18.linux日志收集数据到hdfs上面

先创建一个目录

 

在这个job目录下创建upload.sh文件

[hadoop@node1 ~]$ pwd
/home/hadoop
[hadoop@node1 ~]$ mkdir job
[hadoop@node1 ~]$ ls
Desktop    Downloads  job   Music                                     Pictures  Templates
Documents  hive       logs  mysql-community-release-el7-5.noarch.rpm  Public    Videos
[hadoop@node1 ~]$ cd job/
[hadoop@node1 job]$ vim upload.sh

对upload.sh进行编辑

#!/bin/bash

#set java env
export JAVA_HOME=/opt/modules/jdk1.8.0_65
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH

#set hadoop env
export HADOOP_HOME=/opt/modules/hadoop-2.6.0
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH

log_src_dir=/home/hadoop/logs/log/ 
log_toupload_dir=/home/hadoop/logs/toupload/
hdfs_root_dir=/data/clickLog/20190620/

echo "log_src_dir:"$log_src_dir
ls $log_src_dir | while read fileName
do
    if [[ "$fileName" == access.log ]]; then
    # if [ "access.log" = "$fileName" ];then
        date=`date +%Y_%m_%d_%H_%M_%S`
        #将文件移动到待上传目录并重命名
        #打印信息
        echo "moving $log_src_dir$fileName to $log_toupload_dir"xxxxx_click_log_$fileName"$date"
        mv $log_src_dir$fileName $log_toupload_dir"xxxxx_click_log_$fileName"$date
        #将待上传的文件path写入一个列表文件willDoing
        echo $log_toupload_dir"xxxxx_click_log_$fileName"$date >> $log_toupload_dir"willDoing."$date
    fi
    
done

#找到列表文件willDoing
ls $log_toupload_dir | grep will |grep -v "_COPY_" | grep -v "_DONE_" | while read line
do
    #打印信息
    echo "toupload is in file:"$line
    #将待上传文件列表willDoing改名为willDoing_COPY_
    mv $log_toupload_dir$line $log_toupload_dir$line"_COPY_"
    #读列表文件willDoing_COPY_的内容（一个一个的待上传文件名）  ,此处的line 就是列表中的一个待上传文件的path
    cat $log_toupload_dir$line"_COPY_" |while read line
    do
        #打印信息
        echo "puting...$line to hdfs path.....$hdfs_root_dir"
        hadoop fs -put $line $hdfs_root_dir
    done    
    mv $log_toupload_dir$line"_COPY_"  $log_toupload_dir$line"_DONE_"
done

然后新建目录，并上传日志文件

给脚本赋予权限

[hadoop@node1 job]$ ls
upload.sh
[hadoop@node1 job]$ pwd
/home/hadoop/job
[hadoop@node1 job]$ ll
total 4
-rw-rw-r--. 1 hadoop hadoop 1734 Jun 20 10:57 upload.sh
[hadoop@node1 job]$ chmod 777 upload.sh 
[hadoop@node1 job]$ ll
total 4
-rwxrwxrwx. 1 hadoop hadoop 1734 Jun 20 10:57 upload.sh
[hadoop@node1 job]$ 

在HDFS上新建目录

 执行脚本

 可以看到结果