#!/bin/bash
export JAVA_HOME=/opt/jdk
#HADOOP所在的bin目录
HADOOP_BIN_PATH=/opt/hadoop/bin
#当前时间戳
today_timestamp=$(date -d "$(date +"%Y-%m-%d %H:%M")" +%s)
#Func: 删除指定时间之前的过期,这里设置的是1天前
removeOutDate(){
$HADOOP_BIN_PATH/hdfs dfs -ls /data/* > temp.txt
cat temp.txt | while read quanxian temp user group size day hour filepath
do
current_file_time="$day $hour"
current_file_timestamp=$(date -d "$current_file_time" +%s)
if [ $(($today_timestamp-$current_file_timestamp)) -ge $((24*60*60)) ];then
echo "$(date +'%Y-%m-%d %H:%M:%S') $filepath"
$HADOOP_BIN_PATH/hdfs dfs -rm -r $filepath > /dev/null 2>&1
fi
done
}
#Func: 执行删除
execute(){
echo -e "\n\n"
echo "$(date +'%Y-%m-%d %H:%M:%S') start to remove outdate files in hdfs"
echo "$(date +'%Y-%m-%d %H:%M:%S') today is: $(date +"%Y-%m-%d %H:%M:%S")"
echo "$(date +'%Y-%m-%d %H:%M:%S') processing filepath: $i"
removeOutDate $i
echo -e "\n"
echo "$(date +'%Y-%m-%d %H:%M:%S') remove outdate files in hdfs finished"
echo -e "\n\n"
}
#开始执行
execute
shell定期删除hdfs上的过期文件
最新推荐文章于 2022-05-14 23:36:32 发布