业务背景
约定五天前的HDFS数据为过期版本数据，写一个awk脚本自动删除过期版本数据
$ Hadoop fs -ls /user/pms/workspace/ouyangyewei/data
Found 9 items
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-01
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-02
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-03
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-04
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-05
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-06
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-07
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-08
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-09
脚本实现
# ---------------------------------------------------------
#
# 删除历史版本（五天前的为过期版本数据）
#
# ---------------------------------------------------------
old_version=$(hadoop fs -ls /user/pms/workspace/ouyangyewei/data | awk 'BEGIN{ five_days_ago=strftime("%F", systime()-5*24*3600) }{ split($8,arr,"/"); if(arr[7]<five_days_ago){printf "%s\n", $8} }')
arr=(${old_version// / })
for version in ${arr[@]}
do
hadoop fs -rmr $version
done
执行以后
$ hadoop fs -ls /user/pms/workspace/ouyangyewei/data
Found 4 items
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-06
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-07
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-08
drwxr-xr-x - pms pms 0 2015-08-11 17:03 /user/pms/workspace/ouyangyewei/data/2015-08-09