Hadoop 2.2.0部署安装（笔记，单机安装）详解大数据

<?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>hadoop.tmp.dir</name> 
<value>/root/hadoop/hadoop-${user.name}</value> 
<description>A base for other temporaydirectories</description> 
</property> 
<property> 
<name>fs.default.name</name> 
<value>hdfs://localhost:8010</value> 
<description></description> 
</property> 
</configuration> 
#修改hdfs-site.xml配置文件, namenode和datanode存储路径的设置 
<?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.namenode.name.dir</name> 
<value>/root/hadoop/hdfs/namenode</value> 
<description>Determineswhere on the local filesystem the DFS name node should store the name table. Ifthis is a comma-delimited list of directories then the name table is replicatedin all of the directories, for redundancy. </description> 
<final>true</final> 
</property> 
<property> 
<name>dfs.datanode.data.dir</name> 
<value>/root/hadoop/hdfs/datanode</value> 
<description>Determineswhere on the local filesystem an DFS data node should store its blocks. If thisis a comma-delimited list of directories, then data will be stored in all nameddirectories, typically on different devices.Directories that do not exist areignored. 
</description> 
<final>true</final> 
</property> 
<property> 
　　　　　　　　　　　　<!-- 副本个数--> 
<name>dfs.replication</name> 
<value>1</value> 
</property> 
<property> 
　　 <name>dfs.permissions</name> 
　　  <value>false</value> 
</property> 
</configuration>

<?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. 
--> 
<!-- Put site-specific property overrides in this file. --> 
<configuration> 
<property> 
<name>mapred.job.tracker</name> 
<value>localhost:54311</value> 
<description>The host and port that the MapReduce job tracker runs 
at.  If "local", thenjobs are run in-process as a single map 
and reduce task. 
</description> 
</property> 
<property> 
<name>mapred.map.tasks</name> 
<value>10</value> 
<description>As a rule of thumb, use 10x the number of slaves(i.e., number of tasktrackers).</description> 
</property> 
<property> 
<name>mapred.reduce.tasks</name> 
<value>2</value> 
<description>As a rule of thumb, use 2x the number of slaveprocessors (i.e., number of tasktrackers).</description> 
</property> 
</configuration>

# Copyright 2011 The Apache Software Foundation 
#  
# 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/jdk1.7 
# The jsvc implementation to use. Jsvc is required to run secure datanodes. 
#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" 
# 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 $HADOOP_JAVA_PLATFORM_OPTS" 
# On secure datanodes, user to run the datanode as after dropping privileges 
export HADOOP_SECURE_DN_USER=${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}/${HADOOP_HDFS_USER} 
# The directory where pid files are stored. /tmp by default. 
# NOTE: this should be set to a directory that can only be written to by  
#       the user that will run the hadoop daemons.  Otherwise there is the 
#       potential for a symlink attack. 
export HADOOP_PID_DIR=${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