下面是一个azakaban调度大数据脚本的例子
1、首先上传job，利用定时任务将日志文件上传到hdfs
# upload.job type=command command=bash uploadFile2Hdfs.sh
#!/bin/bash #set java env export JAVA_HOME=/soft/jdk/ export JRE_HOME=${JAVA_HOME}/jre export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib export PATH=${JAVA_HOME}/bin:$PATH #set hadoop env export HADOOP_HOME=/soft/hadoop/ export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH #版本1的问题： #虽然上传到Hadoop集群上了，但是原始文件还在。如何处理？ #日志文件的名称都是xxxx.log1,再次上传文件时，因为hdfs上已经存在了，会报错。如何处理？ #如何解决版本1的问题 # 1、先将需要上传的文件移动到待上传目录 # 2、在讲文件移动到待上传目录时，将文件按照一定的格式重名名 # /export/software/hadoop.log1 /export/data/click_log/xxxxx_click_log_{date} #日志文件存放的目录 log_src_dir=/home/centos/logs/log/ #待上传文件存放的目录 log_toupload_dir=/home/centos/logs/toupload/ day_01=`date -d'-1 day' +%Y-%m-%d` syear=`date --date=$day_01 +%Y` smonth=`date --date=$day_01 +%m` sday=`date --date=$day_01 +%d` #echo $day_01 #echo $syear #echo $smonth #echo $sday #日志文件上传到hdfs的根路径 hdfs_root_dir=/data/clickLog/$syear/$smonth/$sday hadoop fs -mkdir -p $hdfs_root_dir #打印环境变量信息 echo "envs: hadoop_home: $HADOOP_HOME" #读取日志文件的目录，判断是否有需要上传的文件 echo "log_src_dir:"$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
2、清理数据job，将数据清理存入hdfs
# clean.job type=command dependencies=upload command=bash clean.sh
#!/bin/bash export JAVA_HOME=/usr/local/soft/java export JRE_HOME=${JAVA_HOME}/jre export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib export PATH=${JAVA_HOME}/bin:$PATH #set hadoop env export HADOOP_HOME=/usr/local/software/hadoop export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH #log_local_dir=/home/hadoop/flume/ #log_hdfs_dir=/test/2017/7/ day_01=`date -d'-1 day' +%Y-%m-%d` syear=`date --date=$day_01 +%Y` smonth=`date --date=$day_01 +%m` sday=`date --date=$day_01 +%d` #echo $day_01 #echo $syear #echo $smonth #echo $sday log_hdfs_dir=/data/clickLog/$syear/$smonth/$sday #echo $log_hdfs_dir click_log_clean=com.xiaofeiyang.AccessLogDriver clean_dir=/cleaup/$syear/$smonth/$sday echo "hadoop jar /home/centos/hivedemo/hiveaad.jar $click_log_clean $log_hdfs_dir $clean_dir" hadoop fs -rm -r -f $clean_dir hadoop jar /home/hadoop/hadoop.jar $click_log_clean $log_hdfs_dir $clean_dir
3、将清理的数据导入hive
# hivesql.job type=command dependencies=clean command=bash hivesql.sh
#!/bin/bash export JAVA_HOME=/soft/jdk export JRE_HOME=${JAVA_HOME}/jre export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib export PATH=${JAVA_HOME}/bin:$PATH #set hadoop env export HADOOP_HOME=/soft/hadoop export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH export HIVE_HOME=/soft/hive export PATH=${HIVE_HOME}/bin:$PATH log_local_dir=/home/centos/flume/ #log_hdfs_dir=/test/2017/7/ day_01=`date -d'-1 day' +%Y-%m-%d` syear=`date --date=$day_01 +%Y` smonth=`date --date=$day_01 +%m` sday=`date --date=$day_01 +%d` #echo $day_01 #echo $syear #echo $smonth #echo $sday log_hdfs_dir=/test/$syear/$smonth/$sday #echo $log_hdfs_dir click_log_clean=com.it18zhang.project.mr.AccessLogDriver clean_dir=/cleaup/$syear/$smonth/$sday HQL_origin="load data inpath '$clean_dir' into table mydb2.accesslog" #HQL_origin="create external table db2.access(ip string,day string,url string,upflow string) row format delimited fields terminated by ',' location '$clean_dir'" #echo $HQL_origin hive -e "$HQL_origin"
4、根据清理的数据生成统计数据
# ip.job type=command dependencies=hivesqljob command=bash ip.sh
#!/bin/bash export JAVA_HOME=/soft/jdk export JRE_HOME=${JAVA_HOME}/jre export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib export PATH=${JAVA_HOME}/bin:$PATH #set hadoop env export HADOOP_HOME=/soft/hadoop export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH export HIVE_HOME=/soft/hive export PATH=${HIVE_HOME}/bin:$PATH log_local_dir=/home/centos/flume/ #log_hdfs_dir=/test/2017/7/ day_01=`date -d'-1 day' +%Y-%m-%d` syear=`date --date=$day_01 +%Y` smonth=`date --date=$day_01 +%m` sday=`date --date=$day_01 +%d` #echo $day_01 #echo $syear #echo $smonth #echo $sday log_hdfs_dir=/test/$syear/$smonth/$sday #echo $log_hdfs_dir click_log_clean=com.it18zhang.project.mr.AccessLogDriver clean_dir=/cleaup/$syear/$smonth/$sday HQL_origin="insert into mydb2.upflow select ip,sum(upflow) as sum from mydb2.accesslog group by ip order by sum desc " #echo $HQL_origin hive -e "$HQL_origin"
5、将统计数据导入mysql
# mysql.job type=command dependencies=ipjob command=bash mysql.sh
#!/bin/bash export JAVA_HOME=/soft/jdk export JRE_HOME=${JAVA_HOME}/jre export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib export PATH=${JAVA_HOME}/bin:$PATH #set hadoop env export HADOOP_HOME=/soft/hadoop export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH export HIVE_HOME=/soft/hive export PATH=${HIVE_HOME}/bin:$PATH export SQOOP_HOME=/soft/sqoop export PATH=${SQOOP_HOME}/bin:$PATH sqoop export --connect \ jdbc:mysql://s201:3306/userdb \ --username sqoop --password sqoop --table upflow --export-dir \ /user/hive/warehouse/mydb2.db/upflow --input-fields-terminated-by ','
