contab与hive自动执行任务

yum install vixie-cron //cron的主程序
yum install crontabs //驱动，安装、卸载、或列举来驱动cron守护进程的表格程序
service crond start
service crond stop
service crond restart
service crond reload //重新载入
service crond status
查看crontab服务是否已经设置开机启动，执行：ntsysv
加入开机自动启动：chkconfig -level 35 crond on
mkdir sabercrond
crontab sabercrond
crontab -e //编辑
crontab -l //查看
crontab -r //删除

例子：每天定时将数据添加到当天日期分区的分区表中

!/bin/sh

upload logs to hdfs

yesterday=date --date=\'1 days ago\' +%Y%m%d
hive -e \”
use stage;
create table tracklog_tmp (
dateday string,
datetime string,
ip string ,
cookieid string,
userid string,
logserverip string,
referer string,
requesturl string,
remark1 string,
remark2 string,
alexaflag string,
ua string,
wirelessflag string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY \’ \’;\”
hive -e \”
use stage;
set hive.enforce.bucketing=true;
set hive.exec.compress.output=true;
set mapred.output.compress=true;
set mapred.output.compression.codec=org.apache.hadoop.io.compress.GzipCodec;
set io.compression.codecs=org.apache.hadoop.io.compress.GzipCodec;
load data local inpath \’/diskg/logs/tracklog_192.168.1.1/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp;
insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp; load data local inpath \’/diskg/logs/tracklog_192.168.1.2/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp; insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp;
load data local inpath \’/diskg/logs/tracklog_192.168.1.3/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp;
insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp; load data local inpath \’/diskg/logs/trackloguc_192.168.1.1/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp; insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp;
load data local inpath \’/diskg/logs/trackloguc_192.168.1.2/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp;
insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp; load data local inpath \’/diskg/logs/trackloguc_192.168.1.3/${yesterday}/${yesterday}????.dat\’ overwrite into table tracklog_tmp; insert into table tracklog PARTITION (day=\’${yesterday}\’) select * from tracklog_tmp;
\”
hive -e \”
use stage;
drop table tracklog_tmp ;\”

最后
在crontab中加入定时任务：

crontab -e
加入如下代码：

import tracklog

25 07 * * * /opt/bin/hive_opt/import_tracklog.sh