opts</name>
<value>-Xmx1536m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:+UseCMSCompactAtFullCollection -XX:CMSFullGCsBeforeCompaction=15 -XX:CMSInitiatingOccupancyFraction=70 -Dfile.encoding=UTF-8</value>
</property>
<property>
<name>mapreduce.reduce.memory.mb</name>
<value>6144</value>
</property>
<property>
<name>mapreduce.reduce.java.opts</name>
<value>-Xmx4608m -XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:+UseCMSCompactAtFullCollection -XX:CMSFullGCsBeforeCompaction=15 -XX:CMSInitiatingOccupancyFraction=70 -Dfile.encoding=UTF-8</value>
</property>
<property>
<name>mapreduce.map.cpu.vcores</name>
<value>1</value>
</property>
<property>
<name>mapreduce.reduce.cpu.vcores</name>
<value>2</value>
</property>
<property>
<name>mapreduce.cluster.local.dir</name>
<value>file:///data8/HDATA/mapred/local,
file:///data7/HDATA/mapred/local,
file:///data6/HDATA/mapred/local,
file:///data5/HDATA/mapred/local,
file:///data4/HDATA/mapred/local,
file:///data3/HDATA/mapred/local,
file:///data2/HDATA/mapred/local,
file:///data1/HDATA/mapred/local</value>
</property>
<!--map and shuffle and reduce turning -->
<property>
<name>mapreduce.task.io.sort.mb</name>
<value>300</value>
</property>
<!-- 30*10=io.sort.mb -->
<property>
<name>mapreduce.jobhistory.max-age-ms</name>
<value>1296000000</value>
<source>mapred-default.xml</source>
</property>
<property>
<name>mapreduce.jobhistory.joblist.cache.size</name>
<value>200000</value>
<source>mapred-default.xml</source>
</property>
<property>
<name>mapreduce.input.fileinputformat.input.dir.recursive</name>
<value>true</value>
</property>
</configuration>