Saving all output to "!!{outputDirectory}!!/groupby5_map_skew.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/groupby5_map_skew.q >>> set hive.map.aggr=true; No rows affected >>> set hive.groupby.skewindata=true; No rows affected >>> set mapred.reduce.tasks=31; No rows affected >>> >>> CREATE TABLE dest1(key INT) STORED AS TEXTFILE; No rows affected >>> >>> EXPLAIN FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key); 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (. (TOK_TABLE_OR_COL src) key))))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-0 depends on stages: Stage-1' ' Stage-2 depends on stages: Stage-0' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' outputColumnNames: key' ' Group By Operator' ' aggregations:' ' expr: sum(key)' ' bucketGroup: false' ' mode: hash' ' outputColumnNames: _col0' ' Reduce Output Operator' ' sort order: ' ' tag: -1' ' value expressions:' ' expr: _col0' ' type: double' ' Reduce Operator Tree:' ' Group By Operator' ' aggregations:' ' expr: sum(VALUE._col0)' ' bucketGroup: false' ' mode: final' ' outputColumnNames: _col0' ' Select Operator' ' expressions:' ' expr: _col0' ' type: double' ' outputColumnNames: _col0' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' outputColumnNames: _col0' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby5_map_skew.dest1' '' ' Stage: Stage-0' ' Move Operator' ' tables:' ' replace: true' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby5_map_skew.dest1' '' ' Stage: Stage-2' ' Stats-Aggr Operator' '' '' 72 rows selected >>> >>> FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key); '_col0' No rows selected >>> >>> SELECT dest1.* FROM dest1; 'key' '130091' 1 row selected >>> !record