http://git-wip-us.apache.org/repos/asf/hive/blob/47ef02e4/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out new file mode 100644 index 0000000..5d34347 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out @@ -0,0 +1,668 @@ +PREHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_text +POSTHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_text +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_text +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_text +PREHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@t1_text +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@t1_text +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +POSTHOOK: Lineage: t1.a SIMPLE [(t1_text)t1_text.FieldSchema(name:a, type:string, comment:null), ] +POSTHOOK: Lineage: t1.b SIMPLE [(t1_text)t1_text.FieldSchema(name:b, type:string, comment:null), ] +POSTHOOK: Lineage: t1.c SIMPLE [(t1_text)t1_text.FieldSchema(name:c, type:string, comment:null), ] +t1_text.a t1_text.b t1_text.c +PREHOOK: query: SELECT * FROM T1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM T1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +t1.a t1.b t1.c +1 1 3 +2 2 4 +2 3 5 +3 2 8 +5 2 2 +8 1 1 +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 1 +1 NULL 1 +2 2 1 +2 3 1 +2 NULL 2 +3 2 1 +3 NULL 1 +5 2 1 +5 NULL 1 +8 1 1 +8 NULL 1 +NULL 1 2 +NULL 2 3 +NULL 3 1 +NULL NULL 6 +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by cube(a, b) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by cube(a, b) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, count(*) from T1 group by cube(a, b) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, count(*) from T1 group by cube(a, b) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 1 +1 NULL 1 +2 2 1 +2 3 1 +2 NULL 2 +3 2 1 +3 NULL 1 +5 2 1 +5 NULL 1 +8 1 1 +8 NULL 1 +NULL 1 2 +NULL 2 3 +NULL 3 1 +NULL NULL 6 +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b), b, ()) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b), b, ()) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b), b, ()) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b), b, ()) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 1 +1 NULL 1 +2 2 1 +2 3 1 +2 NULL 2 +3 2 1 +3 NULL 1 +5 2 1 +5 NULL 1 +8 1 1 +8 NULL 1 +NULL 1 2 +NULL 2 3 +NULL 3 1 +NULL NULL 6 +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b)) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b)) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b)) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, count(*) FROM T1 GROUP BY a, b GROUPING SETS (a, (a, b)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 1 +1 NULL 1 +2 2 1 +2 3 1 +2 NULL 2 +3 2 1 +3 NULL 1 +5 2 1 +5 NULL 1 +8 1 1 +8 NULL 1 +PREHOOK: query: EXPLAIN +SELECT a FROM T1 GROUP BY a, b, c GROUPING SETS (a, b, c) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a FROM T1 GROUP BY a, b, c GROUPING SETS (a, b, c) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), c (type: string) + outputColumnNames: a, b, c + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: a (type: string), b (type: string), c (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 18 Data size: 4590 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + Statistics: Num rows: 18 Data size: 4590 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 9 Data size: 2295 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 9 Data size: 2295 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 2295 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a FROM T1 GROUP BY a, b, c GROUPING SETS (a, b, c) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a FROM T1 GROUP BY a, b, c GROUPING SETS (a, b, c) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a +1 +2 +3 +5 +8 +NULL +NULL +NULL +NULL +NULL +NULL +NULL +NULL +NULL +PREHOOK: query: EXPLAIN +SELECT a FROM T1 GROUP BY a GROUPING SETS ((a), (a)) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a FROM T1 GROUP BY a GROUPING SETS ((a), (a)) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string) + outputColumnNames: a + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: a (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 765 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 765 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a FROM T1 GROUP BY a GROUPING SETS ((a), (a)) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a FROM T1 GROUP BY a GROUPING SETS ((a), (a)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a +1 +2 +3 +5 +8 +PREHOOK: query: EXPLAIN +SELECT a + b, count(*) FROM T1 GROUP BY a + b GROUPING SETS (a+b) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a + b, count(*) FROM T1 GROUP BY a + b GROUPING SETS (a+b) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (UDFToDouble(a) + UDFToDouble(b)) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: double), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: double), _col1 (type: int) + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: double), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col2 + Statistics: Num rows: 3 Data size: 765 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: double), _col2 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 765 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 765 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a + b, count(*) FROM T1 GROUP BY a + b GROUPING SETS (a+b) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a + b, count(*) FROM T1 GROUP BY a + b GROUPING SETS (a+b) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +_c0 _c1 +2.0 1 +4.0 1 +5.0 2 +7.0 1 +9.0 1
http://git-wip-us.apache.org/repos/asf/hive/blob/47ef02e4/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out new file mode 100644 index 0000000..4deef94 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out @@ -0,0 +1,469 @@ +PREHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_text +POSTHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_text +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_text +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_text +PREHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@t1_text +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@t1_text +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +POSTHOOK: Lineage: t1.a SIMPLE [(t1_text)t1_text.FieldSchema(name:a, type:string, comment:null), ] +POSTHOOK: Lineage: t1.b SIMPLE [(t1_text)t1_text.FieldSchema(name:b, type:string, comment:null), ] +POSTHOOK: Lineage: t1.c SIMPLE [(t1_text)t1_text.FieldSchema(name:c, type:string, comment:null), ] +t1_text.a t1_text.b t1_text.c +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), 0 (type: int) + mode: partials + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: final + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by cube(a, b) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, count(*) from T1 group by cube(a, b) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string) + outputColumnNames: a, b + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), 0 (type: int) + mode: partials + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: final + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 1 +1 NULL 1 +2 2 1 +2 3 1 +2 NULL 2 +3 2 1 +3 NULL 1 +5 2 1 +5 NULL 1 +8 1 1 +8 NULL 1 +NULL 1 2 +NULL 2 3 +NULL 3 1 +NULL NULL 6 +PREHOOK: query: EXPLAIN +SELECT a, b, sum(c) from T1 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, sum(c) from T1 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), c (type: string) + outputColumnNames: a, b, c + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(c) + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: double) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), 0 (type: int) + mode: partials + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: double) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: final + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, sum(c) from T1 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, sum(c) from T1 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 +1 1 3.0 +1 NULL 3.0 +2 2 4.0 +2 3 5.0 +2 NULL 9.0 +3 2 8.0 +3 NULL 8.0 +5 2 2.0 +5 NULL 2.0 +8 1 1.0 +8 NULL 1.0 +NULL 1 4.0 +NULL 2 14.0 +NULL 3 5.0 +NULL NULL 23.0 +PREHOOK: query: CREATE TABLE T2(a STRING, b STRING, c int, d int) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(a STRING, b STRING, c int, d int) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: INSERT OVERWRITE TABLE T2 +SELECT a, b, c, c from T1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t2 +POSTHOOK: query: INSERT OVERWRITE TABLE T2 +SELECT a, b, c, c from T1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t2 +POSTHOOK: Lineage: t2.a SIMPLE [(t1)t1.FieldSchema(name:a, type:string, comment:null), ] +POSTHOOK: Lineage: t2.b SIMPLE [(t1)t1.FieldSchema(name:b, type:string, comment:null), ] +POSTHOOK: Lineage: t2.c EXPRESSION [(t1)t1.FieldSchema(name:c, type:string, comment:null), ] +POSTHOOK: Lineage: t2.d EXPRESSION [(t1)t1.FieldSchema(name:c, type:string, comment:null), ] +_col0 _col1 _col2 _col3 +PREHOOK: query: EXPLAIN +SELECT a, b, sum(c+d) from T2 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, sum(c+d) from T2 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t2 + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), (c + d) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), 0 (type: int) + mode: partials + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: final + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, sum(c+d) from T2 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, sum(c+d) from T2 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +a b _c2 +1 1 6 +1 NULL 6 +2 2 8 +2 3 10 +2 NULL 18 +3 2 16 +3 NULL 16 +5 2 4 +5 NULL 4 +8 1 2 +8 NULL 2 +NULL 1 8 +NULL 2 28 +NULL 3 10 +NULL NULL 46 http://git-wip-us.apache.org/repos/asf/hive/blob/47ef02e4/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out new file mode 100644 index 0000000..b30aabd --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out @@ -0,0 +1,314 @@ +PREHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_text +POSTHOOK: query: CREATE TABLE T1_text(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_text +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets1.txt' INTO TABLE T1_text +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_text +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets1.txt' INTO TABLE T1_text +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_text +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets2.txt' INTO TABLE T1_text +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_text +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets2.txt' INTO TABLE T1_text +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_text +PREHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@t1_text +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1 STORED AS ORC AS SELECT * FROM T1_text +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@t1_text +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +POSTHOOK: Lineage: t1.a SIMPLE [(t1_text)t1_text.FieldSchema(name:a, type:string, comment:null), ] +POSTHOOK: Lineage: t1.b SIMPLE [(t1_text)t1_text.FieldSchema(name:b, type:string, comment:null), ] +POSTHOOK: Lineage: t1.c SIMPLE [(t1_text)t1_text.FieldSchema(name:c, type:string, comment:null), ] +t1_text.a t1_text.b t1_text.c +PREHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), c (type: string) + outputColumnNames: a, b, c + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(c), count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<count:bigint,sum:double,input:string>), _col4 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double), _col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by cube(a, b) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by cube(a, b) +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), c (type: string) + outputColumnNames: a, b, c + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(c), count() + keys: a (type: string), b (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<count:bigint,sum:double,input:string>), _col4 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double), _col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 _c3 +1 1 3.0 2 +1 2 2.0 1 +1 NULL 2.6666666666666665 3 +2 2 5.333333333333333 3 +2 3 5.0 2 +2 NULL 5.2 5 +3 2 8.0 1 +3 NULL 8.0 1 +5 1 2.0 1 +5 NULL 2.0 1 +8 1 1.0 2 +8 NULL 1.0 2 +NULL 1 2.0 5 +NULL 2 5.2 5 +NULL 3 5.0 2 +NULL NULL 3.8333333333333335 12 +PREHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +Explain +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: string), b (type: string), c (type: string) + outputColumnNames: a, b, c + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(c), count() + keys: a (type: string), b (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<count:bigint,sum:double,input:string>), _col3 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), 0 (type: int) + mode: partials + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 48 Data size: 12240 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<count:bigint,sum:double,input:string>), _col4 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: final + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + pruneGroupingSetId: true + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double), _col4 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 6120 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b, avg(c), count(*) from T1 group by a, b with cube +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +a b _c2 _c3 +1 1 3.0 2 +1 2 2.0 1 +1 NULL 2.6666666666666665 3 +2 2 5.333333333333333 3 +2 3 5.0 2 +2 NULL 5.2 5 +3 2 8.0 1 +3 NULL 8.0 1 +5 1 2.0 1 +5 NULL 2.0 1 +8 1 1.0 2 +8 NULL 1.0 2 +NULL 1 2.0 5 +NULL 2 5.2 5 +NULL 3 5.0 2 +NULL NULL 3.8333333333333335 12
