Hadoop高可用平台搭建

export JAVA_HOME=/home/xiaolong/jdk1.8.0_40
export PATH=.:$JAVA_HOME/bin:$PATH

[xiaolong@nna jdk1.8.0_40]$ source /etc/profile
[xiaolong@nna jdk1.8.0_40]$ java -version
java version "1.8.0_40"
Java(TM) SE Runtime Environment (build 1.8.0_40-b26)
Java HotSpot(TM) 64-Bit Server VM (build 25.40-b25, mixed mode)
[xiaolong@nna jdk1.8.0_40]$ 

export JAVA_HOME=/home/xiaolong/jdk1.8.0_40
export ZK_HOME=/home/xiaolong/zookeeper-3.4.6
export PATH=.:$JAVA_HOME/bin:$ZK_HOME/bin:$PATH

export JAVA_HOME=/home/xiaolong/jdk1.8.0_40
export ZK_HOME=/home/xiaolong/zookeeper-3.4.6
export HADOOP_HOME=/home/xiaolong/hadoop-2.6.0
export PATH=.:$JAVA_HOME/bin:$ZK_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH

[xiaolong@nna hadoop-2.6.0]$ source /etc/profile
[xiaolong@nna hadoop-2.6.0]$ hadoop version
Hadoop 2.6.0
Subversion Unknown -r Unknown
Compiled by root on 2014-12-09T11:15Z
Compiled with protoc 2.5.0
From source with checksum 18e43357c8f927c0695f1e9522859d6a
This command was run using /home/xiaolong/hadoop-2.6.0/share/hadoop/common/hadoop-common-2.6.0.jar

# The number of milliseconds of each tick
tickTime=2000
# The number of ticks that the initial 
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between 
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just 
# example sakes.
dataDir=/home/xiaolong/zookeeper-3.4.6/data
# the port at which the clients will connect
clientPort=2181
# the maximum number of client connections.
# increase this if you need to handle more clients
#maxClientCnxns=60
#
# Be sure to read the maintenance section of the 
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
#autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
#autopurge.purgeInterval=1
server.1=192.168.137.101:2888:3888
server.2=192.168.137.102:2888:3888
server.3=192.168.137.103:2888:3888

echo "1" > myid
echo "2" > myid
echo "3" > myid

dn1
dn2
dn3

# 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=${JAVA_HOME}
export JAVA_HOME=/home/hadoop/jdk1.8.0_40

# 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

xml version="1.0" encoding="UTF-8"?>
xml-stylesheet type="text/xsl" href="configuration.xsl"?>




<configuration>
    <property>
        <name>fs.defaultFSname>
        <value>hdfs://ns1value>
    property>
    <property>
      <name>hadoop.tmp.dirname>
      <value>file:/home/hadoop/hadoop-2.6.0/tmpvalue>
    property>
    <property>
      <name>ha.zookeeper.quorumname>
      <value>nna:2181,nns:2181,dn1:2181value>
    property>
configuration>

xml version="1.0" encoding="UTF-8"?>
xml-stylesheet type="text/xsl" href="configuration.xsl"?>




<configuration>
    <property>
      <name>dfs.replicationname>
      <value>2value>
    property>
    <property>
      <name>dfs.nameservicesname>
      <value>ns1value>
    property>
    <property>
      <name>dfs.ha.namenodes.ns1name>
      <value>nn1,nn2value>
    property>
    <property>
      <name>dfs.namenode.rpc-address.ns1.nn1name>
      <value>nna:9000value>
    property>
    <property>
      <name>dfs.namenode.rpc-address.ns1.nn2name>
      <value>nns:9000value>
    property>
    <property>
      <name>dfs.namenode.http-address.ns1.nn1name>
      <value>nna:50070value>
    property>
    <property>
      <name>dfs.namenode.http-address.ns1.nn2name>
      <value>nns:50070value>
    property>
    <property>
      <name>dfs.namenode.shared.edits.dirname>
      <value>qjournal://nns:8485;dn1:8485;dn2:8485/ns1value>
    property>    
    <property>
        <name>dfs.client.failover.proxy.provider.ns1name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvidervalue>
    property>
    <property>
        <name>dfs.ha.fencing.methodsname>
        <value>sshfencevalue>
    property>
    <property>
        <name>dfs.ha.fencing.ssh.private-key-filesname>
        <value>/home/hadoop/.ssh/id_rsavalue>
    property>
    <property>
        <name>dfs.journalnode.edits.dirname>
        <value>/home/hadoop/hadoop-2.6.0/tmp/journalvalue>
    property>
    <property>
        <name>dfs.ha.automatic-failover.enabledname>
        <value>truevalue>
    property>
    <property>   
        <name>dfs.namenode.name.dirname>   
        <value>${hadoop.tmp.dir}/dfs/namevalue>  
    property> 
    <property>   
        <name>dfs.datanode.data.dirname>   
        <value>${hadoop.tmp.dir}/dfs/datavalue>  
    property> 
    <property>
      <name>dfs.permissions.enabledname>
      <value>falsevalue>
    property>
configuration>

xml version="1.0"?>

<configuration>


    <property>
        <name>yarn.resourcemanager.ha.enabledname>
        <value>truevalue>
    property>
    <property> 
       <name>yarn.resourcemanager.ha.automatic-failover.enabledname> 
       <value>truevalue> 
    property> 
     
    <property>
      <name>yarn.resourcemanager.recovery.enabledname> 
      <value>truevalue> 
    property>
    <property>
          <name>yarn.resourcemanager.cluster-idname>
          <value>yarn-havalue>
    property>
    <property>
      <name>yarn.resourcemanager.ha.rm-idsname>
      <value>rm1,rm2value>
    property>
    <property>
      <name>yarn.resourcemanager.hostname.rm1name>
      <value>nnavalue>
    property>
    <property>
      <name>yarn.resourcemanager.hostname.rm2name>
      <value>nnsvalue>
    property>
    
　　<property>
　　　　　<name>yarn.resourcemanager.ha.idname>        <value>rm1value>
    property>
    <property> 
      <name>yarn.resourcemanager.store.classname> 
      <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStorevalue> 
    property> 
    <property>
      <name>yarn.resourcemanager.zk-addressname>
      <value>nna:2181,nns:2181,dn1:2181value>
    property>
    <property>
        <name>yarn.nodemanager.aux-servicesname>
        <value>mapreduce_shufflevalue>
    property>
configuration>

xml version="1.0"?>
xml-stylesheet type="text/xsl" href="configuration.xsl"?>




<configuration>
    <property>
      <name>mapreduce.framework.namename>
      <value>yarnvalue>
    property>
configuration>

#! /bin/bash

# 启动zookeeper集群
echo "启动zookeeper集群"
ssh nna "/home/hadoop/zookeeper-3.4.6/bin/zkServer.sh start" &> /dev/null
ssh nns "/home/hadoop/zookeeper-3.4.6/bin/zkServer.sh start" &> /dev/null
ssh dn1 "/home/hadoop/zookeeper-3.4.6/bin/zkServer.sh start" &> /dev/null

sleep 5s

# 对zookeeper集群进行格式化
echo "对zookeeper集群进行格式化"
ssh nna "/home/hadoop/hadoop-2.6.0/bin/hdfs zkfc -formatZK"

# 启动journalnode元数据共享进程
echo "启动journalnode元数据共享进程"
ssh nna "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemons.sh start journalnode"
#ssh nns "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemon.sh start journalnode" 

# 启动故障恢复进程zkfc
echo "启动故障恢复进程zkfc"
ssh nna "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemon.sh start zkfc"
ssh nns "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemon.sh start zkfc"

# nna上,格式化NameNode,并开启
echo "nna上,格式化NameNode,并开启"
ssh nna "/home/hadoop/hadoop-2.6.0/bin/hdfs namenode -format -clusterid ns1" 
sleep 10
ssh nna "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemon.sh start namenode"

# nns上,同步NameNode,并开启
echo "nns上,同步NameNode,并开启"
ssh nns "/home/hadoop/hadoop-2.6.0/bin/hdfs namenode -bootstrapStandby"
ssh nns "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemon.sh start namenode"

# 启动所有DataNodes
echo "启动所有DataNodes"
ssh nna "/home/hadoop/hadoop-2.6.0/sbin/hadoop-daemons.sh start datanode"

# 启动yarn
echo "启动yarn"
ssh nna "/home/hadoop/hadoop-2.6.0/sbin/start-yarn.sh"

# 在nns上,启动另一个resourcemanager
echo "在nns上,启动另一个resourcemanager"
ssh nns "/home/hadoop/hadoop-2.6.0/sbin/yarn-daemon.sh start resourcemanager"

    <property>
        <name>dfs.journalnode.edits.dirname>
        <value>/home/hadoop/hadoop-2.6.0/tmp/journalvalue>
    property>

    <property>
        <name>yarn.resourcemanager.ha.idname>
        <value>rm1value>
    property>