基于sparksql调用shell脚本执行SQL

[Author]: kwu

基于sparksql调用shell脚本执行SQL，sparksql提供了类似hive中的 -e  , -f ,-i的选项

1、定时调用脚本

#!/bin/sh  
# upload logs to hdfs  
  
yesterday=`date --date='1 days ago' +%Y%m%d`  

/opt/modules/spark/bin/spark-sql -i /opt/bin/spark_opt/init.sql --master spark://10.130.2.20:7077 --executor-memory 6g --total-executor-cores 45 --conf spark.ui.port=4075   -e "\
insert overwrite table st.stock_realtime_analysis PARTITION (DTYPE='01' )
  select t1.stockId as stockId,
         t1.url as url,
         t1.clickcnt as clickcnt,
         0,
         round((t1.clickcnt / (case when t2.clickcntyesday is null then   0 else t2.clickcntyesday end) - 1) * 100, 2) as LPcnt,
         '01' as type,
         t1.analysis_date as analysis_date,
         t1.analysis_time as analysis_time
    from (select stock_code stockId,
                 concat('http://stockdata.stock.hexun.com/', stock_code,'.shtml') url,
                 count(1) clickcnt,
                 substr(from_unixtime(unix_timestamp(),'yyyy-MM-dd HH:mm:ss'),1,10) analysis_date,
                 substr(from_unixtime(unix_timestamp(),'yyyy-MM-dd HH:mm:ss'),12,8) analysis_time
            from dms.tracklog_5min
           where stock_type = 'STOCK'
             and day =
                 substr(from_unixtime(unix_timestamp(), 'yyyyMMdd'), 1, 8)
           group by stock_code
           order by clickcnt desc limit 20) t1
    left join (select stock_code stockId, count(1) clickcntyesday
                 from dms.tracklog_5min a
                where stock_type = 'STOCK'
                  and substr(datetime, 1, 10) = date_sub(from_unixtime(unix_timestamp(),'yyyy-MM-dd HH:mm:ss'),1)
                  and substr(datetime, 12, 5) 

init.sql内容为加载udf:

add jar /opt/bin/UDF/hive-udf.jar;
create temporary function udtf_stockidxfund as 'com.hexun.hive.udf.stock.UDTFStockIdxFund';
create temporary function udf_getbfhourstime as 'com.hexun.hive.udf.time.UDFGetBfHoursTime';
create temporary function udf_getbfhourstime2 as 'com.hexun.hive.udf.time.UDFGetBfHoursTime2';
create temporary function udf_stockidxfund as 'com.hexun.hive.udf.stock.UDFStockIdxFund';
create temporary function udf_md5 as 'com.hexun.hive.udf.common.HashMD5UDF';
create temporary function udf_murhash as 'com.hexun.hive.udf.common.HashMurUDF';
create temporary function udf_url as 'com.hexun.hive.udf.url.UDFUrl';
create temporary function url_host as 'com.hexun.hive.udf.url.UDFHost';
create temporary function udf_ip as 'com.hexun.hive.udf.url.UDFIP';
create temporary function udf_site as 'com.hexun.hive.udf.url.UDFSite';
create temporary function udf_UrlDecode as 'com.hexun.hive.udf.url.UDFUrlDecode';
create temporary function udtf_url as 'com.hexun.hive.udf.url.UDTFUrl';
create temporary function udf_ua as 'com.hexun.hive.udf.useragent.UDFUA';
create temporary function udf_ssh as 'com.hexun.hive.udf.useragent.UDFSSH';
create temporary function udtf_ua as 'com.hexun.hive.udf.useragent.UDTFUA';
create temporary function udf_kw as 'com.hexun.hive.udf.url.UDFKW';
create temporary function udf_chdecode as 'com.hexun.hive.udf.url.UDFChDecode';

设置ui的端口

--conf spark.ui.port=4075 

默认为4040，会与其他正在跑的任务冲突，这里修改为4075

设定任务使用的内存与CPU资源

--executor-memory 6g --total-executor-cores 45

原来的语句是用hive -e 执行的，修改为spark后速度大加快了。原来为15min，提升速度后为 45s.