hadoop2.4-single
(1)机器免登录
ssh-keygen -t rsa
cd ~/.ssh/
cat id_rsa.pub >> authorized_keys
chmod 600 authorized_keys
[tip].ssh目录的权限必须是700
[tip].ssh/authorized_keys文件权限必须是600
(2)修改配置
cp mapred-site.xml.template mapred-site.xml
vi mapred-site.xml
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
vi core-site.xml
<property>
<name>fs.default.name</name>
<value>hdfs://localhost:9000</value>
</property>
vi yarn-site.xml
<property>
<!--注意这里是中划线-->
<name>yarn.nodemanager.aux-services</name>
<!--注意这里是下划线,否则会报名称不符合规范-->
<value>mapreduce_shuffle</value>
</property>
vi hdfs-site.xml
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/home/hadoop/data/yarn/hdfs/namenode</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:/home/hadoop/data/yarn/hdfs/datanode</value>
</property>
vi ~/.bashrc
#Hadoop2
export HADOOP_HOME=/home/hadoop/soft/hadoop-2.4.0
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
source ~/.bashrc
(3)启动
hadoop namenode -format
sh sbin/start-all.sh
[查看节点]
http://localhost:50070/
[查看任务]
http://localhost:8088/
(4)运行示例
在示例的源码包里有一个类叫
hadoop-2.4.0-src/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/ExampleDriver.java
它是程序的入口
/** * 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. */ package org.apache.hadoop.examples; import org.apache.hadoop.examples.dancing.DistributedPentomino; import org.apache.hadoop.examples.dancing.Sudoku; import org.apache.hadoop.examples.pi.DistBbp; import org.apache.hadoop.examples.terasort.TeraGen; import org.apache.hadoop.examples.terasort.TeraSort; import org.apache.hadoop.examples.terasort.TeraValidate; import org.apache.hadoop.util.ProgramDriver; /** * A description of an example program based on its class and a * human-readable description. */ public class ExampleDriver { public static void main(String argv[]){ int exitCode = -1; ProgramDriver pgd = new ProgramDriver(); try { pgd.addClass("wordcount", WordCount.class, "A map/reduce program that counts the words in the input files."); pgd.addClass("wordmean", WordMean.class, "A map/reduce program that counts the average length of the words in the input files."); pgd.addClass("wordmedian", WordMedian.class, "A map/reduce program that counts the median length of the words in the input files."); pgd.addClass("wordstandarddeviation", WordStandardDeviation.class, "A map/reduce program that counts the standard deviation of the length of the words in the input files."); pgd.addClass("aggregatewordcount", AggregateWordCount.class, "An Aggregate based map/reduce program that counts the words in the input files."); pgd.addClass("aggregatewordhist", AggregateWordHistogram.class, "An Aggregate based map/reduce program that computes the histogram of the words in the input files."); pgd.addClass("grep", Grep.class, "A map/reduce program that counts the matches of a regex in the input."); pgd.addClass("randomwriter", RandomWriter.class, "A map/reduce program that writes 10GB of random data per node."); pgd.addClass("randomtextwriter", RandomTextWriter.class, "A map/reduce program that writes 10GB of random textual data per node."); pgd.addClass("sort", Sort.class, "A map/reduce program that sorts the data written by the random writer."); pgd.addClass("pi", QuasiMonteCarlo.class, QuasiMonteCarlo.DESCRIPTION); pgd.addClass("bbp", BaileyBorweinPlouffe.class, BaileyBorweinPlouffe.DESCRIPTION); pgd.addClass("distbbp", DistBbp.class, DistBbp.DESCRIPTION); pgd.addClass("pentomino", DistributedPentomino.class, "A map/reduce tile laying program to find solutions to pentomino problems."); pgd.addClass("secondarysort", SecondarySort.class, "An example defining a secondary sort to the reduce."); pgd.addClass("sudoku", Sudoku.class, "A sudoku solver."); pgd.addClass("join", Join.class, "A job that effects a join over sorted, equally partitioned datasets"); pgd.addClass("multifilewc", MultiFileWordCount.class, "A job that counts words from several files."); pgd.addClass("dbcount", DBCountPageView.class, "An example job that count the pageview counts from a database."); pgd.addClass("teragen", TeraGen.class, "Generate data for the terasort"); pgd.addClass("terasort", TeraSort.class, "Run the terasort"); pgd.addClass("teravalidate", TeraValidate.class, "Checking results of terasort"); exitCode = pgd.run(argv); } catch(Throwable e){ e.printStackTrace(); } System.exit(exitCode); } }
hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.4.0.jar pi 5 10
[默认配置的话运行输出会有这么一句]
running in uber mode : false
运行分本地模式 uber mode 和 no-uber mode
uber mode对于小作业共享container - MapTask,ReduceTask会使用MRAppMaster所在的container