hadoop高可用性配置参考

1.core-site.xml

<configuration>
	<!--指定HDES的nameservice为ns1 -->
	<property>
		<name>fs.defaultFS</name>
		<value>hdfs://ns1</value>
	</property>
	<!--指定Hadoop 临时目录 -->
	<property>
		<name>hadoop.tmp.dir</name>
		<value>/export/servers/hadoop-2.7.4/tmp</value>
		</property>
	<!--指定Zookeeper地址 -->
	<property>
		<name>ha.zookeeper.quorum</name>
		<value>hadoop01:2181,hadoop01:2181,hadoop01:2181</value>
	</property>
</configuration>

2.hdfs-site.xml

<configuration>
    <!--设置副本个数-->
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
    <!--设置namenode .name目录-->
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:/export/data/hadoop/name</value>
    </property>
    <!--设置namenode .data目录-->
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:/export/data/hadoop/data</value>
    </property>
    <!--开启webHDFS-->
    <property>
    <name>dfs.webhdfs.enabled</name>
    <value>true</value>
    <!--在NN 和DN上开启webHDFS (REST API)功能,不是必须-->
    </property>
    <!--指定HDFS的nameservice为ns1,需要和core-site.xml中的保持一致-->
    <property>
        <name>dfs.nameservices</name>
        <value>ns1</value>
    </property>
    <!--ns1下面有两个NameNode,分别是nnl和nn2-->
    <property>
        <name>dfs.ha.namenodes.ns1</name>
        <value>nn1,nn2</value>
    </property>
    <!--nn1的 RPC通信地址-->
    <property>
        <name>dfs.namenode.rpc-address.ns1.nn1</name>
        <value>hadoop01:9000</value>
    </property>
    <!--nn1的http通信地址-->
    <property>
        <name>dfs.namenode.http-address.ns1.nn1</name>
        <value>hadoop01:50070</value>
    </property>
    <!--nn2的 RPC通信地址-->
    <property>
        <name>dfs.namenode.rpc-address.ns1.nn2</name>
        <value>hadoop02:9000</value>
    </property>
    <!--nn2的http通信地址-->
    <property>
        <name>dfs.namenode.http-address.ns1.nn2</name>
        <value>hadoop02:50070</value>
    </property>
    <!--指定 NameNode的元数据在JournalNode 上的存放位置-->
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>
        qjournal://hadoop01:8485;hadoop02:8485;hadoop03:8485/ns1</value>
    </property>
    <!--指定JournalNode在本地磁盘存放数据的位置-->
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/export/data/hadoop/journaldata</value>
    </property>
    <!--开启 Namewode失败自动切换-->
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <!--配置失败自动切换实现方式-->
    <property>
        <name>dfs.client.failover.proxy.provider.ns1</name>
        <value>
        org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider
        </value>
    </property>
    <!--配置隔离机制方法,多个机制用换行分制,即每个机制暂用一行-->
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>
            sshfence
            shell(/bin/true)
        </value>
    </property>
    <!--使用sshfence隔离机制时需要ssh免登录-->
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/root/.ssh/id_rsa</value>
    </property>
    <!--配置sshfence隔离机制超时时间-->
    <property>
        <name>dfs.ha.fencing.ssh.connect-timeout</name>
        <value>30000</value>
    </property>
</configuration>

3.mapred-site.xml

<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
</configuration>

4.yarn-site.xml

<configuration>
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>2048</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>2048</value>
    </property>
    <property>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
        <value>1</value>
    </property>
    <!--开启 ResourceManager高可用-->
    <property>
    <name>yarn.resourcemanager.ha.enableds</name>
    <value> true</value>
    </property>
    <!--指定ResourceManager的ciuster id -->
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>yrc</value>
    </property>
    <!--指定ResourceManager的名字-->
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
    </property>
    <!--分别指定ResourceManager的地址-->
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>hadoop01</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>hadoop02</value>
    </property>
    <!--指定Zookeeper集群地址-->
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>hadoop01:2181,hadoop02:2181,hadoop03:2181</value>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
</configuration>

5.slave

hadoop01 <!-- hadoop主机名，根据实际修改 -->
hadoop02
hadoop03

6.hadoop-env.sh

# 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.

# Set Hadoop-specific environment variables here.

# The only required environment variable is JAVA_HOME.  All others are
# optional.  When running a distributed configuration it is best to
# set JAVA_HOME in this file, so that it is correctly defined on
# remote nodes.

# The java implementation to use.
export JAVA_HOME=/export/servers/jdk #这里写自己的jdk所在的路径

# The jsvc implementation to use. Jsvc is required to run secure datanodes
# that bind to privileged ports to provide authentication of data transfer
# protocol.  Jsvc is not required if SASL is configured for authentication of
# data transfer protocol using non-privileged ports.
#export JSVC_HOME=${JSVC_HOME}

export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop"}

# Extra Java CLASSPATH elements.  Automatically insert capacity-scheduler.
for f in $HADOOP_HOME/contrib/capacity-scheduler/*.jar; do
  if [ "$HADOOP_CLASSPATH" ]; then
    export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
  else
    export HADOOP_CLASSPATH=$f
  fi
done

# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""

# Extra Java runtime options.  Empty by default.
export HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"

# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_NAMENODE_OPTS"
export HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,RFAS $HADOOP_DATANODE_OPTS"

export HADOOP_SECONDARYNAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_SECONDARYNAMENODE_OPTS"

export HADOOP_NFS3_OPTS="$HADOOP_NFS3_OPTS"
export HADOOP_PORTMAP_OPTS="-Xmx512m $HADOOP_PORTMAP_OPTS"

# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
export HADOOP_CLIENT_OPTS="-Xmx512m $HADOOP_CLIENT_OPTS"
#HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData $HADOOP_JAVA_PLATFORM_OPTS"

# On secure datanodes, user to run the datanode as after dropping privileges.
# This **MUST** be uncommented to enable secure HDFS if using privileged ports
# to provide authentication of data transfer protocol.  This **MUST NOT** be
# defined if SASL is configured for authentication of data transfer protocol
# using non-privileged ports.
export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER}

# Where log files are stored.  $HADOOP_HOME/logs by default.
#export HADOOP_LOG_DIR=${HADOOP_LOG_DIR}/$USER

# Where log files are stored in the secure data environment.
export HADOOP_SECURE_DN_LOG_DIR=${HADOOP_LOG_DIR}/${HADOOP_HDFS_USER}

###
# HDFS Mover specific parameters
###
# Specify the JVM options to be used when starting the HDFS Mover.
# These options will be appended to the options specified as HADOOP_OPTS
# and therefore may override any similar flags set in HADOOP_OPTS
#
# export HADOOP_MOVER_OPTS=""

###
# Advanced Users Only!
###

# The directory where pid files are stored. /tmp by default.
# NOTE: this should be set to a directory that can only be written to by 
#       the user that will run the hadoop daemons.  Otherwise there is the
#       potential for a symlink attack.
export HADOOP_PID_DIR=${HADOOP_PID_DIR}
export HADOOP_SECURE_DN_PID_DIR=${HADOOP_PID_DIR}

# A string representing this instance of hadoop. $USER by default.
export HADOOP_IDENT_STRING=$USER