基于:Hadoop 2.6.0-cdh5.4.0 hive1.1.0 HBase 1.0.0-cdh5.4.0 关键配置文件

core-site.xml 

<configuration>
<property>
  <name>fs.defaultFS</name>
  <value>hdfs://gagcluster</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/data1/hadoop_tmp/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>master.hadoop:2181,whoami:2181,slave1.hadoop:2181,slave2.hadoop:2181,slave3.hadoop:2181</value>
</property>
</configuration>

hdfs-site.xml

<configuration>
<property>
<name>dfs.nameservices</name>
<value>gagcluster</value>
</property>
<property>
<name>dfs.ha.namenodes.gagcluster</name>
<value>master.hadoop,whoami</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/data1/hadoop_tmp/hdfs/datanode</value>
</property>
<property>
<name>dfs.replication</name> 
<value>2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.gagcluster.master.hadoop</name>
<value>master.hadoop:9000</value>
</property>  
<property>
<name>dfs.namenode.rpc-address.gagcluster.whoami</name>
<value>whoami:9000</value> 
</property> 
<property>
<name>dfs.namenode.http-address.gagcluster.master.hadoop</name>
<value>master.hadoop:50070</value>
</property> 
<property>
<name>dfs.namenode.http-address.gagcluster.whoami</name>
<value>whoami:50070</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/data1/hadoop_tmp/hdfs/namenode</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://master.hadoop:8485;whoami:8485;slave1.hadoop:8485;slave2.hadoop:8485;slave3.hadoop:8485/gagcluster</value>
</property>

<property>
<name>dfs.journalnode.edits.dir</name>
<value>/data1/hadoop/tmp/journal</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.gagcluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence(hdfs)
          shell(/bin/true)</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/hadoop/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.datanode.max.transfer.threads</name>
<value>8192</value>
</property>
</configuration>

mapred-site.xml

<configuration>
<!--
<property>
<name>mapred.job.tracker</name>
<value>master.hadoop:9001</value>
</property>
-->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<!--<property>
<name>mapreduce.cluster.local.dir</name>
<value>/data1/hadoop_tmp/tmp/map</value>
</property>
-->
    <property>
            <name>mapreduce.jobhistory.address</name>
            <value>0.0.0.0:10020</value>
    </property>
    <property>
            <name>mapreduce.jobhistory.webapp.address</name>
            <value>0.0.0.0:19888</value>
     </property>
     <property>
     <name>dfs.permissions</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.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>rm-cluster</value>
</property>

<property> 
   <name>yarn.resourcemanager.ha.rm-ids</name> 
   <value>rm1,rm2</value> 
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.recover.enabled</name>
<value>true</value>
</property>
<!-- 指定RM的名字 -->
<property>               
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property> 
   <name>yarn.resourcemanager.hostname.rm1</name> 
   <value>master.hadoop</value> 
</property> 
<property>
  <name>yarn.resourcemanager.hostname.rm2</name>
  <value>whoami</value>
</property>
<property> 
<name>yarn.resourcemanager.ha.id</name> 
<value>rm1</value> 
<description>If we want to launch more than one RM in single node, we need this configuration</description> 
</property> 
                   
<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>master.hadoop:2181,whoami:2181,slave1.hadoop:2181,slave2.hadoop:2181,slave3.hadoop:2181</value> 
</property> 
<!--开启自动恢复功能--> 
<property> 
  <name>yarn.resourcemanager.scheduler.address.rm1</name> 
  <value>master.hadoop:8030</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.scheduler.address.rm2</name> 
  <value>whoami:8030</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.resource-tracker.address.rm1</name> 
  <value>master.hadoop:8031</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.resource-tracker.address.rm2</name> 
  <value>whoami:8031</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.address.rm1</name> 
  <value>master.hadoop:8032</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.address.rm2</name> 
  <value>whoami:8032</value> 
</property> 
<property>
   <name>yarn.resourcemanager.admin.address.rm1</name> 
   <value>master.hadoop:8033</value> 
</property> 
<property>
   <name>yarn.resourcemanager.admin.address.rm2</name> 
   <value>whoami:8033</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.webapp.address.rm1</name> 
  <value>master.hadoop:8088</value> 
</property> 
<property> 
  <name>yarn.resourcemanager.webapp.address.rm2</name> 
  <value>whoami:8088</value> 
</property>
<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.resourcemanager.connect.retry-interval.ms</name> 
<value>2000</value> 
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>12288</value>
</property> 
</configuration>

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=/usr/local/java/jdk1.7.0_65

# 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.a
export HADOOP_LOG_DIR=/data1/logs/
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

hive-env.sh

export HIVE_HOME=/usr/local/hive
export JAVA_HOME=/usr/local/java/jdk1.7.0_65
export HADOOP_HOME=/usr/local/hadoop
export HIVE_CONF_DIR=/usr/local/hive/conf
# 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 Hive and Hadoop environment variables here. These variables can be used
# to control the execution of Hive. It should be used by admins to configure
# the Hive installation (so that users do not have to set environment variables
# or set command line parameters to get correct behavior).
#
# The hive service being invoked (CLI/HWI etc.) is available via the environment
# variable SERVICE


# Hive Client memory usage can be an issue if a large number of clients
# are running at the same time. The flags below have been useful in 
# reducing memory usage:
#
# if [ "$SERVICE" = "cli" ]; then
#   if [ -z "$DEBUG" ]; then
#     export HADOOP_OPTS="$HADOOP_OPTS -XX:NewRatio=12 -Xms10m -XX:MaxHeapFreeRatio=40 -XX:MinHeapFreeRatio=15 -XX:+UseParNewGC -XX:-UseGCOverheadLimit"
#   else
#     export HADOOP_OPTS="$HADOOP_OPTS -XX:NewRatio=12 -Xms10m -XX:MaxHeapFreeRatio=40 -XX:MinHeapFreeRatio=15 -XX:-UseGCOverheadLimit"
#   fi
# fi

# The heap size of the jvm stared by hive shell script can be controlled via:
#
 export HADOOP_HEAPSIZE=512
#
# Larger heap size may be required when running queries over large number of files or partitions. 
# By default hive shell scripts use a heap size of 256 (MB).  Larger heap size would also be 
# appropriate for hive server (hwi etc).


# Set HADOOP_HOME to point to a specific hadoop install directory
# HADOOP_HOME=${bin}/../../hadoop

hive-site.xml

<value>jdbc:mysql://127.0.0.1:3306/hive</value>
<description>驱动名</description>
</property>
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>hive</value>
<description>用户名</description>
</property>
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>buzhidao</value>
<description>密码</description>
</property>
<property>
<name>hive.metastore.warehouse.dir</name>
<value>/data1/cloud/hive</value>
<description>数据路径（相对hdfs）</description>
</property>
<property>
<name>hive.metastore.uris</name>
<value>thrift://192.168.0.103:9083</value>
<description>运行hive得主机地址及端口</description>
</property>
<property>
<name>hive.hwi.war.file</name>
<value>lib/hive-hwi-1.2.0.war</value>
<description>hwi得war路径</description>
</property>
<property>
<name>mapred.input.dir.recursive</name>
<value>true</value>
</property>
<property>
<name>hive.mapred.supports.subdirectories</name>
<value>true</value>
</property>
<property>
<name>hive.exec.mode.local.auto</name>
<value>true</value>
</property>
<property>
<name>hive.exec.parallel</name>
<value>true</value>
</property>
<property>
<name>hive.limit.optimize.enable</name>
<value>true</value>
</property>
<property>
<name>mapred.job.reuse.jvm.num.tasks</name>
<value>10</value>
</property>
</configuration>

hbase-site.xml

<configuration>
<property>
<name>hbase.rootdir</name>
<value>hdfs://gagcluster/hbase</value>
</property>
<property>
<name>hbase.zookeeper.property.dataDir</name>
<value>/data1/cloud/zookeeper/data</value>
</property>
<property>
<name>hbase.cluster.distributed</name>
<value>true</value>
</property>
<property>
<name>hbase.master</name>
<value>60000</value>
</property>
<property>
<name>hbase.master.info.port</name>
<value>60010</value>
</property>
<property>
<name>hbase.zookeeper.property.clientPort</name>
<value>2181</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>master.hadoop,slave1.hadoop,slave2.hadoop,slave3.hadoop,whoami</value>
</property>
<property>
<name>hbase.regionserver.handler.count</name>
<value>100</value>
</property>
<property>
<name>hfile.block.cache.size</name>
<value>0.4</value>
</property>
<property>
<name>hbase.hregion.memstore.flush.size</name>
<value>266666</value>
</property>
<property>
<name>hbase.hregion.max.filesize</name>
<value>1000000</value>
</property>
<property>
<name>hbase.hstore.compactionThreshold</name>
<value>2</value>
</property>
<property>
<name>hbase.client.write.buffer</name>
<value>20971520</value>
</property>
<property>
<name>hbase.client.scanner.caching</name>
<value>500</value>
</property>
</configuration>

zoo.cfg

# 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=/data1/cloud/zookeeper/data
dataLogDir=/data1/cloud/zookeeper/logs
# the port at which the clients will connect
clientPort=2181
server.0=master.hadoop:2888:3888
server.1=whoami:2888:3888
server.2=slave1.hadoop:2888:3888
server.3=slave2.hadoop:2888:3888
server.4=slave3.hadoop:2888:3888
#
# 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