Saving all output to "!!{outputDirectory}!!/skewjoinopt17.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/skewjoinopt17.q >>> set hive.internal.ddl.list.bucketing.enable=true; No rows affected >>> set hive.optimize.skewjoin.compiletime = true; No rows affected >>> >>> CREATE TABLE T1(key STRING, val STRING) SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE; No rows affected >>> >>> LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1; No rows affected >>> >>> CREATE TABLE T2(key STRING, val STRING) SKEWED BY (key) ON ((2)) STORED AS TEXTFILE; No rows affected >>> >>> LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2; No rows affected >>> >>> -- One of the tables is skewed by 2 columns, and the other table is >>> -- skewed by one column. Ths join is performed on the first skewed column >>> -- The skewed value for the jon key is common to both the tables. >>> -- In this case, the skewed join value is not repeated in the filter. >>> -- adding a order by at the end to make the results deterministic >>> >>> EXPLAIN SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-2 depends on stages: Stage-1, Stage-4' ' Stage-4 is a root stage' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' subquery1:a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (not (key = '2'))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' tag: 0' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' subquery1:b ' ' TableScan' ' alias: b' ' Filter Operator' ' predicate:' ' expr: (not (key = '2'))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' tag: 1' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0} {VALUE._col1}' ' 1 {VALUE._col0} {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col1, _col4, _col5' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col4' ' type: string' ' expr: _col5' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' ' Stage: Stage-2' ' Map Reduce' ' Alias -> Map Operator Tree:' ' file:!!{hive.exec.scratchdir}!! ' ' TableScan' ' Union' ' Select Operator' ' SELECT * : (no compute)' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' file:!!{hive.exec.scratchdir}!! ' ' TableScan' ' Union' ' Select Operator' ' SELECT * : (no compute)' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' '' ' Stage: Stage-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (key = '2')' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' tag: 0' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' b ' ' TableScan' ' alias: b' ' Filter Operator' ' predicate:' ' expr: (key = '2')' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' tag: 1' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0} {VALUE._col1}' ' 1 {VALUE._col0} {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col1, _col4, _col5' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col4' ' type: string' ' expr: _col5' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' ' Stage: Stage-0' ' Fetch Operator' ' limit: -1' '' '' 185 rows selected >>> >>> SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val; 'key','val','key','val' '2','12','2','22' '3','13','3','13' '8','18','8','18' '8','18','8','18' '8','28','8','18' '8','28','8','18' 6 rows selected >>> >>> DROP TABLE T1; No rows affected >>> DROP TABLE T2; No rows affected >>> >>> >>> CREATE TABLE T1(key STRING, val STRING) SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE; No rows affected >>> >>> LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1; No rows affected >>> >>> CREATE TABLE T2(key STRING, val STRING) SKEWED BY (key) ON ((2)) STORED AS TEXTFILE; No rows affected >>> >>> LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2; No rows affected >>> >>> -- One of the tables is skewed by 2 columns, and the other table is >>> -- skewed by one column. Ths join is performed on the both the columns >>> -- In this case, the skewed join value is repeated in the filter. >>> >>> EXPLAIN SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL b) val))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-2 depends on stages: Stage-1, Stage-4' ' Stage-4 is a root stage' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' subquery1:a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (not (((key = '2') and (val = '12')) or (key = '2')))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' tag: 0' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' subquery1:b ' ' TableScan' ' alias: b' ' Filter Operator' ' predicate:' ' expr: (not (((key = '2') and (val = '12')) or (key = '2')))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' tag: 1' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0} {VALUE._col1}' ' 1 {VALUE._col0} {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col1, _col4, _col5' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col4' ' type: string' ' expr: _col5' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' ' Stage: Stage-2' ' Map Reduce' ' Alias -> Map Operator Tree:' ' file:!!{hive.exec.scratchdir}!! ' ' TableScan' ' Union' ' Select Operator' ' SELECT * : (no compute)' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' file:!!{hive.exec.scratchdir}!! ' ' TableScan' ' Union' ' Select Operator' ' SELECT * : (no compute)' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' '' ' Stage: Stage-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (((key = '2') and (val = '12')) or (key = '2'))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' tag: 0' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' b ' ' TableScan' ' alias: b' ' Filter Operator' ' predicate:' ' expr: (((key = '2') and (val = '12')) or (key = '2'))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' tag: 1' ' value expressions:' ' expr: key' ' type: string' ' expr: val' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0} {VALUE._col1}' ' 1 {VALUE._col0} {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col1, _col4, _col5' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col4' ' type: string' ' expr: _col5' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' ' Stage: Stage-0' ' Fetch Operator' ' limit: -1' '' 200 rows selected >>> >>> SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val ORDER BY a.key, b.key, a.val, b.val; 'key','val','key','val' '3','13','3','13' '8','18','8','18' '8','18','8','18' 3 rows selected >>> !record