1 安装依赖软件

#3台服务器都安装
yum install  lzop -y

2 jar包安装

#3台服务器,都要拷贝安装
cp hadoop-lzo-0.4.20.jar  /data/hadoop/share/hadoop/common/
#查看
[root@master11 01]# ll /data/hadoop/share/hadoop/common/
total 8688
-rw-r--r--. 1 root root 4638196 Mar  4 14:36 hadoop-common-3.4.0.jar
-rw-r--r--. 1 root root 3579389 Mar  4 14:36 hadoop-common-3.4.0-tests.jar
-rw-r--r--. 1 root root   96792 Mar  4 14:38 hadoop-kms-3.4.0.jar
-rw-r--r--. 1 root root  193831 May 15 17:20 hadoop-lzo-0.4.20.jar
-rw-r--r--. 1 root root  170442 Mar  4 14:38 hadoop-nfs-3.4.0.jar
-rw-r--r--. 1 root root  191049 Mar  4 14:39 hadoop-registry-3.4.0.jar
drwxr-xr-x. 2 root root    4096 Mar  4 16:04 jdiff
drwxr-xr-x. 2 root root    8192 Mar  4 14:38 lib
drwxr-xr-x. 2 root root      89 Mar  4 16:05 sources
drwxr-xr-x. 3 root root      20 Mar  4 16:05 webapps

 3 本地压缩测试

[root@master11 soft]# ll  -h access.log 
-rw-r--r--. 1 root root 777M May 15 17:37 access.log
[root@master11 soft]# lzop -v access.log 
compressing access.log into access.log.lzo
[root@master11 soft]# ll  -h access.log* 
-rw-r--r--. 1 root root 777M May 15 17:37 access.log
-rw-r--r--. 1 root root  94M May 15 17:37 access.log.lzo

4 修改配置文件

#3台服务器都要修改，增加如下配置
vi /data/hadoop/etc/hadoop/core-site.xml
    <property>
        <name>io.compression.codecs</name>
        <value>
            org.apache.hadoop.io.compress.GzipCodec,
            org.apache.hadoop.io.compress.DefaultCodec,
            org.apache.hadoop.io.compress.BZip2Codec,
            org.apache.hadoop.io.compress.SnappyCodec,
            com.hadoop.compression.lzo.LzoCodec,
            com.hadoop.compression.lzo.LzopCodec
        </value>
    </property>

    <property>
        <name>io.compression.codec.lzo.class</name>
        <value>com.hadoop.compression.lzo.LzoCodec</value>
    </property>

 5 重新启动集群

stop-all.sh
start-all.sh

6 测试

#上传测试文件
hdfs dfs  -put word.txt /test/02/
#执行
hadoop jar /data/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.4.0.jar  wordcount -Dmapreduce.output.fileoutputformat.compress=true -Dmapreduce.output.fileoutputformat.compress.codec=com.hadoop.compression.lzo.LzopCodec  /test/02/word.txt   /test/output3/
#查看
root@master11 01]# hdfs dfs  -ls  /test/output3
Found 2 items
-rw-r--r--   3 root supergroup          0 2024-05-15 21:27 /test/output3/_SUCCESS
-rw-r--r--   3 root supergroup         89 2024-05-15 21:27 /test/output3/part-r-00000.lzo
#创建lzo索引
hadoop jar /data/hadoop/share/hadoop/common/hadoop-lzo-0.4.20.jar   com.hadoop.compression.lzo.LzoIndexer /test/output3/

#再次执行wordcount
hadoop jar /data/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-3.4.0.jar  wordcount -Dmapreduce.output.fileoutputformat.compress=true -Dmapreduce.output.fileoutputformat.compress.codec=com.hadoop.compression.lzo.LzopCodec  /test/output3/   /test/output5/

[root@master11 soft]# hdfs dfs  -ls  /test/output5/
Found 2 items
-rw-r--r--   3 root supergroup          0 2024-05-15 22:23 /test/output5/_SUCCESS
-rw-r--r--   3 root supergroup    6098076 2024-05-15 22:23 /test/output5/part-r-00000.lzo