小编Man*_*ish的帖子

如果在猪的脚本中运行一个简单的组来获取大数TB的数据,那么脚本就会停留在70%,那么可以采取哪些措施来诊断问题呢？

    create table MY_DATA0(session_id STRING, userid BIGINT,date_time STRING, ip STRING, URL STRING ,country STRING, state STRING, city STRING) 
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES 
TERMINATED BY '\n' STORED AS TEXTFILE ;

    LOAD DATA INPATH '/inputhive' OVERWRITE INTO TABLE MY_DATA0;

    create table part0(session_id STRING, userid BIGINT,date_time STRING, ip STRING, URL STRING) partitioned by (country STRING, state STRING, city STRING) 

    clustered by (userid) into 256 buckets ROW FORMAT DELIMITED FIELDS 
    TERMINATED BY ',' LINES TERMINATED BY '\n' STORED AS TEXTFILE ; …