#ssh root@192.168.1.21 rm -rf /opt/hbase/hadoop-2.7.1/*
#ssh root@192.168.1.22 rm -rf /opt/hbase/hadoop-2.7.1/*
#ssh root@192.168.1.20 rm -rf /opt/hbase/hadoop-2.7.1/*#tar -zvxf /opt/hbase/hadoop-2.7.1.tar.gz -C /opt/hbase/scp core-site.xml root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hdfs-site.xml root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp mapred-site.xml root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp slaves root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-site.xml root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hadoop-env.sh root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-env.sh root@192.168.1.20:/opt/hbase/hadoop-2.7.1/etc/hadoopscp core-site.xml root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hdfs-site.xml root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp mapred-site.xml root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp slaves root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-site.xml root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hadoop-env.sh root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-env.sh root@192.168.1.21:/opt/hbase/hadoop-2.7.1/etc/hadoopscp core-site.xml root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hdfs-site.xml root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp mapred-site.xml root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp slaves root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-site.xml root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp hadoop-env.sh root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop
scp yarn-env.sh root@192.168.1.22:/opt/hbase/hadoop-2.7.1/etc/hadoop

# rm -rf /opt/hbase/hbase-1.2.1/*
#tar -zvxf /opt/hbase/hbase-1.2.1-bin.tar.gz -C /opt/hbase/
#tar -zvxf /opt/hbase/hbase-2.0.1-bin.tar.gz -C /opt/hbase/
#tar -zvxf /opt/hbase/hadoop-2.7.4.tar.gz -C /opt/hbase/scp hbase-env.sh root@192.168.1.20:/opt/hbase/hbase-1.2.1/conf
scp hbase-site.xml root@192.168.1.20:/opt/hbase/hbase-1.2.1/conf
scp regionservers root@192.168.1.20:/opt/hbase/hbase-1.2.1/conf
scp core-site.xml root@192.168.1.20:/opt/hbase/hbase-1.2.1/conf
scp hdfs-site.xml root@192.168.1.20:/opt/hbase/hbase-1.2.1/confscp hbase-env.sh root@192.168.1.21:/opt/hbase/hbase-1.2.1/conf
scp hbase-site.xml root@192.168.1.21:/opt/hbase/hbase-1.2.1/conf
scp regionservers root@192.168.1.21:/opt/hbase/hbase-1.2.1/conf
scp core-site.xml root@192.168.1.21:/opt/hbase/hbase-1.2.1/conf
scp hdfs-site.xml root@192.168.1.21:/opt/hbase/hbase-1.2.1/confscp hbase-env.sh root@192.168.1.22:/opt/hbase/hbase-1.2.1/conf
scp hbase-site.xml root@192.168.1.22:/opt/hbase/hbase-1.2.1/conf
scp regionservers root@192.168.1.22:/opt/hbase/hbase-1.2.1/conf
scp core-site.xml root@192.168.1.22:/opt/hbase/hbase-1.2.1/conf
scp hdfs-site.xml root@192.168.1.22:/opt/hbase/hbase-1.2.1/conf#rm /opt/hbase/hbase-1.2.1/lib/hadoop-common-2.5.1.jar
#cp -r /opt/hbase/hadoop-2.7.1/share/hadoop/common/hadoop-common-2.7.1.jar /opt/hbase/hbase-1.2.1/lib

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><configuration><property> <name>fs.defaultFS</name> <!--NameNode 的URI--><value>hdfs://master:9000</value> </property>
<!-- <property>
<name>fs.hdfs.impl</name>
<value>org.apache.hadoop.hdfs.DistributedFileSystem</value>
<description>The FileSystem for hdfs: uris.</description>
</property> --><property> <name>hadoop.tmp.dir</name> <!--hadoop临时文件的存放目录--><value>/opt/hbase/hadoop-2.7.1/temp</value> </property>
</configuration>

 # 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/lib/jdk/jdk1.8.0_91# 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 $HADOOP_HOME/contrib/capacity-scheduler/*.jar; doif [ "$HADOOP_CLASSPATH" ]; thenexport HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$felseexport HADOOP_CLASSPATH=$ffi
done# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""# Extra Java runtime options.  Empty by default.
export HADOOP_OPTS="$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
export JAVA_HOME=/usr/lib/jdk/jdk1.8.0_91

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><!-- Put site-specific property overrides in this file. -->
<configuration><property> <!--namenode持久存储名字空间及事务日志的本地文件系统路径--> <name>dfs.namenode.name.dir</name> <value>/opt/hbase/hadoop-2.7.1/dfs/name</value> <!--目录无需预先创建，会自动创建--></property> <property>  <!--DataNode存放块数据的本地文件系统路径--> <name>dfs.datanode.data.dir</name><value>/opt/hbase/hadoop-2.7.1/dfs/data</value> </property> <property>  <!--数据需要备份的数量，不能大于集群的机器数量，默认为3--><name>dfs.replication</name><value>2</value> </property><property> <name>dfs.namenode.secondary.http-address</name> <value>master:9001</value> </property>  <property>  <!--设置为true，可以在浏览器中IP+port查看--> <name>dfs.webhdfs.enabled</name><value>true</value> </property>
</configuration>

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><configuration><property> <!--mapreduce运用了yarn框架，设置name为yarn--> <name>mapreduce.framework.name</name> <value>yarn</value> </property> <property> <!--历史服务器,查看Mapreduce作业记录--> <name>mapreduce.jobhistory.address</name> <value>master:10020</value> </property> <property> <name>mapreduce.jobhistory.webapp.address</name> <value>master:19888</value> </property>
</configuration>

master
slave1
slave2
slave3

# 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.# User for YARN daemons
export HADOOP_YARN_USER=${HADOOP_YARN_USER:-yarn}
export JAVA_HOME=/usr/lib/jdk/jdk1.8.0_91# resolve links - $0 may be a softlink
export YARN_CONF_DIR="${YARN_CONF_DIR:-$HADOOP_YARN_HOME/conf}"# some Java parameters
# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
if [ "$JAVA_HOME" != "" ]; then#echo "run java in $JAVA_HOME"JAVA_HOME=$JAVA_HOME
fiif [ "$JAVA_HOME" = "" ]; thenecho "Error: JAVA_HOME is not set."exit 1
fiJAVA=$JAVA_HOME/bin/java
JAVA_HEAP_MAX=-Xmx1000m # For setting YARN specific HEAP sizes please use this
# Parameter and set appropriately
# YARN_HEAPSIZE=1000# check envvars which might override default args
if [ "$YARN_HEAPSIZE" != "" ]; thenJAVA_HEAP_MAX="-Xmx""$YARN_HEAPSIZE""m"
fi# Resource Manager specific parameters# Specify the max Heapsize for the ResourceManager using a numerical value
# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
# the value to 1000.
# This value will be overridden by an Xmx setting specified in either YARN_OPTS
# and/or YARN_RESOURCEMANAGER_OPTS.
# If not specified, the default value will be picked from either YARN_HEAPMAX
# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
#export YARN_RESOURCEMANAGER_HEAPSIZE=1000# Specify the max Heapsize for the timeline server using a numerical value
# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
# the value to 1000.
# This value will be overridden by an Xmx setting specified in either YARN_OPTS
# and/or YARN_TIMELINESERVER_OPTS.
# If not specified, the default value will be picked from either YARN_HEAPMAX
# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
#export YARN_TIMELINESERVER_HEAPSIZE=1000# Specify the JVM options to be used when starting the ResourceManager.
# These options will be appended to the options specified as YARN_OPTS
# and therefore may override any similar flags set in YARN_OPTS
#export YARN_RESOURCEMANAGER_OPTS=# Node Manager specific parameters# Specify the max Heapsize for the NodeManager using a numerical value
# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
# the value to 1000.
# This value will be overridden by an Xmx setting specified in either YARN_OPTS
# and/or YARN_NODEMANAGER_OPTS.
# If not specified, the default value will be picked from either YARN_HEAPMAX
# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
#export YARN_NODEMANAGER_HEAPSIZE=1000# Specify the JVM options to be used when starting the NodeManager.
# These options will be appended to the options specified as YARN_OPTS
# and therefore may override any similar flags set in YARN_OPTS
#export YARN_NODEMANAGER_OPTS=# so that filenames w/ spaces are handled correctly in loops below
IFS=# default log directory & file
if [ "$YARN_LOG_DIR" = "" ]; thenYARN_LOG_DIR="$HADOOP_YARN_HOME/logs"
fi
if [ "$YARN_LOGFILE" = "" ]; thenYARN_LOGFILE='yarn.log'
fi# default policy file for service-level authorization
if [ "$YARN_POLICYFILE" = "" ]; thenYARN_POLICYFILE="hadoop-policy.xml"
fi# restore ordinary behaviour
unset IFSYARN_OPTS="$YARN_OPTS -Dhadoop.log.dir=$YARN_LOG_DIR"
YARN_OPTS="$YARN_OPTS -Dyarn.log.dir=$YARN_LOG_DIR"
YARN_OPTS="$YARN_OPTS -Dhadoop.log.file=$YARN_LOGFILE"
YARN_OPTS="$YARN_OPTS -Dyarn.log.file=$YARN_LOGFILE"
YARN_OPTS="$YARN_OPTS -Dyarn.home.dir=$YARN_COMMON_HOME"
YARN_OPTS="$YARN_OPTS -Dyarn.id.str=$YARN_IDENT_STRING"
YARN_OPTS="$YARN_OPTS -Dhadoop.root.logger=${YARN_ROOT_LOGGER:-INFO,console}"
YARN_OPTS="$YARN_OPTS -Dyarn.root.logger=${YARN_ROOT_LOGGER:-INFO,console}"
if [ "x$JAVA_LIBRARY_PATH" != "x" ]; thenYARN_OPTS="$YARN_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
fi
YARN_OPTS="$YARN_OPTS -Dyarn.policy.file=$YARN_POLICYFILE"
export JAVA_HOME=/usr/lib/jdk/jdk1.8.0_91

<?xml version="1.0"?>
<configuration><property> <!--NodeManager上运行的附属服务，用于运行mapreduce--> <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> <!--ResourceManager 对客户端暴露的地址--> <name>yarn.resourcemanager.address</name> <value>master:8032</value> </property> <property> <!--ResourceManager 对ApplicationMaster暴露的地址-->  <name>yarn.resourcemanager.scheduler.address</name> <value>master:8030</value> </property> <property> <!--ResourceManager 对NodeManager暴露的地址--> <name>yarn.resourcemanager.resource-tracker.address</name>  <value>master:8031</value> </property> <property> <!--ResourceManager 对管理员暴露的地址--> <name>yarn.resourcemanager.admin.address</name>   <value>master:8033</value> </property> <property> <!--ResourceManager 对外web暴露的地址，可在浏览器查看-->   <name>yarn.resourcemanager.webapp.address</name> <value>master:8088</value> </property> </configuration>

#
#/**
# * 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 environment variables here.# This script sets variables multiple times over the course of starting an hbase process,
# so try to keep things idempotent unless you want to take an even deeper look
# into the startup scripts (bin/hbase, etc.)# The java implementation to use.  Java 1.7+ required.
# export JAVA_HOME=/usr/java/jdk1.6.0/# Extra Java CLASSPATH elements.  Optional.
# export HBASE_CLASSPATH=# The maximum amount of heap to use. Default is left to JVM default.
# export HBASE_HEAPSIZE=1G# Uncomment below if you intend to use off heap cache. For example, to allocate 8G of
# offheap, set the value to "8G".
# export HBASE_OFFHEAPSIZE=1G# Extra Java runtime options.
# Below are what we set by default.  May only work with SUN JVM.
# For more on why as well as other possible settings,
# see http://wiki.apache.org/hadoop/PerformanceTuning
export HBASE_OPTS="-XX:+UseConcMarkSweepGC"# Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+
#export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
#export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"# Uncomment one of the below three options to enable java garbage collection logging for the server-side processes.# This enables basic gc logging to the .out file.
# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"# This enables basic gc logging to its own file.
# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"# Uncomment one of the below three options to enable java garbage collection logging for the client processes.# This enables basic gc logging to the .out file.
# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"# This enables basic gc logging to its own file.
# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"# See the package documentation for org.apache.hadoop.hbase.io.hfile for other configurations
# needed setting up off-heap block caching. # Uncomment and adjust to enable JMX exporting
# See jmxremote.password and jmxremote.access in $JRE_HOME/lib/management to configure remote password access.
# More details at: http://java.sun.com/javase/6/docs/technotes/guides/management/agent.html
# NOTE: HBase provides an alternative JMX implementation to fix the random ports issue, please see JMX
# section in HBase Reference Guide for instructions.# export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=false -Dcom.sun.management.jmxremote.authenticate=false"
# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10101"
# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10102"
# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10103"
# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10104"
# export HBASE_REST_OPTS="$HBASE_REST_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10105"# File naming hosts on which HRegionServers will run.  $HBASE_HOME/conf/regionservers by default.
# export HBASE_REGIONSERVERS=${HBASE_HOME}/conf/regionservers# Uncomment and adjust to keep all the Region Server pages mapped to be memory resident
#HBASE_REGIONSERVER_MLOCK=true
#HBASE_REGIONSERVER_UID="hbase"# File naming hosts on which backup HMaster will run.  $HBASE_HOME/conf/backup-masters by default.
# export HBASE_BACKUP_MASTERS=${HBASE_HOME}/conf/backup-masters# Extra ssh options.  Empty by default.
# export HBASE_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HBASE_CONF_DIR"# Where log files are stored.  $HBASE_HOME/logs by default.
# export HBASE_LOG_DIR=${HBASE_HOME}/logs# Enable remote JDWP debugging of major HBase processes. Meant for Core Developers
# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8070"
# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8071"
# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8072"
# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8073"# A string representing this instance of hbase. $USER by default.
# export HBASE_IDENT_STRING=$USER# The scheduling priority for daemon processes.  See 'man nice'.
# export HBASE_NICENESS=10# The directory where pid files are stored. /tmp by default.
# export HBASE_PID_DIR=/var/hadoop/pids# Seconds to sleep between slave commands.  Unset by default.  This
# can be useful in large clusters, where, e.g., slave rsyncs can
# otherwise arrive faster than the master can service them.f
# export HBASE_SLAVE_SLEEP=0.1# Tell HBase whether it should manage it's own instance of Zookeeper or not.
export HBASE_MANAGES_ZK=true# The default log rolling policy is RFA, where the log file is rolled as per the size defined for the
# RFA appender. Please refer to the log4j.properties file to see more details on this appender.
# In case one needs to do log rolling on a date change, one should set the environment property
# HBASE_ROOT_LOGGER to "<DESIRED_LOG LEVEL>,DRFA".
# For example:
# HBASE_ROOT_LOGGER=INFO,DRFA
# The reason for changing default to RFA is to avoid the boundary case of filling out disk space as
# DRFA doesn't put any cap on the log size. Please refer to HBase-5655 for more context.
export JAVA_HOME=/usr/lib/jdk/jdk1.8.0_91

<?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.*/
-->
<configuration><property> <name>hbase.rootdir</name> <!-- hbase存放数据目录 --><value>hdfs://master:9000/opt/hbase/hbase_db</value><!-- 端口要和Hadoop的fs.defaultFS端口一致--></property> <property> <name>hbase.cluster.distributed</name> <!-- 是否分布式部署 --><value>true</value> </property> <property> <name>hbase.zookeeper.quorum</name> <!-- list of  zookooper --><value>master,slave1,slave2,slave3</value> </property> 　　　 <property><!--zookooper配置、日志等的存储位置 --><name>hbase.zookeeper.property.dataDir</name> <value>/opt/hbase/zookeeper</value></property></configuration>

master
slave1
slave2
slave3

Hadoop安装部署基本步骤：

1、安装jdk，配置环境变量。

jdk可以去网上自行下载，环境变量如下：

编辑  vim  /etc/profile 文件，添加如下内容：

export JAVA_HOME=/opt/java_environment/jdk1.7.0_80（填写自己的jdk安装路径）
       export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
       export PATH=$PATH:$JAVA_HOME/bin

输入命令，source /etc/profile  使配置生效

分别输入命令，java 、 javac 、 java -version，查看jdk环境变量是否配置成功

2、linux环境下，至少需要3台机子，一台作为master，2台（以上）作为slave。

　　  这里我以3台机器为例，linux用的是CentOS  6.5  x64为机器。

master 192.168.172.71
         slave1 192.168.172.72
         slave2 192.168.172.73

3、配置所有机器的hostname和hosts。

（1）更改hostname，可以编辑 vim /etc/sysconfig/network

　　　　　更改master的HOSTNAME，这里改为HOSTNAME=master

　　　　　其它slave为HOSTNAME=slave1、HOSTNAME=slave2 ，重启后生效。

　　　　　或者直接输：  hostname   名字，更改成功，这种方式无需重启即可生效，

　　　　　但是重启系统后更改的名字会失效，仍是原来的名字

　　　（2）更改host，可以编辑 vim /etc/hosts，增加如下内容：

　　　　　　   192.168.172.71    master 
       　　 　　192.168.172.72    slave1 
         　　　  192.168.172.73     slave2

　　　   　hosts可以和hostname不一致 ，这里为了好记就写一致了。

4、配置SSH所有机器之间免密码登录

　　（1）CentOS默认没有启动ssh无密登录,编辑 vim  /etc/ssh/sshd_config，

　　　　  去掉以下两行注释，开启Authentication免登陆。

　　　　  #RSAAuthentication yes
      　　   #PubkeyAuthentication yes

　　   如果是root用户下进行操作，还要去掉 #PermitRootLogin yes注释，允许root用户登录。

　　（2）输入命令，ssh-keygen -t rsa，生成key，一直按回车，

　　　　  就会在/root/.ssh生成：authorized_keys   id_rsa.pub   id_rsa 三个文件，

　　　　 这里要说的是，为了各个机器之间的免登陆，在每一台机器上都要进行此操作。

　　（3） 接下来，在master服务器，合并公钥到authorized_keys文件，

　　　　　进入/root/.ssh目录，输入以下命令

　　　       cat id_rsa.pub>> authorized_keys    把master公钥合并到authorized_keys 中

　　　　   ssh root@192.168.172.72 cat ~/.ssh/id_rsa.pub>> authorized_keys

　　　　   ssh root@192.168.172.73 cat ~/.ssh/id_rsa.pub>> authorized_keys

　　　　   把slave1、slave2公钥合并到authorized_keys 中

完成之后输入命令，把authorized_keys远程copy到slave1和slave2之中

　　　  　scp authorized_keys 192.168.172.72:/root/.ssh/

　　　     scp authorized_keys 192.168.172.73:/root/.ssh/

　　　 　 最好在每台机器上进行chmod 600  authorized_keys操作，

　　　　   使当前用户具有 authorized_keys的读写权限。

　　　　  拷贝完成后，在每台机器上进行 service sshd restart  操作， 重新启动ssh服务。

　　　　  之后在每台机器输入 ssh 192.168.172.xx，测试能否无需输入密码连接另外两台机器。

5、配置Hadoop环境变量，HADOOP_HOME、hadoop-env.sh、yarn-env.sh。

　　（1）配置HADOOP_HOME，编辑  vim  /etc/profile 文件，添加如下内容：

　　　　　export HADOOP_HOME=/opt/hbase/hadoop-2.7.3 （Hadoop的安装路径）

　　　　　export PATH=$PATH:$HADOOP_HOME/sbin

　　　　　export PATH=$PATH:$HADOOP_HOME/bin　

　　　　 （以下两行最好加上，若没有启动Hadoop、hbase时都会有没加载lib成功的警告）　　　　

　　　　　  export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
　　　　　export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib/native"

　　（2）配置hadoop-env.sh、yarn-env.sh，在Hadoop安装目录下

　　　　 编辑  vim etc/hadoop/hadoop-env.sh

　　　　　　加入export JAVA_HOME=/opt/java_environment/jdk1.7.0_80（jdk安装路径）

　　　　 编辑  vim etc/hadoop/yarn-env.sh

　　　　　　加入export JAVA_HOME=/opt/java_environment/jdk1.7.0_80（jdk安装路径）

　　　　 保存退出

6、配置基本相关xml，core-site.xml、hdfs-site.xml、mapred-site.xml、mapred-site.xml

　　（1）配置core-site.xml，在Hadoop安装目录下 编辑  vim etc/hadoop/core-site.xml

　　　　<configuration>

　　　　　　<property> 
　　　　　　　　<name>fs.defaultFS</name> <!--NameNode 的URI-->
　　　　　　　　<value>hdfs://mater:9000</value> 
　　　　　　</property> 
　　　　　　<property> 
　　　　　　　　<name>hadoop.tmp.dir</name> <!--hadoop临时文件的存放目录-->
　　　　　　　　<value>/opt/hbase/hadoop-2.7.3/temp</value> 
　　　　　　</property> 
　　　　</configuration>

　　（2）配置hdfs-site.xml，在Hadoop安装目录下 编辑  vim etc/hadoop/hdfs-site.xml

　　　　 <configuration>

　　　　　　<property> <!--namenode持久存储名字空间及事务日志的本地文件系统路径--> 
　　　　　　　　<name>dfs.namenode.name.dir</name> 
　　　　　　　　<value>/opt/hbase/hadoop-2.7.3/dfs/name</value>

　　　　　　　　　　<!--目录无需预先创建，会自动创建-->
　　　　　　</property> 
　　　　　　<property>  <!--DataNode存放块数据的本地文件系统路径--> 
　　　　　　　　<name>dfs.datanode.data.dir</name>
　　　　　　　　<value>/opt/hbase/hadoop-2.7.3/dfs/data</value> 
　　　　　　　</property> 
　　　　　　<property>  <!--数据需要备份的数量，不能大于集群的机器数量，默认为3-->
　　　　　　　　<name>dfs.replication</name>
　　　　　　　　<value>2</value> 
　　　　　　</property>

　　　　　　<property> 
　　　　　　　　<name>dfs.namenode.secondary.http-address</name> 
　　　　　　　　<value>master:9001</value> 
　　　　　　</property>  
　　　　　　<property>  <!--设置为true，可以在浏览器中IP+port查看--> 
　　　　　　　　<name>dfs.webhdfs.enabled</name>
　　　　　　　　<value>true</value> 
　　　　　　</property> 
　　　　</configuration>

（3）配置mapred-site.xml，在Hadoop安装目录下 编辑  vim etc/hadoop/mapred-site.xml

　　 <configuration>

　　　　<property> <!--mapreduce运用了yarn框架，设置name为yarn--> 
　　　　　　<name>mapreduce.framework.name</name> 
　　　　　　<value>yarn</value> 
　　　　</property> 
　　　　<property> <!--历史服务器,查看Mapreduce作业记录--> 
　　　　　　<name>mapreduce.jobhistory.address</name> 
　　　　　　<value>master:10020</value> 
　　　　</property> 
　　　　<property> 
　　　　　　<name>mapreduce.jobhistory.webapp.address</name> 
　　　　　　<value>master:19888</value> 
　　　　</property> 
　　</configuration>

（4）配置yarn-site.xml，在Hadoop安装目录下 编辑  vim etc/hadoop/yarn-site.xml

　　<configuration>

　　　　<property> <!--NodeManager上运行的附属服务，用于运行mapreduce--> 
　　　　　　<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> <!--ResourceManager 对客户端暴露的地址--> 
　　　　　　<name>yarn.resourcemanager.address</name> 
　　　　　　<value>master:8032</value> 
　　　　</property> 
　　　　<property> <!--ResourceManager 对ApplicationMaster暴露的地址-->  
　　　　　　<name>yarn.resourcemanager.scheduler.address</name> 
　　　　　　<value>master:8030</value> 
　　　　</property> 
　　　　<property> <!--ResourceManager 对NodeManager暴露的地址--> 
　　　　　　<name>yarn.resourcemanager.resource-tracker.address</name>  
　　　　　　<value>master:8031</value> 
　　　　</property> 
　　　　<property> <!--ResourceManager 对管理员暴露的地址--> 
　　　　　　<name>yarn.resourcemanager.admin.address</name>   
　　　　　　<value>master:8033</value> 
　　　　</property> 
　　　　<property> <!--ResourceManager 对外web暴露的地址，可在浏览器查看-->   
　　　　　　<name>yarn.resourcemanager.webapp.address</name> 
　　　　　　<value>master:8088</value> 
　　　　</property> 
　　</configuration>

7、配置slaves文件

　　在Hadoop安装目录下，编辑vim etc/hadoop/slaves，

　　去除默认的localhost，加入slave1、slave2，保存退出。

8、通过远程复制命令scp，将配置好的Hadoop复制到各个节点对应位置

　　scp -r /opt/hadoop-2.7.3 192.168.172.72:/opt/hadoop-2.7.3 
　　scp -r /opt/hadoop-2.7.3 192.168.172.73:/opt/hadoop-2.7.3

9、Hadoop的启动与停止

　　（1）在Master服务器启动hadoop，从节点会自动启动，进入Hadoop目录下，

　　　　　　输入命令，bin/hdfs namenode -format进行hdfs格式化

　　　　　　输入命令，sbin/start-all.sh，进行启动

　　　　　　也可以分开启动，sbin/start-dfs.sh、sbin/start-yarn.sh

　　　　　　在master 上输入命令：jps， 看到ResourceManager、

　　　　　　NameNode、SecondaryNameNode进程

　　　　　　   在slave 上输入命令：jps， 看到DataNode、NodeManager进程

　　　　　　出现这5个进程就表示Hadoop启动成功。

　　（2）接下来配置本地hosts，编辑 C:\Windows\System32\drivers\etc的hosts文件，加入

　　　　　　192.168.172.71   master

　　　　　　192.168.172.72   slave1

　　　　　　192.168.172.73   slave2

　　　　 在浏览器中输入http://master:50070查看master状态，

　　　　 输入http://192.168.172.72:8088查看集群状态

　　（3）停止hadoop，进入Hadoop目录下，输入命令：sbin/stop-all.sh，

　　　　  即可停止master和slave的Hadoop进程

Hbase安装部署基本步骤：

　　1、在Hadoop配置的基础上，配置环境变量HBASE_HOME、hbase-env.sh

　　　　编辑 vim /etc/profile  加入

　　　　　 export  HBASE_HOME=/opt/hbase-1.2.6

　　　　     export  PATH=$HBASE_HOME/bin:$PATH

　　　　编辑vim /opt/hbase-1.2.6/conf/hbase-env.sh  加入

　　　　　 export JAVA_HOME=/opt/java_environment/jdk1.7.0_80（jdk安装路径）

　　　　去掉注释 # export  HBASE_MANAGES_ZK=true，使用hbase自带zookeeper。

　　 2、配置hbase-site.xml文件　

　　　　<configuration>

　　　　　　<property> 
　　　　　　　　<name>hbase.rootdir</name> <!-- hbase存放数据目录 -->
　　　　　　　　<value>hdfs://master:9000/opt/hbase/hbase_db</value>

　　　　　　　　　　<!-- 端口要和Hadoop的fs.defaultFS端口一致-->
　　　　　　</property> 
　　　　　　<property> 
　　　　　　　　<name>hbase.cluster.distributed</name> <!-- 是否分布式部署 -->
　　　　　　　　<value>true</value> 
　　　　　　</property> 
　　　　　　<property> 
　　　　　　　　<name>hbase.zookeeper.quorum</name> <!-- list of  zookooper -->
　　　　　　　　<value>master,slave1,slave2</value> 
　　　　　　</property> 　　　

　　　　　　　<property><!--zookooper配置、日志等的存储位置 -->
　　　　　　　　　　<name>hbase.zookeeper.property.dataDir</name> 
　　　　　　　　　　<value>/opt/hbase/zookeeper</value>
　　　　　　　</property>

　　　　</configuration>

　　3、配置regionservers

　　　　编辑 vim /opt/hbase-1.2.6/conf/regionservers   去掉默认的localhost，
　　　  加入slave1、slave2，保存退出　

　　　  然后把在master上配置好的hbase，通过远程复制命令

　　　  scp -r /opt/hbase-1.2.6  192.168.172.72/73:/opt/hbase-1.2.6

　　　  复制到slave1、slave2对应的位置

　　4、启动与停止Hbase

　　　 　（1）在Hadoop已经启动成功的基础上，输入start-hbase.sh，过几秒钟便启动完成，

　　　　　　输入jps命令查看进程是否启动成功，若 master上出现HMaster、HQuormPeer，

　　　　　　slave上出现HRegionServer、HQuorumPeer，就是启动成功了。

　　　   （2）输入hbase shell 命令 进入hbase命令模式

　　　  　　   输入status命令可以看到如下内容，1个master，2 servers，3机器全部成功启动。

　　　  　　   1 active master, 0 backup masters, 2 servers, 0 dead, 2.0000 average load

　　　　（3）接下来配置本地hosts，（前边配置过的无需再配置了）

　　　　　　 编辑 C:\Windows\System32\drivers\etc的hosts文件，加入

　　　　　　　　192.168.172.71   master

　　　　　　　　192.168.172.72   slave1

　　　　　　　　192.168.172.73   slave2

　　　　　　在浏览器中输入http://master:16010就可以在界面上看到hbase的配置了

　　　　（4）当要停止hbase时输入stop-hbase.sh，过几秒后hbase就会被停止了。